diff --git a/.github/workflows/e2e.yml b/.github/workflows/e2e.yml index e06fb025bd..9111f50153 100644 --- a/.github/workflows/e2e.yml +++ b/.github/workflows/e2e.yml @@ -82,7 +82,7 @@ jobs: - name: Install (immutable) run: pnpm install --frozen-lockfile - # The with-key escalation e2e (examples/sandbox-acp-agent/tests/ + # The with-key escalation e2e (examples/acp-agent/tests/ # escalation.e2e.ts) self-skips without a usable runner — without this # step it would never actually execute anywhere (CI had no bwrap, dev # macs run Seatbelt instead), which is exactly how a broken harness diff --git a/docs/architecture.md b/docs/architecture.md index ae158c3785..947cf3f909 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -34,6 +34,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.subagents` | [`subagent/`](../packages/subagent/README.md) | named delegation providers | | `ctx.workflows` | [`workflow/`](../packages/workflow/README.md) | script-driven multi-agent orchestration | | `ctx.sessionPersistence` | [`session-persistence/`](../packages/session-persistence/README.md) | durable storage for session logs | +| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | live-preferred logical-corpus and exact-event reads | ## Event @@ -53,9 +54,9 @@ Waterfall events behave like around-middleware: a listener delegates by calling Default loop processing remains exposed through plugin-visible services and events. -A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. +A **session** is an append-only event log. A **turn** drains queued input until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. -Declarative startup chooses one agent/session identity. No id mints `-session-`; exact `sessionId` resumes when stored and otherwise creates; `resumeSessionId` requires stored history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, letting front doors reject buffered work. +Startup resolves one identity. No id mints `-session-`; `sessionId` resumes stored or creates; `resumeSessionId` requires history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject buffered work. ### Turn Flow diff --git a/docs/capability-seams.md b/docs/capability-seams.md index a6c9c766aa..fb4746dc68 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -18,12 +18,14 @@ flowchart LR svc_sessions["ctx.sessions
In-memory session store"] pkg_agent["agent"] pkg_session_persistence["session-persistence"] + pkg_session_query["session-query"] pkg_subagent_inprocess["subagent-inprocess"] pkg_invariants["invariants"] svc_sessionPersistence["ctx.sessionPersistence
Durable session persistence seam"] pkg_session_persistence_jsonl["session-persistence-jsonl"] pkg_session_persistence_sqlite["session-persistence-sqlite"] pkg_acp["acp"] + svc_sessionQuery["ctx.sessionQuery
Exact session-history reads"] pkg_system_prompt["system-prompt"] svc_systemPrompt["ctx.systemPrompt
System prompt assembly registry"] pkg_tools["tools"] @@ -56,6 +58,8 @@ flowchart LR pkg_sandbox_local["sandbox-local"] pkg_approval["approval"] svc_approval["ctx.approval
Approval seam"] + pkg_permission["permission"] + svc_permission["ctx.permission
Permission presets"] pkg_code_runtime["code-runtime"] svc_codeRuntime["ctx.codeRuntime
Code-execution seam"] pkg_code_runtime_worker["code-runtime-worker"] @@ -99,12 +103,14 @@ flowchart LR pkg_llm_deepseek --> svc_llm pkg_llm_pi_ai --> svc_llm pkg_llm_replay --> svc_llm + pkg_permission --> svc_permission pkg_sandbox --> svc_sandbox pkg_sandbox_local --> svc_sandbox pkg_session --> svc_sessions pkg_session_persistence --> svc_sessionPersistence pkg_session_persistence_jsonl --> svc_sessionPersistence pkg_session_persistence_sqlite --> svc_sessionPersistence + pkg_session_query --> svc_sessionQuery pkg_skill --> svc_skills pkg_skill_local --> svc_skills pkg_stdio_agent --> svc_userInteraction @@ -139,13 +145,16 @@ flowchart LR svc_fs --> pkg_tool_fs svc_llm --> pkg_agent_loop svc_llm --> pkg_compact_basic + svc_permission --> pkg_acp svc_sandbox --> pkg_bash_sandbox svc_sessionPersistence --> pkg_acp svc_sessionPersistence --> pkg_agent_loop + svc_sessionPersistence --> pkg_session_query svc_sessions --> pkg_agent svc_sessions --> pkg_agent_loop svc_sessions --> pkg_invariants svc_sessions --> pkg_session_persistence + svc_sessions --> pkg_session_query svc_sessions --> pkg_subagent_inprocess svc_skills --> pkg_tool_skill svc_subagents --> pkg_tool_subagent @@ -174,8 +183,9 @@ flowchart LR | ctx key | Role | Owner | Implementations | Direct consumers | Companion plugins | Note | | --- | --- | --- | --- | --- | --- | --- | | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | -| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | -| `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | +| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | +| `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | +| `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | | `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. | | `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. | | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-agent`](../packages/ui/stdio-agent), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-agent`](../packages/ui/stdio-agent), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. | @@ -185,6 +195,7 @@ flowchart LR | `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. | | `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. | | `ctx.approval` | `seam` | `approval` | [`acp`](../packages/ui/acp) | [`tools`](../packages/core/tools), [`tool-bash`](../packages/bash/tool-bash) | - | One-shot permission decisions dispatched over the `approval/request` waterfall; answerers are listeners (the ACP bridge for its own agents), absence fails closed to `unavailable`. | +| `ctx.permission` | `core` | [`permission`](../packages/ui/permission) | - | [`acp`](../packages/ui/acp) | - | User-facing preset table (`workspace-write`/`danger-full-access`) bundling the sandbox-mode and approval-policy knobs; a switch writes one `permission/preset` event through to both knob events. | | `ctx.codeRuntime` | `seam` | [`code-runtime`](../packages/code-runtime/code-runtime) | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | [`tools`](../packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for Code Mode). | | `ctx.fs` | `seam` | [`fs`](../packages/fs/fs) | [`fs-local`](../packages/fs/fs-local) | [`tool-fs`](../packages/fs/tool-fs) | [`fs-policy`](../packages/fs/fs-policy) | tool-fs executes read/write/edit through ctx.fs; fs-policy contributes observed-state checks through the fs/* event gate. | | `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index cba46af12d..2fd8d8d05a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:246`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:244`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` @@ -446,6 +446,41 @@ export interface Config { Source: [`packages/support/llm-replay/src/index.ts:429`](../packages/support/llm-replay/src/index.ts) +## `@deepseek-ai/dsh-permission` + +Requires: `bash` · `approval` + +```ts config-catalog +/** The {@link PermissionService} config: the deployment's preset table. */ +export interface Config { + /** + * The preset table: name → knob bundle. Defaults to `workspace-write` + * (workspace-write + ask) and `danger-full-access` (danger-full-access + + * never). The name `custom` is reserved for the derived not-a-preset state. + */ + presets?: Record +} + +/** + * One preset's knob bundle — the sandbox mode and approval policy a session + * runs under while the preset is active — plus its presentation. + */ +export interface PresetSpec { + /** The `bash/sandbox-mode` value the preset writes through. */ + sandbox: SandboxMode + /** The `approval/policy` value the preset writes through. */ + approval: ApprovalPolicy + /** The display label a client shows for this preset; the raw table key when omitted. */ + name?: string + /** One user-facing sentence on what the preset means; omitted when not configured. */ + description?: string +} +``` + +Depends on: [`ApprovalPolicy`](core-data-structures/approval.md) · [`SandboxMode`](core-data-structures/sandbox.md) + +Source: [`packages/ui/permission/src/index.ts:97`](../packages/ui/permission/src/index.ts) + ## `@deepseek-ai/dsh-repeat-tool-guard` ```ts config-catalog @@ -578,6 +613,20 @@ export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:50`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) +## `@deepseek-ai/dsh-session-query` + +Requires: `sessions` + +```ts config-catalog +/** Configuration for exact session-query reads. */ +export interface Config { + /** Maximum accepted raw read context on either side. Defaults to 50. */ + readWindowMax?: number +} +``` + +Source: [`packages/session-query/session-query/src/config.ts:9`](../packages/session-query/session-query/src/config.ts) + ## `@deepseek-ai/dsh-skill` ```ts config-catalog diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 1228f6aee9..72a66a3ef7 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -263,7 +263,7 @@ A session was created in the store. A synchronous listener throw vetoes publicat 'session/created'(this: Scoped, session: Session): void ``` -Source: [`packages/core/session/src/index.ts:51`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:52`](../../packages/core/session/src/index.ts) ### `session/disposed` — emit @@ -273,7 +273,7 @@ A previously announced session left the store. Emitted exactly once on normal de 'session/disposed'(this: Scoped, session: Session): void ``` -Source: [`packages/core/session/src/index.ts:63`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:64`](../../packages/core/session/src/index.ts) ### `session/event` — emit @@ -285,7 +285,7 @@ An event was appended to a session log (sync, fire-and-forget). This is the per- Types: [SessionEvent](../core-data-structures/core.md) -Source: [`packages/core/session/src/index.ts:82`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:83`](../../packages/core/session/src/index.ts) ### `session/flush` — parallel @@ -295,7 +295,7 @@ Awaited durability checkpoint. The agent loop awaits `ctx.sessions.flush(session 'session/flush'(this: Scoped, session: Session): Promise | void ``` -Source: [`packages/core/session/src/index.ts:100`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:101`](../../packages/core/session/src/index.ts) ## `skill/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 6ef72e78dd..512fc1240a 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -165,6 +165,21 @@ Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../co Source: [`packages/llm/llm/src/index.ts:88`](../../packages/llm/llm/src/index.ts) +## `ctx.permission` — `PermissionService` + +The permission service (`ctx.permission`). Owns the deployment's preset table and THE write path for preset switches; presentation layers (the ACP bridge's single `Permissions` select) advertise names and call set. Composing it REQUIRES both mechanism knobs — a confining `ctx.bash` executor and the `ctx.approval` seam. A knob state matching no table entry is not an error but the derived CUSTOM_PRESET state: shown as the current value, never a switch target. + +```ts cordis-catalog +current(events: readonly SessionEvent[]): string +resolve(name: string): PresetSpec +optionOf(name: string): PresetOption +set(session: Session, name: string): void +``` + +Types: [SessionEvent](../core-data-structures/core.md) + +Source: [`packages/ui/permission/src/index.ts:115`](../../packages/ui/permission/src/index.ts) + ## `ctx.sandbox` — `SandboxProvider` (abstract seam) Abstract process-sandbox service. Subclass, implement confine, and load the subclass as a plugin — it registers as `ctx.sandbox` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior). @@ -205,6 +220,18 @@ Types: [SessionEvent](../core-data-structures/core.md) Source: [`packages/session-persistence/session-persistence/src/index.ts:68`](../../packages/session-persistence/session-persistence/src/index.ts) +## `ctx.sessionQuery` — `SessionQueryService` + +Live-preferred logical-corpus and exact-event read service. + +```ts cordis-catalog +listSessions(): Promise +async listEvents(sessionId: SessionId): Promise +async readEvent(request: SessionEventReadRequest): Promise +``` + +Source: [`packages/session-query/session-query/src/index.ts:35`](../../packages/session-query/session-query/src/index.ts) + ## `ctx.sessions` — `SessionStore` In-memory session store (`ctx.sessions`). @@ -222,7 +249,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:597`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:598`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 897b04240b..ebf70f4d35 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -19,6 +19,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t | [scope.md](scope.md) | scoped registration identity, dispatch carriers, and the owned `Scope` context | | [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, the turn-enclosure invariant | | [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` | +| [session-query.md](session-query.md) | logical session/event records and bounded exact-event reads | | [system-prompt.md](system-prompt.md) | per-assembly context, tool-provider results, prompt sections, and cooperative assembly | | [tools.md](tools.md) | `ToolDefinition` full fields, the schema DSL, `ToolExecution`/`ToolResult`, tool-presentation UI types, and the guarded execution pipeline | | [user-interaction.md](user-interaction.md) | the UI-backed human question/answer seam: `AskUserQuestionRequest`, answer/options vocabulary, provider API, error taxonomy | diff --git a/docs/core-data-structures/session-query.md b/docs/core-data-structures/session-query.md new file mode 100644 index 0000000000..ded8ca3f7e --- /dev/null +++ b/docs/core-data-structures/session-query.md @@ -0,0 +1,69 @@ +# Session Query + +Exact reads over the live-preferred logical session corpus. The [package contract](../../packages/session-query/session-query) owns source precedence, dynamic optional persistence, cloning, surface classification, bounded windows, and typed failures. Full-text search is a separate proposed SQLite phase. + +Source: [`packages/session-query/session-query/src/types.ts`](../../packages/session-query/session-query/src/types.ts) + +## Logical records + +`SessionRecord` is returned by the cross-corpus list. It exposes source availability independently from the cloned live-preferred header. `SessionEventRecord` is a lightweight raw-log projection; classification uses the same `foldSurface()` transitions as model-history derivation. + +```ts type-equiv +export type SessionEventSurface = 'current' | 'shadowed' | 'log-only' +``` + +```ts type-equiv +export interface SessionRecord { + header: SessionHeader + live: boolean + persisted: boolean +} +``` + +```ts type-equiv +export interface SessionEventRecord { + sessionId: SessionId + seq: number + type: SessionEventType + time: number + surface: SessionEventSurface +} +``` + +## Bounded event reads + +The request addresses one raw seq and optional neighboring counts. The result carries a `SessionHeader` rather than availability flags so a known live target can remain independent of persistence health. + +```ts type-equiv +export interface SessionEventReadRequest { + sessionId: SessionId + seq: number + before?: number + after?: number +} +``` + +```ts type-equiv +export interface SessionEventWindow { + session: SessionHeader + target: SessionEvent + events: SessionEvent[] + startSeq: number + endSeq: number +} +``` + +## Errors + +The closed code union distinguishes request validation, missing targets, malformed surface logs, optional-backend failure, and contradictory source metadata. + +```ts type-equiv +export type SessionQueryErrorCode = + | 'SESSION_QUERY_EVENT_NOT_FOUND' + | 'SESSION_QUERY_INVALID_CONFIG' + | 'SESSION_QUERY_INVALID_SURFACE' + | 'SESSION_QUERY_INVALID_WINDOW' + | 'SESSION_QUERY_PERSISTENCE_FAILED' + | 'SESSION_QUERY_SESSION_NOT_FOUND' + | 'SESSION_QUERY_SOURCE_CONFLICT' +``` diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 47517f53c3..e4a508e4dd 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -175,6 +175,26 @@ export interface SurfaceIntent { Required for `SurfaceEventType` events — every message-producing event must declare how it joins the surface, the sole source of derived history. Non-surface types reject it at compile time. +### `SurfaceFoldReplacement` and `SurfaceFoldResult` — a complete surface replay + +`foldSurface(events)` returns detached current event sequences together with the actual sequences shadowed by each declared replacement range. `SurfaceManager` uses the same transitions for its incremental cache without retaining replacement history. + +```ts type-equiv +export interface SurfaceFoldReplacement { + seq: number + start: number + end: number + shadowedSeqs: number[] +} +``` + +```ts type-equiv +export interface SurfaceFoldResult { + nodes: number[] + replacements: SurfaceFoldReplacement[] +} +``` + ## Derived history: `deriveMessages()` and `deriveEventMessage()` `Session.deriveMessages()` projects the event log into the `Message[]` the model sees — cached (each surface node projected once, when first seen; a surface rewrite rebuilds) and frozen (a fresh array per call over shared, deep-frozen messages, so mutating logged history through a projection is unrepresentable). `deriveEventMessage(event)` is the per-node pure function the fold applies — public so external reconstructors and the dev invariant project a log prefix with exactly the same rules and cannot disagree with the cache. The projection rules: diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 3d0b83aba3..da3564298f 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -26,10 +26,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:109`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | -| `session/created` | `emit` | [`packages/core/session/src/index.ts:51`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | -| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:63`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:82`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | -| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:100`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/created` | `emit` | [`packages/core/session/src/index.ts:52`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:64`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:83`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | +| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:101`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | diff --git a/docs/module-graph.md b/docs/module-graph.md index 87f34603f2..0b23048f04 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -82,6 +82,9 @@ flowchart TD pkg_session_persistence_jsonl["session-persistence-jsonl"] pkg_session_persistence_sqlite["session-persistence-sqlite"] end + subgraph group_session_query["packages/session-query"] + pkg_session_query["session-query"] + end subgraph group_support["packages/support"] pkg_acp_snapshot["acp-snapshot"] pkg_invariants["invariants"] @@ -94,6 +97,7 @@ flowchart TD pkg_app_boot["app-boot"] pkg_jsonrpc["jsonrpc"] pkg_jsonrpc_agent["jsonrpc-agent"] + pkg_permission["permission"] pkg_stdio_agent["stdio-agent"] pkg_tool_ask_user["tool-ask-user"] pkg_user_approval["user-approval"] @@ -164,6 +168,9 @@ flowchart TD pkg_session_persistence_jsonl --> pkg_session_persistence pkg_session_persistence_sqlite --> pkg_session pkg_session_persistence_sqlite --> pkg_session_persistence + pkg_session_query --> pkg_llm + pkg_session_query --> pkg_session + pkg_session_query --> pkg_session_persistence pkg_invariants --> pkg_agent pkg_invariants --> pkg_llm pkg_invariants --> pkg_scope @@ -190,6 +197,10 @@ flowchart TD pkg_bash_sandbox --> pkg_bash pkg_bash_sandbox --> pkg_bash_local pkg_bash_sandbox --> pkg_sandbox + pkg_permission --> pkg_bash + pkg_permission --> pkg_sandbox + pkg_permission --> pkg_session + pkg_permission --> pkg_user_approval pkg_agent_loop --> pkg_agent pkg_agent_loop --> pkg_llm pkg_agent_loop --> pkg_scope @@ -238,6 +249,7 @@ flowchart TD pkg_acp --> pkg_agent pkg_acp --> pkg_bash pkg_acp --> pkg_llm + pkg_acp --> pkg_permission pkg_acp --> pkg_sandbox pkg_acp --> pkg_session pkg_acp --> pkg_session_persistence @@ -365,12 +377,14 @@ flowchart TD | [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) | | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | | [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | +| [`session-query`](../packages/session-query/session-query) | `session-query` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | | [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) | | [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | +| [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | @@ -381,7 +395,7 @@ flowchart TD | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | | [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | -| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) | +| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) | | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 7971f84c71..c38c655c44 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -153,6 +153,18 @@ A hook command's outcome — log-only, paired with a prior `hook/invoked` (same Source: [`packages/hooks/hook-protocol/src/types.ts:45`](../packages/hooks/hook-protocol/src/types.ts) +### `permission/*` + +#### `permission/preset` — log-only + +The session's permission preset was switched — log-only (the `bash/sandbox-mode` precedent): durable and replayable, never in the model transcript. The LAST such event is the session's preset (effectivePermissionPreset); the knob events the switch wrote through follow it in the same turn, and they — not this record of the user's choice — are what execution reads. + +```ts persistence-catalog +'permission/preset': { preset: string } +``` + +Source: [`packages/ui/permission/src/index.ts:42`](../packages/ui/permission/src/index.ts) + ### `prompt/*` #### `prompt/blocked` — log-only diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 5ed8c6ae6d..cd00c78c3a 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -11,6 +11,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Pre-tool input rewrite — a consistent design](proposed/feature/2026-06-30-pre-tool-input-rewrite.md) | 2026-06-30 | | [Claude Code and Codex subagent backends (out-of-process delegation to external coding agents)](proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md) | 2026-07-07 | | [Interactive side sessions and merge-back](proposed/feature/2026-07-08-interactive-side-sessions.md) | 2026-07-08 | +| [SQLite FTS5 session search](proposed/feature/2026-07-10-sqlite-session-query-provider.md) | 2026-07-10 | | [Stream workflow progress through tool calls](proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md) | 2026-07-13 | ### Simplification @@ -73,6 +74,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The session prefix — request-only messages in front of the derived history](implemented/feature/2026-07-07-session-prefix.md) | 2026-07-07 | | [Repeat-tool-call guard plugin](implemented/feature/2026-07-08-repeat-tool-guard.md) | 2026-07-08 | | [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 | +| [Exact session query service](implemented/feature/2026-07-10-session-query-service.md) | 2026-07-10 | | [Configure subagent persona, tool visibility, and depth](implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) | 2026-07-12 | ### Simplification diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md b/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md index 293b1bbde6..317d244d29 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md +++ b/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md @@ -24,7 +24,7 @@ Tool-call presentation remains tool-owned. A tool's `presentCall` and `presentRe Permission handling is an answerer on the [user-approval seam](2026-07-06-approval-seam.md), not an ask-every-tool policy in ACP. An `approval/request` for a bridge-owned agent with a call id becomes `session/request_permission` on that agent's editor session, with one-shot allow/reject choices. Foreign or call-less requests delegate; a missing or failed answerer remains fail-closed. The plugin that asks—such as a pre-execute policy or bash escalation—owns the decision to ask. -The bridge advertises ACP config options instead of session modes. `sandbox-mode` exists only when the mounted bash executor reports sandbox capability, and `approval-policy` exists only when `ctx.approval` is composed. Each option is an independent select whose current value is the session event fold over the composition default. `session/set_config_option` validates against the owning domain vocabulary and writes through `setSandboxMode` or `setApprovalPolicy`. An open-turn switch appends immediately; an idle switch is overlaid in the response and anchored at the next turn start. Until that anchor it is memory-only and a crash reverts to the durable fold. ACP session modes are deliberately not modeled because one mode list cannot represent these orthogonal knobs and config options are the forward protocol surface. Runtime model selection remains outside this decision; `AcpConfig.model` is connection-wide. +The bridge advertises ACP config options instead of session modes. When `ctx.permission` is composed, it exposes one `permission` select whose options come from the deployment's preset table; the shipped presets are `workspace-write` and `danger-full-access`, and each bundles a sandbox mode with an approval policy. The current value comes from `PermissionService.current()`, including the derived switch-away-only `custom` state when the effective knobs match no preset. `session/set_config_option` validates through `PermissionService.set()` and writes the chosen preset through to both owning knob events. An open-turn switch appends immediately; an idle switch is overlaid in the response and anchored at the next turn start. Until that anchor it is memory-only and a crash reverts to the durable fold. ACP session modes are deliberately not modeled because config options are the forward protocol surface. Runtime model selection remains outside this decision; `AcpConfig.model` is connection-wide. The bridge also provides the ACP-backed `UserInteractionProvider`: `ask_user_question` requests become form elicitations on the owning session. Select, multi-select, option descriptions, and custom-answer override semantics are preserved. @@ -40,7 +40,7 @@ The precise supported and deferred protocol rows live in [`packages/ui/acp/acp-f **Execute bash through ACP `terminal/*`** — rejected. That would move execution outside the harness and bypass its sandbox, credential scrub, task ownership, cwd resolution, and session log. Terminal metadata is presentation only. -**Represent sandbox and approval as ACP session modes** — rejected. They are independent composable settings, while a single current mode is mutually exclusive. ACP config options represent both without a cross-product and match the protocol's forward direction. +**Represent permission presets as ACP session modes** — rejected. The deployment-defined preset is already one config-option select, while session modes are the legacy surface slated for removal in ACP v2. **Hijack stdout defensively** — rejected. Process-wide monkey-patching is outside Cordis effect ownership and races the protocol transport. The app composition owns stdout purity. diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index c5d61b0edb..7da83c4e16 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -23,7 +23,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou # policy: never # deployment default for sessions without an override; 'ask' when omitted ``` -The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-agent`, as in [the sandbox example](../../../../examples/sandbox-acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. +The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-agent`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. diff --git a/docs/rfc/implemented/feature/2026-07-06-sandbox.md b/docs/rfc/implemented/feature/2026-07-06-sandbox.md index cbfe4feee3..58321fbf81 100644 --- a/docs/rfc/implemented/feature/2026-07-06-sandbox.md +++ b/docs/rfc/implemented/feature/2026-07-06-sandbox.md @@ -16,7 +16,7 @@ One seam, one per-platform chain of local backends, one consumer, and two levers ### How a deployment uses it -Three `cordis.yml` entries turn an unconfined coding agent into the sandboxed product path; [`examples/sandbox-acp-agent`](../../../../examples/sandbox-acp-agent/README.md) is this composition, live: +Four `cordis.yml` entries turn an unconfined coding agent into the sandboxed product path; [`examples/acp-agent`](../../../../examples/acp-agent/README.md) uses this composition by default: ```yaml - id: sandbox @@ -24,17 +24,21 @@ Three `cordis.yml` entries turn an unconfined coding agent into the sandboxed pr - id: bash name: '@deepseek-ai/dsh-bash-sandbox' # the confined executor, replacing dsh-bash-local behind ctx.bash config: - mode: read-only # the deployment default every session starts from + mode: workspace-write # the deployment default every session starts from workspaceRoot: !!js process.cwd() # the boundary workspace-write may write under - id: approval name: '@deepseek-ai/dsh-user-approval' # the escalation gate's channel (the approval RFC) + config: + policy: ask +- id: permission + name: '@deepseek-ai/dsh-permission' # one product-facing select over both mechanism knobs ``` -The swap is invisible to every consumer of `ctx.bash`: the bash tools, hook commands, and background tasks run exactly as before, spawned through the wrapped argv the provider returns. Deleting the `sandbox` and `bash` entries and loading `@deepseek-ai/dsh-bash-local` instead is the opt-out — execution is unconfined again and the escalation fields vanish from the tool schema, because they are capability-gated on the mounted executor, not on configuration. Omitting only `approval` keeps confinement but fails every escalation closed with its own error text. +The swap is invisible to every consumer of `ctx.bash`: the bash tools, hook commands, and background tasks run exactly as before, spawned through the wrapped argv the provider returns. Deleting the `sandbox` and `permission` entries and replacing `bash` with `@deepseek-ai/dsh-bash-local` is the opt-out — execution is unconfined again and the escalation fields vanish from the tool schema, because they are capability-gated on the mounted executor, not on configuration. Omitting only `approval` keeps confinement but fails every escalation closed with its own error text; `permission` also requires the approval seam and a confining executor, so a partially composed preset layer fails loud at load. Misconfiguration fails loud: `mode` outside the closed vocabulary is rejected at plugin load, and a host with no usable backend throws the structured `SANDBOX_UNAVAILABLE` — at `confine()` before the command ever spawns — rather than degrading to unconfined execution. `runnerCommand` on `dsh-sandbox-local` is the operator's explicit assertion of a bwrap-compatible runner (chain and probes skipped); it doubles as the deterministic fake-runner seam for keyless tests. -What the model then experiences: denied file effects come back as result facts with a `[sandbox: file access denied under mode]` marker plus standing instructions not to retry around them; under a confining executor the schema offers `sandbox_permissions` + `justification` for the one-approval escalated retry (validated strictly wider than the session's effective mode at execution); the system prompt deliberately does NOT state the sandbox mode — the model learns the boundary from the marker (which names the mode) when it hits it, instead of preemptively refusing work a standing declaration discourages. What an ACP editor experiences: a `sandbox-mode` and an `approval-policy` config-option select per session (each advertised only when its knob is composable), switchable at runtime; a sandbox switch simply changes what subsequent commands may do, while an approval-policy switch to `'never'` is stated in the prompt and narrated. +What the model then experiences: denied file effects come back as result facts with a `[sandbox: file access denied under mode]` marker plus standing instructions not to retry around them; under a confining executor the schema offers `sandbox_permissions` + `justification` for the one-approval escalated retry (validated strictly wider than the session's effective mode at execution); the system prompt deliberately does NOT state the sandbox mode — the model learns the boundary from the marker (which names the mode) when it hits it, instead of preemptively refusing work a standing declaration discourages. What an ACP editor experiences: one `Permissions` config-option select per session (advertised when the `dsh-permission` preset layer is composed; each preset bundles a sandbox mode and an approval policy and writes through to both knob events — a knob state outside the table derives a switch-away-only `custom` current), switchable at runtime; a sandbox switch simply changes what subsequent commands may do, while an approval-policy switch to `'never'` is stated in the prompt and narrated. The product path, concretely (the escalation arc is verbatim from the recorded `escalation-approved` scenario; the denial leg is pinned on the real-kernel e2e tier): @@ -57,7 +61,7 @@ Reject instead and nothing executes: the result is the verbatim `the user reject - Everything else executes inside the harness process (fs is in-process `node:fs`, web is in-process `fetch`, every `ToolDefinition.execute()` closes over `ctx`): an OS sandbox wraps `execve` and cannot wrap an in-process function call, so "sandbox any tool" is policy at each tool's seam, never a mechanical transport change. - `tools/pre-execute` (`allow`/`deny`/`ask`) exists, with `ask` serviced by [the approval seam](2026-07-06-approval-seam.md); the fs intent gates are version guards with no mode input yet. - `dsh-bash`'s request/spec split (`BashExecRequest` → `resolve()` → `BashExecSpec`) carries per-call fields the way escalation needs — `owner` is the template: request-optional, spec required-but-nullable, carried verbatim — and the result types already speak `SandboxMode`, so a per-call policy field adds no dependency edge. -- The pinned-header snapshot design means a schema/description change churns at most one pinning fixture per suite, and the escalation fields are advertised only under a sandboxing executor — so they live in exactly one pinned header, the sandbox example suite's `mode-switching` fixture. +- The pinned-header snapshot design means a schema/description change churns at most one pinning fixture per suite, and the escalation fields are advertised only under a sandboxing executor — so they live in exactly one pinned header, the acp example suite's `permission-switching` fixture. #### The seam: `ctx.sandbox` @@ -120,7 +124,7 @@ Each owner exports the same three-piece kit: the event declaration, a pure fold **Visibility is deliberately asymmetric between the knobs.** The SANDBOX mode is stated nowhere and its switches are not narrated: a standing "you are read-only" declaration teaches the model to refuse preemptively (observed live: sessions where the model would not even attempt a write it could have escalated), while the denial marker already names the mode the command ran under at exactly the moment the boundary matters — behavior, not belief, carries the state, and a switch simply changes what the next command does. The APPROVAL policy keeps both layers, because its failure mode is the opposite: an auto-rejected ask under `'never'` returns "the user rejected …" wording no behavior can disambiguate, so the prompt states `'never'` (and ONLY `'never'` — an `'ask'` promise is unknowable without asking, and absence under a logged header is how the narrator reads `'ask'` back), and an `agent/pre-step` narrator injects at most one coalesced notice per policy switch: idle flip-flops collapse to one notice at the next turn's first step, a net-zero round trip to none, and a mid-turn change is narrated no later than the next step. Its "last told" is in-memory with a log-derived fallback (the folded header's system text parsed against the closed candidate sentence; LAST occurrence wins, so a persona quoting it cannot shadow the real section), so restarts lose nothing; attribution is positional (a knob event after the log's last `request/header` reads `changed by the user`, a drift with no such event reads `changed by the operator/config`). -**The editor surface** is protocol-native [Session Config Options](https://agentclientprotocol.com/protocol/session-config-options) — the spec's replacement for session modes (slated for removal in ACP v2), already SDK-typed. The bridge advertises one independent `select` per composable knob — `sandbox-mode` (category `mode`) iff the mounted executor confines, `approval-policy` iff the approval seam is composed — with `currentValue` folded from each session's own log, in `session/new` and `session/load` responses. `session/set_config_option` validates against the same closed lists, routes to the domain setter, and returns the complete refreshed state (the spec contract). +**The editor surface** is protocol-native [Session Config Options](https://agentclientprotocol.com/protocol/session-config-options) — the spec's replacement for session modes (slated for removal in ACP v2), already SDK-typed. When `ctx.permission` is composed, the bridge advertises one `permission` select (category `mode`) in `session/new` and `session/load`; its options are the deployment's preset table, and its `currentValue` is `PermissionService.current()` over the session log plus composition defaults. The shipped `workspace-write` and `danger-full-access` presets each bundle a sandbox mode with an approval policy and write through to both domain setters; a knob combination outside the table is reported as switch-away-only `custom`. `session/set_config_option` validates and switches through the permission service, then returns the complete refreshed state (the spec contract). **Anchoring: turn-enclosure is the commit boundary.** The turn-enclosure contract makes a bare between-turns append invalid (the JSONL backend treats a post-`turn/end` tail as crash garbage; dev invariants throw). A switch while a turn is open appends immediately — openness read from the LOG (last boundary event is `turn/start`), not `agent.status`, which stays `running` between queued turns. An idle switch is held on the bridge's session record and anchored at the next turn's `agent/prompt-submit` — inside the turn, before anything in it assembles or executes, last write per knob, and OUTSIDE any `session/event` emit (appending from inside that feed reorders events for later-registered listeners — a bug the dev invariants caught live). Until anchored, the switch exists only in bridge memory: responses overlay it truthfully, and a crash before the next turn reverts it — `session/load` then reports the fold's truth, so the editor UI self-corrects rather than lies. @@ -133,9 +137,9 @@ FIXME: Revisit this tool-local boundary. The follow-up design needs to determine ### Testing - Unit tier (no real runner anywhere): profile dialects, per-platform chain selection (sole candidate unprobed, no chain fails closed, multi-candidate probe order), verdict caching, the fail-closed end, probe-report parsing, and the launcher/`sandbox-exec` CLI contracts via fake runner scripts in `dsh-sandbox-local`; wrapping, policy hand-off, fact stamping, and runner-failure-outranks-denial classification (foreground throw, background `runnerFailed` fact) against a fake provider in `dsh-bash-sandbox`; the error's structured identity in `dsh-sandbox`. The escalation matrix spans the three bash packages: verbatim carry-through in `dsh-bash-local`, stamp/branch/per-task-facts in `dsh-bash-sandbox`, and the capability gate, `justification` pairing, fail-closed texts (pinned verbatim), and grant stamping in `dsh-tool-bash`. The switching surface pins the folds, the stamping precedence, the `'never'` gate, per-session section rendering, the full narrator matrix (cold start, coalescing, net-zero, resume drift with operator wording, positional attribution, persona-shadow hardening), and the bridge's advertisement gating, validation rejections, idle-vs-mid-turn anchoring (dev invariants mounted), and `session/load` reporting over a real two-process JSONL round trip. -- Keyless real-runner e2e, split along the seam and per rung: CI's `sandbox-e2e` matrix runs bwrap and Landlock on Linux (the Landlock leg once per architecture, each confining through the registry-installed launcher) and Seatbelt on macOS against real kernels, failing on a silent all-skip. World-proofs live in `dsh-sandbox-local` (denied writes absent on disk, workspace writes landing, temp-area grants pinned, kernel denial text matching the advertised dialect) and `dsh-bash-sandbox` (the through-`ctx.bash` consumer proofs, including denied-then-overridden-write-lands). This package's own publish path is rehearsed without publishing (`packed-install.e2e.ts`): `pnpm pack`, tarballs installed into a throwaway consumer with the launcher family resolving from the registry, plain `node` confining through the INSTALLED launcher — asserted executable apart, so a mode-stripped binary can never masquerade as a non-enforcing kernel. The switching surface has its own keyless e2e (`examples/sandbox-acp-agent`): the real `cordis.yml` tree advertises both options, honors switches end to end, and rejects out-of-vocabulary values. -- With-key e2e (`examples/sandbox-acp-agent/tests/escalation.e2e.ts`): real model + real runner + the REAL bridge answerer, world-verified — denied under `read-only`, escalates with justification, the scripted editor grants and the retried write lands on disk, while a rejected escalation leaves no write. Self-skips without `DEEPSEEK_API_KEY` or a usable runner (e2e.yml installs bubblewrap so it actually executes in CI). -- Snapshot tier (`examples/sandbox-acp-agent/tests/acp.snapshot.ts`): the keyless config-option wire; the recorded mode-switching arc as the suite's pinned header — necessarily, since its mid-session switch emits the changed `request/header` the uniformity guard licenses only in the pin — committing both switches, the full changed prompt and one "changed by the user" notice per knob, and a confined write landing under the switched mode; and both recorded escalation branches over scripted `permissionAnswers` (grant runs confined under `workspace-write`; rejection executes nothing and pins the fail-closed text). Replay re-executes every fixture's bash calls under the host's real runner (ci.yml's snapshot lane installs bubblewrap). Deliberately absent: a fixture carrying a real DENIAL — denial stderr is the backend's dialect and would pin a fixture to its recording platform; the escalation prompts assert the prior denial instead, and the denial→marker path stays on the tiers above. +- Keyless real-runner e2e, split along the seam and per rung: CI's `sandbox-e2e` matrix runs bwrap and Landlock on Linux (the Landlock leg once per architecture, each confining through the registry-installed launcher) and Seatbelt on macOS against real kernels, failing on a silent all-skip. World-proofs live in `dsh-sandbox-local` (denied writes absent on disk, workspace writes landing, temp-area grants pinned, kernel denial text matching the advertised dialect) and `dsh-bash-sandbox` (the through-`ctx.bash` consumer proofs, including denied-then-overridden-write-lands). This package's own publish path is rehearsed without publishing (`packed-install.e2e.ts`): `pnpm pack`, tarballs installed into a throwaway consumer with the launcher family resolving from the registry, plain `node` confining through the INSTALLED launcher — asserted executable apart, so a mode-stripped binary can never masquerade as a non-enforcing kernel. The switching surface has its own keyless e2e (the acp-agent example's `escalation.e2e.ts`): the real default `cordis.yml` tree advertises the one permission option, honors switches end to end, and rejects out-of-vocabulary values. +- With-key e2e (`examples/acp-agent/tests/escalation.e2e.ts`): real model + real runner + the REAL bridge answerer, world-verified — denied under `read-only`, escalates with justification, the scripted editor grants and the retried write lands on disk, while a rejected escalation leaves no write. Self-skips without `DEEPSEEK_API_KEY` or a usable runner (e2e.yml installs bubblewrap so it actually executes in CI). +- Snapshot tier (`examples/acp-agent/tests/acp.snapshot.ts`): the keyless config-option wire; the recorded permission-switching arc as the pinned header of its class — necessarily, since mid-session switches emit the changed `request/header` snapshot the uniformity guard licenses only in the pin — committing one `workspace-write`→`danger-full-access` preset switch (the `permission/preset` event written through to both knobs), the changed approval prompt section and its "changed by the user" notice; and both recorded escalation branches over scripted `permissionAnswers` (grant runs under the granted `danger-full-access`; rejection executes nothing and pins the fail-closed text). Snapshot mode starts the shared example tree at `danger-full-access` so established fixtures remain runner-independent; the switching and escalation inputs explicitly select `workspace-write` before exercising the policy path. Deliberately absent: a fixture carrying a real DENIAL — denial stderr is the backend's dialect and would pin a fixture to its recording platform; the escalation prompts assert the prior denial instead, and the denial→marker path stays on the real-runner tiers above. ## Deferred phases @@ -169,7 +173,7 @@ Each phase gets its full design when picked up, validated against the code at th - **Narrate via `agent/user-message` + a bus event** — rejected: it presupposes a turn-entry seam that does not exist (the real seam is `agent/prompt-submit`), and pre-step's position serves both the coalesced turn-entry notice and the mid-turn immediacy bound with one listener. - **A standing prompt statement of the sandbox mode (+ a switch narrator)** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery; the approval knob keeps its statement because an auto-rejection is behaviorally indistinguishable from a human "no". - **Track "last told" with its own bookkeeping events** — rejected: the latest `request/header` already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store. -- **ACP session modes instead of config options** — rejected: one mode list cannot carry two orthogonal knobs; config options are the spec's designed surface and modes are slated for removal in ACP v2. +- **ACP session modes instead of config options** — rejected: the preset is already one deployment-defined config-option select, and modes are slated for removal in ACP v2. ## Consequences diff --git a/docs/rfc/implemented/feature/2026-07-10-session-query-service.md b/docs/rfc/implemented/feature/2026-07-10-session-query-service.md new file mode 100644 index 0000000000..2bc6e456fb --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-10-session-query-service.md @@ -0,0 +1,41 @@ +# RFC: Exact session query service + +Status: implemented + +## Problem + +Session history exists in two places: current `SessionStore` objects and an optional persistence backend. Consumers that need exact inspection would otherwise duplicate live-versus-persisted precedence, persistence lifecycle handling, raw-event surface classification, and defensive cloning. Durable state can lag the live log between checkpoints, so persistence alone is not a truthful current source. + +Full-text search is related but materially larger. Designing provider registration, extraction, synchronization, invalidation, ranking, and cursor contracts before a real backend exists creates two speculative state machines: one in the interface service and another in the eventual database package. + +## Decision + +`@deepseek-ai/dsh-session-query` owns `ctx.sessionQuery`, a small trusted exact-read service over one logical corpus. It exposes `listSessions()`, `listEvents(sessionId)`, and bounded `readEvent(request)`. It does not expose filters, lineage or provenance traversals, text extractors, search requests, provider registration, or derived-index synchronization. + +The service observes the optional `ctx.sessionPersistence` binding dynamically but retains no persisted cache or invalidation listener. Each cross-corpus list asks the active backend for authoritative metadata, then overlays a fresh live-store list. Matching ids become one `SessionRecord`: the live header wins and `live`/`persisted` independently report source availability. Immutable header disagreement is `SESSION_QUERY_SOURCE_CONFLICT`. + +An exact target read first checks the live store and snapshots the live header and event log. This path never consults persistence, so a failing durable backend cannot make known live history unreadable. With no live target, the service lists current persistence metadata, proves the id exists, loads it, and rejects a list/load header mismatch. All returned headers and events cross one structured-clone boundary. + +## Surface semantics + +`dsh-session` exports `foldSurface(events)`, and `SurfaceManager` uses the same transition functions for its incremental cache. The fold returns detached current event sequences and each replacement's actual removed seqs. `listEvents()` uses that result to classify every raw event as `current`, `shadowed`, or `log-only`, so inspection cannot disagree with model-history derivation about positional replacement semantics. + +`readEvent()` returns the complete target plus raw neighbors by contiguous seq. `before` and `after` default to zero and are independently bounded by `readWindowMax`, default 50. The result carries a cloned `SessionHeader`, not a source-availability record, because determining a live target's persisted flag would violate the guarantee that live exact reads do not depend on persistence health. + +## Security boundary + +The service is context-wide trusted infrastructure, not an authorization layer. A future model-facing history tool or human UI applies explicit caller/session scope. This phase adds no model-facing tool and changes no transcript or snapshot surface. + +## Alternatives considered + +- **Put logical-corpus resolution directly in every consumer** — rejected because source precedence, conflicts, optional-service lifecycle, cloning, and surface classification are shared correctness rules. +- **Query only persistence** — rejected because checkpoints can lag the current live log. +- **Cache persisted metadata and listen for writes/removals** — rejected because exact reads can ask the authoritative sources directly, while cache invalidation adds lifecycle and concurrency state before scale requires it. +- **Define a provider-neutral search protocol now** — rejected because no provider consumes it. The first SQLite FTS package should own one reconciliation/transaction state machine; a smaller shared seam can be extracted later only when a second implementation proves the boundary. +- **Include lineage, provenance, and generic filters in phase one** — rejected because no current consumer requires them and canonical logs remain sufficient to add them with evidence later. + +## Consequences + +Phase one has one source-resolution state variable: the currently mounted persistence service. There are no provider queues, fingerprints, extractor registries, observation generations, or derived index updates. Exact reads remain usable in live-only deployments and deterministic when persistence is present. + +Cross-corpus listing and persisted exact reads perform backend I/O on each call. That is deliberate: correctness comes from current authoritative state, and scale-oriented search belongs to the phase-two database. Full-text search is unavailable until that package defines and implements its complete contract. diff --git a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md b/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md index dae2ecbec3..4f4bf8d569 100644 --- a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md +++ b/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md @@ -14,7 +14,7 @@ This proposal deliberately retains append and replacement `sourceEventSeqs`, cra ## Decision -`SurfaceManager.nodes` is a `readonly number[]` of event sequences; the public `SurfaceNode` shape, node links, and seq-to-node map are removed. The internal replace-generation signal remains. Tool-pairing balance and compaction use array values and indices for successor and replacement ranges. +`SurfaceManager.nodes` is a `readonly number[]` of event sequences; the public `SurfaceNode` shape, node links, and seq-to-node map are removed. The internal replace-generation signal remains. The complete `foldSurface()` read used by session-query returns the same number-array representation plus replacement metadata without making the incremental manager retain history. Tool-pairing balance and compaction use array values and indices for successor and replacement ranges. Request headers use canonical full snapshots only. Initial and resume anchors remain full snapshots even when unchanged; an in-instance change appends another full `request/header` with reason `change`. The delta event, codec types, diff/apply helpers, and codec-only `fallback` reason are removed. Request reconstruction selects the latest snapshot. diff --git a/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md b/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md new file mode 100644 index 0000000000..acfdf23bee --- /dev/null +++ b/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md @@ -0,0 +1,51 @@ +# RFC: SQLite FTS5 session search + +Status: proposed + +## Problem + +The exact-read `ctx.sessionQuery` service deliberately has no derived index. Large persisted histories need full-text search without scanning every event on every query, while current live sessions need an overlay newer than the last durability checkpoint. Search also needs concrete ranking, snippets, filters, pagination, cancellation, and rebuild behavior. + +Splitting those concerns across a speculative provider coordinator and a database implementation would create two coupled reconciliation state machines. The first real implementation should own the source observation, extraction, SQLite transaction, generation, and query as one lifecycle. + +## Proposal + +Add `@deepseek-ai/dsh-session-query-sqlite` beside the exact-read package. The package will expose a search service or extend the family with the smallest API required by its actual consumers; phase one does not pre-commit a provider-registration protocol. It will depend on `ctx.sessions` and optional `ctx.sessionPersistence`, own a separate derived SQLite database, and reuse the canonical `foldSurface()` classification. + +The implementation owns one serialized reconciliation/DB transaction state machine. A transaction observes authoritative persisted metadata and live snapshots, extracts semantic documents, updates derived tables, advances relevant cursor generations, and executes or enables the corresponding query. No second service maintains parallel fingerprints, dirty flags, live-id sets, or invalidation generations. + +Persisted documents survive restarts. Live overrides are connection-local and shadow the persisted rows for the same session, then disappear when the live owner or database closes. The derived database remains separate from canonical persistence so index reset, corruption, tokenizer changes, and schema churn cannot endanger durable conversation logs. + +## Search semantics to decide with implementation + +The implementation must define both cross-session and within-session scopes from executable use cases. Each searchable event is one document with session metadata, event metadata, surface classification, normalized semantic text, and a bounded plain-text snippet. Session results group by their strongest matching event; numeric backend scores remain private. + +Filters compile to parameterized SQL before ranking. Query syntax is treated as data. Ordering includes stable tie fields. Opaque cursors bind to normalized request shape and the smallest relevant generation; unrelated session changes should not invalidate a within-session cursor. Cancellation must stop caller waiting and interrupt SQLite work where the runtime permits. + +Tokenizer choice remains an implementation experiment. FTS5 trigram supports substring recall but rejects useful terms shorter than three characters and increases index size; the proposal must benchmark that tradeoff against the default Unicode tokenizer before making it contract. + +## Extraction and reconciliation + +The package starts with first-party semantic extraction for messages, reasoning, tool calls/results, blocked prompts, context, steering, todos, and error/status detail. Structural events and stream chunks contribute no document. Unknown declaration-merged event/content types remain non-searchable unless a real extension consumer demonstrates the need for a public extractor registry. + +Reconciliation may use stable fingerprints to avoid rewriting unchanged persisted sessions, but the database package owns their calculation and storage. It must never report a row current when source observation or extraction failed. Provider-schema mismatch may reset only the derived database; ordinary source changes use transactional upsert/delete. Mounted but unreadable persistence fails affected searches without affecting canonical writes or known live exact reads. + +## Alternatives considered + +- **Add FTS tables to the canonical persistence database** — rejected because a rebuildable index must not share the authoritative log's schema/reset/failure boundary. +- **Reintroduce phase-one provider coordination** — rejected because there is one planned implementation and no evidence for a stable multi-provider seam. +- **Persist live overrides immediately** — rejected because live events are not canonical until the existing checkpoint commits. +- **Return BM25 scores** — rejected because provider-specific numeric scales are unstable across corpus changes. + +## Acceptance criteria + +- Restart tests cover unchanged, new, changed, and deleted persisted sessions without rebuilding the whole index. +- Reopening preserves persisted rows and removes live rows; live rows shadow and then reveal their persisted base. +- Tests cover both search scopes, metadata filters, surface defaults, snippets, escaping, deterministic ties, pagination, scoped stale cursors, cancellation, dynamic persistence mount/unmount, and recovery after a failed transaction. +- A schema mismatch resets only the derived database. +- A keyless end-to-end test combines a real persistence backend with the real SQLite search package. +- The RFC is amended to the measured tokenizer and public API actually implemented before moving to `implemented/`. + +## Risks + +A single owner is simpler but initially less reusable than a provider-neutral seam. That is intentional: a second real backend can reveal what to extract. SQLite runtime differences can affect FTS ranking and snippets, so tests must pin only contract-controlled ordering and presentation. The separate database adds configuration and lifecycle work, but preserves the canonical store's safety boundary. diff --git a/examples/AGENTS.md b/examples/AGENTS.md index d54104a189..46a4eaa27b 100644 --- a/examples/AGENTS.md +++ b/examples/AGENTS.md @@ -22,7 +22,6 @@ A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_P | `echo-agent` | `tests/echo.e2e.ts` — boots the real `cordis.yml`, drives the echo tool round-trip and the direct canned reply | **N/A — keyless by nature** (the `mock-echo` model has no real provider) | | `coding-agent` | `tests/keyless-smoke.e2e.ts` — boots the full real tree (dummy key, no prompt → no model call), asserts banner + clean exit; `tests/code-mode-keyless-smoke.e2e.ts` — the same boot guard for the Code Mode overlay | `tests/{full-loop,coding-task,resume,compaction,todo-write}.e2e.ts` — real model + real bash + real todo_write, world-verified; `tests/code-mode.e2e.ts` — a real model composes two bash calls in one `run_code` program; collapsed header, dispatch events, written file all verified | | `cordis-agent` | `tests/keyless-smoke.e2e.ts` — boots the real tree incl. `@deepseek-ai/dsh-tool-cordis` by package name; the tool logic is unit-tested in `packages/cordis/tool-cordis` | `tests/cordis-tools.e2e.ts` — real model mounts a listener (tagged line fires), builds+calls its own tool, composes two mounts via provide/inject | -| `sandbox-acp-agent` | `escalation.e2e.ts` — boots the real tree (sandbox + approval + bridge) keyless: initialize + `session/new` | same file — denied → escalates → a scripted client grants (the write must land) or rejects (it must not); skips without key/runner | -| `acp-agent` | `pnpm run test:snapshot` — boots the real ACP subprocess and replays a recorded session keyless (incl. the hook matrix: a scenario per hook point × outcome for BOTH the Claude and Codex bridges — block, deny, ask, context-fold, force-continue); `tests/acp.e2e.ts` also asserts stdout purity without a key | `tests/acp.e2e.ts` — real ACP prompt, verifies a file the agent wrote; `tests/hooks.e2e.ts` — a real `PreToolUse` hook blocks bash, verifies the file is NOT written | +| `acp-agent` | `pnpm run test:snapshot` — boots the real ACP subprocess and replays a recorded session keyless (incl. the hook matrix: a scenario per hook point × outcome for BOTH the Claude and Codex bridges — block, deny, ask, context-fold, force-continue); `tests/acp.e2e.ts` also asserts stdout purity without a key; `tests/escalation.e2e.ts` boots the default tree (sandbox + approval + permission + bridge) keyless: initialize + `session/new` | `tests/acp.e2e.ts` — real ACP prompt, verifies a file the agent wrote; `tests/hooks.e2e.ts` — a real `PreToolUse` hook blocks bash, verifies the file is NOT written; `tests/escalation.e2e.ts` — denied → escalates → a scripted client grants (the write must land) or rejects (it must not); skips without key/runner | See [the root AGENTS.md](../AGENTS.md) for repo-wide conventions and [docs/architecture.md](../docs/architecture.md) for the design. diff --git a/examples/README.md b/examples/README.md index 7f711cb297..1319acd60b 100644 --- a/examples/README.md +++ b/examples/README.md @@ -33,8 +33,4 @@ An agent demo exposed as an **Agent Client Protocol (ACP)** server over JSON-RPC Run with: `pnpm run demo:acp` (needs `DEEPSEEK_API_KEY`); `pnpm run demo:code-mode acp` boots the same server in Code Mode via the `code-mode.cordis.yml` overlay. See [acp-agent/README.md](acp-agent/README.md) for the Zed setup and the snapshot-test design. -## sandbox-acp-agent - -The coding agent with its bash executor swapped for the sandbox stack ([`@deepseek-ai/dsh-sandbox-local`](../packages/sandbox/sandbox-local) + [`@deepseek-ai/dsh-bash-sandbox`](../packages/bash/bash-sandbox) — the one-entry executor swap the `ctx.bash` capability seam exists for), served over ACP with [`@deepseek-ai/dsh-user-approval`](../packages/ui/user-approval) mounted — the first composition where the approval loop is LIVE: a sandbox denial escalated by the model becomes a `session/request_permission` prompt in the editor, and "Allow once" runs exactly that command under the wider mode. - -Run with: `pnpm run demo:sandbox-acp` (needs `DEEPSEEK_API_KEY`; bwrap, a Landlock-enforcing kernel, or macOS for confined runs). See [sandbox-acp-agent/README.md](sandbox-acp-agent/README.md). +The default `cordis.yml` composes [`@deepseek-ai/dsh-sandbox-local`](../packages/sandbox/sandbox-local), [`@deepseek-ai/dsh-bash-sandbox`](../packages/bash/bash-sandbox), [`@deepseek-ai/dsh-user-approval`](../packages/ui/user-approval), and [`@deepseek-ai/dsh-permission`](../packages/ui/permission). A capable client gets one `Permissions` select: `workspace-write` confines bash to the configured workspace and asks before a wider retry, while `danger-full-access` removes file confinement and disables approval prompts. A denied command can therefore surface a one-shot `session/request_permission` prompt in the editor; "Allow once" runs exactly that retry under the requested wider mode. diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md index e3d8542efd..6a48b1f5b0 100644 --- a/examples/acp-agent/README.md +++ b/examples/acp-agent/README.md @@ -7,7 +7,7 @@ pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env) pnpm run demo:code-mode acp # the same server in Code Mode: one wire tool, run_code ``` -This example is just a leaf `cordis.yml`: it loads the [`@deepseek-ai/dsh-acp-agent`](../../packages/ui/acp-agent) app (which bundles the [`@deepseek-ai/dsh-agent-core`](../../packages/core/agent-core) spine, JSONL session persistence, and the `@deepseek-ai/dsh-acp` bridge — with **no pre-created agents**, since ACP `session/new` creates them on demand), the swappable DeepSeek, bash, and filesystem backends, the model-facing `read`/`write`/`edit`/`subagent`/`subagent_fork`/`todo_write` tool entries, and the advisory `repeat-tool-guard` loop-hygiene plugin. The app package bakes in the no-stdout-logger cluster, so a leaf has no logger entry to get wrong by default — keeping stdout pure for JSON-RPC. `demo:code-mode acp` boots the same tree through the [`code-mode.cordis.yml`](code-mode.cordis.yml) overlay — the tool surface collapses to `run_code` + the generated TypeScript SDK, dispatching through the worker-thread code runtime (see the [dsh-tools Code Mode section](../../packages/core/tools/README.md#code-mode)). +This example is one leaf `cordis.yml`: it loads the [`@deepseek-ai/dsh-acp-agent`](../../packages/ui/acp-agent) app (the [`@deepseek-ai/dsh-agent-core`](../../packages/core/agent-core) spine, JSONL session persistence, and the `@deepseek-ai/dsh-acp` bridge), the DeepSeek adapter, sandboxed bash, approval and permission services, subagent/workflow/todo tools, and the advisory `repeat-tool-guard`. ACP `session/new` creates agents on demand. The app package bakes in the no-stdout-logger cluster, so the leaf has no logger entry to get wrong by default. `demo:code-mode acp` boots the same tree through [`code-mode.cordis.yml`](code-mode.cordis.yml), collapsing the tool surface to `run_code` plus the generated TypeScript SDK (see the [dsh-tools Code Mode section](../../packages/core/tools/README.md#code-mode)). ## stdout is the protocol @@ -29,12 +29,22 @@ Add to your Zed `settings.json` under `agent_servers`: } ``` -The editor sets each session's `cwd` to the project it opens; both the agent's bash tools and the `read`/`write`/`edit` filesystem tools resolve relative paths against that per-session workspace (see the per-session `cwd` note in `packages/ui/acp` and [the per-session cwd RFC](../../docs/rfc/implemented/architecture/2026-07-02-fs-per-session-cwd.md)), so the server can be launched anywhere and each session still acts on its own project directory. +The editor sets each session's `cwd` to the project it opens, and bash uses that directory as its workdir. The current sandbox write boundary is nevertheless fixed when the server starts (`workspaceRoot: process.cwd()`), so launch the server from the workspace it should be allowed to modify; making that root session-scoped is deferred in the [sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). Filesystem tools are omitted from the confined default because they execute in-process and do not ride the bash sandbox. ## Snapshot tests (record-once / replay-deterministic) This example is the home of the harness's **snapshot tests** — they boot this server as a real subprocess, drive it with a deterministic input script, and diff its normalized output against committed golden files. The model is made deterministic by `@deepseek-ai/dsh-llm-replay`, a function/namespace plugin that installs an `llm/stream` waterfall listener and short-circuits it, serving model streams reconstructed from a recorded **session JSONL** fixture (`/session.jsonl`) — so replay needs no API key. The fixture IS the persisted session log: its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each `stream()` call (one model call per loop step). Recording is therefore "run the real agent once and harvest the `.jsonl`"; use `pnpm run test:snapshot:record` when the model transcript itself should change, and `pnpm run test:snapshot:refresh` when the committed model transcript is still the right mock input and only the current replay output/goldens need to be rewritten. The two failure modes not expressible as logged chunks — a pure throw before any chunk, and cancel/hang — use an optional `/replay.override.json` sidecar (a `ReplayEntry[]` that replaces the derived script). A scenario that needs the agent to operate on existing files ships an optional `/workspace/` directory — the harness copies its contents into the temp cwd before the run (see `workspace-edit`). See [the ACP snapshot tests RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) for the full design. +## Permissions and sandboxing + +The default tree composes [`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/), [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/), [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/), and [`@deepseek-ai/dsh-permission`](../../packages/ui/permission/). Bash starts in `workspace-write`; a denied operation returns a structured marker, and a retry with `sandbox_permissions` plus `justification` becomes a one-shot `session/request_permission` prompt in the editor. "Allow once" runs exactly that retry under the wider mode ([sandbox RFC § Escalation](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). + +- **One session config option is live**: a capable client shows one `Permissions` select. `workspace-write` means workspace-confined bash plus `ask`; `danger-full-access` means unconfined file access plus `never`. Switching writes one `permission/preset` event through to the sandbox-mode and approval-policy events, and `session/load` reports the resumed value. +- **Every approval is one-shot**: the choices are `Allow once` and `Reject`; a dismissal, rejection, missing editor, or unavailable runner fails closed. +- **The boundary is bash-only and config-fixed today**: in-process filesystem tools are omitted from the confined live default, while the sandbox workspace root remains the server's launch directory. + +`tests/escalation.e2e.ts` boots this default tree keyless, drives the permission select, and—with a key and usable runner—proves both approval outcomes against the filesystem. The snapshot suite uses the same tree: snapshot mode starts at `danger-full-access` so established fixtures remain runner-independent, while the permission-switching and escalation inputs explicitly select `workspace-write` before exercising that policy path. No fixture pins a real denial because kernel error text is backend-specific; real confinement remains covered by the sandbox packages' kernel e2e suites. + ## MVP limitations -The bridge supports N concurrent sessions per connection, each in its own workspace `cwd` (RFC 011). Remaining limits: prompts support ACP's baseline `text` and `resource_link` blocks only, and `additionalDirectories` and `mcpServers` are rejected. Permission prompts (`session/request_permission`) are wired through the approval seam, but this example composes no ask-producing policy, so tools run with the executor's full authority. See `packages/ui/acp/README.md` for the full contract. +The bridge supports N concurrent sessions per connection, each with its own `cwd` (RFC 011). Prompts support ACP's baseline `text` and `resource_link` blocks only; `additionalDirectories` and `mcpServers` are rejected. See [`packages/ui/acp/README.md`](../../packages/ui/acp/README.md) for the full contract. diff --git a/examples/acp-agent/composition.md b/examples/acp-agent/composition.md index fb882a06a0..d5c3096666 100644 --- a/examples/acp-agent/composition.md +++ b/examples/acp-agent/composition.md @@ -10,8 +10,14 @@ flowchart LR cfg["examples/acp-agent
cordis.yml"] plugin_acp_llm_deepseek["llm-deepseek
@deepseek-ai/dsh-llm-deepseek"] cfg --> plugin_acp_llm_deepseek - plugin_acp_bash["bash
@deepseek-ai/dsh-bash-local"] + plugin_acp_sandbox["sandbox
@deepseek-ai/dsh-sandbox-local"] + cfg --> plugin_acp_sandbox + plugin_acp_bash["bash
@deepseek-ai/dsh-bash-sandbox"] cfg --> plugin_acp_bash + plugin_acp_approval["approval
@deepseek-ai/dsh-user-approval"] + cfg --> plugin_acp_approval + plugin_acp_permission["permission
@deepseek-ai/dsh-permission"] + cfg --> plugin_acp_permission plugin_acp_acp_agent["acp-agent
@deepseek-ai/dsh-acp-agent"] cfg --> plugin_acp_acp_agent plugin_acp_acp_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-core"] @@ -54,7 +60,10 @@ flowchart LR | Plugin id | Package / module | | --- | --- | | `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` | -| `bash` | `@deepseek-ai/dsh-bash-local` | +| `sandbox` | `@deepseek-ai/dsh-sandbox-local` | +| `bash` | `@deepseek-ai/dsh-bash-sandbox` | +| `approval` | `@deepseek-ai/dsh-user-approval` | +| `permission` | `@deepseek-ai/dsh-permission` | | `acp-agent` | `@deepseek-ai/dsh-acp-agent` | | `subagent` | `@deepseek-ai/dsh-subagent` | | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index dc03ea6b03..42c8bb46f0 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -1,9 +1,9 @@ # The acp-agent plugin tree: the ACP server. Also the snapshot RECORD config # (the dsh-acp-agent bin selects it for DSH_SNAPSHOT=record): a real llm-deepseek # run whose persisted log the snapshot harness harvests. The swappable DeepSeek -# adapter, local bash/filesystem executors, the ACP server app -# (@deepseek-ai/dsh-acp-agent), and the optional model-facing fs/subagent/todo -# tools loaded below. +# adapter, sandboxed bash executor, the ACP server app +# (@deepseek-ai/dsh-acp-agent), and the optional model-facing +# fs/subagent/todo tools loaded below. # # CRITICAL: this tree loads NO stdout logger and NO hmr — stdout is reserved for # the ACP JSON-RPC protocol (see packages/ui/acp). That guarantee is now a @@ -23,12 +23,27 @@ - deepseek-v4-flash - deepseek-v4-pro -# Local bash executor for agent-core's tool-bash schema (one of several tool -# stacks in this tree: filesystem, subagent, and todo_write load below). +# The default composition confines bash to the workspace and asks before a +# wider retry. Snapshot runs select danger-full-access so the established +# scenarios remain runner-independent; DSH_PERMISSION_MODE provides the same +# explicit deployment/test override outside the snapshot harness. +- id: sandbox + name: '@deepseek-ai/dsh-sandbox-local' + - id: bash - name: '@deepseek-ai/dsh-bash-local' + name: '@deepseek-ai/dsh-bash-sandbox' config: timeoutMs: 60000 + mode: !!js "process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')" + workspaceRoot: !!js process.cwd() + +- id: approval + name: '@deepseek-ai/dsh-user-approval' + config: + policy: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) === 'danger-full-access' ? 'never' : 'ask'" + +- id: permission + name: '@deepseek-ai/dsh-permission' # The ACP server app: the agent-core spine + JSONL persistence + the ACP bridge. # Persistence root: $DSH_SNAPSHOT_SESSIONS_ROOT when the snapshot harness sets it @@ -44,7 +59,7 @@ # loop resolves per session (every ACP session carries the client's cwd, # so the persona can state the workspace). persona: | - You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. + You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. Verify your work by running the code or tests. Keep answers brief and factual. @@ -104,20 +119,22 @@ - id: repeat-tool-guard name: '@deepseek-ai/dsh-repeat-tool-guard' -# Filesystem capability stack: local provider, read-before-write/edit policy -# gate, then the model-facing read/write/edit tools. Relative filesystem paths -# resolve from the server launch cwd; the documented Zed setup launches this -# demo from the harness checkout with `pnpm --dir`. +# Filesystem tools do not ride the bash sandbox, so the confined default omits +# them. Snapshot tests and explicit danger-full-access launches keep the +# established filesystem scenarios by enabling the whole stack together. - id: fs-local name: '@deepseek-ai/dsh-fs-local' + disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'" config: cwd: !!js process.cwd() - id: fs-policy name: '@deepseek-ai/dsh-fs-policy' + disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'" - id: tool-fs name: '@deepseek-ai/dsh-tool-fs' + disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'" # The Claude Code hook bridge. `configPath` is PROCESS-LEVEL: it is read ONCE at # load and the relative `./hooks.json` resolves against the ACP server's launch diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index 871006dfb4..a1ddbeccc6 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -25,6 +25,7 @@ const AGENT: AgentUnderTest = { configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } +const DANGER_FULL_ACCESS_ENV = { DSH_PERMISSION_MODE: 'danger-full-access' } let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined @@ -52,7 +53,10 @@ describe('acp-agent over real stdio (no key required)', () => { spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir, - env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, + env: { + DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', + ...DANGER_FULL_ACCESS_ENV, + }, }) await spawned.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -83,7 +87,10 @@ describe('acp-agent over real stdio (no key required)', () => { spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir, - env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, + env: { + DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', + ...DANGER_FULL_ACCESS_ENV, + }, }) const { client } = spawned @@ -97,7 +104,7 @@ describe('acp-agent over real stdio (no key required)', () => { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over ACP', () => { it('runs a real turn and the agent writes the requested file (verified on disk)', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir, env: DANGER_FULL_ACCESS_ENV }) const { client, updates } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -138,7 +145,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over it('with the terminal_output capability, a real bash call renders as a terminal card (content + _meta + exit)', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir, env: DANGER_FULL_ACCESS_ENV }) const { client, updates } = spawned // Advertise the Zed `_meta.terminal_output` capability so the bridge emits diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 61d747a87c..2e05bef069 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -133,6 +133,15 @@ const SCENARIOS: Scenario[] = [ // therefore pins its own class. { name: 'code-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'code', configPath: CODE_MODE_CONFIG }, { name: 'both-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'both', configPath: BOTH_MODE_CONFIG }, + // The default tree owns the single Permissions select. Snapshot mode starts + // in danger-full-access so established fixtures stay runner-independent; + // these policy scenarios switch to workspace-write in their input scripts. + // Real-kernel confinement remains in escalation.e2e.ts and the sandbox + // packages' e2e suites. + { name: 'config-options', hasModelTurn: false, recorded: false, headerClass: 'sandbox' }, + { name: 'permission-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'sandbox' }, + { name: 'escalation-approved', hasModelTurn: true, recorded: true, headerClass: 'sandbox' }, + { name: 'escalation-rejected', hasModelTurn: true, recorded: true, headerClass: 'sandbox' }, ] defineAcpSnapshotSuite({ diff --git a/examples/sandbox-acp-agent/tests/escalation.e2e.ts b/examples/acp-agent/tests/escalation.e2e.ts similarity index 72% rename from examples/sandbox-acp-agent/tests/escalation.e2e.ts rename to examples/acp-agent/tests/escalation.e2e.ts index 0ddaa6426e..da8d3408c2 100644 --- a/examples/sandbox-acp-agent/tests/escalation.e2e.ts +++ b/examples/acp-agent/tests/escalation.e2e.ts @@ -15,7 +15,7 @@ import { } from '@deepseek-ai/dsh-acp-snapshot' /** - * examples/sandbox-acp-agent end to end. + * The default ACP composition (`cordis.yml`) end to end. * * Keyless smoke: boot the REAL `cordis.yml` through the `dsh-acp-agent` bin as * an ACP subprocess and drive initialize + session/new — the real-Loader-path @@ -24,13 +24,13 @@ import { * model nor a sandbox runner is ever exercised. * * With-key escalation flow (self-skips without DEEPSEEK_API_KEY or a usable - * platform runner): a scripted ACP client plays the human. The real model is - * denied under `read-only`, escalates with `sandbox_permissions` + + * platform runner): a scripted ACP client plays the human. The prompt asserts + * a prior denial (the organic denial→marker path lives on the sandbox e2e + * legs and unit tiers), the real model escalates with `sandbox_permissions` + * `justification`, the bridge prompts THIS client over * `session/request_permission`, the client answers `allow-once`, and the - * retried write must land ON DISK (world-verified). The session cwd is a temp - * dir under the platform temp area, which `workspace-write` grants — so either - * escalation target the model picks can land the write. + * retried write must land ON DISK (world-verified) — under the granted mode, + * a temp-dir session cwd is writable either way. */ const AGENT: AgentUnderTest = { @@ -58,7 +58,7 @@ interface Spawned extends LaunchedAcpTestAgent { } /** Boot the example as an ACP subprocess; the scripted client answers every permission prompt with `answer`. */ -function launchSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned { +function launchExampleAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned { const permissionRequests: RequestPermissionRequest[] = [] const launched = launchAcpTestAgent({ agent: AGENT, @@ -93,10 +93,10 @@ afterEach(async () => { } }) -describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () => { +describe('default sandbox composition keyless smoke (real cordis.yml via the Loader)', () => { it('boots the tree — sandbox executor + approval service + bridge — and opens a session', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-smoke-')) - spawned = launchSandboxAcpAgent(workdir, 'reject-once') + spawned = launchExampleAcpAgent(workdir, 'reject-once') const { client } = spawned // A dummy key boots the adapter; no prompt is ever sent, so no model call // and no sandbox runner probe happen. This drives the fiber tree the same @@ -107,53 +107,52 @@ describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () expect(sessionId.length).toBeGreaterThan(0) }, 30_000) - it('advertises both session config options and honors a switch end to end (no key, no model)', async () => { + it('advertises the Permissions select and honors a switch end to end (no key, no model)', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-config-')) - spawned = launchSandboxAcpAgent(workdir, 'reject-once') + spawned = launchExampleAcpAgent(workdir, 'reject-once') const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) - // This tree composes bash-sandbox (mode: read-only) + approval → both - // knobs advertise, currents from composition config. + // This tree composes the permission presets over bash-sandbox + approval → + // ONE select advertises, current from the configured default preset. const created = await client.newSession({ cwd: workdir, mcpServers: [] }) const advertised = created.configOptions ?? [] expect(advertised.map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined])) - .toEqual([['sandbox-mode', 'read-only'], ['approval-policy', 'ask']]) + .toEqual([['permission', 'workspace-write']]) // A switch responds with the COMPLETE refreshed state (the spec contract), - // and the new currents survive in the response of a second switch. - const afterSandbox = await client.setSessionConfigOption({ - sessionId: created.sessionId, configId: 'sandbox-mode', value: 'workspace-write', + // and the new current survives in the response of a second switch. + const afterFullAccess = await client.setSessionConfigOption({ + sessionId: created.sessionId, configId: 'permission', value: 'danger-full-access', }) - const afterApproval = await client.setSessionConfigOption({ - sessionId: created.sessionId, configId: 'approval-policy', value: 'never', + expect(afterFullAccess.configOptions?.find(option => option.id === 'permission')) + .toMatchObject({ currentValue: 'danger-full-access' }) + const again = await client.setSessionConfigOption({ + sessionId: created.sessionId, configId: 'permission', value: 'danger-full-access', }) - const currents = (afterApproval.configOptions ?? []).map(option => - [option.id, 'currentValue' in option ? option.currentValue : undefined]) - expect(afterSandbox.configOptions?.find(option => option.id === 'sandbox-mode')) - .toMatchObject({ currentValue: 'workspace-write' }) - expect(currents).toEqual([['sandbox-mode', 'workspace-write'], ['approval-policy', 'never']]) + expect((again.configOptions ?? []).map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined])) + .toEqual([['permission', 'danger-full-access']]) // An out-of-vocabulary value is a protocol error, never a silent default. await expect(client.setSessionConfigOption({ - sessionId: created.sessionId, configId: 'sandbox-mode', value: 'yolo', - })).rejects.toThrow(/unknown sandbox-mode value/) + sessionId: created.sessionId, configId: 'permission', value: 'plan', + })).rejects.toThrow(/unknown permission value/) }, 30_000) }) -describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent e2e: the live approval loop', () => { +describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('default sandbox composition e2e: the live approval loop', () => { it('denial → model escalation → editor prompt → allow-once → the retried write lands on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-')) - spawned = launchSandboxAcpAgent(workdir, 'allow-once') + spawned = launchExampleAcpAgent(workdir, 'allow-once') const { client, permissionRequests } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await client.newSession({ cwd: workdir, mcpServers: [] }) const res = await client.prompt({ sessionId, - prompt: [{ type: 'text', text: `Use the bash tool to create the file ${workdir}/escalated.txt containing exactly "ACP_ESCALATION_OK". ` - + 'If the sandbox denies it, retry once with sandbox_permissions and a one-sentence justification, then stop.' }], + prompt: [{ type: 'text', text: `The sandbox already denied writing ${workdir}/escalated.txt. Create it now containing exactly "ACP_ESCALATION_OK": ` + + 'one single bash call with sandbox_permissions set to danger-full-access and a one-sentence justification, then stop.' }], }) expect(['end_turn', 'max_tokens']).toContain(res.stopReason) - // The WORLD: the approved escalated retry landed the write read-only denied. + // The WORLD: the approved escalated retry landed the write. const proof = await readFile(join(workdir, 'escalated.txt'), 'utf8') expect(proof).toContain('ACP_ESCALATION_OK') @@ -170,15 +169,15 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent it('a rejected escalation stays denied: no write lands, the turn still ends', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-')) - spawned = launchSandboxAcpAgent(workdir, 'reject-once') + spawned = launchExampleAcpAgent(workdir, 'reject-once') const { client, permissionRequests } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await client.newSession({ cwd: workdir, mcpServers: [] }) const res = await client.prompt({ sessionId, - prompt: [{ type: 'text', text: `Use the bash tool to create the file ${workdir}/refused.txt containing "NO". ` - + 'If the sandbox denies it, retry once with sandbox_permissions and a one-sentence justification. If that is rejected, stop and say so.' }], + prompt: [{ type: 'text', text: `The sandbox already denied writing ${workdir}/refused.txt. Create it now containing "NO": ` + + 'one single bash call with sandbox_permissions set to danger-full-access and a one-sentence justification. If that is rejected, stop and say so.' }], }) expect(['end_turn', 'max_tokens']).toContain(res.stopReason) diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index 8dc169f437..df231184c3 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -60,7 +60,11 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook hooks: { PreToolUse: [{ hooks: [{ type: 'command', command: 'echo "bash blocked by policy" >&2; exit 2' }] }] }, })) - spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) + spawned = launchAcpTestAgent({ + agent: AGENT, + cwd: workdir, + env: { DSH_PERMISSION_MODE: 'danger-full-access' }, + }) const { client, updates } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 1eabba53b3..cdc09c92c0 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 7787ed2ab1..79d9b94ad9 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index bb74382b22..7155b1c2a6 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl index 2e9174f026..72b41e8d89 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-code","title":"return await tools.cordis_inspect({ what: 'dynamic' })","kind":"execute","status":"in_progress","rawInput":"return await tools.cordis_inspect({ what: 'dynamic' })"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index e70cfcce44..6e8f157ace 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -5,14 +5,11 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. - Check the [exit code: N] marker on every bash result; investigate failures before moving on. +Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + + Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. ## Writing code for run_code @@ -28,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; @@ -40,6 +37,10 @@ declare const tools: { workdir?: string; /** Run in the background and return a task id immediately. No timeout applies. */ run_in_background?: boolean; + /** The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ + justification?: string; }): Promise; /** Ask the executor to kill a running background bash task by task id. */ bash_kill(args: { @@ -66,26 +67,6 @@ declare const tools: { /** The dynamic mount id returned by cordis_mount (e.g. "dyn-1"). */ id: string; }): Promise; - /** Edit an existing UTF-8 text file by replacing literal text. */ - edit(args: { - /** Path to edit, resolved by the filesystem backend. */ - file_path: string; - /** Literal text to replace. Must match exactly. */ - old_string: string; - /** Literal replacement text. Use an empty string to delete the match. */ - new_string: string; - /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ - replace_all?: boolean; - }): Promise; - /** Read a UTF-8 text file and return line-numbered content. */ - read(args: { - /** Path to read, resolved by the filesystem backend. */ - file_path: string; - /** 1-based first line to return. Defaults to 1. */ - offset?: number; - /** Maximum number of lines to return. Defaults to 2000. */ - limit?: number; - }): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -140,12 +121,5 @@ declare const tools: { /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */ args?: Record; }): Promise; - /** Create or fully replace a UTF-8 text file. */ - write(args: { - /** Path to write, resolved by the filesystem backend. */ - file_path: string; - /** Full UTF-8 text content to write. */ - content: string; - }): Promise; } ``` diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index b49097188e..66cdecedfb 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl index e54775b7ff..f5bf912125 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 5dd8547aa8..98b4f97fee 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -5,14 +5,11 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. - Check the [exit code: N] marker on every bash result; investigate failures before moving on. +Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + + Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. ## Writing code for run_code @@ -28,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; @@ -40,6 +37,10 @@ declare const tools: { workdir?: string; /** Run in the background and return a task id immediately. No timeout applies. */ run_in_background?: boolean; + /** The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ + justification?: string; }): Promise; /** Ask the executor to kill a running background bash task by task id. */ bash_kill(args: { @@ -51,26 +52,6 @@ declare const tools: { /** Task id returned by the bash tool. */ task_id: string; }): Promise; - /** Edit an existing UTF-8 text file by replacing literal text. */ - edit(args: { - /** Path to edit, resolved by the filesystem backend. */ - file_path: string; - /** Literal text to replace. Must match exactly. */ - old_string: string; - /** Literal replacement text. Use an empty string to delete the match. */ - new_string: string; - /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ - replace_all?: boolean; - }): Promise; - /** Read a UTF-8 text file and return line-numbered content. */ - read(args: { - /** Path to read, resolved by the filesystem backend. */ - file_path: string; - /** 1-based first line to return. Defaults to 1. */ - offset?: number; - /** Maximum number of lines to return. Defaults to 2000. */ - limit?: number; - }): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -125,12 +106,5 @@ declare const tools: { /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */ args?: Record; }): Promise; - /** Create or fully replace a UTF-8 text file. */ - write(args: { - /** Path to write, resolved by the filesystem backend. */ - file_path: string; - /** Full UTF-8 text content to write. */ - content: string; - }): Promise; } ``` diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl index 3400223f4d..ea8a9c2bb7 100644 --- a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl index 97610ed1c0..c0b2346444 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 5dd8547aa8..98b4f97fee 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -5,14 +5,11 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. - Check the [exit code: N] marker on every bash result; investigate failures before moving on. +Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + + Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. ## Writing code for run_code @@ -28,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; @@ -40,6 +37,10 @@ declare const tools: { workdir?: string; /** Run in the background and return a task id immediately. No timeout applies. */ run_in_background?: boolean; + /** The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ + justification?: string; }): Promise; /** Ask the executor to kill a running background bash task by task id. */ bash_kill(args: { @@ -51,26 +52,6 @@ declare const tools: { /** Task id returned by the bash tool. */ task_id: string; }): Promise; - /** Edit an existing UTF-8 text file by replacing literal text. */ - edit(args: { - /** Path to edit, resolved by the filesystem backend. */ - file_path: string; - /** Literal text to replace. Must match exactly. */ - old_string: string; - /** Literal replacement text. Use an empty string to delete the match. */ - new_string: string; - /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ - replace_all?: boolean; - }): Promise; - /** Read a UTF-8 text file and return line-numbered content. */ - read(args: { - /** Path to read, resolved by the filesystem backend. */ - file_path: string; - /** 1-based first line to return. Defaults to 1. */ - offset?: number; - /** Maximum number of lines to return. Defaults to 2000. */ - limit?: number; - }): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -125,12 +106,5 @@ declare const tools: { /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */ args?: Record; }): Promise; - /** Create or fully replace a UTF-8 text file. */ - write(args: { - /** Path to write, resolved by the filesystem backend. */ - file_path: string; - /** Full UTF-8 text content to write. */ - content: string; - }): Promise; } ``` diff --git a/examples/acp-agent/tests/snapshots/config-options/input.json b/examples/acp-agent/tests/snapshots/config-options/input.json new file mode 100644 index 0000000000..900367cea8 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/config-options/input.json @@ -0,0 +1,30 @@ +{ + "steps": [ + { + "op": "initialize" + }, + { + "op": "newSession" + }, + { + "op": "setConfigOption", + "configId": "permission", + "value": "workspace-write" + }, + { + "op": "setConfigOption", + "configId": "permission", + "value": "danger-full-access" + }, + { + "op": "setConfigOptionExpectError", + "configId": "permission", + "value": "plan" + }, + { + "op": "setConfigOptionExpectError", + "configId": "reasoning-effort", + "value": "max" + } + ] +} diff --git a/examples/sandbox-acp-agent/tests/snapshots/config-options/session.jsonl b/examples/acp-agent/tests/snapshots/config-options/session.jsonl similarity index 100% rename from examples/sandbox-acp-agent/tests/snapshots/config-options/session.jsonl rename to examples/acp-agent/tests/snapshots/config-options/session.jsonl diff --git a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl new file mode 100644 index 0000000000..0bcb0245d0 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl @@ -0,0 +1,6 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} +{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} +{"jsonrpc":"2.0","id":5,"error":{"code":-32602,"message":"Invalid params: unknown permission value \"plan\""}} +{"jsonrpc":"2.0","id":6,"error":{"code":-32602,"message":"Invalid params: unknown config option \"reasoning-effort\""}} diff --git a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl index 8515dacf5a..63d9032ca2 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"error":{"code":-32603,"message":"Internal error: turn failed: simulated provider error (HTTP 401)"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/input.json b/examples/acp-agent/tests/snapshots/escalation-approved/input.json new file mode 100644 index 0000000000..99f9f8821b --- /dev/null +++ b/examples/acp-agent/tests/snapshots/escalation-approved/input.json @@ -0,0 +1,24 @@ +{ + "steps": [ + { + "op": "initialize" + }, + { + "op": "newSession" + }, + { + "op": "setConfigOption", + "configId": "permission", + "value": "workspace-write" + }, + { + "op": "prompt", + "text": "The sandbox already denied writing /tmp/dsh-escalated.txt earlier (it is outside this workspace). Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt, with sandbox_permissions set to danger-full-access and the justification 'the user asked to write a file outside the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop." + } + ], + "permissionAnswers": [ + { + "kind": "allow_once" + } + ] +} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl new file mode 100644 index 0000000000..8aac1627bc --- /dev/null +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -0,0 +1,188 @@ +{"type":"session","version":0,"id":"f3cbd087-fb45-4b32-b0f2-3082d65bfcb4","createdAt":1783860675270,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-cbBLh2"} +{"type":"turn/start","seq":0,"time":1783860675271,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"permission/preset","seq":1,"time":1783962245380,"data":{"preset":"workspace-write"}} +{"type":"bash/sandbox-mode","seq":2,"time":1783962245380,"data":{"mode":"workspace-write"}} +{"type":"approval/policy","seq":3,"time":1783962245380,"data":{"policy":"ask"}} +{"type":"user/message","seq":4,"time":1783962245380,"data":{"content":[{"type":"text","text":"The sandbox already denied writing /tmp/dsh-escalated.txt earlier (it is outside this workspace). Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt, with sandbox_permissions set to danger-full-access and the justification 'the user asked to write a file outside the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":5,"time":1783962245382,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":6,"time":1783962245382,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":7,"time":1783860676464,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":8,"time":1783860676465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":9,"time":1783860676465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":10,"time":1783860676465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":11,"time":1783860676465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":12,"time":1783860676499,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":13,"time":1783860676499,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":14,"time":1783860676499,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":15,"time":1783860676522,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} +{"type":"assistant/chunk","seq":16,"time":1783860676525,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":17,"time":1783860676525,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sand"}}} +{"type":"assistant/chunk","seq":18,"time":1783860676525,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}} +{"type":"assistant/chunk","seq":19,"time":1783860676553,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_per"}}} +{"type":"assistant/chunk","seq":20,"time":1783860676553,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"missions"}}} +{"type":"assistant/chunk","seq":21,"time":1783860676554,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" set"}}} +{"type":"assistant/chunk","seq":22,"time":1783860676554,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":23,"time":1783860676554,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" danger"}}} +{"type":"assistant/chunk","seq":24,"time":1783860676583,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-full"}}} +{"type":"assistant/chunk","seq":25,"time":1783860676583,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-access"}}} +{"type":"assistant/chunk","seq":26,"time":1783860676611,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":27,"time":1783860676639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" no"}}} +{"type":"assistant/chunk","seq":28,"time":1783860676640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" prior"}}} +{"type":"assistant/chunk","seq":29,"time":1783860676672,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":30,"time":1783860676673,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" needed"}}} +{"type":"assistant/chunk","seq":31,"time":1783860676705,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":32,"time":1783860676728,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" justified"}}} +{"type":"assistant/chunk","seq":33,"time":1783860676787,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} +{"type":"assistant/chunk","seq":34,"time":1783860676788,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" instructed"}}} +{"type":"assistant/chunk","seq":35,"time":1783860676816,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":36,"time":1783860676816,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":37,"time":1783860676816,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":38,"time":1783860676816,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":39,"time":1783860676845,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":40,"time":1783860676845,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"command"}}} +{"type":"assistant/chunk","seq":41,"time":1783860676846,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":42,"time":1783860676846,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":43,"time":1783860676878,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":44,"time":1783860676878,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"printf"}}} +{"type":"assistant/chunk","seq":45,"time":1783860676878,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" '"}}} +{"type":"assistant/chunk","seq":46,"time":1783860676878,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"es"}}} +{"type":"assistant/chunk","seq":47,"time":1783860676878,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":48,"time":1783860676879,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":49,"time":1783860676909,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\\\\n"}}} +{"type":"assistant/chunk","seq":50,"time":1783860676911,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"'"}}} +{"type":"assistant/chunk","seq":51,"time":1783860676912,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" >"}}} +{"type":"assistant/chunk","seq":52,"time":1783860676912,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" /"}}} +{"type":"assistant/chunk","seq":53,"time":1783860676912,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"tmp"}}} +{"type":"assistant/chunk","seq":54,"time":1783860676939,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"/d"}}} +{"type":"assistant/chunk","seq":55,"time":1783860676941,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"sh"}}} +{"type":"assistant/chunk","seq":56,"time":1783860676941,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"-es"}}} +{"type":"assistant/chunk","seq":57,"time":1783860676941,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":58,"time":1783860676941,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":59,"time":1783860676967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":60,"time":1783860676969,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" &&"}}} +{"type":"assistant/chunk","seq":61,"time":1783860676969,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" cat"}}} +{"type":"assistant/chunk","seq":62,"time":1783860676970,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" /"}}} +{"type":"assistant/chunk","seq":63,"time":1783860676970,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"tmp"}}} +{"type":"assistant/chunk","seq":64,"time":1783860676970,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"/d"}}} +{"type":"assistant/chunk","seq":65,"time":1783860677003,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"sh"}}} +{"type":"assistant/chunk","seq":66,"time":1783860677003,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"-es"}}} +{"type":"assistant/chunk","seq":67,"time":1783860677003,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":68,"time":1783860677003,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":69,"time":1783860677004,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":70,"time":1783860677004,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" &&"}}} +{"type":"assistant/chunk","seq":71,"time":1783860677026,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" rm"}}} +{"type":"assistant/chunk","seq":72,"time":1783860677026,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" /"}}} +{"type":"assistant/chunk","seq":73,"time":1783860677026,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"tmp"}}} +{"type":"assistant/chunk","seq":74,"time":1783860677026,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"/d"}}} +{"type":"assistant/chunk","seq":75,"time":1783860677026,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"sh"}}} +{"type":"assistant/chunk","seq":76,"time":1783860677026,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"-es"}}} +{"type":"assistant/chunk","seq":77,"time":1783860677055,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":78,"time":1783860677085,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":79,"time":1783860677087,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":80,"time":1783860677087,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":81,"time":1783860677087,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":82,"time":1783860677087,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":83,"time":1783860677115,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":84,"time":1783860677115,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":85,"time":1783860677116,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":86,"time":1783860677116,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":87,"time":1783860677146,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"Write"}}} +{"type":"assistant/chunk","seq":88,"time":1783860677147,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" file"}}} +{"type":"assistant/chunk","seq":89,"time":1783860677148,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" outside"}}} +{"type":"assistant/chunk","seq":90,"time":1783860677174,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" workspace"}}} +{"type":"assistant/chunk","seq":91,"time":1783860677202,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":92,"time":1783860677202,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" verify"}}} +{"type":"assistant/chunk","seq":93,"time":1783860677202,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":94,"time":1783860677202,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":95,"time":1783860677202,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":96,"time":1783860677238,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"sand"}}} +{"type":"assistant/chunk","seq":97,"time":1783860677238,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"box"}}} +{"type":"assistant/chunk","seq":98,"time":1783860677238,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"_per"}}} +{"type":"assistant/chunk","seq":99,"time":1783860677238,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"missions"}}} +{"type":"assistant/chunk","seq":100,"time":1783860677275,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":101,"time":1783860677275,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":102,"time":1783860677276,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":103,"time":1783860677276,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"danger"}}} +{"type":"assistant/chunk","seq":104,"time":1783860677292,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"-full"}}} +{"type":"assistant/chunk","seq":105,"time":1783860677293,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"-access"}}} +{"type":"assistant/chunk","seq":106,"time":1783860677320,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":107,"time":1783860677321,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":108,"time":1783860677321,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":109,"time":1783860677321,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"just"}}} +{"type":"assistant/chunk","seq":110,"time":1783860677349,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"ification"}}} +{"type":"assistant/chunk","seq":111,"time":1783860677349,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":112,"time":1783860677349,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":113,"time":1783860677349,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":114,"time":1783860677349,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"the"}}} +{"type":"assistant/chunk","seq":115,"time":1783860677349,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" user"}}} +{"type":"assistant/chunk","seq":116,"time":1783860677388,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" asked"}}} +{"type":"assistant/chunk","seq":117,"time":1783860677388,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" to"}}} +{"type":"assistant/chunk","seq":118,"time":1783860677388,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" write"}}} +{"type":"assistant/chunk","seq":119,"time":1783860677388,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" a"}}} +{"type":"assistant/chunk","seq":120,"time":1783860677492,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" file"}}} +{"type":"assistant/chunk","seq":121,"time":1783860677493,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" outside"}}} +{"type":"assistant/chunk","seq":122,"time":1783860677493,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":123,"time":1783860677493,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":" workspace"}}} +{"type":"assistant/chunk","seq":124,"time":1783860677493,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":125,"time":1783860677493,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":126,"time":1783860677493,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."}}}} +{"type":"assistant/chunk","seq":127,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}}} +{"type":"assistant/chunk","seq":128,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}}}} +{"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} +{"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","outcome":"allowed-once"}} +{"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"} +{"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":137,"time":1783860678811,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":138,"time":1783860678811,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":139,"time":1783860678833,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} +{"type":"assistant/chunk","seq":140,"time":1783860678834,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" succeeded"}}} +{"type":"assistant/chunk","seq":141,"time":1783860678834,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" —"}}} +{"type":"assistant/chunk","seq":142,"time":1783860678868,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":143,"time":1783860678868,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" wrote"}}} +{"type":"assistant/chunk","seq":144,"time":1783860678868,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":145,"time":1783860678904,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" file"}}} +{"type":"assistant/chunk","seq":146,"time":1783860678905,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":147,"time":1783860678926,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" read"}}} +{"type":"assistant/chunk","seq":148,"time":1783860678926,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":149,"time":1783860678926,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" back"}}} +{"type":"assistant/chunk","seq":150,"time":1783860678975,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} +{"type":"assistant/chunk","seq":151,"time":1783860678976,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"output"}}} +{"type":"assistant/chunk","seq":152,"time":1783860678976,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":153,"time":1783860678976,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"es"}}} +{"type":"assistant/chunk","seq":154,"time":1783860678976,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"cal"}}} +{"type":"assistant/chunk","seq":155,"time":1783860678976,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ated"}}} +{"type":"assistant/chunk","seq":156,"time":1783860678999,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"),"}}} +{"type":"assistant/chunk","seq":157,"time":1783860679001,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":158,"time":1783860679002,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" removed"}}} +{"type":"assistant/chunk","seq":159,"time":1783860679002,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":160,"time":1783860679002,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":161,"time":1783860679016,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} +{"type":"assistant/chunk","seq":162,"time":1783860679017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":163,"time":1783860679017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} +{"type":"assistant/chunk","seq":164,"time":1783860679017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":165,"time":1783860679046,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":166,"time":1783860679047,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":167,"time":1783860679048,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":168,"time":1783860679048,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":169,"time":1783860679079,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":170,"time":1783860679079,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":171,"time":1783860679103,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" D"}}} +{"type":"assistant/chunk","seq":172,"time":1783860679136,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":173,"time":1783860679136,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" after"}}} +{"type":"assistant/chunk","seq":174,"time":1783860679136,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":175,"time":1783860679136,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} +{"type":"assistant/chunk","seq":176,"time":1783860679136,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":177,"time":1783860679137,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":178,"time":1783860679137,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} +{"type":"assistant/chunk","seq":179,"time":1783860679137,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":180,"time":1783860679137,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The command succeeded — it wrote the file, read it back (output \"escalated\"), and removed it. The user asked me to reply with the single word DONE after the result."}}}} +{"type":"assistant/chunk","seq":181,"time":1783962245402,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":182,"time":1783962245402,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":27,"outputTokens":42,"cacheReadTokens":1664,"reasoningTokens":39}}}} +{"type":"assistant/chunk","seq":183,"time":1783962245402,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":184,"time":1783962245402,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command succeeded — it wrote the file, read it back (output \"escalated\"), and removed it. The user asked me to reply with the single word DONE after the result."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":27,"outputTokens":42,"cacheReadTokens":1664,"reasoningTokens":39}},"sourceEventSeqs":[137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183],"surfaceOp":"append"} +{"type":"step/end","seq":185,"time":1783962245402,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":186,"time":1783962245402,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl similarity index 63% rename from examples/sandbox-acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl rename to examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl index 88fe79c0ce..d8074c0757 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl @@ -1,13 +1,13 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ret"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ry"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sand"}}}} @@ -16,30 +16,44 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"missions"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" set"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" workspace"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-w"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"rite"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" danger"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-full"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-access"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" no"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" prior"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" needed"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" justified"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" as"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instructed"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" They"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" explicitly"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" said"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" they"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" will"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" approve"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" permission"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" prompt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" proceed"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","title":"printf 'escalated\\n' > escalated.txt && cat escalated.txt","kind":"execute","status":"in_progress","rawInput":"printf 'escalated\\n' > escalated.txt && cat escalated.txt","content":[{"type":"content","content":{"type":"text","text":"Write escalated.txt and cat its content"}}]}}} -{"jsonrpc":"2.0","id":1,"method":"session/request_permission","params":{"sessionId":"{{sessionId}}","toolCall":{"toolCallId":"call_00_ZSEIrZNdgQhL2QJgVHww8689"},"options":[{"optionId":"allow-once","name":"Allow once","kind":"allow_once"},{"optionId":"reject-once","name":"Reject","kind":"reject_once"}]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nescalated\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","title":"printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt","kind":"execute","status":"in_progress","rawInput":"printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt","content":[{"type":"content","content":{"type":"text","text":"Write file outside workspace and verify"}}]}}} +{"jsonrpc":"2.0","id":1,"method":"session/request_permission","params":{"sessionId":"{{sessionId}}","toolCall":{"toolCallId":"call_00_d0sAHpJ9mYOJi0z7KNy30441"},"options":[{"optionId":"allow-once","name":"Allow once","kind":"allow_once"},{"optionId":"reject-once","name":"Reject","kind":"reject_once"}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nescalated\n```"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" succeeded"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" —"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wrote"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" read"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" back"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ("}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"output"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"es"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"cal"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ated"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"),"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" removed"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} @@ -53,7 +67,10 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" after"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} +{"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/input.json b/examples/acp-agent/tests/snapshots/escalation-rejected/input.json new file mode 100644 index 0000000000..83b9d8aab5 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/input.json @@ -0,0 +1,24 @@ +{ + "steps": [ + { + "op": "initialize" + }, + { + "op": "newSession" + }, + { + "op": "setConfigOption", + "configId": "permission", + "value": "workspace-write" + }, + { + "op": "prompt", + "text": "The sandbox already denied writing /tmp/dsh-escalated.txt earlier (it is outside this workspace). Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt, with sandbox_permissions set to danger-full-access and the justification 'the user asked to write a file outside the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it \u2014 explain in one short sentence and stop." + } + ], + "permissionAnswers": [ + { + "kind": "reject_once" + } + ] +} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl new file mode 100644 index 0000000000..7c0a743413 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -0,0 +1,215 @@ +{"type":"session","version":0,"id":"d692fe7f-7079-4ee4-8b06-f44fd026d4ea","createdAt":1783860679475,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-Hn29Od"} +{"type":"turn/start","seq":0,"time":1783860679476,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"permission/preset","seq":1,"time":1783962246267,"data":{"preset":"workspace-write"}} +{"type":"bash/sandbox-mode","seq":2,"time":1783962246267,"data":{"mode":"workspace-write"}} +{"type":"approval/policy","seq":3,"time":1783962246267,"data":{"policy":"ask"}} +{"type":"user/message","seq":4,"time":1783962246267,"data":{"content":[{"type":"text","text":"The sandbox already denied writing /tmp/dsh-escalated.txt earlier (it is outside this workspace). Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt, with sandbox_permissions set to danger-full-access and the justification 'the user asked to write a file outside the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":5,"time":1783962246269,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":6,"time":1783962246269,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":7,"time":1783860680779,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":8,"time":1783860680782,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":9,"time":1783860680782,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":10,"time":1783860680782,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":11,"time":1783860680830,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":12,"time":1783860680831,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":13,"time":1783860680831,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":14,"time":1783860680859,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":15,"time":1783860680859,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} +{"type":"assistant/chunk","seq":16,"time":1783860680868,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} +{"type":"assistant/chunk","seq":17,"time":1783860680871,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":18,"time":1783860680871,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} +{"type":"assistant/chunk","seq":19,"time":1783860680872,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"sand"}}} +{"type":"assistant/chunk","seq":20,"time":1783860680872,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}} +{"type":"assistant/chunk","seq":21,"time":1783860680902,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_per"}}} +{"type":"assistant/chunk","seq":22,"time":1783860680903,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"missions"}}} +{"type":"assistant/chunk","seq":23,"time":1783860680903,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}} +{"type":"assistant/chunk","seq":24,"time":1783860680903,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" set"}}} +{"type":"assistant/chunk","seq":25,"time":1783860680903,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":26,"time":1783860680903,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} +{"type":"assistant/chunk","seq":27,"time":1783860680937,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"danger"}}} +{"type":"assistant/chunk","seq":28,"time":1783860680938,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-full"}}} +{"type":"assistant/chunk","seq":29,"time":1783860680938,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-access"}}} +{"type":"assistant/chunk","seq":30,"time":1783860680956,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}} +{"type":"assistant/chunk","seq":31,"time":1783860680958,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":32,"time":1783860680958,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":33,"time":1783860680958,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} +{"type":"assistant/chunk","seq":34,"time":1783860680985,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" justification"}}} +{"type":"assistant/chunk","seq":35,"time":1783860680985,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":36,"time":1783860681022,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" They"}}} +{"type":"assistant/chunk","seq":37,"time":1783860681024,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" explicitly"}}} +{"type":"assistant/chunk","seq":38,"time":1783860681024,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" said"}}} +{"type":"assistant/chunk","seq":39,"time":1783860681024,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" NOT"}}} +{"type":"assistant/chunk","seq":40,"time":1783860681024,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":41,"time":1783860681043,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":42,"time":1783860681091,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":43,"time":1783860681091,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" without"}}} +{"type":"assistant/chunk","seq":44,"time":1783860681091,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sand"}}} +{"type":"assistant/chunk","seq":45,"time":1783860681091,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}} +{"type":"assistant/chunk","seq":46,"time":1783860681091,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_per"}}} +{"type":"assistant/chunk","seq":47,"time":1783860681091,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"missions"}}} +{"type":"assistant/chunk","seq":48,"time":1783860681107,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" first"}}} +{"type":"assistant/chunk","seq":49,"time":1783860681107,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":50,"time":1783860681108,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":51,"time":1783860681138,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":52,"time":1783860681138,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} +{"type":"assistant/chunk","seq":53,"time":1783860681251,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":54,"time":1783860681251,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} +{"type":"assistant/chunk","seq":55,"time":1783860681251,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":56,"time":1783860681251,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":57,"time":1783860681252,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":58,"time":1783860681252,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":59,"time":1783860681252,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":60,"time":1783860681252,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"command"}}} +{"type":"assistant/chunk","seq":61,"time":1783860681280,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":62,"time":1783860681281,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":63,"time":1783860681281,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":64,"time":1783860681324,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"printf"}}} +{"type":"assistant/chunk","seq":65,"time":1783860681324,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" '"}}} +{"type":"assistant/chunk","seq":66,"time":1783860681324,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"es"}}} +{"type":"assistant/chunk","seq":67,"time":1783860681324,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":68,"time":1783860681324,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":69,"time":1783860681324,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\\\\n"}}} +{"type":"assistant/chunk","seq":70,"time":1783860681342,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"'"}}} +{"type":"assistant/chunk","seq":71,"time":1783860681343,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" >"}}} +{"type":"assistant/chunk","seq":72,"time":1783860681343,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" /"}}} +{"type":"assistant/chunk","seq":73,"time":1783860681343,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"tmp"}}} +{"type":"assistant/chunk","seq":74,"time":1783860681368,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"/d"}}} +{"type":"assistant/chunk","seq":75,"time":1783860681371,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"sh"}}} +{"type":"assistant/chunk","seq":76,"time":1783860681371,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"-es"}}} +{"type":"assistant/chunk","seq":77,"time":1783860681371,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":78,"time":1783860681371,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":79,"time":1783860681400,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":80,"time":1783860681400,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" &&"}}} +{"type":"assistant/chunk","seq":81,"time":1783860681400,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" cat"}}} +{"type":"assistant/chunk","seq":82,"time":1783860681400,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" /"}}} +{"type":"assistant/chunk","seq":83,"time":1783860681401,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"tmp"}}} +{"type":"assistant/chunk","seq":84,"time":1783860681402,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"/d"}}} +{"type":"assistant/chunk","seq":85,"time":1783860681432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"sh"}}} +{"type":"assistant/chunk","seq":86,"time":1783860681432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"-es"}}} +{"type":"assistant/chunk","seq":87,"time":1783860681432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":88,"time":1783860681432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":89,"time":1783860681432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":90,"time":1783860681432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" &&"}}} +{"type":"assistant/chunk","seq":91,"time":1783860681456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" rm"}}} +{"type":"assistant/chunk","seq":92,"time":1783860681456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" /"}}} +{"type":"assistant/chunk","seq":93,"time":1783860681456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"tmp"}}} +{"type":"assistant/chunk","seq":94,"time":1783860681456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"/d"}}} +{"type":"assistant/chunk","seq":95,"time":1783860681456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"sh"}}} +{"type":"assistant/chunk","seq":96,"time":1783860681456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"-es"}}} +{"type":"assistant/chunk","seq":97,"time":1783860681485,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":98,"time":1783860681519,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":99,"time":1783860681521,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":100,"time":1783860681521,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":101,"time":1783860681521,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":102,"time":1783860681521,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":103,"time":1783860681542,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":104,"time":1783860681545,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":105,"time":1783860681545,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":106,"time":1783860681573,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":107,"time":1783860681573,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"Write"}}} +{"type":"assistant/chunk","seq":108,"time":1783860681574,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" to"}}} +{"type":"assistant/chunk","seq":109,"time":1783860681605,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" /"}}} +{"type":"assistant/chunk","seq":110,"time":1783860681608,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"tmp"}}} +{"type":"assistant/chunk","seq":111,"time":1783860681630,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":112,"time":1783860681632,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" verify"}}} +{"type":"assistant/chunk","seq":113,"time":1783860681661,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":","}}} +{"type":"assistant/chunk","seq":114,"time":1783860681661,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" then"}}} +{"type":"assistant/chunk","seq":115,"time":1783860681693,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" clean"}}} +{"type":"assistant/chunk","seq":116,"time":1783860681693,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" up"}}} +{"type":"assistant/chunk","seq":117,"time":1783860681693,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":118,"time":1783860681693,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":119,"time":1783860681725,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":120,"time":1783860681725,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"sand"}}} +{"type":"assistant/chunk","seq":121,"time":1783860681726,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"box"}}} +{"type":"assistant/chunk","seq":122,"time":1783860681726,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"_per"}}} +{"type":"assistant/chunk","seq":123,"time":1783860681751,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"missions"}}} +{"type":"assistant/chunk","seq":124,"time":1783860681753,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":125,"time":1783860681754,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":126,"time":1783860681754,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":127,"time":1783860681754,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"danger"}}} +{"type":"assistant/chunk","seq":128,"time":1783860681813,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"-full"}}} +{"type":"assistant/chunk","seq":129,"time":1783860681813,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"-access"}}} +{"type":"assistant/chunk","seq":130,"time":1783860681813,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":131,"time":1783860681813,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":132,"time":1783860681813,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":133,"time":1783860681815,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"just"}}} +{"type":"assistant/chunk","seq":134,"time":1783860681840,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"ification"}}} +{"type":"assistant/chunk","seq":135,"time":1783860681842,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":136,"time":1783860681842,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":137,"time":1783860681842,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":138,"time":1783860681842,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"the"}}} +{"type":"assistant/chunk","seq":139,"time":1783860681870,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" user"}}} +{"type":"assistant/chunk","seq":140,"time":1783860681870,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" asked"}}} +{"type":"assistant/chunk","seq":141,"time":1783860681870,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" to"}}} +{"type":"assistant/chunk","seq":142,"time":1783860681870,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" write"}}} +{"type":"assistant/chunk","seq":143,"time":1783860681870,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" a"}}} +{"type":"assistant/chunk","seq":144,"time":1783860681872,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" file"}}} +{"type":"assistant/chunk","seq":145,"time":1783860681901,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" outside"}}} +{"type":"assistant/chunk","seq":146,"time":1783860681903,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":147,"time":1783860681967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":" workspace"}}} +{"type":"assistant/chunk","seq":148,"time":1783860681967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":149,"time":1783860681967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":150,"time":1783860681967,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."}}}} +{"type":"assistant/chunk","seq":151,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}}} +{"type":"assistant/chunk","seq":152,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}}}} +{"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"} +{"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"9e6c7946-af56-4535-9cce-993e0165c2f9","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"9e6c7946-af56-4535-9cce-993e0165c2f9","outcome":"rejected"}} +{"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"} +{"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":161,"time":1783860683140,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":162,"time":1783860683141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":163,"time":1783860683141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":164,"time":1783860683170,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} +{"type":"assistant/chunk","seq":165,"time":1783860683170,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":166,"time":1783860683170,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" escalation"}}} +{"type":"assistant/chunk","seq":167,"time":1783860683205,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":168,"time":1783860683208,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" As"}}} +{"type":"assistant/chunk","seq":169,"time":1783860683208,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instructed"}}} +{"type":"assistant/chunk","seq":170,"time":1783860683208,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":171,"time":1783860683208,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":172,"time":1783860683230,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" will"}}} +{"type":"assistant/chunk","seq":173,"time":1783860683232,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" not"}}} +{"type":"assistant/chunk","seq":174,"time":1783860683233,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" ret"}}} +{"type":"assistant/chunk","seq":175,"time":1783860683260,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ry"}}} +{"type":"assistant/chunk","seq":176,"time":1783860683260,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":177,"time":1783860683260,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" will"}}} +{"type":"assistant/chunk","seq":178,"time":1783860683260,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" not"}}} +{"type":"assistant/chunk","seq":179,"time":1783860683260,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" work"}}} +{"type":"assistant/chunk","seq":180,"time":1783860683294,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" around"}}} +{"type":"assistant/chunk","seq":181,"time":1783860683296,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":182,"time":1783860683296,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" —"}}} +{"type":"assistant/chunk","seq":183,"time":1783860683317,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} +{"type":"assistant/chunk","seq":184,"time":1783860683317,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" explain"}}} +{"type":"assistant/chunk","seq":185,"time":1783860683317,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} +{"type":"assistant/chunk","seq":186,"time":1783860683318,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" one"}}} +{"type":"assistant/chunk","seq":187,"time":1783860683318,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" short"}}} +{"type":"assistant/chunk","seq":188,"time":1783860683318,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sentence"}}} +{"type":"assistant/chunk","seq":189,"time":1783860683347,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":190,"time":1783860683347,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":191,"time":1783860683349,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":192,"time":1783860683349,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":193,"time":1783860683375,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}} +{"type":"assistant/chunk","seq":194,"time":1783860683376,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" user"}}} +{"type":"assistant/chunk","seq":195,"time":1783860683409,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} +{"type":"assistant/chunk","seq":196,"time":1783860683410,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} +{"type":"assistant/chunk","seq":197,"time":1783860683410,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" permission"}}} +{"type":"assistant/chunk","seq":198,"time":1783860683435,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" escalation"}}} +{"type":"assistant/chunk","seq":199,"time":1783860683437,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":","}}} +{"type":"assistant/chunk","seq":200,"time":1783860683437,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" so"}}} +{"type":"assistant/chunk","seq":201,"time":1783860683462,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" this"}}} +{"type":"assistant/chunk","seq":202,"time":1783860683464,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" command"}}} +{"type":"assistant/chunk","seq":203,"time":1783860683464,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" cannot"}}} +{"type":"assistant/chunk","seq":204,"time":1783860683506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" be"}}} +{"type":"assistant/chunk","seq":205,"time":1783860683506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" run"}}} +{"type":"assistant/chunk","seq":206,"time":1783860683506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"."}}} +{"type":"assistant/chunk","seq":207,"time":1783860683506,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user rejected the escalation. As instructed, I will not retry and will not work around it — just explain in one short sentence and stop."}}}} +{"type":"assistant/chunk","seq":208,"time":1783962246279,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The user rejected the permission escalation, so this command cannot be run."}}}} +{"type":"assistant/chunk","seq":209,"time":1783962246279,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":69,"outputTokens":45,"cacheReadTokens":1664,"reasoningTokens":30}}}} +{"type":"assistant/chunk","seq":210,"time":1783962246279,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":211,"time":1783962246279,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user rejected the escalation. As instructed, I will not retry and will not work around it — just explain in one short sentence and stop."},{"type":"text","text":"The user rejected the permission escalation, so this command cannot be run."}],"usage":{"inputTokens":69,"outputTokens":45,"cacheReadTokens":1664,"reasoningTokens":30}},"sourceEventSeqs":[161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210],"surfaceOp":"append"} +{"type":"step/end","seq":212,"time":1783962246279,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":213,"time":1783962246279,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl similarity index 74% rename from examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl rename to examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl index f8b292e4c3..c14b05f06a 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl @@ -1,31 +1,15 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ret"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ry"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exact"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specific"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"printf"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" '"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"es"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"cal"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ated"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" >"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" escalated"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" &&"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cat"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" escalated"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"sand"}}}} @@ -36,52 +20,60 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" set"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"works"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"pace"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-w"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"rite"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"danger"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-full"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-access"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specific"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" justification"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" they"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specified"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" They"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" explicitly"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" say"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" they"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" will"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reject"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" permission"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" prompt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" so"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" after"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejection"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" explain"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" in"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" one"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" short"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sentence"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" said"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" NOT"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" without"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sand"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"box"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_per"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"missions"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_ODln9LCQtuvTw4FDZEfe3479","title":"printf 'escalated\\n' > escalated.txt && cat escalated.txt","kind":"execute","status":"in_progress","rawInput":"printf 'escalated\\n' > escalated.txt && cat escalated.txt","content":[{"type":"content","content":{"type":"text","text":"Write escalated.txt with workspace-write permission"}}]}}} -{"jsonrpc":"2.0","id":1,"method":"session/request_permission","params":{"sessionId":"{{sessionId}}","toolCall":{"toolCallId":"call_00_ODln9LCQtuvTw4FDZEfe3479"},"options":[{"optionId":"allow-once","name":"Allow once","kind":"allow_once"},{"optionId":"reject-once","name":"Reject","kind":"reject_once"}]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_ODln9LCQtuvTw4FDZEfe3479","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: the user rejected escalating this command to \"workspace-write\"\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" do"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_WB1vnPomi8yr6MlcFKTj7912","title":"printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt","kind":"execute","status":"in_progress","rawInput":"printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt","content":[{"type":"content","content":{"type":"text","text":"Write to /tmp and verify, then clean up"}}]}}} +{"jsonrpc":"2.0","id":1,"method":"session/request_permission","params":{"sessionId":"{{sessionId}}","toolCall":{"toolCallId":"call_00_WB1vnPomi8yr6MlcFKTj7912"},"options":[{"optionId":"allow-once","name":"Allow once","kind":"allow_once"},{"optionId":"reject-once","name":"Reject","kind":"reject_once"}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_WB1vnPomi8yr6MlcFKTj7912","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: the user rejected escalating this command to \"danger-full-access\"\n```"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" escalation"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" As"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instructed"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" will"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" not"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ret"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ry"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" will"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" not"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" work"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" around"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" —"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" just"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" explain"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" in"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" one"}}}} @@ -91,21 +83,17 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" escalation"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" request"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" write"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" workspace"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" was"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" rejected"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" permission"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" escalation"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":","}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" so"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" this"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" command"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" was"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" not"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" executed"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" cannot"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" be"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" run"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} +{"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl index 90f009946d..723282d1a8 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl @@ -69,7 +69,7 @@ {"type":"assistant/chunk","seq":67,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":68,"time":1783352086059,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read config.txt in the current directory\n2. Use the edit tool to replace DEBUG with RELEASE\n3. Reply with exactly \"DONE\"\n\nLet me start by reading the file."},{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}],"usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67],"surfaceOp":"append"} {"type":"tool/call","seq":69,"time":1783352086059,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}} -{"type":"tool/result","seq":70,"time":1783352086065,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","content":[{"type":"text","text":"/tmp/acp-snap-cwd-0BxHdV/config.txt\nfile\n\n1: mode=DEBUG\n2: level=info\n\n(End of file - total 2 lines)\n"}],"isError":false},"sourceEventSeqs":[69],"surfaceOp":"append"} +{"type":"tool/result","seq":70,"time":1783352086065,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[69],"surfaceOp":"append"} {"type":"step/end","seq":71,"time":1783352086065,"data":{"turn":1,"step":1}} {"type":"step/start","seq":72,"time":1783352086066,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":73,"time":1783352086901,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -129,7 +129,7 @@ {"type":"assistant/chunk","seq":127,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":128,"time":1783352087469,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Now I need to replace \"DEBUG\" with \"RELEASE\" using the edit tool."},{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}],"usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"surfaceOp":"append"} {"type":"tool/call","seq":129,"time":1783352087469,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}} -{"type":"tool/result","seq":130,"time":1783352087476,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","content":[{"type":"text","text":"The file /tmp/acp-snap-cwd-0BxHdV/config.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"config.txt","oldText":"mode=DEBUG\nlevel=info","newText":"mode=RELEASE\nlevel=info"}]}},"sourceEventSeqs":[129],"surfaceOp":"append"} +{"type":"tool/result","seq":130,"time":1783352087476,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[129],"surfaceOp":"append"} {"type":"step/end","seq":131,"time":1783352087477,"data":{"turn":1,"step":2}} {"type":"step/start","seq":132,"time":1783352087477,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":133,"time":1783352088286,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl index e585a34fbe..5bc88537ce 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -46,8 +46,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","title":"Read config.txt","kind":"read","status":"in_progress","locations":[{"path":"config.txt","line":1}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/config.txt\nfile\n\n1: mode=DEBUG\n2: level=info\n\n(End of file - total 2 lines)\n"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"config.txt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Now"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} @@ -66,8 +66,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" edit"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","title":"Edit config.txt","kind":"edit","status":"in_progress","locations":[{"path":"config.txt"}],"content":[{"type":"diff","path":"config.txt","oldText":"DEBUG","newText":"RELEASE"}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","status":"completed","content":[{"type":"diff","path":"config.txt","oldText":"mode=DEBUG\nlevel=info","newText":"mode=RELEASE\nlevel=info"}],"title":"Edit config.txt"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"config.txt","old_string":"DEBUG","new_string":"RELEASE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Done"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl index 802120fd9c..8a500475c0 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl @@ -77,7 +77,7 @@ {"type":"assistant/chunk","seq":75,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":76,"time":1783611703972,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the edit tool to replace \"blue\" with \"green\" in settings.txt without reading the file first, and then reply with just \"DONE\"."},{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"} {"type":"tool/call","seq":77,"time":1783611703972,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}} -{"type":"tool/result","seq":78,"time":1783611703978,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: edit requires reading \"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\" first"}],"isError":true,"error":{"name":"FsError","code":"FS_NOT_OBSERVED"}},"sourceEventSeqs":[77],"surfaceOp":"append"} +{"type":"tool/result","seq":78,"time":1783611703978,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[77],"surfaceOp":"append"} {"type":"step/end","seq":79,"time":1783611703978,"data":{"turn":1,"step":1}} {"type":"step/start","seq":80,"time":1783611703978,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":81,"time":1783611704825,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -144,7 +144,7 @@ {"type":"assistant/chunk","seq":142,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":143,"time":1783611705573,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The edit tool requires reading the file first. The user said \"Do not read the file first\" but the tool's own constraints require reading. I need to follow the tool requirements. Let me read the file first."},{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}],"usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}},"sourceEventSeqs":[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} {"type":"tool/call","seq":144,"time":1783611705573,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}} -{"type":"tool/result","seq":145,"time":1783611705579,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","content":[{"type":"text","text":"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\nfile\n\n1: color: blue\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"} +{"type":"tool/result","seq":145,"time":1783611705579,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[144],"surfaceOp":"append"} {"type":"step/end","seq":146,"time":1783611705579,"data":{"turn":1,"step":2}} {"type":"step/start","seq":147,"time":1783611705579,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":148,"time":1783611706200,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -225,7 +225,7 @@ {"type":"assistant/chunk","seq":223,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":224,"time":1783611707097,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file contains \"color: blue\". I need to replace \"blue\" with \"green\". The edit tool said it requires reading first — now I've read it, so the edit should work."},{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223],"surfaceOp":"append"} {"type":"tool/call","seq":225,"time":1783611707097,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}} -{"type":"tool/result","seq":226,"time":1783611707114,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","content":[{"type":"text","text":"The file /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"settings.txt","oldText":"color: blue","newText":"color: green"}]}},"sourceEventSeqs":[225],"surfaceOp":"append"} +{"type":"tool/result","seq":226,"time":1783611707114,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[225],"surfaceOp":"append"} {"type":"step/end","seq":227,"time":1783611707114,"data":{"turn":1,"step":3}} {"type":"step/start","seq":228,"time":1783611707114,"data":{"turn":1,"step":4}} {"type":"assistant/chunk","seq":229,"time":1783611707747,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl index dfe2cd6ec5..864cc3de9f 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -36,8 +36,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","title":"Edit settings.txt","kind":"edit","status":"in_progress","locations":[{"path":"settings.txt"}],"content":[{"type":"diff","path":"settings.txt","oldText":"blue","newText":"green"}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: edit requires reading \"{{cwd}}/settings.txt\" first"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt","old_string":"blue","new_string":"green"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" edit"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} @@ -82,8 +82,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","title":"Read settings.txt","kind":"read","status":"in_progress","locations":[{"path":"settings.txt","line":1}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/settings.txt\nfile\n\n1: color: blue\n\n(End of file - total 1 lines)\n"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}} @@ -124,8 +124,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" work"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","title":"Edit settings.txt","kind":"edit","status":"in_progress","locations":[{"path":"settings.txt"}],"content":[{"type":"diff","path":"settings.txt","oldText":"blue","newText":"green"}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","status":"completed","content":[{"type":"diff","path":"settings.txt","oldText":"color: blue","newText":"color: green"}],"title":"Edit settings.txt"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt","old_string":"blue","new_string":"green"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" replacement"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl index becc503c65..f22aba96b2 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl @@ -91,7 +91,7 @@ {"type":"assistant/chunk","seq":89,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":90,"time":1783352101348,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the read tool with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE.\n\nLet me first check the current directory, then read the file."},{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}],"usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89],"surfaceOp":"append"} {"type":"tool/call","seq":91,"time":1783352101348,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}} -{"type":"tool/result","seq":92,"time":1783352101353,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","content":[{"type":"text","text":"/tmp/acp-snap-cwd-N9HCkt/big.txt\nfile\n\n5: line five\n6: line six\n7: line seven\n8: line eight\n\n(Showing lines 5-8 of 10. Use offset=9 to continue.)\n"}],"isError":false},"sourceEventSeqs":[91],"surfaceOp":"append"} +{"type":"tool/result","seq":92,"time":1783352101353,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[91],"surfaceOp":"append"} {"type":"step/end","seq":93,"time":1783352101353,"data":{"turn":1,"step":1}} {"type":"step/start","seq":94,"time":1783352101354,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":95,"time":1783352102021,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl index e265e7d51d..c283736334 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -56,8 +56,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","title":"Read big.txt (5 - 8)","kind":"read","status":"in_progress","locations":[{"path":"big.txt","line":5}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/big.txt\nfile\n\n5: line five\n6: line six\n7: line seven\n8: line eight\n\n(Showing lines 5-8 of 10. Use offset=9 to continue.)\n"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"big.txt","offset":5,"limit":4}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" read"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl index 3af4b2ac61..d91d10d39a 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl @@ -53,7 +53,7 @@ {"type":"assistant/chunk","seq":51,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":52,"time":1783352073708,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file greeting.txt using the read tool (not bash), then reply with exactly the single word \"DONE\"."},{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352073709,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}} -{"type":"tool/result","seq":54,"time":1783352073717,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","content":[{"type":"text","text":"/tmp/acp-snap-cwd-PEETkS/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"} +{"type":"tool/result","seq":54,"time":1783352073717,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":55,"time":1783352073718,"data":{"turn":1,"step":1}} {"type":"step/start","seq":56,"time":1783352073719,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":57,"time":1783352074666,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl index 6efc6f6d67..4f2973bcc5 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -29,8 +29,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","title":"Read greeting.txt","kind":"read","status":"in_progress","locations":[{"path":"greeting.txt","line":1}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"greeting.txt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl index e9dcb4c77d..6ab374dc0a 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl index 47627ae7a5..0233abbe39 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl @@ -65,7 +65,7 @@ {"type":"assistant/chunk","seq":63,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":64,"time":1783352093617,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read data.txt using the read tool\n2. Replace its entire contents with exactly \"replaced\" using the write tool\n3. Reply with exactly \"DONE\""},{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}],"usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"} {"type":"tool/call","seq":65,"time":1783352093617,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}} -{"type":"tool/result","seq":66,"time":1783352093624,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","content":[{"type":"text","text":"/tmp/acp-snap-cwd-hH2sGY/data.txt\nfile\n\n1: original contents\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[65],"surfaceOp":"append"} +{"type":"tool/result","seq":66,"time":1783352093624,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[65],"surfaceOp":"append"} {"type":"step/end","seq":67,"time":1783352093624,"data":{"turn":1,"step":1}} {"type":"step/start","seq":68,"time":1783352093625,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":69,"time":1783352094455,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -114,7 +114,7 @@ {"type":"assistant/chunk","seq":112,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":113,"time":1783352094988,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"original contents\". Now I'll replace it with \"replaced\"."},{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}],"usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"tool/call","seq":114,"time":1783352094988,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}} -{"type":"tool/result","seq":115,"time":1783352094995,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","content":[{"type":"text","text":"/tmp/acp-snap-cwd-hH2sGY/data.txt\nfile\n\nUpdated file\n"}],"isError":false,"meta":{"diffs":[{"path":"data.txt","oldText":"original contents","newText":"replaced"}]}},"sourceEventSeqs":[114],"surfaceOp":"append"} +{"type":"tool/result","seq":115,"time":1783352094995,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","content":[{"type":"text","text":"Error: unknown tool \"write\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[114],"surfaceOp":"append"} {"type":"step/end","seq":116,"time":1783352094995,"data":{"turn":1,"step":2}} {"type":"step/start","seq":117,"time":1783352094995,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":118,"time":1783352096090,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl index 6eec0d1f76..03c77cae98 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -42,8 +42,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","title":"Read data.txt","kind":"read","status":"in_progress","locations":[{"path":"data.txt","line":1}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/data.txt\nfile\n\n1: original contents\n\n(End of file - total 1 lines)\n"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"data.txt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}} @@ -61,8 +61,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"re"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"placed"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","title":"Write data.txt","kind":"edit","status":"in_progress","locations":[{"path":"data.txt"}],"content":[{"type":"diff","path":"data.txt","oldText":null,"newText":"replaced"}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","status":"completed","content":[{"type":"diff","path":"data.txt","oldText":"original contents","newText":"replaced"}],"title":"Write data.txt"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","title":"write","kind":"other","status":"in_progress","rawInput":{"file_path":"data.txt","content":"replaced"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"write\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" has"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl index 7e4b2dda01..6170af99a5 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl @@ -62,7 +62,7 @@ {"type":"assistant/chunk","seq":60,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":61,"time":1783352079888,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file named notes.txt with the content \"hello world\" using the write tool, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}],"usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"tool/call","seq":62,"time":1783352079888,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}} -{"type":"tool/result","seq":63,"time":1783352079897,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","content":[{"type":"text","text":"/tmp/acp-snap-cwd-sNvn5N/notes.txt\nfile\n\nCreated file\n"}],"isError":false},"sourceEventSeqs":[62],"surfaceOp":"append"} +{"type":"tool/result","seq":63,"time":1783352079897,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","content":[{"type":"text","text":"Error: unknown tool \"write\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[62],"surfaceOp":"append"} {"type":"step/end","seq":64,"time":1783352079898,"data":{"turn":1,"step":1}} {"type":"step/start","seq":65,"time":1783352079899,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":66,"time":1783352080825,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl index 6f3dd77daf..1e68a6b90a 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -30,8 +30,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","title":"Write notes.txt","kind":"edit","status":"in_progress","locations":[{"path":"notes.txt"}],"content":[{"type":"diff","path":"notes.txt","oldText":null,"newText":"hello world"}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","status":"completed","content":[{"type":"diff","path":"notes.txt","oldText":null,"newText":"hello world"}],"title":"Write notes.txt"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","title":"write","kind":"other","status":"in_progress","rawInput":{"file_path":"notes.txt","content":"hello world"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"write\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" has"}}}} diff --git a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl index ad3f94a046..e39f3694a8 100644 --- a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl @@ -1,2 +1,2 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl index ae14559ea9..7247d4ae37 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl index 81b44b06cc..be13a31a84 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index 46a5e135a6..b975c54aac 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -55,59 +55,61 @@ {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} -{"type":"tool/result","seq":56,"time":1783352172573,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: bash requires manual approval in this session"}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} -{"type":"step/end","seq":57,"time":1783352172574,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":58,"time":1783352172574,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":59,"time":1783352173493,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":60,"time":1783352173493,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":61,"time":1783352173584,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} -{"type":"assistant/chunk","seq":62,"time":1783352173615,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":63,"time":1783352173615,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} -{"type":"assistant/chunk","seq":64,"time":1783352173644,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" an"}}} -{"type":"assistant/chunk","seq":65,"time":1783352173645,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" error"}}} -{"type":"assistant/chunk","seq":66,"time":1783352173645,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" saying"}}} -{"type":"assistant/chunk","seq":67,"time":1783352173645,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} -{"type":"assistant/chunk","seq":68,"time":1783352173669,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" requires"}}} -{"type":"assistant/chunk","seq":69,"time":1783352173669,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" manual"}}} -{"type":"assistant/chunk","seq":70,"time":1783352173670,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" approval"}}} -{"type":"assistant/chunk","seq":71,"time":1783352173670,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} -{"type":"assistant/chunk","seq":72,"time":1783352173698,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} -{"type":"assistant/chunk","seq":73,"time":1783352173699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" session"}}} -{"type":"assistant/chunk","seq":74,"time":1783352173699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":75,"time":1783352173699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":76,"time":1783352173728,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"'ll"}}} -{"type":"assistant/chunk","seq":77,"time":1783352173728,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":78,"time":1783352173729,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} -{"type":"assistant/chunk","seq":79,"time":1783352173729,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":80,"time":1783352173755,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":81,"time":1783352173756,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":82,"time":1783352173756,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":83,"time":1783352173756,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}} -{"type":"assistant/chunk","seq":84,"time":1783352173756,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" tool"}}} -{"type":"assistant/chunk","seq":85,"time":1783352173789,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" result"}}} -{"type":"assistant/chunk","seq":86,"time":1783352173823,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" I"}}} -{"type":"assistant/chunk","seq":87,"time":1783352173854,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" got"}}} -{"type":"assistant/chunk","seq":88,"time":1783352173854,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" back"}}} -{"type":"assistant/chunk","seq":89,"time":1783352173879,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" verb"}}} -{"type":"assistant/chunk","seq":90,"time":1783352173906,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"atim"}}} -{"type":"assistant/chunk","seq":91,"time":1783352173906,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}} -{"type":"assistant/chunk","seq":92,"time":1783352173907,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":\n\n"}}} -{"type":"assistant/chunk","seq":93,"time":1783352173907,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```\n"}}} -{"type":"assistant/chunk","seq":94,"time":1783352173907,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"Error"}}} -{"type":"assistant/chunk","seq":95,"time":1783352173932,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}} -{"type":"assistant/chunk","seq":96,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" bash"}}} -{"type":"assistant/chunk","seq":97,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" requires"}}} -{"type":"assistant/chunk","seq":98,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" manual"}}} -{"type":"assistant/chunk","seq":99,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" approval"}}} -{"type":"assistant/chunk","seq":100,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" in"}}} -{"type":"assistant/chunk","seq":101,"time":1783352173963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" this"}}} -{"type":"assistant/chunk","seq":102,"time":1783352173963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" session"}}} -{"type":"assistant/chunk","seq":103,"time":1783352173963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\n"}}} -{"type":"assistant/chunk","seq":104,"time":1783352173963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```"}}} -{"type":"assistant/chunk","seq":105,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The bash tool returned an error saying it requires manual approval in this session. I'll report this verbatim."}}}} -{"type":"assistant/chunk","seq":106,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}}}} -{"type":"assistant/chunk","seq":107,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}}}} -{"type":"assistant/chunk","seq":108,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":109,"time":1783352173964,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool returned an error saying it requires manual approval in this session. I'll report this verbatim."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}],"usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} -{"type":"step/end","seq":110,"time":1783352173964,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":111,"time":1783352173965,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","outcome":"rejected"}} +{"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} +{"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":61,"time":1783352173584,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":62,"time":1783352173615,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":63,"time":1783352173615,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} +{"type":"assistant/chunk","seq":64,"time":1783352173644,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":65,"time":1783352173645,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":66,"time":1783352173645,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" an"}}} +{"type":"assistant/chunk","seq":67,"time":1783352173645,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" error"}}} +{"type":"assistant/chunk","seq":68,"time":1783352173669,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" saying"}}} +{"type":"assistant/chunk","seq":69,"time":1783352173669,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":70,"time":1783352173670,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" requires"}}} +{"type":"assistant/chunk","seq":71,"time":1783352173670,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" manual"}}} +{"type":"assistant/chunk","seq":72,"time":1783352173698,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" approval"}}} +{"type":"assistant/chunk","seq":73,"time":1783352173699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} +{"type":"assistant/chunk","seq":74,"time":1783352173699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} +{"type":"assistant/chunk","seq":75,"time":1783352173699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" session"}}} +{"type":"assistant/chunk","seq":76,"time":1783352173728,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":77,"time":1783352173728,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":78,"time":1783352173729,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"'ll"}}} +{"type":"assistant/chunk","seq":79,"time":1783352173729,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} +{"type":"assistant/chunk","seq":80,"time":1783352173755,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} +{"type":"assistant/chunk","seq":81,"time":1783352173756,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} +{"type":"assistant/chunk","seq":82,"time":1783352173756,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} +{"type":"assistant/chunk","seq":83,"time":1783352173756,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":84,"time":1783352173756,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":85,"time":1783352173789,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}} +{"type":"assistant/chunk","seq":86,"time":1783352173823,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" tool"}}} +{"type":"assistant/chunk","seq":87,"time":1783352173854,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" result"}}} +{"type":"assistant/chunk","seq":88,"time":1783352173854,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" I"}}} +{"type":"assistant/chunk","seq":89,"time":1783352173879,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" got"}}} +{"type":"assistant/chunk","seq":90,"time":1783352173906,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" back"}}} +{"type":"assistant/chunk","seq":91,"time":1783352173906,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" verb"}}} +{"type":"assistant/chunk","seq":92,"time":1783352173907,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"atim"}}} +{"type":"assistant/chunk","seq":93,"time":1783352173907,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}} +{"type":"assistant/chunk","seq":94,"time":1783352173907,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":\n\n"}}} +{"type":"assistant/chunk","seq":95,"time":1783352173932,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```\n"}}} +{"type":"assistant/chunk","seq":96,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"Error"}}} +{"type":"assistant/chunk","seq":97,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}} +{"type":"assistant/chunk","seq":98,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" bash"}}} +{"type":"assistant/chunk","seq":99,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" requires"}}} +{"type":"assistant/chunk","seq":100,"time":1783352173933,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" manual"}}} +{"type":"assistant/chunk","seq":101,"time":1783352173963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" approval"}}} +{"type":"assistant/chunk","seq":102,"time":1783352173963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" in"}}} +{"type":"assistant/chunk","seq":103,"time":1783352173963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" this"}}} +{"type":"assistant/chunk","seq":104,"time":1783352173963,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" session"}}} +{"type":"assistant/chunk","seq":105,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\n"}}} +{"type":"assistant/chunk","seq":106,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```"}}} +{"type":"assistant/chunk","seq":107,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The bash tool returned an error saying it requires manual approval in this session. I'll report this verbatim."}}}} +{"type":"assistant/chunk","seq":108,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}}}} +{"type":"assistant/chunk","seq":109,"time":1783962235816,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}}}} +{"type":"assistant/chunk","seq":110,"time":1783962235816,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":111,"time":1783962235816,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool returned an error saying it requires manual approval in this session. I'll report this verbatim."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}],"usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110],"surfaceOp":"append"} +{"type":"step/end","seq":112,"time":1783962235816,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":113,"time":1783962235816,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl index 15abe487af..ce7acef1f3 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -18,7 +18,7 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_6k0oGSliVHxGSgqBmMEO4311","title":"echo HELLO","kind":"execute","status":"in_progress","rawInput":"echo HELLO","content":[{"type":"content","content":{"type":"text","text":"Echo HELLO"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_6k0oGSliVHxGSgqBmMEO4311","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: bash requires manual approval in this session\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_6k0oGSliVHxGSgqBmMEO4311","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: the user rejected tool \"bash\"\n```"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl index cd59430ee0..d31dd2c810 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl index 6f6e5b662f..19dd593b09 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl index 567d3d98cb..19ae540ab1 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'s"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl index ff6e09bff9..d76b8537f0 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index 1c99b178a3..e612fb942a 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl index 21af4a0783..38a3055a16 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl index 878b9777e8..93ff9f89fc 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl index 6f6e5b662f..19dd593b09 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl index 96a03f233e..a2028ef4b8 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl index 88ce7ce421..e628431ee3 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl index 22bb6757fd..f288d7a05f 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/input.json b/examples/acp-agent/tests/snapshots/permission-switching/input.json new file mode 100644 index 0000000000..9adb6b1562 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/permission-switching/input.json @@ -0,0 +1,32 @@ +{ + "steps": [ + { + "op": "initialize" + }, + { + "op": "newSession" + }, + { + "op": "setConfigOption", + "configId": "permission", + "value": "workspace-write" + }, + { + "op": "prompt", + "text": "Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop." + }, + { + "op": "setConfigOption", + "configId": "permission", + "value": "danger-full-access" + }, + { + "op": "prompt", + "text": "Use the bash tool to run exactly: cat out.txt. Then reply with the single word DONE and stop." + }, + { + "op": "prompt", + "text": "Without using any tools, state your current approval policy in one short sentence and stop." + } + ] +} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl new file mode 100644 index 0000000000..a30f9e4a46 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -0,0 +1,238 @@ +{"type":"session","version":0,"id":"df041acb-2f14-4d5f-b6e2-2fb6b9eb6427","createdAt":1783860666204,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-4oJKT4"} +{"type":"turn/start","seq":0,"time":1783860666206,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"permission/preset","seq":1,"time":1783962244578,"data":{"preset":"workspace-write"}} +{"type":"bash/sandbox-mode","seq":2,"time":1783962244578,"data":{"mode":"workspace-write"}} +{"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} +{"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":10,"time":1783860667446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":11,"time":1783860667446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":12,"time":1783860667446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":13,"time":1783860667478,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":14,"time":1783860667478,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":15,"time":1783860667478,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} +{"type":"assistant/chunk","seq":16,"time":1783860667479,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} +{"type":"assistant/chunk","seq":17,"time":1783860667501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":18,"time":1783860667502,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":19,"time":1783860667502,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":20,"time":1783860667502,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":21,"time":1783860667502,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":22,"time":1783860667595,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":23,"time":1783860667596,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":24,"time":1783860667623,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":25,"time":1783860667624,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":26,"time":1783860667624,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":27,"time":1783860667624,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":28,"time":1783860667624,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":29,"time":1783860667656,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"command"}}} +{"type":"assistant/chunk","seq":30,"time":1783860667657,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":31,"time":1783860667657,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":32,"time":1783860667657,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":33,"time":1783860667657,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"printf"}}} +{"type":"assistant/chunk","seq":34,"time":1783860667686,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" '"}}} +{"type":"assistant/chunk","seq":35,"time":1783860667687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"before"}}} +{"type":"assistant/chunk","seq":36,"time":1783860667687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\\\\n"}}} +{"type":"assistant/chunk","seq":37,"time":1783860667687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"'"}}} +{"type":"assistant/chunk","seq":38,"time":1783860667687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" >"}}} +{"type":"assistant/chunk","seq":39,"time":1783860667687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":40,"time":1783860667710,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":41,"time":1783860667710,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" &&"}}} +{"type":"assistant/chunk","seq":42,"time":1783860667711,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" cat"}}} +{"type":"assistant/chunk","seq":43,"time":1783860667738,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":44,"time":1783860667739,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":45,"time":1783860667739,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":46,"time":1783860667776,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":47,"time":1783860667776,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":48,"time":1783860667776,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":49,"time":1783860667776,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":50,"time":1783860667796,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":51,"time":1783860667796,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":52,"time":1783860667834,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"Write"}}} +{"type":"assistant/chunk","seq":53,"time":1783860667835,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":54,"time":1783860667863,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" then"}}} +{"type":"assistant/chunk","seq":55,"time":1783860667863,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" read"}}} +{"type":"assistant/chunk","seq":56,"time":1783860667889,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":57,"time":1783860667918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":58,"time":1783860667918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":59,"time":1783860667918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":60,"time":1783860667918,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a specific command and then reply with \"DONE\"."}}}} +{"type":"assistant/chunk","seq":61,"time":1783962244582,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","arguments":"{\"command\": \"printf 'before\\\\n' > out.txt && cat out.txt\", \"description\": \"Write and then read out.txt\"}"}}}} +{"type":"assistant/chunk","seq":62,"time":1783962244582,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1411,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":17}}}} +{"type":"assistant/chunk","seq":63,"time":1783962244582,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":64,"time":1783962244582,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","arguments":"{\"command\": \"printf 'before\\\\n' > out.txt && cat out.txt\", \"description\": \"Write and then read out.txt\"}"}],"usage":{"inputTokens":1411,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"} +{"type":"tool/call","seq":65,"time":1783962244582,"data":{"turn":1,"step":1,"callId":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","arguments":"{\"command\": \"printf 'before\\\\n' > out.txt && cat out.txt\", \"description\": \"Write and then read out.txt\"}"}} +{"type":"tool/result","seq":66,"time":1783962244599,"data":{"turn":1,"step":1,"callId":"call_00_E1vtulcKU1LKUgLahxdR3767","content":[{"type":"text","text":"before\n"}],"isError":false},"sourceEventSeqs":[65],"surfaceOp":"append"} +{"type":"step/end","seq":67,"time":1783962244599,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":68,"time":1783962244600,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":69,"time":1783860669145,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":70,"time":1783860669172,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":71,"time":1783860669174,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} +{"type":"assistant/chunk","seq":72,"time":1783860669209,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" ran"}}} +{"type":"assistant/chunk","seq":73,"time":1783860669210,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} +{"type":"assistant/chunk","seq":74,"time":1783860669235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":75,"time":1783860669235,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} +{"type":"assistant/chunk","seq":76,"time":1783860669236,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":77,"time":1783860669262,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"before"}}} +{"type":"assistant/chunk","seq":78,"time":1783860669264,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":79,"time":1783860669264,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":80,"time":1783860669264,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":81,"time":1783860669264,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":82,"time":1783860669292,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":83,"time":1783860669292,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":84,"time":1783860669322,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":85,"time":1783860669323,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} +{"type":"assistant/chunk","seq":86,"time":1783860669356,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":87,"time":1783860669357,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":88,"time":1783860669357,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" D"}}} +{"type":"assistant/chunk","seq":89,"time":1783860669357,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":90,"time":1783860669357,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":91,"time":1783860669357,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":92,"time":1783860669357,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} +{"type":"assistant/chunk","seq":93,"time":1783860669357,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":94,"time":1783860669357,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The command ran successfully, output \"before\". Now I need to reply with just the word DONE."}}}} +{"type":"assistant/chunk","seq":95,"time":1783962244601,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":96,"time":1783962244601,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":109,"outputTokens":24,"cacheReadTokens":1408,"reasoningTokens":21}}}} +{"type":"assistant/chunk","seq":97,"time":1783962244601,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":98,"time":1783962244601,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully, output \"before\". Now I need to reply with just the word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":109,"outputTokens":24,"cacheReadTokens":1408,"reasoningTokens":21}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97],"surfaceOp":"append"} +{"type":"step/end","seq":99,"time":1783962244601,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":100,"time":1783962244601,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":101,"time":1783962244623,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"permission/preset","seq":102,"time":1783962244624,"data":{"preset":"danger-full-access"}} +{"type":"bash/sandbox-mode","seq":103,"time":1783962244624,"data":{"mode":"danger-full-access"}} +{"type":"approval/policy","seq":104,"time":1783962244624,"data":{"policy":"never"}} +{"type":"user/message","seq":105,"time":1783962244624,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"context/message","seq":106,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"} +{"type":"step/start","seq":107,"time":1783962244624,"data":{"turn":2,"step":1}} +{"type":"request/header","seq":108,"time":1784000791271,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"change"}} +{"type":"assistant/chunk","seq":109,"time":1783860671025,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":110,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":111,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":112,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":113,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":114,"time":1783860671079,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":115,"time":1783860671080,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":116,"time":1783860671080,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} +{"type":"assistant/chunk","seq":117,"time":1783860671080,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"cat"}}} +{"type":"assistant/chunk","seq":118,"time":1783860671080,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" out"}}} +{"type":"assistant/chunk","seq":119,"time":1783860671080,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".txt"}}} +{"type":"assistant/chunk","seq":120,"time":1783860671097,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}} +{"type":"assistant/chunk","seq":121,"time":1783860671101,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":122,"time":1783860671101,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":123,"time":1783860671102,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":124,"time":1783860671102,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":125,"time":1783860671102,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":126,"time":1783860671175,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":127,"time":1783860671175,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":128,"time":1783860671211,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":129,"time":1783860671212,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":130,"time":1783860671212,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":131,"time":1783860671228,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":132,"time":1783860671229,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":133,"time":1783860671229,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":134,"time":1783860671229,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":135,"time":1783860671261,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":136,"time":1783860671262,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":137,"time":1783860671301,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"Read"}}} +{"type":"assistant/chunk","seq":138,"time":1783860671316,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":139,"time":1783860671316,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":140,"time":1783860671316,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":141,"time":1783860671316,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":142,"time":1783860671316,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":143,"time":1783860671350,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"command"}}} +{"type":"assistant/chunk","seq":144,"time":1783860671351,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":145,"time":1783860671351,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":146,"time":1783860671351,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":147,"time":1783860671388,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"cat"}}} +{"type":"assistant/chunk","seq":148,"time":1783860671388,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":149,"time":1783860671435,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":".txt"}}} +{"type":"assistant/chunk","seq":150,"time":1783860671435,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":151,"time":1783860671436,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":152,"time":1783860671436,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run `cat out.txt` and then reply with \"DONE\"."}}}} +{"type":"assistant/chunk","seq":153,"time":1783962244626,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","arguments":"{\"description\": \"Read out.txt\", \"command\": \"cat out.txt\"}"}}}} +{"type":"assistant/chunk","seq":154,"time":1783962244626,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1608,"outputTokens":82,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":155,"time":1783962244626,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":156,"time":1783962244626,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `cat out.txt` and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","arguments":"{\"description\": \"Read out.txt\", \"command\": \"cat out.txt\"}"}],"usage":{"inputTokens":1608,"outputTokens":82,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"} +{"type":"tool/call","seq":157,"time":1783962244626,"data":{"turn":2,"step":1,"callId":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","arguments":"{\"description\": \"Read out.txt\", \"command\": \"cat out.txt\"}"}} +{"type":"tool/result","seq":158,"time":1783962244631,"data":{"turn":2,"step":1,"callId":"call_00_7Jb7FWHNjIBVML49dEJl1990","content":[{"type":"text","text":"before\n"}],"isError":false},"sourceEventSeqs":[157],"surfaceOp":"append"} +{"type":"step/end","seq":159,"time":1783962244631,"data":{"turn":2,"step":1}} +{"type":"step/start","seq":160,"time":1783962244631,"data":{"turn":2,"step":2}} +{"type":"assistant/chunk","seq":161,"time":1783860673229,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":162,"time":1783860673229,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":163,"time":1783860673229,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":164,"time":1783962244632,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":165,"time":1783962244632,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":3,"cacheReadTokens":1664,"reasoningTokens":0}}}} +{"type":"assistant/chunk","seq":166,"time":1783962244632,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":167,"time":1783962244632,"data":{"turn":2,"step":2,"content":[{"type":"text","text":"DONE"}],"usage":{"inputTokens":40,"outputTokens":3,"cacheReadTokens":1664,"reasoningTokens":0}},"sourceEventSeqs":[161,162,163,164,165,166],"surfaceOp":"append"} +{"type":"step/end","seq":168,"time":1783962244632,"data":{"turn":2,"step":2}} +{"type":"turn/end","seq":169,"time":1783962244632,"data":{"turn":2,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":170,"time":1783962244637,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":171,"time":1783962244637,"data":{"content":[{"type":"text","text":"Without using any tools, state your current approval policy in one short sentence and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":172,"time":1783962244637,"data":{"turn":3,"step":1}} +{"type":"assistant/chunk","seq":173,"time":1783860674433,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":174,"time":1783860674435,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":175,"time":1783860674435,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":176,"time":1783860674465,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":177,"time":1783860674465,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":178,"time":1783860674499,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":179,"time":1783860674500,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" state"}}} +{"type":"assistant/chunk","seq":180,"time":1783860674500,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":181,"time":1783860674500,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" current"}}} +{"type":"assistant/chunk","seq":182,"time":1783860674500,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" approval"}}} +{"type":"assistant/chunk","seq":183,"time":1783860674525,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} +{"type":"assistant/chunk","seq":184,"time":1783860674526,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" without"}}} +{"type":"assistant/chunk","seq":185,"time":1783860674526,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} +{"type":"assistant/chunk","seq":186,"time":1783860674526,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" any"}}} +{"type":"assistant/chunk","seq":187,"time":1783860674526,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":188,"time":1783860674550,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":189,"time":1783860674550,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" From"}}} +{"type":"assistant/chunk","seq":190,"time":1783860674581,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":191,"time":1783860674582,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" context"}}} +{"type":"assistant/chunk","seq":192,"time":1783860674582,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" provided"}}} +{"type":"assistant/chunk","seq":193,"time":1783860674610,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":194,"time":1783860674611,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":195,"time":1783860674611,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" approval"}}} +{"type":"assistant/chunk","seq":196,"time":1783860674611,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} +{"type":"assistant/chunk","seq":197,"time":1783860674638,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" changed"}}} +{"type":"assistant/chunk","seq":198,"time":1783860674638,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" from"}}} +{"type":"assistant/chunk","seq":199,"time":1783860674638,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":200,"time":1783860674638,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ask"}}} +{"type":"assistant/chunk","seq":201,"time":1783860674638,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":202,"time":1783860674640,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":203,"time":1783860674698,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":204,"time":1783860674698,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"never"}}} +{"type":"assistant/chunk","seq":205,"time":1783860674700,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":206,"time":1783860674726,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":207,"time":1783860674726,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":"My"}}} +{"type":"assistant/chunk","seq":208,"time":1783860674727,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" approval"}}} +{"type":"assistant/chunk","seq":209,"time":1783860674727,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} +{"type":"assistant/chunk","seq":210,"time":1783860674754,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" is"}}} +{"type":"assistant/chunk","seq":211,"time":1783860674757,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" set"}}} +{"type":"assistant/chunk","seq":212,"time":1783860674757,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" to"}}} +{"type":"assistant/chunk","seq":213,"time":1783860674757,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" \""}}} +{"type":"assistant/chunk","seq":214,"time":1783860674757,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":"never"}}} +{"type":"assistant/chunk","seq":215,"time":1783860674786,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":"\""}}} +{"type":"assistant/chunk","seq":216,"time":1783860674817,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" —"}}} +{"type":"assistant/chunk","seq":217,"time":1783860674846,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" no"}}} +{"type":"assistant/chunk","seq":218,"time":1783860674875,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" actions"}}} +{"type":"assistant/chunk","seq":219,"time":1783860674879,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" requiring"}}} +{"type":"assistant/chunk","seq":220,"time":1783860674880,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" approval"}}} +{"type":"assistant/chunk","seq":221,"time":1783860674904,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" are"}}} +{"type":"assistant/chunk","seq":222,"time":1783860674906,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" permitted"}}} +{"type":"assistant/chunk","seq":223,"time":1783860674906,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":","}}} +{"type":"assistant/chunk","seq":224,"time":1783860674939,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" and"}}} +{"type":"assistant/chunk","seq":225,"time":1783860674940,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" they"}}} +{"type":"assistant/chunk","seq":226,"time":1783860674940,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" are"}}} +{"type":"assistant/chunk","seq":227,"time":1783860674940,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} +{"type":"assistant/chunk","seq":228,"time":1783860674940,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" automatically"}}} +{"type":"assistant/chunk","seq":229,"time":1783860674940,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":"."}}} +{"type":"assistant/chunk","seq":230,"time":1783860674940,"data":{"turn":3,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to state the current approval policy without using any tools. From the context provided, the approval policy changed from \"ask\" to \"never\"."}}}} +{"type":"assistant/chunk","seq":231,"time":1783962244639,"data":{"turn":3,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"My approval policy is set to \"never\" — no actions requiring approval are permitted, and they are rejected automatically."}}}} +{"type":"assistant/chunk","seq":232,"time":1783962244639,"data":{"turn":3,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":64,"outputTokens":56,"cacheReadTokens":1664,"reasoningTokens":32}}}} +{"type":"assistant/chunk","seq":233,"time":1783962244639,"data":{"turn":3,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":234,"time":1783962244640,"data":{"turn":3,"step":1,"content":[{"type":"reasoning","text":"The user wants me to state the current approval policy without using any tools. From the context provided, the approval policy changed from \"ask\" to \"never\"."},{"type":"text","text":"My approval policy is set to \"never\" — no actions requiring approval are permitted, and they are rejected automatically."}],"usage":{"inputTokens":64,"outputTokens":56,"cacheReadTokens":1664,"reasoningTokens":32}},"sourceEventSeqs":[173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233],"surfaceOp":"append"} +{"type":"step/end","seq":235,"time":1783962244640,"data":{"turn":3,"step":1}} +{"type":"turn/end","seq":236,"time":1783962244640,"data":{"turn":3,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl similarity index 74% rename from examples/sandbox-acp-agent/tests/snapshots/mode-switching/stdout.golden.jsonl rename to examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl index e6b16698af..65ab7ae4e7 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl @@ -1,45 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"cat"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" notes"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","title":"cat notes.txt","kind":"execute","status":"in_progress","rawInput":"cat notes.txt","content":[{"type":"content","content":{"type":"text","text":"Show contents of notes.txt"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nhello from the sandboxed workspace\n```"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ran"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" successfully"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" D"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} -{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -49,36 +10,72 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specific"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" execute"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_htXcbtvwTFK0NqfclLWL7784","title":"printf 'switched\\n' > out.txt && cat out.txt","kind":"execute","status":"in_progress","rawInput":"printf 'switched\\n' > out.txt && cat out.txt","content":[{"type":"content","content":{"type":"text","text":"Write and read out.txt"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_htXcbtvwTFK0NqfclLWL7784","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nswitched\n```"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Command"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" executed"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" successfully"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" then"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"sw"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"itched"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_E1vtulcKU1LKUgLahxdR3767","title":"printf 'before\\n' > out.txt && cat out.txt","kind":"execute","status":"in_progress","rawInput":"printf 'before\\n' > out.txt && cat out.txt","content":[{"type":"content","content":{"type":"text","text":"Write and then read out.txt"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_E1vtulcKU1LKUgLahxdR3767","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nbefore\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ran"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" successfully"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"before"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Now"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" just"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","id":5,"result":{"stopReason":"end_turn"}} -{"jsonrpc":"2.0","id":6,"result":{"configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"never","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}} +{"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} +{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"cat"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" out"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".txt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" then"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_7Jb7FWHNjIBVML49dEJl1990","title":"cat out.txt","kind":"execute","status":"in_progress","rawInput":"cat out.txt","content":[{"type":"content","content":{"type":"text","text":"Read out.txt"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_7Jb7FWHNjIBVML49dEJl1990","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nbefore\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","id":6,"result":{"stopReason":"end_turn"}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" state"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" my"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" current"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" approval"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}} @@ -90,45 +87,41 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" From"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" context"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" provided"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" approval"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" changed"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" from"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ask"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"never"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" —"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" meaning"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" actions"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" require"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" approval"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" are"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" automatically"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" not"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" request"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sand"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"box"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" escalation"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"Appro"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"vals"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" are"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" never"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" asked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":";"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" any"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" action"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"My"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" approval"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" policy"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" set"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"never"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" —"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" no"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" actions"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" requiring"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" approval"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" automatically"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" are"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" permitted"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" they"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" are"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" rejected"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" automatically"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","id":7,"result":{"stopReason":"end_turn"}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md similarity index 64% rename from examples/sandbox-acp-agent/tests/snapshots/mode-switching/system-prompt.golden.md rename to examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md index 1e6e8a5ee0..ba208ba1c7 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md @@ -9,6 +9,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor +Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. + You are an AI agent powered by the DeepSeek Harness SDK. @@ -22,3 +24,5 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + +Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/workspace/notes.txt b/examples/acp-agent/tests/snapshots/permission-switching/workspace/notes.txt similarity index 100% rename from examples/sandbox-acp-agent/tests/snapshots/mode-switching/workspace/notes.txt rename to examples/acp-agent/tests/snapshots/permission-switching/workspace/notes.txt diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl index a3ae2e3870..42d0507e3f 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_1","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"watch the kettle boil","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"watch the kettle boil","priority":"medium","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_1","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}}]}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 645671709e..1c85ee81ba 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl index 00e707088e..7cc0dd72f2 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md index 18f0cbcd07..d0ce1272d0 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md @@ -1,16 +1,13 @@ You are an AI agent powered by the DeepSeek Harness SDK. -You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. +You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. Verify your work by running the code or tests. Keep answers brief and factual. -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. - Check the [exit code: N] marker on every bash result; investigate failures before moving on. +Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + + Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl index e73195eeee..0c9ef3b472 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl index e709fd09cd..b7e669238f 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl index 1a6b466e2b..519d784c79 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl index 8a42b58e7e..8cf5765647 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 324ef8d4eb..c66f5676cc 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl index dda3afb9c5..40c8434937 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md index 18f0cbcd07..d0ce1272d0 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md @@ -1,16 +1,13 @@ You are an AI agent powered by the DeepSeek Harness SDK. -You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. +You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. Verify your work by running the code or tests. Keep answers brief and factual. -Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. - -Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. - -Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. - Check the [exit code: N] marker on every bash result; investigate failures before moving on. +Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + + Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl index fb9635366b..b99e45c699 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl index 3d0352468c..1ed804a0d6 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl index 63af2375d5..b188480ad5 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl index 9a908f24a3..04e3c3b59e 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl @@ -79,7 +79,7 @@ {"type":"assistant/chunk","seq":77,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":78,"time":1783352265491,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read the file greeting.txt\n2. Append the word WORLD as a second line\n3. Read the file back with cat to confirm\n4. Reply with DONE\n\nLet me start by reading the file to see its contents."},{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"surfaceOp":"append"} {"type":"tool/call","seq":79,"time":1783352265491,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}} -{"type":"tool/result","seq":80,"time":1783352265504,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","content":[{"type":"text","text":"/tmp/acp-snap-cwd-rxbEpP/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[79],"surfaceOp":"append"} +{"type":"tool/result","seq":80,"time":1783352265504,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[79],"surfaceOp":"append"} {"type":"step/end","seq":81,"time":1783352265504,"data":{"turn":1,"step":1}} {"type":"step/start","seq":82,"time":1783352265505,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":83,"time":1783352266385,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl index 7b1ded9550..d3fd50b416 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace; anything wider asks for your approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access, no approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -55,8 +55,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" its"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contents"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","title":"Read greeting.txt","kind":"read","status":"in_progress","locations":[{"path":"greeting.txt","line":1}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"greeting.txt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}} diff --git a/examples/sandbox-acp-agent/README.md b/examples/sandbox-acp-agent/README.md deleted file mode 100644 index bada288bde..0000000000 --- a/examples/sandbox-acp-agent/README.md +++ /dev/null @@ -1,16 +0,0 @@ -# sandbox-acp-agent - -The coding agent with its bash executor swapped for the sandbox stack ([`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/) + [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/) — the one-entry executor swap the `ctx.bash` capability seam exists for), served over the **Agent Client Protocol**, plus [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/) — which makes this the first composition where the approval loop is LIVE end to end: bash runs under `read-only`, a denial comes back as the structured marker, the model retries once with `sandbox_permissions` + `justification`, the ACP bridge's answerer turns that ask into a `session/request_permission` prompt in your editor, and "Allow once" runs exactly that command under the wider mode ([sandbox RFC § Escalation](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). - -```sh -pnpm run demo:sandbox-acp # needs DEEPSEEK_API_KEY; drive it from Zed or any ACP client -``` - -Zed setup is the same as [acp-agent](../acp-agent/README.md) with this example's command; only the leaf `cordis.yml` differs (the sandbox stack + the approval entry in place of the local bash executor and the extra tool stacks). - -- **Every approval is one-shot** (`Allow once` / `Reject` — no `allow_always`: the harness has no grant storage yet), and a dismissed prompt or a rejected ask fails closed with its own error text; so does every ask when no editor is attached to answer. -- **Two session config options are live** ([sandbox RFC § Per-session mode switching](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): a capable client shows `Sandbox` (`read-only`/`workspace-write`/`danger-full-access`) and `Approvals` (`ask`/`never`) selectors per session — a switch is one log-only event on that session's log and execution follows it; the sandbox mode is deliberately NOT stated in the prompt or narrated (the model learns the boundary from the denial marker — behavior, not belief), while an approval switch to `never` is stated and narrated; a resumed session reports its overrides back on `session/load`. -- **The write boundary is config-fixed**: an escalated `workspace-write` run may write under the launch directory (`workspaceRoot: process.cwd()`) plus the platform temp area — a per-session root is config-phase future work in the [sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). -- **No usable runner fails closed per command** (structured `SANDBOX_UNAVAILABLE`), and the filesystem tools stay unloaded for the same reason as `sandbox-agent`: they would bypass the bash sandbox. - -Tests: `tests/escalation.e2e.ts` — keyless, it boots the real `cordis.yml` through the Loader as an ACP subprocess, proves the whole tree (sandbox executor + approval service + bridge) initializes and opens a session, and drives the config options end to end (both advertised with composition currents, switches honored and echoed as complete state, out-of-vocabulary values rejected); with a key and a usable runner, a scripted ACP client plays the human — the real model gets denied, escalates, the client answers `allow-once`, and the retried write must land on disk. `tests/acp.snapshot.ts` (the [shared snapshot kit](../../packages/support/acp-snapshot/) over this composition's `cordis.snapshot.yml` replay overlay) pins four scenarios as committed wire bytes: the keyless config-option exchange, the recorded `mode-switching` arc (the suite's pinned header — both switches, their prompt-section deltas, one "changed by the user" notice per knob, and a confined write landing under the switched mode), and both recorded escalation branches (`session/request_permission` answered allow-once / reject-once). Replay re-executes every recorded bash call under the host's real runner — Seatbelt works out of the box on macOS; on Linux install bubblewrap (or build the Landlock launcher) first, exactly what ci.yml's snapshot lane does. No fixture carries a real denial: denial stderr is backend dialect and would pin a fixture to its recording platform (the rationale comment atop the suite file). diff --git a/examples/sandbox-acp-agent/cordis.snapshot.yml b/examples/sandbox-acp-agent/cordis.snapshot.yml deleted file mode 100644 index b5f8ac73ed..0000000000 --- a/examples/sandbox-acp-agent/cordis.snapshot.yml +++ /dev/null @@ -1,30 +0,0 @@ -# Snapshot-test REPLAY overlay for the sandboxed composition: the SAME app -# tree as cordis.yml, derived from it by an include — the one difference is -# the model backend. A keyless replay run cannot boot the real adapter -# (llm-deepseek's apply() throws without DEEPSEEK_API_KEY), so the include -# patches the live tree at load time: the llm-deepseek entry is disabled by -# id, and the llm-replay entry (which serves a recorded session JSONL — no -# API key, no network) is inserted. Every other entry — the sandbox provider, -# the confined bash executor, the approval seam, the app — IS the live tree. -# The sandbox provider probes for a platform runner per EXECUTION, not at -# boot, so a protocol-only scenario (session config options) replays on hosts -# with no runner at all. -# -# The dsh-acp-agent bin selects this file for DSH_SNAPSHOT=replay (the -# sibling-swap of whatever config path it was handed). The replay fixture -# path comes from $DSH_SNAPSHOT_FILE, set by the snapshot harness. stdout -# stays reserved for the ACP JSON-RPC protocol. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - # The name is an assertion, not an override: the include skips the patch - # (warning) when the id points at a different plugin, so this can never - # disable the wrong entry. - - id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - disabled: true - - insert: - - id: llm-replay - name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/sandbox-acp-agent/cordis.yml b/examples/sandbox-acp-agent/cordis.yml deleted file mode 100644 index d02253342e..0000000000 --- a/examples/sandbox-acp-agent/cordis.yml +++ /dev/null @@ -1,60 +0,0 @@ -# The sandbox-acp-agent plugin tree: the sandboxed coding agent served over the -# Agent Client Protocol, with the approval seam composed — the first LIVE -# approval composition. A sandbox denial escalated by the model -# (sandbox_permissions + justification) reaches the EDITOR as a -# session/request_permission prompt through the ACP bridge's answerer, and an -# "Allow once" runs exactly that command under the wider mode. -# -# CRITICAL: this tree loads NO stdout logger and NO hmr — stdout is reserved -# for the ACP JSON-RPC protocol (a property of @deepseek-ai/dsh-acp-agent, -# same as examples/acp-agent). -# -# Requires DEEPSEEK_API_KEY (and optionally DEEPSEEK_BASE_URL) — the -# dsh-acp-agent bin loads the gitignored repo-root .env first (on STDERR only). - -# The DeepSeek adapter. -- id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - config: - apiKey: !!js process.env.DEEPSEEK_API_KEY - baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-flash - -# The sandbox stack: the platform-runner provider (bwrap → per-platform -# Landlock launcher → Seatbelt, functionally probed), then the confined bash executor. -# read-only is the fail-safe default; the write boundary for an escalated -# workspace-write run is workspaceRoot + the platform's temp area. NOTE: the -# workspace root is CONFIG-FIXED for the executor's lifetime (the launch dir -# here), while each ACP session has its own cwd — a per-session root is config- -# phase future work in the sandbox RFC. -- id: sandbox - name: '@deepseek-ai/dsh-sandbox-local' -- id: bash - name: '@deepseek-ai/dsh-bash-sandbox' - config: - mode: read-only - workspaceRoot: !!js process.cwd() - -# The approval seam (ctx.approval — mechanism only, no config): with it -# mounted, the bash tool's escalation gate has a channel, and the ACP bridge -# inside dsh-acp-agent answers for the sessions it owns by prompting the -# editor. Without an editor attached nothing can answer, and every ask fails -# closed. -- id: approval - name: '@deepseek-ai/dsh-user-approval' - -# The ACP server app: the agent-core spine + JSONL persistence + the ACP -# bridge (whose approval answerer completes the loop). -- id: acp-agent - name: '@deepseek-ai/dsh-acp-agent' - config: - model: deepseek-v4-flash - # Persistence root: $DSH_SNAPSHOT_SESSIONS_ROOT when the snapshot harness - # sets it (so a record run's logs land where the harness harvests them), - # else the local ./.sessions default. - persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' - persona: | - You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. - - Verify your work by running the code or tests. Keep answers brief and factual. diff --git a/examples/sandbox-acp-agent/package.json b/examples/sandbox-acp-agent/package.json deleted file mode 100644 index 5a4c9a989e..0000000000 --- a/examples/sandbox-acp-agent/package.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "name": "sandbox-acp-agent-example", - "description": "Runnable demo: the sandboxed coding agent as an ACP server, with sandbox-escalation approval prompts answered by the editor", - "private": true, - "version": "0.0.1", - "type": "module" -} diff --git a/examples/sandbox-acp-agent/tests/acp.snapshot.ts b/examples/sandbox-acp-agent/tests/acp.snapshot.ts deleted file mode 100644 index 95667d5b6b..0000000000 --- a/examples/sandbox-acp-agent/tests/acp.snapshot.ts +++ /dev/null @@ -1,82 +0,0 @@ -import { dirname, join } from 'node:path' -import { fileURLToPath } from 'node:url' -import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from '@deepseek-ai/dsh-acp-snapshot' - -/** - * Snapshot suite for the SANDBOXED composition (`../cordis.yml`, swapped to - * the sibling `cordis.snapshot.yml` replay overlay by the bin under - * `DSH_SNAPSHOT=replay`). Replay swaps only the MODEL for the recorded - * transcript — every bash call re-executes for real under the host's actual - * runner (Seatbelt on macOS, bwrap on Linux CI: ci.yml's snapshot lane - * installs bubblewrap for exactly this), so the recorded scenarios double as - * cross-backend confinement regression: an allowed command a runner change - * starts denying fails replay outright. Their commands are limited to - * `cat`/`printf` shapes whose bytes are identical across those backends and - * across GNU/BSD userlands. - * - * Deliberately ABSENT: a scenario whose transcript carries a real sandbox - * DENIAL. The harness-authored `[sandbox: file access denied …]` marker is - * byte-stable, but the denied command's own stderr is the backend's dialect - * (bwrap EROFS "Read-only file system", Landlock EACCES "Permission - * denied", Seatbelt EPERM "Operation not permitted", GNU vs BSD phrasing on - * top), and stderr reaches both compared surfaces — such a fixture replays - * only on the platform that recorded it. The denial→marker path stays on - * dsh-tool-bash's unit tests and the real-kernel sandbox e2e legs - * (.github/workflows/sandbox.yml); the escalation scenarios below sidestep - * it by having the USER assert the prior denial, so the recorded model - * escalates without a platform-variant denial in the log. - */ -const SCENARIOS: Scenario[] = [ - // Protocol-only (keyless, authored): the session config-option surface - // this composition adds — both advertised selects on session/new, the - // complete refreshed state every session/set_config_option answers with, - // and both rejection shapes — as committed wire bytes. No bash runs, so - // this one still replays on runner-less hosts. - { name: 'config-options', hasModelTurn: false, recorded: false }, - // The runtime mode-switching arc, and NECESSARILY the pinned-header - // scenario: an approval-policy switch rewrites its prompt section, and the - // resulting changed request/header is legal only in the pinning scenario - // (the factory's uniformity guard). The pin commits this composition's - // full header — persona, tool schemas WITH the escalation fields — plus - // the approval delta and its "changed by the user" notice verbatim. The - // SANDBOX switch is deliberately silent (no section, no notice — the - // sandbox RFC's visibility asymmetry): the recorded arc proves it by - // BEHAVIOR, a confined write landing under the switched mode with no - // header change. - { name: 'mode-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1 }, - // The approval wire end-to-end, under the DEFAULT read-only/ask (a switch - // would emit a changed header the uniformity guard forbids here): the - // escalating bash call streams, session/request_permission attaches to it - // (allow-once / reject-once), and the scripted answer drives each branch — - // an approved run executes CONFINED under the granted workspace-write; a - // rejected one executes nothing and fails with the deterministic - // rejection text. - { name: 'escalation-approved', hasModelTurn: true, recorded: true }, - { name: 'escalation-rejected', hasModelTurn: true, recorded: true }, -] - -function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] { - switch (value) { - case undefined: - case '': - case 'replay': - return 'replay' - case 'record': - return 'record' - case 'refresh': - return 'refresh' - default: - throw new Error(`unknown DSH_SNAPSHOT mode: ${value}`) - } -} - -defineAcpSnapshotSuite({ - agent: { - binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), - configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), - tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), - }, - snapshotsDir: join(dirname(fileURLToPath(import.meta.url)), 'snapshots'), - scenarios: SCENARIOS, - mode: snapshotModeFromEnv(process.env.DSH_SNAPSHOT), -}) diff --git a/examples/sandbox-acp-agent/tests/snapshots/config-options/input.json b/examples/sandbox-acp-agent/tests/snapshots/config-options/input.json deleted file mode 100644 index 043019b659..0000000000 --- a/examples/sandbox-acp-agent/tests/snapshots/config-options/input.json +++ /dev/null @@ -1,10 +0,0 @@ -{ - "steps": [ - { "op": "initialize" }, - { "op": "newSession" }, - { "op": "setConfigOption", "configId": "sandbox-mode", "value": "workspace-write" }, - { "op": "setConfigOption", "configId": "approval-policy", "value": "never" }, - { "op": "setConfigOptionExpectError", "configId": "sandbox-mode", "value": "yolo" }, - { "op": "setConfigOptionExpectError", "configId": "reasoning-effort", "value": "max" } - ] -} diff --git a/examples/sandbox-acp-agent/tests/snapshots/config-options/stdout.golden.jsonl b/examples/sandbox-acp-agent/tests/snapshots/config-options/stdout.golden.jsonl deleted file mode 100644 index 3fab1e81fa..0000000000 --- a/examples/sandbox-acp-agent/tests/snapshots/config-options/stdout.golden.jsonl +++ /dev/null @@ -1,6 +0,0 @@ -{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"ask","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}} -{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"sandbox-mode","name":"Sandbox","description":"The file sandbox mode bash commands in this session run under.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"read-only","name":"read-only"},{"value":"workspace-write","name":"workspace-write"},{"value":"danger-full-access","name":"danger-full-access"}]},{"id":"approval-policy","name":"Approvals","description":"ask: permission prompts reach you; never: they are rejected automatically.","type":"select","currentValue":"never","options":[{"value":"ask","name":"ask"},{"value":"never","name":"never"}]}]}} -{"jsonrpc":"2.0","id":5,"error":{"code":-32602,"message":"Invalid params: unknown sandbox-mode value \"yolo\""}} -{"jsonrpc":"2.0","id":6,"error":{"code":-32602,"message":"Invalid params: unknown config option \"reasoning-effort\""}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/input.json b/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/input.json deleted file mode 100644 index 4cfa610f55..0000000000 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/input.json +++ /dev/null @@ -1,10 +0,0 @@ -{ - "steps": [ - { "op": "initialize" }, - { "op": "newSession" }, - { "op": "prompt", "text": "The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop." } - ], - "permissionAnswers": [ - { "kind": "allow_once" } - ] -} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl deleted file mode 100644 index 2ac9d27044..0000000000 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ /dev/null @@ -1,149 +0,0 @@ -{"type":"session","version":0,"id":"8f399407-f505-45e5-9058-0994ff7b0865","createdAt":1783486769425,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-xKPr5d"} -{"type":"turn/start","seq":0,"time":1783486769426,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783486769426,"data":{"content":[{"type":"text","text":"The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783486769427,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783486769427,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783486770051,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783486770052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783486770179,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783486770212,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783486770213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783486770214,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783486770214,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ret"}}} -{"type":"assistant/chunk","seq":11,"time":1783486770215,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ry"}}} -{"type":"assistant/chunk","seq":12,"time":1783486770215,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":13,"time":1783486770242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} -{"type":"assistant/chunk","seq":14,"time":1783486770243,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":15,"time":1783486770277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sand"}}} -{"type":"assistant/chunk","seq":16,"time":1783486770278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}} -{"type":"assistant/chunk","seq":17,"time":1783486770278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_per"}}} -{"type":"assistant/chunk","seq":18,"time":1783486770306,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"missions"}}} -{"type":"assistant/chunk","seq":19,"time":1783486770307,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" set"}}} -{"type":"assistant/chunk","seq":20,"time":1783486770335,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":21,"time":1783486770337,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" workspace"}}} -{"type":"assistant/chunk","seq":22,"time":1783486770338,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-w"}}} -{"type":"assistant/chunk","seq":23,"time":1783486770338,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"rite"}}} -{"type":"assistant/chunk","seq":24,"time":1783486770338,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":25,"time":1783486770368,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" They"}}} -{"type":"assistant/chunk","seq":26,"time":1783486770369,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" explicitly"}}} -{"type":"assistant/chunk","seq":27,"time":1783486770430,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" said"}}} -{"type":"assistant/chunk","seq":28,"time":1783486770431,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" they"}}} -{"type":"assistant/chunk","seq":29,"time":1783486770431,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" will"}}} -{"type":"assistant/chunk","seq":30,"time":1783486770458,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" approve"}}} -{"type":"assistant/chunk","seq":31,"time":1783486770459,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":32,"time":1783486770459,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" permission"}}} -{"type":"assistant/chunk","seq":33,"time":1783486770474,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" prompt"}}} -{"type":"assistant/chunk","seq":34,"time":1783486770474,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":35,"time":1783486770475,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} -{"type":"assistant/chunk","seq":36,"time":1783486770475,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":37,"time":1783486770475,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" proceed"}}} -{"type":"assistant/chunk","seq":38,"time":1783486770518,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":39,"time":1783486770606,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":40,"time":1783486770606,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":41,"time":1783486770606,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":42,"time":1783486770606,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":43,"time":1783486770634,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"command"}}} -{"type":"assistant/chunk","seq":44,"time":1783486770634,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":45,"time":1783486770634,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":46,"time":1783486770634,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":47,"time":1783486770682,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"printf"}}} -{"type":"assistant/chunk","seq":48,"time":1783486770683,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" '"}}} -{"type":"assistant/chunk","seq":49,"time":1783486770683,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"es"}}} -{"type":"assistant/chunk","seq":50,"time":1783486770683,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"cal"}}} -{"type":"assistant/chunk","seq":51,"time":1783486770694,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"ated"}}} -{"type":"assistant/chunk","seq":52,"time":1783486770694,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\\\\n"}}} -{"type":"assistant/chunk","seq":53,"time":1783486770694,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"'"}}} -{"type":"assistant/chunk","seq":54,"time":1783486770695,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" >"}}} -{"type":"assistant/chunk","seq":55,"time":1783486770697,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" escalated"}}} -{"type":"assistant/chunk","seq":56,"time":1783486770697,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":57,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" &&"}}} -{"type":"assistant/chunk","seq":58,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" cat"}}} -{"type":"assistant/chunk","seq":59,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" escalated"}}} -{"type":"assistant/chunk","seq":60,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":61,"time":1783486770740,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":62,"time":1783486770802,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":63,"time":1783486770802,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":64,"time":1783486770802,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":65,"time":1783486770802,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":66,"time":1783486770803,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":67,"time":1783486770820,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":68,"time":1783486770821,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"Write"}}} -{"type":"assistant/chunk","seq":69,"time":1783486770821,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" escalated"}}} -{"type":"assistant/chunk","seq":70,"time":1783486770909,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":71,"time":1783486770910,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":72,"time":1783486770910,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" cat"}}} -{"type":"assistant/chunk","seq":73,"time":1783486770910,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" its"}}} -{"type":"assistant/chunk","seq":74,"time":1783486770924,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" content"}}} -{"type":"assistant/chunk","seq":75,"time":1783486770925,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":76,"time":1783486770953,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":77,"time":1783486770953,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":78,"time":1783486770953,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"sand"}}} -{"type":"assistant/chunk","seq":79,"time":1783486770953,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"box"}}} -{"type":"assistant/chunk","seq":80,"time":1783486770981,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"_per"}}} -{"type":"assistant/chunk","seq":81,"time":1783486770983,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"missions"}}} -{"type":"assistant/chunk","seq":82,"time":1783486770983,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":83,"time":1783486770983,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":84,"time":1783486771018,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":85,"time":1783486771018,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"works"}}} -{"type":"assistant/chunk","seq":86,"time":1783486771018,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"pace"}}} -{"type":"assistant/chunk","seq":87,"time":1783486771019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"-w"}}} -{"type":"assistant/chunk","seq":88,"time":1783486771019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"rite"}}} -{"type":"assistant/chunk","seq":89,"time":1783486771050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":90,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":91,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":92,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"just"}}} -{"type":"assistant/chunk","seq":93,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"ification"}}} -{"type":"assistant/chunk","seq":94,"time":1783486771083,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":95,"time":1783486771084,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":96,"time":1783486771113,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":97,"time":1783486771114,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"the"}}} -{"type":"assistant/chunk","seq":98,"time":1783486771114,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" user"}}} -{"type":"assistant/chunk","seq":99,"time":1783486771114,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" asked"}}} -{"type":"assistant/chunk","seq":100,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" to"}}} -{"type":"assistant/chunk","seq":101,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" write"}}} -{"type":"assistant/chunk","seq":102,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" escalated"}}} -{"type":"assistant/chunk","seq":103,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":104,"time":1783486771142,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" in"}}} -{"type":"assistant/chunk","seq":105,"time":1783486771216,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":106,"time":1783486771217,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":" workspace"}}} -{"type":"assistant/chunk","seq":107,"time":1783486771217,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":108,"time":1783486771219,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":109,"time":1783486771231,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."}}}} -{"type":"assistant/chunk","seq":110,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}}} -{"type":"assistant/chunk","seq":111,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}}}} -{"type":"assistant/chunk","seq":112,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":113,"time":1783486771236,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."},{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} -{"type":"tool/call","seq":114,"time":1783486771236,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}} -{"type":"approval/asked","seq":115,"time":1783486771238,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","toolName":"bash","callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} -{"type":"approval/decided","seq":116,"time":1783486771243,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","outcome":"allowed-once"}} -{"type":"tool/result","seq":117,"time":1783486771442,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[114],"surfaceOp":"append"} -{"type":"step/end","seq":118,"time":1783486771443,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":119,"time":1783486771443,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":120,"time":1783486771965,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":121,"time":1783486771965,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":122,"time":1783486772052,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} -{"type":"assistant/chunk","seq":123,"time":1783486772113,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" succeeded"}}} -{"type":"assistant/chunk","seq":124,"time":1783486772113,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":125,"time":1783486772113,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} -{"type":"assistant/chunk","seq":126,"time":1783486772114,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":127,"time":1783486772115,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":128,"time":1783486772115,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":129,"time":1783486772141,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":130,"time":1783486772142,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":131,"time":1783486772142,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":132,"time":1783486772185,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":133,"time":1783486772186,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} -{"type":"assistant/chunk","seq":134,"time":1783486772186,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":135,"time":1783486772186,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" D"}}} -{"type":"assistant/chunk","seq":136,"time":1783486772204,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":137,"time":1783486772205,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":138,"time":1783486772205,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":139,"time":1783486772205,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} -{"type":"assistant/chunk","seq":140,"time":1783486772205,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} -{"type":"assistant/chunk","seq":141,"time":1783486772228,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The command succeeded. The user asked me to reply with the single word DONE."}}}} -{"type":"assistant/chunk","seq":142,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} -{"type":"assistant/chunk","seq":143,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}}}} -{"type":"assistant/chunk","seq":144,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":145,"time":1783486772230,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command succeeded. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}},"sourceEventSeqs":[120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144],"surfaceOp":"append"} -{"type":"step/end","seq":146,"time":1783486772230,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":147,"time":1783486772230,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/input.json b/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/input.json deleted file mode 100644 index d645402478..0000000000 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/input.json +++ /dev/null @@ -1,10 +0,0 @@ -{ - "steps": [ - { "op": "initialize" }, - { "op": "newSession" }, - { "op": "prompt", "text": "The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence that the escalation was rejected, then stop." } - ], - "permissionAnswers": [ - { "kind": "reject_once" } - ] -} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl deleted file mode 100644 index ee2586bc34..0000000000 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ /dev/null @@ -1,202 +0,0 @@ -{"type":"session","version":0,"id":"46ee90bb-006b-477c-9c56-04dd4923aeb6","createdAt":1783486772550,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-OivXMN"} -{"type":"turn/start","seq":0,"time":1783486772551,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783486772551,"data":{"content":[{"type":"text","text":"The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence that the escalation was rejected, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783486772552,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783486772552,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783486773136,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783486773136,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783486773275,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783486773326,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783486773328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783486773328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783486773328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ret"}}} -{"type":"assistant/chunk","seq":11,"time":1783486773347,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ry"}}} -{"type":"assistant/chunk","seq":12,"time":1783486773348,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":13,"time":1783486773349,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exact"}}} -{"type":"assistant/chunk","seq":14,"time":1783486773381,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} -{"type":"assistant/chunk","seq":15,"time":1783486773382,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} -{"type":"assistant/chunk","seq":16,"time":1783486773412,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"printf"}}} -{"type":"assistant/chunk","seq":17,"time":1783486773413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" '"}}} -{"type":"assistant/chunk","seq":18,"time":1783486773413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"es"}}} -{"type":"assistant/chunk","seq":19,"time":1783486773413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"cal"}}} -{"type":"assistant/chunk","seq":20,"time":1783486773414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ated"}}} -{"type":"assistant/chunk","seq":21,"time":1783486773414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\\n"}}} -{"type":"assistant/chunk","seq":22,"time":1783486773445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'"}}} -{"type":"assistant/chunk","seq":23,"time":1783486773446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" >"}}} -{"type":"assistant/chunk","seq":24,"time":1783486773446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" escalated"}}} -{"type":"assistant/chunk","seq":25,"time":1783486773446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".txt"}}} -{"type":"assistant/chunk","seq":26,"time":1783486773446,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" &&"}}} -{"type":"assistant/chunk","seq":27,"time":1783486773447,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cat"}}} -{"type":"assistant/chunk","seq":28,"time":1783486773473,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" escalated"}}} -{"type":"assistant/chunk","seq":29,"time":1783486773473,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".txt"}}} -{"type":"assistant/chunk","seq":30,"time":1783486773473,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}} -{"type":"assistant/chunk","seq":31,"time":1783486773473,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":32,"time":1783486773474,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} -{"type":"assistant/chunk","seq":33,"time":1783486773500,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"sand"}}} -{"type":"assistant/chunk","seq":34,"time":1783486773501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}} -{"type":"assistant/chunk","seq":35,"time":1783486773501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_per"}}} -{"type":"assistant/chunk","seq":36,"time":1783486773501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"missions"}}} -{"type":"assistant/chunk","seq":37,"time":1783486773501,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}} -{"type":"assistant/chunk","seq":38,"time":1783486773542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" set"}}} -{"type":"assistant/chunk","seq":39,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":40,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} -{"type":"assistant/chunk","seq":41,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"works"}}} -{"type":"assistant/chunk","seq":42,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"pace"}}} -{"type":"assistant/chunk","seq":43,"time":1783486773543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-w"}}} -{"type":"assistant/chunk","seq":44,"time":1783486773568,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"rite"}}} -{"type":"assistant/chunk","seq":45,"time":1783486773569,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}} -{"type":"assistant/chunk","seq":46,"time":1783486773569,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":47,"time":1783486773569,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":48,"time":1783486773597,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" justification"}}} -{"type":"assistant/chunk","seq":49,"time":1783486773632,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" they"}}} -{"type":"assistant/chunk","seq":50,"time":1783486773667,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specified"}}} -{"type":"assistant/chunk","seq":51,"time":1783486773668,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":52,"time":1783486773669,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" They"}}} -{"type":"assistant/chunk","seq":53,"time":1783486773685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" explicitly"}}} -{"type":"assistant/chunk","seq":54,"time":1783486773716,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" say"}}} -{"type":"assistant/chunk","seq":55,"time":1783486773731,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" they"}}} -{"type":"assistant/chunk","seq":56,"time":1783486773732,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" will"}}} -{"type":"assistant/chunk","seq":57,"time":1783486773732,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reject"}}} -{"type":"assistant/chunk","seq":58,"time":1783486773746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":59,"time":1783486773746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" permission"}}} -{"type":"assistant/chunk","seq":60,"time":1783486773747,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" prompt"}}} -{"type":"assistant/chunk","seq":61,"time":1783486773773,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":62,"time":1783486773773,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" so"}}} -{"type":"assistant/chunk","seq":63,"time":1783486773774,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" after"}}} -{"type":"assistant/chunk","seq":64,"time":1783486773774,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" rejection"}}} -{"type":"assistant/chunk","seq":65,"time":1783486773806,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":66,"time":1783486773807,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":67,"time":1783486773833,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" explain"}}} -{"type":"assistant/chunk","seq":68,"time":1783486773834,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} -{"type":"assistant/chunk","seq":69,"time":1783486773861,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" one"}}} -{"type":"assistant/chunk","seq":70,"time":1783486773862,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" short"}}} -{"type":"assistant/chunk","seq":71,"time":1783486773862,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sentence"}}} -{"type":"assistant/chunk","seq":72,"time":1783486773862,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":73,"time":1783486773862,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} -{"type":"assistant/chunk","seq":74,"time":1783486773900,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":75,"time":1783486773978,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":76,"time":1783486773979,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":77,"time":1783486774009,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":78,"time":1783486774011,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":79,"time":1783486774012,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"command"}}} -{"type":"assistant/chunk","seq":80,"time":1783486774012,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":81,"time":1783486774012,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":82,"time":1783486774049,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":83,"time":1783486774050,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"printf"}}} -{"type":"assistant/chunk","seq":84,"time":1783486774051,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" '"}}} -{"type":"assistant/chunk","seq":85,"time":1783486774051,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"es"}}} -{"type":"assistant/chunk","seq":86,"time":1783486774068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"cal"}}} -{"type":"assistant/chunk","seq":87,"time":1783486774068,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"ated"}}} -{"type":"assistant/chunk","seq":88,"time":1783486774069,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\\\\n"}}} -{"type":"assistant/chunk","seq":89,"time":1783486774069,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"'"}}} -{"type":"assistant/chunk","seq":90,"time":1783486774069,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" >"}}} -{"type":"assistant/chunk","seq":91,"time":1783486774069,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" escalated"}}} -{"type":"assistant/chunk","seq":92,"time":1783486774107,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":93,"time":1783486774108,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" &&"}}} -{"type":"assistant/chunk","seq":94,"time":1783486774108,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" cat"}}} -{"type":"assistant/chunk","seq":95,"time":1783486774108,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" escalated"}}} -{"type":"assistant/chunk","seq":96,"time":1783486774108,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":97,"time":1783486774138,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":98,"time":1783486774162,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":99,"time":1783486774162,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":100,"time":1783486774162,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":101,"time":1783486774162,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":102,"time":1783486774163,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":103,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":104,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"Write"}}} -{"type":"assistant/chunk","seq":105,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" escalated"}}} -{"type":"assistant/chunk","seq":106,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":107,"time":1783486774194,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":108,"time":1783486774221,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" workspace"}}} -{"type":"assistant/chunk","seq":109,"time":1783486774221,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"-w"}}} -{"type":"assistant/chunk","seq":110,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"rite"}}} -{"type":"assistant/chunk","seq":111,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" permission"}}} -{"type":"assistant/chunk","seq":112,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":113,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":114,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":115,"time":1783486774283,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"sand"}}} -{"type":"assistant/chunk","seq":116,"time":1783486774303,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"box"}}} -{"type":"assistant/chunk","seq":117,"time":1783486774303,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"_per"}}} -{"type":"assistant/chunk","seq":118,"time":1783486774303,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"missions"}}} -{"type":"assistant/chunk","seq":119,"time":1783486774304,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":120,"time":1783486774304,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":121,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":122,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"works"}}} -{"type":"assistant/chunk","seq":123,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"pace"}}} -{"type":"assistant/chunk","seq":124,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"-w"}}} -{"type":"assistant/chunk","seq":125,"time":1783486774339,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"rite"}}} -{"type":"assistant/chunk","seq":126,"time":1783486774368,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":127,"time":1783486774392,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":128,"time":1783486774395,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":129,"time":1783486774395,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"just"}}} -{"type":"assistant/chunk","seq":130,"time":1783486774395,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"ification"}}} -{"type":"assistant/chunk","seq":131,"time":1783486774395,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":132,"time":1783486774440,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":133,"time":1783486774441,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":134,"time":1783486774441,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"the"}}} -{"type":"assistant/chunk","seq":135,"time":1783486774441,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" user"}}} -{"type":"assistant/chunk","seq":136,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" asked"}}} -{"type":"assistant/chunk","seq":137,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" to"}}} -{"type":"assistant/chunk","seq":138,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" write"}}} -{"type":"assistant/chunk","seq":139,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" escalated"}}} -{"type":"assistant/chunk","seq":140,"time":1783486774469,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":141,"time":1783486774470,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" in"}}} -{"type":"assistant/chunk","seq":142,"time":1783486774480,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":143,"time":1783486774480,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":" workspace"}}} -{"type":"assistant/chunk","seq":144,"time":1783486774481,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":145,"time":1783486774510,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":146,"time":1783486774568,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."}}}} -{"type":"assistant/chunk","seq":147,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}}} -{"type":"assistant/chunk","seq":148,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}}}} -{"type":"assistant/chunk","seq":149,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":150,"time":1783486774572,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."},{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} -{"type":"tool/call","seq":151,"time":1783486774572,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}} -{"type":"approval/asked","seq":152,"time":1783486774574,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","toolName":"bash","callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} -{"type":"approval/decided","seq":153,"time":1783486774578,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","outcome":"rejected"}} -{"type":"tool/result","seq":154,"time":1783486774579,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"workspace-write\""}],"isError":true},"sourceEventSeqs":[151],"surfaceOp":"append"} -{"type":"step/end","seq":155,"time":1783486774579,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":156,"time":1783486774580,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":157,"time":1783486775719,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":158,"time":1783486775719,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":159,"time":1783486775820,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":160,"time":1783486775856,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} -{"type":"assistant/chunk","seq":161,"time":1783486775857,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":162,"time":1783486775857,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" escalation"}}} -{"type":"assistant/chunk","seq":163,"time":1783486775857,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":164,"time":1783486775879,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":165,"time":1783486775879,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} -{"type":"assistant/chunk","seq":166,"time":1783486775921,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":167,"time":1783486775922,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" explain"}}} -{"type":"assistant/chunk","seq":168,"time":1783486775922,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} -{"type":"assistant/chunk","seq":169,"time":1783486775934,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" one"}}} -{"type":"assistant/chunk","seq":170,"time":1783486775934,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" short"}}} -{"type":"assistant/chunk","seq":171,"time":1783486775935,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sentence"}}} -{"type":"assistant/chunk","seq":172,"time":1783486775935,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":173,"time":1783486775935,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} -{"type":"assistant/chunk","seq":174,"time":1783486775935,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":175,"time":1783486775977,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":176,"time":1783486775978,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}} -{"type":"assistant/chunk","seq":177,"time":1783486775978,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" escalation"}}} -{"type":"assistant/chunk","seq":178,"time":1783486775978,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" request"}}} -{"type":"assistant/chunk","seq":179,"time":1783486776011,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" to"}}} -{"type":"assistant/chunk","seq":180,"time":1783486776026,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" write"}}} -{"type":"assistant/chunk","seq":181,"time":1783486776027,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" to"}}} -{"type":"assistant/chunk","seq":182,"time":1783486776027,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":183,"time":1783486776057,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" workspace"}}} -{"type":"assistant/chunk","seq":184,"time":1783486776057,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" was"}}} -{"type":"assistant/chunk","seq":185,"time":1783486776057,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} -{"type":"assistant/chunk","seq":186,"time":1783486776058,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":","}}} -{"type":"assistant/chunk","seq":187,"time":1783486776128,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" so"}}} -{"type":"assistant/chunk","seq":188,"time":1783486776128,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":189,"time":1783486776129,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" command"}}} -{"type":"assistant/chunk","seq":190,"time":1783486776129,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" was"}}} -{"type":"assistant/chunk","seq":191,"time":1783486776145,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" not"}}} -{"type":"assistant/chunk","seq":192,"time":1783486776146,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" executed"}}} -{"type":"assistant/chunk","seq":193,"time":1783486776184,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"."}}} -{"type":"assistant/chunk","seq":194,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user rejected the escalation. I need to explain in one short sentence and stop."}}}} -{"type":"assistant/chunk","seq":195,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}}}} -{"type":"assistant/chunk","seq":196,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}}}} -{"type":"assistant/chunk","seq":197,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":198,"time":1783486776186,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user rejected the escalation. I need to explain in one short sentence and stop."},{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}],"usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}},"sourceEventSeqs":[157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197],"surfaceOp":"append"} -{"type":"step/end","seq":199,"time":1783486776186,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":200,"time":1783486776186,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/input.json b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/input.json deleted file mode 100644 index e11cec253e..0000000000 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/input.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "steps": [ - { "op": "initialize" }, - { "op": "newSession" }, - { "op": "prompt", "text": "Use the bash tool to run exactly: cat notes.txt. Then reply with the single word DONE and stop." }, - { "op": "setConfigOption", "configId": "sandbox-mode", "value": "workspace-write" }, - { "op": "prompt", "text": "Use the bash tool to run exactly this one command in a single call: printf 'switched\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop." }, - { "op": "setConfigOption", "configId": "approval-policy", "value": "never" }, - { "op": "prompt", "text": "Without using any tools, state your current approval policy in one short sentence and stop." } - ] -} diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl deleted file mode 100644 index e63e644459..0000000000 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl +++ /dev/null @@ -1,245 +0,0 @@ -{"type":"session","version":0,"id":"eee406bd-e76b-4d87-8fb7-0ffa2dc94fe6","createdAt":1783613224994,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-mNdf7I"} -{"type":"turn/start","seq":0,"time":1783613224997,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783613224997,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat notes.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783613224997,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783613224997,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783613225437,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783613225438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783613225658,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783613225687,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783613225687,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783613225687,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783613225687,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} -{"type":"assistant/chunk","seq":11,"time":1783613225688,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} -{"type":"assistant/chunk","seq":12,"time":1783613225717,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"cat"}}} -{"type":"assistant/chunk","seq":13,"time":1783613225718,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" notes"}}} -{"type":"assistant/chunk","seq":14,"time":1783613225718,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".txt"}}} -{"type":"assistant/chunk","seq":15,"time":1783613225718,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`"}}} -{"type":"assistant/chunk","seq":16,"time":1783613225718,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} -{"type":"assistant/chunk","seq":17,"time":1783613225746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":18,"time":1783613225747,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} -{"type":"assistant/chunk","seq":19,"time":1783613225747,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":20,"time":1783613225747,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":21,"time":1783613225832,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":22,"time":1783613225832,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":23,"time":1783613225859,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":24,"time":1783613225860,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":25,"time":1783613225860,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"command"}}} -{"type":"assistant/chunk","seq":26,"time":1783613225860,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":27,"time":1783613225860,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":28,"time":1783613225888,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":29,"time":1783613225888,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"cat"}}} -{"type":"assistant/chunk","seq":30,"time":1783613225889,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":" notes"}}} -{"type":"assistant/chunk","seq":31,"time":1783613225889,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":32,"time":1783613225889,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":33,"time":1783613225945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":34,"time":1783613225945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":35,"time":1783613225945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":36,"time":1783613225945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":37,"time":1783613225946,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":38,"time":1783613225979,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":39,"time":1783613225979,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"Show"}}} -{"type":"assistant/chunk","seq":40,"time":1783613225979,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":" contents"}}} -{"type":"assistant/chunk","seq":41,"time":1783613225979,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":" of"}}} -{"type":"assistant/chunk","seq":42,"time":1783613225980,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":" notes"}}} -{"type":"assistant/chunk","seq":43,"time":1783613226003,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":44,"time":1783613226004,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":45,"time":1783613226031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":46,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run `cat notes.txt` using the bash tool."}}}} -{"type":"assistant/chunk","seq":47,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}}}} -{"type":"assistant/chunk","seq":48,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1202,"outputTokens":81,"cacheReadTokens":0,"reasoningTokens":16}}}} -{"type":"assistant/chunk","seq":49,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":50,"time":1783613226064,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `cat notes.txt` using the bash tool."},{"type":"tool-call","id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}],"usage":{"inputTokens":1202,"outputTokens":81,"cacheReadTokens":0,"reasoningTokens":16}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"surfaceOp":"append"} -{"type":"tool/call","seq":51,"time":1783613226064,"data":{"turn":1,"step":1,"callId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}} -{"type":"tool/result","seq":52,"time":1783613226148,"data":{"turn":1,"step":1,"callId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","content":[{"type":"text","text":"hello from the sandboxed workspace\n"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} -{"type":"step/end","seq":53,"time":1783613226148,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":54,"time":1783613226148,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":55,"time":1783613226790,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":56,"time":1783613226791,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":57,"time":1783613226970,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} -{"type":"assistant/chunk","seq":58,"time":1783613227003,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" ran"}}} -{"type":"assistant/chunk","seq":59,"time":1783613227025,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} -{"type":"assistant/chunk","seq":60,"time":1783613227025,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":61,"time":1783613227025,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} -{"type":"assistant/chunk","seq":62,"time":1783613227025,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":63,"time":1783613227052,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":64,"time":1783613227053,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":65,"time":1783613227053,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":66,"time":1783613227053,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":67,"time":1783613227053,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":68,"time":1783613227053,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":69,"time":1783613227082,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} -{"type":"assistant/chunk","seq":70,"time":1783613227082,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":71,"time":1783613227083,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" D"}}} -{"type":"assistant/chunk","seq":72,"time":1783613227110,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":73,"time":1783613227110,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":74,"time":1783613227140,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":75,"time":1783613227140,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} -{"type":"assistant/chunk","seq":76,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} -{"type":"assistant/chunk","seq":77,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The command ran successfully. The user asked me to reply with the single word DONE."}}}} -{"type":"assistant/chunk","seq":78,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} -{"type":"assistant/chunk","seq":79,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":23,"outputTokens":21,"cacheReadTokens":1280,"reasoningTokens":18}}}} -{"type":"assistant/chunk","seq":80,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":81,"time":1783613227142,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":23,"outputTokens":21,"cacheReadTokens":1280,"reasoningTokens":18}},"sourceEventSeqs":[55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80],"surfaceOp":"append"} -{"type":"step/end","seq":82,"time":1783613227142,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":83,"time":1783613227142,"data":{"turn":1,"reason":{"kind":"completed"}}} -{"type":"turn/start","seq":84,"time":1783613227169,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"bash/sandbox-mode","seq":85,"time":1783613227169,"data":{"mode":"workspace-write"}} -{"type":"user/message","seq":86,"time":1783613227169,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'switched\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":87,"time":1783613227169,"data":{"turn":2,"step":1}} -{"type":"assistant/chunk","seq":88,"time":1783613227737,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":89,"time":1783613227738,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":90,"time":1783613227839,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":91,"time":1783613227858,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":92,"time":1783613227859,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":93,"time":1783613227859,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":94,"time":1783613227859,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} -{"type":"assistant/chunk","seq":95,"time":1783613227859,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} -{"type":"assistant/chunk","seq":96,"time":1783613227859,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} -{"type":"assistant/chunk","seq":97,"time":1783613227888,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} -{"type":"assistant/chunk","seq":98,"time":1783613227888,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":99,"time":1783613227888,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} -{"type":"assistant/chunk","seq":100,"time":1783613227916,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":101,"time":1783613227916,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" execute"}}} -{"type":"assistant/chunk","seq":102,"time":1783613227917,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} -{"type":"assistant/chunk","seq":103,"time":1783613227917,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":104,"time":1783613228006,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":105,"time":1783613228006,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":106,"time":1783613228034,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":107,"time":1783613228035,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":108,"time":1783613228035,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":109,"time":1783613228035,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":110,"time":1783613228035,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":111,"time":1783613228063,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":112,"time":1783613228063,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"Write"}}} -{"type":"assistant/chunk","seq":113,"time":1783613228063,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":114,"time":1783613228100,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" read"}}} -{"type":"assistant/chunk","seq":115,"time":1783613228100,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" out"}}} -{"type":"assistant/chunk","seq":116,"time":1783613228100,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":117,"time":1783613228121,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":118,"time":1783613228150,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":119,"time":1783613228150,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":120,"time":1783613228151,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"command"}}} -{"type":"assistant/chunk","seq":121,"time":1783613228151,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":122,"time":1783613228151,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":123,"time":1783613228179,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":124,"time":1783613228179,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"printf"}}} -{"type":"assistant/chunk","seq":125,"time":1783613228179,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" '"}}} -{"type":"assistant/chunk","seq":126,"time":1783613228179,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"sw"}}} -{"type":"assistant/chunk","seq":127,"time":1783613228209,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"itched"}}} -{"type":"assistant/chunk","seq":128,"time":1783613228209,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\\\\n"}}} -{"type":"assistant/chunk","seq":129,"time":1783613228209,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"'"}}} -{"type":"assistant/chunk","seq":130,"time":1783613228209,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" >"}}} -{"type":"assistant/chunk","seq":131,"time":1783613228209,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" out"}}} -{"type":"assistant/chunk","seq":132,"time":1783613228209,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":133,"time":1783613228237,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" &&"}}} -{"type":"assistant/chunk","seq":134,"time":1783613228237,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" cat"}}} -{"type":"assistant/chunk","seq":135,"time":1783613228237,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":" out"}}} -{"type":"assistant/chunk","seq":136,"time":1783613228237,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":".txt"}}} -{"type":"assistant/chunk","seq":137,"time":1783613228237,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":138,"time":1783613228265,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":139,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a specific command. Let me execute it."}}}} -{"type":"assistant/chunk","seq":140,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}}}} -{"type":"assistant/chunk","seq":141,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":70,"outputTokens":90,"cacheReadTokens":1280,"reasoningTokens":15}}}} -{"type":"assistant/chunk","seq":142,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":143,"time":1783613228325,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command. Let me execute it."},{"type":"tool-call","id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}],"usage":{"inputTokens":70,"outputTokens":90,"cacheReadTokens":1280,"reasoningTokens":15}},"sourceEventSeqs":[88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} -{"type":"tool/call","seq":144,"time":1783613228325,"data":{"turn":2,"step":1,"callId":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}} -{"type":"tool/result","seq":145,"time":1783613228412,"data":{"turn":2,"step":1,"callId":"call_00_htXcbtvwTFK0NqfclLWL7784","content":[{"type":"text","text":"switched\n"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"} -{"type":"step/end","seq":146,"time":1783613228412,"data":{"turn":2,"step":1}} -{"type":"step/start","seq":147,"time":1783613228412,"data":{"turn":2,"step":2}} -{"type":"assistant/chunk","seq":148,"time":1783613228863,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":149,"time":1783613228864,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"Command"}}} -{"type":"assistant/chunk","seq":150,"time":1783613228966,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" executed"}}} -{"type":"assistant/chunk","seq":151,"time":1783613228994,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} -{"type":"assistant/chunk","seq":152,"time":1783613228994,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":153,"time":1783613228994,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} -{"type":"assistant/chunk","seq":154,"time":1783613228995,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":155,"time":1783613228995,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} -{"type":"assistant/chunk","seq":156,"time":1783613229020,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":157,"time":1783613229020,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"sw"}}} -{"type":"assistant/chunk","seq":158,"time":1783613229020,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"itched"}}} -{"type":"assistant/chunk","seq":159,"time":1783613229020,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":160,"time":1783613229020,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":161,"time":1783613229020,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} -{"type":"assistant/chunk","seq":162,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} -{"type":"assistant/chunk","seq":163,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Command executed successfully. The output is \"switched\"."}}}} -{"type":"assistant/chunk","seq":164,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} -{"type":"assistant/chunk","seq":165,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":47,"outputTokens":14,"cacheReadTokens":1408,"reasoningTokens":11}}}} -{"type":"assistant/chunk","seq":166,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":167,"time":1783613229049,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"Command executed successfully. The output is \"switched\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":47,"outputTokens":14,"cacheReadTokens":1408,"reasoningTokens":11}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166],"surfaceOp":"append"} -{"type":"step/end","seq":168,"time":1783613229049,"data":{"turn":2,"step":2}} -{"type":"turn/end","seq":169,"time":1783613229049,"data":{"turn":2,"reason":{"kind":"completed"}}} -{"type":"turn/start","seq":170,"time":1783613229056,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"approval/policy","seq":171,"time":1783613229056,"data":{"policy":"never"}} -{"type":"user/message","seq":172,"time":1783613229056,"data":{"content":[{"type":"text","text":"Without using any tools, state your current approval policy in one short sentence and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"context/message","seq":173,"time":1783613229057,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"} -{"type":"step/start","seq":174,"time":1783613229057,"data":{"turn":3,"step":1}} -{"type":"request/header","seq":175,"time":1783613229057,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"change"}} -{"type":"assistant/chunk","seq":176,"time":1783613230100,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":177,"time":1783613230100,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":178,"time":1783613230192,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":179,"time":1783613230221,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":180,"time":1783613230249,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":181,"time":1783613230250,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":182,"time":1783613230250,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" state"}}} -{"type":"assistant/chunk","seq":183,"time":1783613230250,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" my"}}} -{"type":"assistant/chunk","seq":184,"time":1783613230250,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" current"}}} -{"type":"assistant/chunk","seq":185,"time":1783613230278,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" approval"}}} -{"type":"assistant/chunk","seq":186,"time":1783613230279,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} -{"type":"assistant/chunk","seq":187,"time":1783613230279,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" without"}}} -{"type":"assistant/chunk","seq":188,"time":1783613230279,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} -{"type":"assistant/chunk","seq":189,"time":1783613230306,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" any"}}} -{"type":"assistant/chunk","seq":190,"time":1783613230307,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} -{"type":"assistant/chunk","seq":191,"time":1783613230307,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":192,"time":1783613230307,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" From"}}} -{"type":"assistant/chunk","seq":193,"time":1783613230335,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":194,"time":1783613230335,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" context"}}} -{"type":"assistant/chunk","seq":195,"time":1783613230335,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":196,"time":1783613230335,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":197,"time":1783613230363,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" approval"}}} -{"type":"assistant/chunk","seq":198,"time":1783613230363,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} -{"type":"assistant/chunk","seq":199,"time":1783613230364,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} -{"type":"assistant/chunk","seq":200,"time":1783613230392,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":201,"time":1783613230393,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"never"}}} -{"type":"assistant/chunk","seq":202,"time":1783613230393,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":203,"time":1783613230393,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" —"}}} -{"type":"assistant/chunk","seq":204,"time":1783613230393,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" meaning"}}} -{"type":"assistant/chunk","seq":205,"time":1783613230423,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" actions"}}} -{"type":"assistant/chunk","seq":206,"time":1783613230450,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":207,"time":1783613230451,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" require"}}} -{"type":"assistant/chunk","seq":208,"time":1783613230451,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" approval"}}} -{"type":"assistant/chunk","seq":209,"time":1783613230451,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" are"}}} -{"type":"assistant/chunk","seq":210,"time":1783613230451,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} -{"type":"assistant/chunk","seq":211,"time":1783613230478,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" automatically"}}} -{"type":"assistant/chunk","seq":212,"time":1783613230479,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":213,"time":1783613230479,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":214,"time":1783613230507,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":215,"time":1783613230507,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":216,"time":1783613230507,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" not"}}} -{"type":"assistant/chunk","seq":217,"time":1783613230508,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" request"}}} -{"type":"assistant/chunk","seq":218,"time":1783613230508,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sand"}}} -{"type":"assistant/chunk","seq":219,"time":1783613230536,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}} -{"type":"assistant/chunk","seq":220,"time":1783613230536,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" escalation"}}} -{"type":"assistant/chunk","seq":221,"time":1783613230536,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":222,"time":1783613230537,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":223,"time":1783613230537,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":"Appro"}}} -{"type":"assistant/chunk","seq":224,"time":1783613230564,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":"vals"}}} -{"type":"assistant/chunk","seq":225,"time":1783613230564,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" are"}}} -{"type":"assistant/chunk","seq":226,"time":1783613230564,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" never"}}} -{"type":"assistant/chunk","seq":227,"time":1783613230565,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" asked"}}} -{"type":"assistant/chunk","seq":228,"time":1783613230605,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":";"}}} -{"type":"assistant/chunk","seq":229,"time":1783613230606,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" any"}}} -{"type":"assistant/chunk","seq":230,"time":1783613230625,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" action"}}} -{"type":"assistant/chunk","seq":231,"time":1783613230626,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" requiring"}}} -{"type":"assistant/chunk","seq":232,"time":1783613230626,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" approval"}}} -{"type":"assistant/chunk","seq":233,"time":1783613230653,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" is"}}} -{"type":"assistant/chunk","seq":234,"time":1783613230654,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" automatically"}}} -{"type":"assistant/chunk","seq":235,"time":1783613230654,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} -{"type":"assistant/chunk","seq":236,"time":1783613230654,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":1,"text":"."}}} -{"type":"assistant/chunk","seq":237,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to state my current approval policy without using any tools. From the context, the approval policy is \"never\" — meaning actions that require approval are rejected automatically, and I should not request sandbox escalation."}}}} -{"type":"assistant/chunk","seq":238,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"Approvals are never asked; any action requiring approval is automatically rejected."}}}} -{"type":"assistant/chunk","seq":239,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1530,"outputTokens":60,"cacheReadTokens":0,"reasoningTokens":45}}}} -{"type":"assistant/chunk","seq":240,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":241,"time":1783613230690,"data":{"turn":3,"step":1,"content":[{"type":"reasoning","text":"The user wants me to state my current approval policy without using any tools. From the context, the approval policy is \"never\" — meaning actions that require approval are rejected automatically, and I should not request sandbox escalation."},{"type":"text","text":"Approvals are never asked; any action requiring approval is automatically rejected."}],"usage":{"inputTokens":1530,"outputTokens":60,"cacheReadTokens":0,"reasoningTokens":45}},"sourceEventSeqs":[176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240],"surfaceOp":"append"} -{"type":"step/end","seq":242,"time":1783613230690,"data":{"turn":3,"step":1}} -{"type":"turn/end","seq":243,"time":1783613230690,"data":{"turn":3,"reason":{"kind":"completed"}}} diff --git a/package.json b/package.json index d97a81096d..ee5b9f6e35 100644 --- a/package.json +++ b/package.json @@ -71,8 +71,7 @@ "demo:repl": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/coding-agent/cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/cordis-agent/cordis.yml", - "demo:acp": "node --import tsx packages/ui/acp-agent/src/bin.ts examples/acp-agent/cordis.yml", - "demo:sandbox-acp": "node --import tsx packages/ui/acp-agent/src/bin.ts examples/sandbox-acp-agent/cordis.yml", + "demo:acp": "node --import tsx packages/ui/acp-agent/src/bin.ts --config examples/acp-agent/cordis.yml", "postinstall": "node scripts/install-lefthook.mjs" }, "devDependencies": { diff --git a/packages/README.md b/packages/README.md index 7b6b1bb32a..d3dd6818df 100644 --- a/packages/README.md +++ b/packages/README.md @@ -25,6 +25,7 @@ Packages are grouped by modular role at `packages///`. The group dir | [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface | | [`hooks/`](hooks/README.md) | Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface | | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface | +| [`session-query/`](session-query/README.md) | Session retrieval family: logical corpus, surface records, and bounded exact reads | Product — stable surface | | [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, JSON-RPC SDK server, app packages, user-approval and user-interaction seams, ask-user tool | Product — stable surface | | [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, replay adapter, subagent mock) | Support — lower compatibility expectations | | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (the `Branded` primitive) | Support — small, stable, harness-dep-free | diff --git a/packages/bash/README.md b/packages/bash/README.md index 4072998f3e..c850ce2c15 100644 --- a/packages/bash/README.md +++ b/packages/bash/README.md @@ -9,4 +9,4 @@ The canonical three-package capability seam (see [capability seams](../../docs/r | `bash-sandbox/` | Sandbox-consuming `BashExecutor` (wraps every command argv via `ctx.sandbox`, stamps denial/enforcement facts; extends `bash-local`'s mechanics) | (registers `ctx.bash`) | | `tool-bash/` | Model-facing `bash`/`bash_output`/`bash_kill` tool schemas | (registers on `ctx.tools`) | -The interface lives at `bash/bash/`. `bash-sandbox` replacing `bash-local` without touching the interface or the tool is the split doing exactly what it exists for — a leaf `cordis.yml` picks one executor entry, plus a `ctx.sandbox` provider entry for the confined one (see [examples/sandbox-acp-agent](../../examples/sandbox-acp-agent/)). +The interface lives at `bash/bash/`. `bash-sandbox` replacing `bash-local` without touching the interface or the tool is the split doing exactly what it exists for — a leaf `cordis.yml` picks one executor entry, plus a `ctx.sandbox` provider entry for the confined one (see [the acp-agent example's default composition](../../examples/acp-agent/)). diff --git a/packages/bash/bash-sandbox/README.md b/packages/bash/bash-sandbox/README.md index 2a5ae63b8e..c3407b5d1e 100644 --- a/packages/bash/bash-sandbox/README.md +++ b/packages/bash/bash-sandbox/README.md @@ -30,4 +30,4 @@ Deny-only at the seam: a denial is a reported fact, and this executor never nego workspaceRoot: !!js process.cwd() ``` -The keyless consumer-integration proofs are `tests/bwrap.e2e.ts`, `tests/landlock.e2e.ts`, and `tests/seatbelt.e2e.ts` (the real provider + real runner driven through `ctx.bash`, world-verified, each self-skipping where its runner is absent); see [`examples/sandbox-acp-agent`](../../../examples/sandbox-acp-agent/) for the runnable demo. +The keyless consumer-integration proofs are `tests/bwrap.e2e.ts`, `tests/landlock.e2e.ts`, and `tests/seatbelt.e2e.ts` (the real provider + real runner driven through `ctx.bash`, world-verified, each self-skipping where its runner is absent); see [the acp-agent example's default composition](../../../examples/acp-agent/) for the runnable demo. diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 8b66539ad3..67aeb57166 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -136,6 +136,16 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'stream(options: GenerateOptions): AsyncIterable', ], }, + { + key: 'permission', + summary: 'The permission service (`ctx.permission`).', + methods: [ + 'current(events: readonly SessionEvent[]): string', + 'resolve(name: string): PresetSpec', + 'optionOf(name: string): PresetOption', + 'set(session: Session, name: string): void', + ], + }, { key: 'sandbox', summary: 'Abstract process-sandbox service.', @@ -153,6 +163,15 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'abstract list(): Promise', ], }, + { + key: 'sessionQuery', + summary: 'Live-preferred logical-corpus and exact-event read service.', + methods: [ + 'listSessions(): Promise', + 'async listEvents(sessionId: SessionId): Promise', + 'async readEvent(request: SessionEventReadRequest): Promise', + ], + }, { key: 'sessions', summary: 'In-memory session store (`ctx.sessions`).', @@ -518,6 +537,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'ApprovalOutcome', declaration: 'export type ApprovalOutcome = \'allowed-once\' | \'rejected\' | \'cancelled\' | \'unavailable\';', }, + { + name: 'ApprovalPolicy', + declaration: 'export type ApprovalPolicy = \'ask\' | \'never\';', + }, { name: 'ApprovalRequest', declaration: 'export interface ApprovalRequest {\n readonly agent: Agent;\n readonly toolName: string;\n readonly callId?: CallId;\n readonly reason?: string;\n readonly signal?: AbortSignal;\n}', @@ -746,6 +769,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'OwnerToken', declaration: 'export type OwnerToken = Branded<\'OwnerToken\'>;', }, + { + name: 'PresetOption', + declaration: 'export interface PresetOption {\n value: string;\n name: string;\n description?: string;\n}', + }, + { + name: 'PresetSpec', + declaration: 'export interface PresetSpec {\n sandbox: SandboxMode;\n approval: ApprovalPolicy;\n name?: string;\n description?: string;\n}', + }, { name: 'PromptAssembly', declaration: 'export interface PromptAssembly {\n sections: AssembledSection[];\n tools: ToolSchema[];\n variables: Record;\n}', @@ -790,10 +821,26 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionEventMap', declaration: 'export interface SessionEventMap {\n \'turn/start\': {\n turn: number;\n trigger: TurnTrigger;\n };\n \'turn/end\': {\n turn: number;\n reason: TurnEndReason;\n };\n \'step/start\': {\n turn: number;\n step: number;\n };\n \'step/end\': {\n turn: number;\n step: number;\n };\n \'user/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'prompt/blocked\': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n \'context/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'assistant/chunk\': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n \'assistant/message\': {\n turn: number;\n step: number;\n content: ContentBlock[];\n usage?: TokenUsage;\n };\n \'tool/call\': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n \'tool/result\': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: unknown;\n };\n \'steering/message\': {\n turn: number;\n content: ContentBlock[];\n source: MessageSource;\n };\n \'todo/write\': {\n todos: TodoItem[];\n };\n \'request/header\': {\n header: E /* …truncated — full shape in source */', }, + { + name: 'SessionEventReadRequest', + declaration: 'export interface SessionEventReadRequest {\n sessionId: SessionId;\n seq: number;\n before?: number;\n after?: number;\n}', + }, + { + name: 'SessionEventRecord', + declaration: 'export interface SessionEventRecord {\n sessionId: SessionId;\n seq: number;\n type: SessionEventType;\n time: number;\n surface: SessionEventSurface;\n}', + }, + { + name: 'SessionEventSurface', + declaration: 'export type SessionEventSurface = \'current\' | \'shadowed\' | \'log-only\';', + }, { name: 'SessionEventType', declaration: 'export type SessionEventType = keyof SessionEventMap;', }, + { + name: 'SessionEventWindow', + declaration: 'export interface SessionEventWindow {\n session: SessionHeader;\n target: SessionEvent;\n events: SessionEvent[];\n startSeq: number;\n endSeq: number;\n}', + }, { name: 'SessionForkSource', declaration: 'export type SessionForkSource = Session | SessionId;', @@ -806,6 +853,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionId', declaration: 'export type SessionId = Branded<\'SessionId\'>;', }, + { + name: 'SessionRecord', + declaration: 'export interface SessionRecord {\n header: SessionHeader;\n live: boolean;\n persisted: boolean;\n}', + }, { name: 'SkillCandidate', declaration: 'export interface SkillCandidate extends SkillSummary {\n readonly rank: number;\n readonly locator: unknown;\n readonly path?: string;\n readonly metadata?: Readonly>;\n}', diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 39582ad555..ae168ad3eb 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -48,7 +48,8 @@ Durable values need one accepted representation, not a check followed by a secon - `SurfaceOp` — how an event entered the ordered surface: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace entries from `start` through `end` inclusive — both must be valid surface seqs; `start === end` replaces one entry). Used by compaction to shadow old events without deleting them. - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types. -- `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event (type is surface-eligible AND `surfaceOp` present); the second is the type-only check (is this one of the five `SurfaceEventType` values?), used to detect a surface-eligible event MISSING its marker — e.g. when validating a seed/load log. +- `foldSurface(events)` — replay the canonical surface transitions into detached current event sequences and actual replacement ranges, rejecting surface-eligible events that lack their mandatory marker. `SurfaceManager` shares the same transitions while retaining only its incremental sequence cache. +- `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event (type is surface-eligible AND `surfaceOp` present); the second is the type-only check, used to detect a surface-eligible event MISSING its marker when validating a seed or loaded log. ### Request-header reconstruction (`request-header.ts`) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index cb6e1304c3..a11aee5809 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -22,7 +22,8 @@ export * from './types.ts' export { isJsonValue, snapshotJsonValue } from './json.ts' export type { JsonValue } from './json.ts' export { interruptedTurnClosers } from './repair.ts' -export { isSurfaceEvent, isSurfaceEligibleType } from './surface.ts' +export type { SurfaceFoldReplacement, SurfaceFoldResult } from './surface.ts' +export { foldSurface, isSurfaceEvent, isSurfaceEligibleType } from './surface.ts' export { isToolPairingBalanced } from './tool-pairing.ts' export { canonicalHeader, foldRequestHeader, headerEquals } from './request-header.ts' diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index 18721281db..0b07186100 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -1,19 +1,13 @@ /** - * Surface layer on top of the session event log: a derived, cached sequence - * list of events that produce LLM messages. Folded deterministically from - * `surfaceOp` markers in the log — the log is the source of truth; the surface - * is a view. + * Surface layer on top of the session event log: an ordered view of events + * that produce LLM messages. The append-only log remains the source of truth. * * @module @deepseek-ai/dsh-session/surface */ import type { SessionEvent, SurfaceEvent, SurfaceEventType, SurfaceOp } from './types.ts' -/** - * The set of event type strings that are eligible for the surface sequence. - * Mirrors the {@link SurfaceEventType} union; kept as a runtime set so the - * type guard can check membership without a chain of string comparisons. - */ +/** Runtime counterpart of the message-producing event union. */ const SURFACE_EVENT_TYPES = new Set([ 'user/message', 'assistant/message', @@ -23,115 +17,144 @@ const SURFACE_EVENT_TYPES = new Set([ ]) /** - * Whether an event's `type` is surface-eligible (one of the five - * message-producing {@link SurfaceEventType} values). This is the TYPE check - * only — it does NOT require `surfaceOp` to be present. Use it to detect a - * surface-eligible event that is MISSING its mandatory marker (e.g. validating - * a seed/load log); use {@link isSurfaceEvent} to narrow to a fully-formed - * {@link SurfaceEvent} with `surfaceOp` present. - * @param type - the event type string to test. - * @returns true when the type is one of the five message-producing types. + * Whether an event type can join the model-visible surface. + * @param type - event type to test. + * @returns true for one of the five message-producing event types. */ export function isSurfaceEligibleType(type: string): boolean { return SURFACE_EVENT_TYPES.has(type) } /** - * Narrow a {@link SessionEvent} to {@link SurfaceEvent}: checks that the - * event's `type` is surface-eligible AND that `surfaceOp` is present. - * The narrowed type has mandatory {@link SurfaceOp}. - * @param event - the event to narrow. - * @returns true when the event is surface-eligible and carries its `surfaceOp` marker. + * Narrow an event to a surface-eligible event carrying its required marker. + * @param event - event to test. + * @returns true when both the type and marker identify a surface event. */ export function isSurfaceEvent(event: SessionEvent): event is SurfaceEvent { if (!SURFACE_EVENT_TYPES.has(event.type)) return false - // surfaceOp is optional on SessionEvent (even for surface-eligible types) - // but mandatory on SurfaceEvent — this check is the narrowing gate. - if ((event as SessionEvent).surfaceOp === undefined) return false - return true + return (event as SessionEvent).surfaceOp !== undefined +} + +/** One replacement operation observed while folding a session surface. */ +export interface SurfaceFoldReplacement { + /** Seq of the event that replaced the prior surface range. */ + seq: number + /** Declared inclusive start seq of the replaced surface range. */ + start: number + /** Declared inclusive end seq of the replaced surface range. */ + end: number + /** Actual surface entries removed by the operation, in surface order. */ + shadowedSeqs: number[] +} + +/** Complete result of replaying the surface operations in a session log. */ +export interface SurfaceFoldResult { + /** Current surface event sequences in model-visible order. */ + nodes: number[] + /** Replacement operations in event order. */ + replacements: SurfaceFoldReplacement[] +} + +/** Mutable state shared by complete and incremental folds. */ +interface SurfaceFoldState { + nodes: number[] + replaceGeneration: number +} + +/** Create one empty fold state. */ +function createFoldState(): SurfaceFoldState { + return { nodes: [], replaceGeneration: 0 } +} + +/** Apply one event and return replacement metadata when one occurred. */ +function applySurfaceEvent( + state: SurfaceFoldState, + event: SessionEvent, +): SurfaceFoldReplacement | undefined { + if (!isSurfaceEligibleType(event.type)) return + if (!isSurfaceEvent(event)) { + throw new Error(`surface event "${event.type}" (seq ${event.seq}) carries no surfaceOp marker`) + } + if (event.surfaceOp === 'append') { + state.nodes.push(event.seq) + return + } + + const shadowedSeqs = replaceSurface(state, event.seq, event.surfaceOp) + return { + seq: event.seq, + start: event.surfaceOp.start, + end: event.surfaceOp.end, + shadowedSeqs, + } +} + +/** Replace one inclusive surface range and return the removed sequences. */ +function replaceSurface( + state: SurfaceFoldState, + newSeq: number, + op: Extract, +): number[] { + const startIdx = state.nodes.indexOf(op.start) + if (startIdx === -1) { + throw new Error(`surface replace: start seq ${op.start} not found in surface`) + } + const endIdx = state.nodes.indexOf(op.end) + if (endIdx === -1) { + throw new Error(`surface replace: end seq ${op.end} not found in surface`) + } + if (startIdx > endIdx) { + throw new Error(`surface replace: start seq ${op.start} (index ${startIdx}) is after end seq ${op.end} (index ${endIdx})`) + } + + const shadowedSeqs = state.nodes.splice(startIdx, endIdx - startIdx + 1, newSeq) + state.replaceGeneration += 1 + return shadowedSeqs } /** - * Maintains a cached ordered list of surface event sequences, folded lazily from - * `surfaceOp` markers in the event log. Because the log is append-only, it - * processes only the delta since the last rebuild — new events are folded - * into the existing surface in O(new events) rather than rescanning the - * whole log. + * Replay a complete event log through the canonical surface fold. + * @param events - events in contiguous seq order. + * @returns detached current sequences and replacement history. + * @throws when a surface marker is missing or names an invalid range. */ -export class SurfaceManager { - /** Surface event sequences in head-to-tail order. Empty until first access. */ - private _nodes: number[] = [] - /** The last processed seq. -1 folds the seeded log on first access. */ - private _lastProcessedSeq = -1 +export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult { + const state = createFoldState() + const replacements: SurfaceFoldReplacement[] = [] + for (const event of events) { + const replacement = applySurfaceEvent(state, event) + if (replacement !== undefined) replacements.push(replacement) + } + return { nodes: [...state.nodes], replacements } +} - /** Rewrite generation — see {@link replaceGeneration}. */ - private _replaceGeneration = 0 +/** Incremental ordered surface view over an append-only session log. */ +export class SurfaceManager { + /** Shared transition state; replacement history is not retained. */ + private _state = createFoldState() + /** Last processed seq; -1 folds a seeded log on first access. */ + private _lastProcessedSeq = -1 constructor(private log: readonly SessionEvent[]) {} - /** - * The surface's rewrite generation, bumped by every folded `replace` op. - * A replace is the ONE operation that rewrites the - * surface non-monotonically, so an incremental consumer of {@link nodes} - * (the session's derived-message cache) compares this between visits — an - * unchanged generation guarantees every node it has not seen is a pure tail - * append; a changed one means its view must rebuild. Monotonic: it never - * moves backwards, so comparisons cannot be fooled by a re-fold. - */ + /** Monotonic count of folded positional replacements. */ get replaceGeneration(): number { if (this._lastProcessedSeq < this.log.length - 1) this._processDelta() - return this._replaceGeneration + return this._state.replaceGeneration } - /** Surface event sequences in head-to-tail order. */ + /** Surface event sequences in model-visible order. */ get nodes(): readonly number[] { if (this._lastProcessedSeq < this.log.length - 1) this._processDelta() - return this._nodes + return this._state.nodes } - /** - * Process events from `_lastProcessedSeq + 1` through the end of the log, - * folding new surface markers into the existing sequence list. - */ + /** Fold events appended since the previous access. */ private _processDelta(): void { for (let i = this._lastProcessedSeq + 1; i < this.log.length; i++) { - // Index is bounded by i < this.log.length — never undefined. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const event = this.log[i]! - // isSurfaceEvent checks event.type first (is it a surface-eligible type?) - // then checks that surfaceOp is present. Only after both pass do we treat - // it as a SurfaceEvent with mandatory surfaceOp. - if (!isSurfaceEvent(event)) continue - - if (event.surfaceOp === 'append') { - this._nodes.push(event.seq) - } else { - this._replace(event.seq, event.surfaceOp) - } + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded by the loop condition + applySurfaceEvent(this._state, this.log[i]!) } this._lastProcessedSeq = this.log.length - 1 } - - /** Apply a replace operation to the in-progress surface. */ - private _replace( - newSeq: number, - op: Extract, - ): void { - const startIdx = this._nodes.indexOf(op.start) - if (startIdx === -1) { - throw new Error(`surface replace: start seq ${op.start} not found in surface`) - } - const endIdx = this._nodes.indexOf(op.end) - if (endIdx === -1) { - throw new Error(`surface replace: end seq ${op.end} not found in surface`) - } - if (startIdx > endIdx) { - throw new Error(`surface replace: start seq ${op.start} (index ${startIdx}) is after end seq ${op.end} (index ${endIdx})`) - } - - // Remove shadowed nodes from `[startIdx, endIdx]` inclusive. - const count = endIdx - startIdx + 1 - this._nodes.splice(startIdx, count, newSeq) - this._replaceGeneration += 1 - } } diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index 2a658ff82a..5f09efe089 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it } from 'vitest' import type { SessionEvent, SurfaceEvent, SurfaceEventType } from '@deepseek-ai/dsh-session' -import { Session, SessionId, isSurfaceEligibleType, isSurfaceEvent } from '@deepseek-ai/dsh-session' +import { Session, SessionId, foldSurface, isSurfaceEligibleType, isSurfaceEvent } from '@deepseek-ai/dsh-session' import { CallId } from '@deepseek-ai/dsh-llm' /** Build a minimal session with turn boundaries and a single user message. */ @@ -14,6 +14,60 @@ function surfaceSession(): Session { } describe('SurfaceManager', () => { + it('shares ordered entries and nested replacement ranges with foldSurface', () => { + const s = new Session(SessionId('shared-fold')) + s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] }) + s.append('assistant/message', { turn: 1, step: 2, content: [{ type: 'text', text: 'summary 2' }] }, { surfaceOp: { op: 'replace', start: 2, end: 1 }, sourceEventSeqs: [2, 1] }) + + const folded = foldSurface(s.events) + expect(folded.nodes).toEqual(s.surface.nodes) + expect(folded.replacements).toEqual([ + { seq: 2, start: 0, end: 0, shadowedSeqs: [0] }, + { seq: 3, start: 2, end: 1, shadowedSeqs: [2, 1] }, + ]) + folded.nodes[0] = 99 + folded.replacements[0]!.shadowedSeqs.push(99) + expect(s.surface.nodes).toEqual([3]) + expect(foldSurface(s.events).nodes).toEqual([3]) + expect(foldSurface(s.events).replacements[0]!.shadowedSeqs).toEqual([0]) + }) + + it('does not retain fold-only replacement history in incremental state', () => { + const s = new Session(SessionId('incremental-state')) + s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'b' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 } }) + + expect(s.surface.nodes).toEqual([1]) + const manager = s.surface as unknown as { _state: object } + expect(Object.hasOwn(manager._state, 'replacements')).toBe(false) + expect(foldSurface(s.events).replacements).toEqual([ + { seq: 1, start: 0, end: 0, shadowedSeqs: [0] }, + ]) + }) + + it('foldSurface reports the same invalid replacement failures as the incremental manager', () => { + const s = new Session(SessionId('shared-fold-invalid')) + s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + s.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 42, end: 0 }, sourceEventSeqs: [0] }) + + expect(() => foldSurface(s.events)).toThrow(/start seq 42 not found/) + expect(() => s.surface.nodes).toThrow(/start seq 42 not found/) + }) + + it('foldSurface rejects a surface-eligible event without its mandatory marker', () => { + const malformed: SessionEvent = { + type: 'user/message', + seq: 0, + time: 1, + data: { content: [{ type: 'text', text: 'hidden' }], source: { kind: 'user' } }, + } + + expect(() => foldSurface([malformed])) + .toThrow(/surface event "user\/message" \(seq 0\) carries no surfaceOp marker/) + }) + it('folds an ordered sequence list from surfaceOp: append markers', () => { const s = surfaceSession() const nodes = s.surface.nodes diff --git a/packages/sandbox/README.md b/packages/sandbox/README.md index 9e104192d1..cb2c7b5747 100644 --- a/packages/sandbox/README.md +++ b/packages/sandbox/README.md @@ -9,4 +9,4 @@ The confinement half of the [capability-seam split](../../docs/rfc/implemented/a The seam confines SAME-WORLD subprocesses only (shared filesystem and kernel). Containers, microVMs, and remote executors are NOT backends here — they replace whole capability implementations (`ctx.bash`, `ctx.fs`) as environment-coherent groups; the boundary is recorded in [the sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). -Consumers today: [`bash/bash-sandbox`](../bash/bash-sandbox/) (wraps `['bash', '-c', command]`; see [examples/sandbox-acp-agent](../../examples/sandbox-acp-agent/) for the composed leaf). In-process tools (fs/web) cannot be confined by an OS wrapper — their sandbox semantics are policy at their own seams (the sandbox RFC's cross-family phase). +Consumers today: [`bash/bash-sandbox`](../bash/bash-sandbox/) (wraps `['bash', '-c', command]`; see [the acp-agent example's default composition](../../examples/acp-agent/) for the composed leaf). In-process tools (fs/web) cannot be confined by an OS wrapper — their sandbox semantics are policy at their own seams (the sandbox RFC's cross-family phase). diff --git a/packages/sandbox/sandbox-local/README.md b/packages/sandbox/sandbox-local/README.md index abf7511438..87f65048e4 100644 --- a/packages/sandbox/sandbox-local/README.md +++ b/packages/sandbox/sandbox-local/README.md @@ -15,4 +15,4 @@ Every rung has its keyless world-proof (`tests/bwrap.e2e.ts`, `tests/landlock.e2 name: '@deepseek-ai/dsh-sandbox-local' ``` -Consumers: [`@deepseek-ai/dsh-bash-sandbox`](../../bash/bash-sandbox/); see [`examples/sandbox-acp-agent`](../../../examples/sandbox-acp-agent/) for the runnable composition. +Consumers: [`@deepseek-ai/dsh-bash-sandbox`](../../bash/bash-sandbox/); see [the acp-agent example](../../../examples/acp-agent/) for the runnable default composition. diff --git a/packages/session-query/README.md b/packages/session-query/README.md new file mode 100644 index 0000000000..8b0c06a30c --- /dev/null +++ b/packages/session-query/README.md @@ -0,0 +1,9 @@ +# session-query/ — session retrieval capability family + +Trusted exact reads over live and durable session logs. Phase one contains one interface package that owns `ctx.sessionQuery`, logical-corpus precedence, surface classification, and bounded event reads. + +| Package | Role | ctx key | +|---|---|---| +| [`session-query/`](session-query/README.md) | Logical-corpus and exact-event read service | `ctx.sessionQuery` | + +The family is independent of compaction: it reads the canonical session log but does not participate in compaction policy or execution. Full-text search remains proposed as a phase-two SQLite package rather than a speculative provider seam in this interface package. diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md new file mode 100644 index 0000000000..55f9b32fcd --- /dev/null +++ b/packages/session-query/session-query/README.md @@ -0,0 +1,23 @@ +# @deepseek-ai/dsh-session-query + +Exact session-history retrieval through `ctx.sessionQuery`. The service presents live `ctx.sessions` and an optional, dynamically mounted `ctx.sessionPersistence` as one logical corpus. Matching ids produce one record: live events win, while `live` and `persisted` report both source availabilities. Conflicting immutable headers fail with `SESSION_QUERY_SOURCE_CONFLICT`. + +This is trusted context-wide infrastructure. It performs no caller authorization; a future model tool or UI must constrain which sessions its caller may inspect. + +## Reads + +- `listSessions()` reads current persistence metadata, merges live records with live precedence, and returns cloned records in deterministic newest-first order. +- `listEvents(sessionId)` loads the live-preferred raw log and classifies each event as `current`, `shadowed`, or `log-only` with the shared `dsh-session` surface fold. +- `readEvent(request)` returns a cloned header, the full target event, and a bounded raw-seq window. `before` and `after` default to zero and may not exceed `readWindowMax`. + +Persistence is optional and may mount or unmount dynamically. A cross-corpus list fails with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. A read targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory history unreadable. Persisted exact reads list before loading, and reject a metadata mismatch rather than combining inconsistent observations. + +`SessionQueryError.code` is a closed union: `SESSION_QUERY_EVENT_NOT_FOUND`, `SESSION_QUERY_INVALID_CONFIG`, `SESSION_QUERY_INVALID_SURFACE`, `SESSION_QUERY_INVALID_WINDOW`, `SESSION_QUERY_PERSISTENCE_FAILED`, `SESSION_QUERY_SESSION_NOT_FOUND`, and `SESSION_QUERY_SOURCE_CONFLICT`. + +## Configuration + +| Key | Default | Contract | +|---|---:|---| +| `readWindowMax` | `50` | Maximum `before` or `after` raw-event count. | + +This phase deliberately has no filters, lineage/provenance traversal, extraction registry, search-provider protocol, index synchronization, or model-facing tool. Full-text search belongs beside its first real implementation; the proposed SQLite package and its single transaction/reconciliation owner are described in the [phase-two RFC](../../../docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md). diff --git a/packages/session-query/session-query/package.json b/packages/session-query/session-query/package.json new file mode 100644 index 0000000000..9f78d4f1db --- /dev/null +++ b/packages/session-query/session-query/package.json @@ -0,0 +1,44 @@ +{ + "name": "@deepseek-ai/dsh-session-query", + "description": "Live-preferred exact session-history retrieval service (ctx.sessionQuery)", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-session-persistence": "^0.0.1", + "cordis": "^4.0.0-rc.6" + }, + "peerDependenciesMeta": { + "@deepseek-ai/dsh-session-persistence": { + "optional": true + } + }, + "dependencies": { + "schemastery": "^3.18.0" + }, + "devDependencies": { + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence": "workspace:^", + "cordis": "^4.0.0-rc.6" + } +} diff --git a/packages/session-query/session-query/src/config.ts b/packages/session-query/session-query/src/config.ts new file mode 100644 index 0000000000..2736f68cbd --- /dev/null +++ b/packages/session-query/session-query/src/config.ts @@ -0,0 +1,33 @@ +/** Public configuration and typed failures for session-query. */ + +import { HarnessError } from '@deepseek-ai/dsh-llm' + +/** Default maximum `before`/`after` raw-event window. */ +export const SESSION_QUERY_READ_WINDOW_MAX = 50 + +/** Configuration for exact session-query reads. */ +export interface Config { + /** Maximum accepted raw read context on either side. Defaults to 50. */ + readWindowMax?: number +} + +/** Stable machine-routable failure taxonomy for exact session reads. */ +export type SessionQueryErrorCode = + | 'SESSION_QUERY_EVENT_NOT_FOUND' + | 'SESSION_QUERY_INVALID_CONFIG' + | 'SESSION_QUERY_INVALID_SURFACE' + | 'SESSION_QUERY_INVALID_WINDOW' + | 'SESSION_QUERY_PERSISTENCE_FAILED' + | 'SESSION_QUERY_SESSION_NOT_FOUND' + | 'SESSION_QUERY_SOURCE_CONFLICT' + +/** Typed session-query failure whose `code` is one closed taxonomy member. */ +export class SessionQueryError extends HarnessError { + declare readonly code: SessionQueryErrorCode + + // The base stores the value; this signature narrows its open string code. + // eslint-disable-next-line @typescript-eslint/no-useless-constructor + constructor(message: string, code: SessionQueryErrorCode, options?: ErrorOptions) { + super(message, code, options) + } +} diff --git a/packages/session-query/session-query/src/corpus.ts b/packages/session-query/session-query/src/corpus.ts new file mode 100644 index 0000000000..ebc3d92577 --- /dev/null +++ b/packages/session-query/session-query/src/corpus.ts @@ -0,0 +1,136 @@ +/** Live/persisted logical-corpus resolution for session-query. */ + +import type { Context } from 'cordis' +import type { Session, SessionEvent, SessionHeader, SessionId } from '@deepseek-ai/dsh-session' +import type SessionPersistence from '@deepseek-ai/dsh-session-persistence' +import type { SessionRecord } from './types.ts' +import { SessionQueryError } from './config.ts' + +/** Detached source selected for one exact read. */ +export interface LogicalSession { + /** Cloned source header. */ + header: SessionHeader + /** Cloned raw event log. */ + events: SessionEvent[] +} + +/** Resolves a live-preferred corpus against the persistence service mounted now. */ +export class SessionCorpus { + private _persistence: SessionPersistence | undefined + + constructor(private readonly _ctx: Context) { + _ctx.effect(() => { + const fiber = _ctx.inject(['sessionPersistence'], (childCtx: Context) => { + const service = childCtx.sessionPersistence + this._persistence = service + childCtx.effect(() => () => { + /* v8 ignore next -- a stale optional-service disposer cannot clear a replacement */ + if (this._persistence === service) this._persistence = undefined + }, 'sessionQuery.persistenceBinding') + }) + return () => void fiber.dispose() + }, 'sessionQuery.optionalPersistence') + } + + /** + * List the complete logical corpus with live precedence and cloned headers. + * @returns records in deterministic newest-first order. + */ + async listSessions(): Promise { + const persistence = this._persistence + const persisted = persistence === undefined ? [] : await listPersisted(persistence) + const records = new Map() + for (const header of persisted) { + records.set(header.id, { header: structuredClone(header), live: false, persisted: true }) + } + for (const session of this._ctx.sessions.list()) { + const durable = records.get(session.id) + if (durable !== undefined) assertCompatibleHeaders(session.header, durable.header) + records.set(session.id, { + header: structuredClone(session.header), + live: true, + persisted: durable !== undefined, + }) + } + return [...records.values()].sort(compareSessions) + } + + /** + * Load one logical source, preferring a detached live snapshot. + * + * A known live target never consults persistence, so an optional backend's + * failure cannot make current in-memory history unreadable. + * @param sessionId - session to resolve. + * @returns detached live-preferred header and events. + */ + async load(sessionId: SessionId): Promise { + const live = this._ctx.sessions.get(sessionId) + if (live !== undefined) return snapshotLive(live) + const persistence = this._persistence + if (persistence === undefined) throw notFound(sessionId) + const listed = (await listPersisted(persistence)).find(header => header.id === sessionId) + if (listed === undefined) throw notFound(sessionId) + let loaded: Awaited> + try { + loaded = await persistence.load(sessionId) + } catch (error: unknown) { + throw new SessionQueryError( + `failed to load session "${sessionId}": ${errorMessage(error)}`, + 'SESSION_QUERY_PERSISTENCE_FAILED', + { cause: error }, + ) + } + assertCompatibleHeaders(loaded.meta, listed) + return { + header: structuredClone(loaded.meta), + events: loaded.events.map(event => structuredClone(event)), + } + } +} + +async function listPersisted(persistence: SessionPersistence): Promise { + try { + return await persistence.list() + } catch (error: unknown) { + throw new SessionQueryError( + `session persistence listing failed: ${errorMessage(error)}`, + 'SESSION_QUERY_PERSISTENCE_FAILED', + { cause: error }, + ) + } +} + +function snapshotLive(session: Session): LogicalSession { + return { + header: structuredClone(session.header), + events: session.events.map(event => structuredClone(event)), + } +} + +function assertCompatibleHeaders(a: SessionHeader, b: SessionHeader): void { + if ( + a.version !== b.version + || a.id !== b.id + || a.createdAt !== b.createdAt + || a.cwd !== b.cwd + || a.parentSession !== b.parentSession + || a.seedLength !== b.seedLength + ) { + throw new SessionQueryError( + `live and persisted headers conflict for session "${a.id}"`, + 'SESSION_QUERY_SOURCE_CONFLICT', + ) + } +} + +function compareSessions(a: SessionRecord, b: SessionRecord): number { + return b.header.createdAt - a.header.createdAt || a.header.id.localeCompare(b.header.id) +} + +function notFound(sessionId: SessionId): SessionQueryError { + return new SessionQueryError(`session "${sessionId}" not found`, 'SESSION_QUERY_SESSION_NOT_FOUND') +} + +function errorMessage(error: unknown): string { + return error instanceof Error ? error.message : 'unknown error' +} diff --git a/packages/session-query/session-query/src/index.ts b/packages/session-query/session-query/src/index.ts new file mode 100644 index 0000000000..cd219d9934 --- /dev/null +++ b/packages/session-query/session-query/src/index.ts @@ -0,0 +1,136 @@ +/** + * Exact session-history reads over live and optionally persisted logs. + * + * @module @deepseek-ai/dsh-session-query + */ + +import { Context, Service } from 'cordis' +import z from 'schemastery' +import { foldSurface } from '@deepseek-ai/dsh-session' +import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' +import type { + SessionEventReadRequest, + SessionEventRecord, + SessionEventWindow, + SessionRecord, +} from './types.ts' +import { + SESSION_QUERY_READ_WINDOW_MAX, + SessionQueryError, + type Config, +} from './config.ts' +import { SessionCorpus } from './corpus.ts' + +export type * from './types.ts' +export type { Config, SessionQueryErrorCode } from './config.ts' +export { SESSION_QUERY_READ_WINDOW_MAX, SessionQueryError } from './config.ts' + +declare module 'cordis' { + interface Context { + sessionQuery: SessionQueryService + } +} + +/** Live-preferred logical-corpus and exact-event read service. */ +export class SessionQueryService extends Service { + static inject = ['sessions'] + static Config: z = z.object({ + readWindowMax: z.number().step(1).min(0).default(SESSION_QUERY_READ_WINDOW_MAX), + }) + + private readonly _readWindowMax: number + private readonly _corpus: SessionCorpus + + constructor(ctx: Context, config: Config = {}) { + super(ctx, 'sessionQuery') + this._readWindowMax = config.readWindowMax ?? SESSION_QUERY_READ_WINDOW_MAX + if (!Number.isInteger(this._readWindowMax) || this._readWindowMax < 0) { + throw new SessionQueryError( + 'session-query: readWindowMax must be a non-negative integer', + 'SESSION_QUERY_INVALID_CONFIG', + ) + } + this._corpus = new SessionCorpus(ctx) + } + + /** + * List the complete logical corpus using live-preferred records. + * @returns deterministic newest-first cloned session records. + */ + listSessions(): Promise { + return this._corpus.listSessions() + } + + /** + * List lightweight raw-log event records for one logical session. + * @param sessionId - live-preferred session id to read. + * @returns event records in ascending seq order. + */ + async listEvents(sessionId: SessionId): Promise { + const loaded = await this._corpus.load(sessionId) + return eventRecords(sessionId, loaded.events) + } + + /** + * Read one full event plus a bounded raw-log context window. + * @param request - target session/seq and context sizes. + * @returns cloned target and neighboring events. + */ + async readEvent(request: SessionEventReadRequest): Promise { + const before = this._readWindow('before', request.before) + const after = this._readWindow('after', request.after) + const loaded = await this._corpus.load(request.sessionId) + const target = loaded.events[request.seq] + if (target === undefined || target.seq !== request.seq) { + throw new SessionQueryError( + `session "${request.sessionId}" has no event at seq ${request.seq}`, + 'SESSION_QUERY_EVENT_NOT_FOUND', + ) + } + const startSeq = Math.max(0, request.seq - before) + const endSeq = Math.min(loaded.events.length - 1, request.seq + after) + return { + session: loaded.header, + target, + events: loaded.events.slice(startSeq, endSeq + 1), + startSeq, + endSeq, + } + } + + private _readWindow(name: 'before' | 'after', value: number | undefined): number { + if (value === undefined) return 0 + if (!Number.isInteger(value) || value < 0 || value > this._readWindowMax) { + throw new SessionQueryError( + `${name} must be an integer between 0 and ${this._readWindowMax}`, + 'SESSION_QUERY_INVALID_WINDOW', + ) + } + return value + } +} + +function eventRecords(sessionId: SessionId, events: readonly SessionEvent[]): SessionEventRecord[] { + let folded: ReturnType + try { + folded = foldSurface(events) + } catch (error: unknown) { + throw new SessionQueryError( + /* v8 ignore next -- foldSurface throws Error instances */ + `invalid session surface: ${error instanceof Error ? error.message : 'unknown error'}`, + 'SESSION_QUERY_INVALID_SURFACE', + { cause: error }, + ) + } + const current = new Set(folded.nodes) + const shadowed = new Set(folded.replacements.flatMap(replacement => replacement.shadowedSeqs)) + return events.map(event => ({ + sessionId, + seq: event.seq, + type: event.type, + time: event.time, + surface: current.has(event.seq) ? 'current' : shadowed.has(event.seq) ? 'shadowed' : 'log-only', + })) +} + +export default SessionQueryService diff --git a/packages/session-query/session-query/src/types.ts b/packages/session-query/session-query/src/types.ts new file mode 100644 index 0000000000..5c49695dda --- /dev/null +++ b/packages/session-query/session-query/src/types.ts @@ -0,0 +1,60 @@ +/** + * Public records for exact reads over the live-preferred logical session corpus. + * + * @module @deepseek-ai/dsh-session-query/types + */ + +import type { SessionEvent, SessionEventType, SessionHeader, SessionId } from '@deepseek-ai/dsh-session' + +/** Whether an event is current model context, replaced context, or raw-log-only. */ +export type SessionEventSurface = 'current' | 'shadowed' | 'log-only' + +/** Lightweight identity and source availability for one logical session. */ +export interface SessionRecord { + /** Cloned session header selected from the live-preferred corpus. */ + header: SessionHeader + /** Whether the id currently exists in `ctx.sessions`. */ + live: boolean + /** Whether the active persistence backend currently materializes the id. */ + persisted: boolean +} + +/** Lightweight metadata for one event within a logical session. */ +export interface SessionEventRecord { + /** Session that owns the event. */ + sessionId: SessionId + /** Monotonic event seq within the session. */ + seq: number + /** Discriminant of the session event. */ + type: SessionEventType + /** Event timestamp in Unix epoch milliseconds. */ + time: number + /** Event placement in the folded session surface. */ + surface: SessionEventSurface +} + +/** Request for one event plus raw neighboring log context. */ +export interface SessionEventReadRequest { + /** Session that owns the target event. */ + sessionId: SessionId + /** Target event seq. */ + seq: number + /** Number of preceding raw events to include. */ + before?: number + /** Number of following raw events to include. */ + after?: number +} + +/** Full target event and a bounded raw-log window. */ +export interface SessionEventWindow { + /** Cloned header for the live-preferred source read. */ + session: SessionHeader + /** Full cloned target event. */ + target: SessionEvent + /** Full cloned events from `startSeq` through `endSeq`. */ + events: SessionEvent[] + /** First seq included in `events`. */ + startSeq: number + /** Last seq included in `events`. */ + endSeq: number +} diff --git a/packages/session-query/session-query/tests/session-query.spec.ts b/packages/session-query/session-query/tests/session-query.spec.ts new file mode 100644 index 0000000000..3b50feee45 --- /dev/null +++ b/packages/session-query/session-query/tests/session-query.spec.ts @@ -0,0 +1,270 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import SessionStore, { SESSION_FORMAT_VERSION, SessionId } from '@deepseek-ai/dsh-session' +import type { SessionEvent, SessionHeader, SessionId as SessionIdType } from '@deepseek-ai/dsh-session' +import SessionPersistence from '@deepseek-ai/dsh-session-persistence' +import SessionQueryService, { + type SessionQueryErrorCode, +} from '@deepseek-ai/dsh-session-query' + +function header(id: string, createdAt = 1, extra: Partial = {}): SessionHeader { + return { version: SESSION_FORMAT_VERSION, id: SessionId(id), createdAt, ...extra } +} + +function eventLog(text = 'hello'): SessionEvent[] { + return [{ + type: 'user/message', + seq: 0, + time: 10, + data: { content: [{ type: 'text', text }], source: { kind: 'user' } }, + surfaceOp: 'append', + }] +} + +class TestPersistence extends SessionPersistence { + static entries = new Map() + static listFailure: unknown + static loadFailure: unknown + static afterList: (() => void) | undefined + + static reset(entries: readonly { meta: SessionHeader; events: SessionEvent[] }[] = []): void { + this.entries = new Map(entries.map(entry => [entry.meta.id, structuredClone(entry)])) + this.listFailure = undefined + this.loadFailure = undefined + this.afterList = undefined + } + + create(meta: SessionHeader): Promise { + TestPersistence.entries.set(meta.id, { meta: structuredClone(meta), events: [] }) + return Promise.resolve() + } + + append(id: SessionIdType, events: readonly SessionEvent[]): Promise { + const entry = TestPersistence.entries.get(id) + if (entry === undefined) return Promise.reject(new Error('missing test session')) + entry.events.push(...structuredClone(events)) + return Promise.resolve() + } + + load(id: SessionIdType): Promise<{ meta: SessionHeader; events: SessionEvent[] }> { + if (TestPersistence.loadFailure !== undefined) return rejectUnknown(TestPersistence.loadFailure) + const entry = TestPersistence.entries.get(id) + if (entry === undefined) return Promise.reject(new Error('missing test session')) + return Promise.resolve(structuredClone(entry)) + } + + list(): Promise { + if (TestPersistence.listFailure !== undefined) return rejectUnknown(TestPersistence.listFailure) + const headers = [...TestPersistence.entries.values()].map(entry => structuredClone(entry.meta)) + TestPersistence.afterList?.() + return Promise.resolve(headers) + } +} + +async function liveContext(config: ConstructorParameters[1] = {}): Promise { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(SessionQueryService, config) + return ctx +} + +function expectCode(code: SessionQueryErrorCode): Error { + return expect.objectContaining({ code }) as Error +} + +function rejectUnknown(reason: unknown): Promise { + return new Promise((_resolve, reject) => { + // Exercise containment for an implementation that violates the Error rejection convention. + // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors + reject(reason) + }) +} + +describe('session-query exact reads', () => { + it('lists live sessions deterministically and returns detached headers', async () => { + const ctx = await liveContext() + const older = ctx.sessions.create(SessionId('older'), { meta: { createdAt: 1 } }) + ctx.sessions.create(SessionId('z'), { meta: { createdAt: 2 } }) + ctx.sessions.create(SessionId('a'), { meta: { createdAt: 2 } }) + + const records = await ctx.sessionQuery.listSessions() + expect(records.map(record => record.header.id)).toEqual([SessionId('a'), SessionId('z'), older.id]) + expect(records.every(record => record.live && !record.persisted)).toBe(true) + Object.assign(records[2]!.header, { createdAt: 99 }) + expect(older.header.createdAt).toBe(1) + }) + + it('classifies current, shadowed, and raw-log-only events through foldSurface', async () => { + const ctx = await liveContext() + const session = ctx.sessions.create(SessionId('surface')) + const first = session.append( + 'user/message', + { content: [{ type: 'text', text: 'first' }], source: { kind: 'user' } }, + { surfaceOp: 'append' }, + ) + session.append('assistant/chunk', { + turn: 1, + step: 1, + chunk: { type: 'text-delta', index: 0, text: 'draft' }, + }) + session.append( + 'assistant/message', + { turn: 1, step: 1, content: [{ type: 'text', text: 'replacement' }] }, + { surfaceOp: { op: 'replace', start: first.seq, end: first.seq } }, + ) + + expect((await ctx.sessionQuery.listEvents(session.id)).map(record => record.surface)) + .toEqual(['shadowed', 'log-only', 'current']) + }) + + it('returns a bounded detached raw-event window and validates the request', async () => { + const ctx = await liveContext({ readWindowMax: 1 }) + const session = ctx.sessions.create(SessionId('window'), { meta: { cwd: '/work' } }) + for (const text of ['one', 'two', 'three']) { + session.append( + 'user/message', + { content: [{ type: 'text', text }], source: { kind: 'user' } }, + { surfaceOp: 'append' }, + ) + } + + const result = await ctx.sessionQuery.readEvent({ sessionId: session.id, seq: 1, before: 1, after: 1 }) + expect([result.startSeq, result.endSeq, result.target.seq]).toEqual([0, 2, 1]) + expect(result.session).toEqual(session.header) + Object.assign(result.session, { createdAt: -1 }) + if (result.events[0]?.type !== 'user/message') throw new Error('expected user message') + result.events[0].data.content = [] + expect(session.header.createdAt).not.toBe(-1) + expect(session.events[0]?.type === 'user/message' && session.events[0].data.content).toHaveLength(1) + + await expect(ctx.sessionQuery.readEvent({ sessionId: session.id, seq: 9 })) + .rejects.toThrow(expectCode('SESSION_QUERY_EVENT_NOT_FOUND')) + for (const request of [ + { sessionId: session.id, seq: 0, before: -1 }, + { sessionId: session.id, seq: 0, before: 2 }, + { sessionId: session.id, seq: 0, after: 0.5 }, + ]) { + await expect(ctx.sessionQuery.readEvent(request)).rejects.toThrow(expectCode('SESSION_QUERY_INVALID_WINDOW')) + } + }) + + it('merges authoritative persistence with live precedence and detects conflicts', async () => { + const shared = header('shared', 3, { cwd: '/same' }) + const durable = header('durable', 2) + TestPersistence.reset([ + { meta: shared, events: eventLog('persisted') }, + { meta: durable, events: eventLog('durable') }, + ]) + const ctx = await liveContext() + const live = ctx.sessions.create(shared.id, { meta: { createdAt: 3, cwd: '/same' } }) + live.append( + 'user/message', + { content: [{ type: 'text', text: 'live' }], source: { kind: 'user' } }, + { surfaceOp: 'append' }, + ) + const persistence = await ctx.plugin(TestPersistence) + + expect((await ctx.sessionQuery.listSessions()).map(record => [record.header.id, record.live, record.persisted])) + .toEqual([[shared.id, true, true], [durable.id, false, true]]) + const liveRead = await ctx.sessionQuery.readEvent({ sessionId: shared.id, seq: 0 }) + expect(liveRead.target.type === 'user/message' && liveRead.target.data.content[0]) + .toMatchObject({ text: 'live' }) + await expect(ctx.sessionQuery.readEvent({ sessionId: durable.id, seq: 0 })) + .resolves.toMatchObject({ session: durable }) + + const sharedEntry = TestPersistence.entries.get(shared.id)! + sharedEntry.meta = { ...sharedEntry.meta, cwd: '/conflict' } + await expect(ctx.sessionQuery.listSessions()).rejects.toThrow(expectCode('SESSION_QUERY_SOURCE_CONFLICT')) + await persistence.dispose() + await expect(ctx.sessionQuery.listSessions()).resolves.toEqual([ + { header: shared, live: true, persisted: false }, + ]) + }) + + it('keeps known live reads independent from persistence health', async () => { + TestPersistence.reset() + const ctx = await liveContext() + const live = ctx.sessions.create(SessionId('live')) + live.append( + 'user/message', + { content: [{ type: 'text', text: 'available' }], source: { kind: 'user' } }, + { surfaceOp: 'append' }, + ) + await ctx.plugin(TestPersistence) + TestPersistence.listFailure = new Error('list unavailable') + TestPersistence.loadFailure = new Error('load unavailable') + + await expect(ctx.sessionQuery.listEvents(live.id)).resolves.toHaveLength(1) + await expect(ctx.sessionQuery.readEvent({ sessionId: live.id, seq: 0 })).resolves.toMatchObject({ target: { seq: 0 } }) + await expect(ctx.sessionQuery.listSessions()).rejects.toThrow(expectCode('SESSION_QUERY_PERSISTENCE_FAILED')) + await expect(ctx.sessionQuery.listEvents(SessionId('durable'))).rejects.toThrow(expectCode('SESSION_QUERY_PERSISTENCE_FAILED')) + }) + + it('reports absent sessions, persisted load failures, and persisted header conflicts', async () => { + const durable = header('durable') + TestPersistence.reset([{ meta: durable, events: eventLog() }]) + const ctx = await liveContext() + await expect(ctx.sessionQuery.listEvents(SessionId('absent'))) + .rejects.toThrow(expectCode('SESSION_QUERY_SESSION_NOT_FOUND')) + await ctx.plugin(TestPersistence) + await expect(ctx.sessionQuery.listEvents(SessionId('absent'))) + .rejects.toThrow(expectCode('SESSION_QUERY_SESSION_NOT_FOUND')) + + TestPersistence.loadFailure = 'raw failure' + await expect(ctx.sessionQuery.listEvents(durable.id)) + .rejects.toThrow(expectCode('SESSION_QUERY_PERSISTENCE_FAILED')) + TestPersistence.loadFailure = undefined + const durableEntry = TestPersistence.entries.get(durable.id)! + durableEntry.meta = { ...durableEntry.meta, cwd: '/changed-after-list' } + TestPersistence.afterList = () => { + const listedEntry = TestPersistence.entries.get(durable.id)! + listedEntry.meta = { ...listedEntry.meta, cwd: '/changed-during-read' } + } + await expect(ctx.sessionQuery.listEvents(durable.id)) + .rejects.toThrow(expectCode('SESSION_QUERY_SOURCE_CONFLICT')) + }) + + it('turns malformed surfaces and direct invalid config into typed errors', async () => { + const ctx = await liveContext() + const session = ctx.sessions.create(SessionId('bad-surface')) + session.append( + 'assistant/message', + { turn: 1, step: 1, content: [] }, + { surfaceOp: { op: 'replace', start: 9, end: 9 } }, + ) + await expect(ctx.sessionQuery.listEvents(session.id)) + .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_SURFACE')) + + const persisted = header('bad-persisted-surface') + TestPersistence.reset([{ + meta: persisted, + events: [{ + type: 'user/message', + seq: 0, + time: 1, + data: { content: [{ type: 'text', text: 'hidden' }], source: { kind: 'user' } }, + }], + }]) + const persistence = await ctx.plugin(TestPersistence) + await expect(ctx.sessionQuery.listEvents(persisted.id)) + .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_SURFACE')) + await persistence.dispose() + + const direct = new Context() + await direct.plugin(SessionStore) + expect(new SessionQueryService(direct)).toBeInstanceOf(SessionQueryService) + const invalid = new Context() + await invalid.plugin(SessionStore) + expect(() => new SessionQueryService(invalid, { readWindowMax: -1 })) + .toThrow(expectCode('SESSION_QUERY_INVALID_CONFIG')) + }) + + it('leaves the optional persistence dependency optional', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(SessionQueryService) + expect(ctx.sessionQuery).toBeInstanceOf(SessionQueryService) + await fiber.dispose() + expect(ctx.sessionQuery).toBeUndefined() + }) +}) diff --git a/packages/session-query/session-query/tsconfig.json b/packages/session-query/session-query/tsconfig.json new file mode 100644 index 0000000000..7153dae8bb --- /dev/null +++ b/packages/session-query/session-query/tsconfig.json @@ -0,0 +1,30 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../../vendor/schemastery" + }, + { + "path": "../../llm/llm" + }, + { + "path": "../../core/session" + }, + { + "path": "../../session-persistence/session-persistence" + } + ] +} diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index 03b1a856ed..99aeea8a53 100644 --- a/packages/subagent/subagent-acp/README.md +++ b/packages/subagent/subagent-acp/README.md @@ -35,7 +35,7 @@ ACP advertises no start-time capabilities because this process cannot enforce th config: providerName: acp command: node - args: ['--import', 'tsx', './packages/ui/acp-agent/src/bin.ts', './examples/acp-agent/cordis.yml'] + args: ['--import', 'tsx', './packages/ui/acp-agent/src/bin.ts', '--config', './examples/acp-agent/cordis.yml'] permission: reject env: DEEPSEEK_API_KEY: !!js process.env.DEEPSEEK_API_KEY diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.e2e.ts b/packages/subagent/subagent-acp/tests/subagent-acp.e2e.ts index 7814dfaca3..75e4febc3e 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.e2e.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.e2e.ts @@ -48,7 +48,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('ACP backend with-key e2e (drive await ctx.plugin(acp, { providerName: 'acp', command: process.execPath, - args: ['--import', tsxLoader, binScript, exampleConfig], + args: ['--import', tsxLoader, binScript, '--config', exampleConfig], cwd: workdir, permission: 'reject', // The child harness needs the key to reach the model; forward it @@ -57,6 +57,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('ACP backend with-key e2e (drive ...process.env.DEEPSEEK_API_KEY !== undefined ? { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY } : {}, ...process.env.DEEPSEEK_BASE_URL !== undefined ? { DEEPSEEK_BASE_URL: process.env.DEEPSEEK_BASE_URL } : {}, TSX_TSCONFIG_PATH: repoTsconfig, + DSH_PERMISSION_MODE: 'danger-full-access', }, }) @@ -83,7 +84,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('ACP backend with-key e2e (drive await ctx.plugin(acp, { providerName: 'acp', command: process.execPath, - args: ['--import', tsxLoader, binScript, exampleConfig], + args: ['--import', tsxLoader, binScript, '--config', exampleConfig], cwd: workdir, // The child needs to act (run bash), so approve its permission prompts. permission: 'allow', @@ -91,6 +92,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('ACP backend with-key e2e (drive ...process.env.DEEPSEEK_API_KEY !== undefined ? { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY } : {}, ...process.env.DEEPSEEK_BASE_URL !== undefined ? { DEEPSEEK_BASE_URL: process.env.DEEPSEEK_BASE_URL } : {}, TSX_TSCONFIG_PATH: repoTsconfig, + DSH_PERMISSION_MODE: 'danger-full-access', }, }) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 8d25a6f56c..3f9a21d596 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -79,7 +79,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const { agent, cwd } = options const child = spawn( process.execPath, - ['--import', tsxLoader, agent.binScript, options.configPath ?? agent.configPath], + ['--import', tsxLoader, agent.binScript, '--config', options.configPath ?? agent.configPath], { cwd, env: { diff --git a/packages/ui/README.md b/packages/ui/README.md index 4f5a6dc920..fdd0bc694b 100644 --- a/packages/ui/README.md +++ b/packages/ui/README.md @@ -6,6 +6,7 @@ Integrations that expose the agent to an external editor or client. These are ** |---|---|---| | `acp/` | Agent Client Protocol bridge: serves the agent to an ACP editor (Zed) over JSON-RPC stdio | (drives `ctx.agents`/`ctx.sessions`) | | `user-approval/` | One-shot user-approval mechanism, closed outcome vocabulary, audit events, and per-session approval policy | `ctx.approval` | +| `permission/` | User-facing permission presets (`workspace-write`/`danger-full-access`): one product-level select bundling the sandbox-mode and approval-policy knobs, written through to their session events | `ctx.permission` | | `user-interaction/` | Abstract human question/answer seam used by UI-backed confirmation tools | `ctx.userInteraction` | | `tool-ask-user/` | Model-facing `ask_user_question` tool over `ctx.userInteraction` | (registers on `ctx.tools`) | | `stdio-agent/` | Terminal stdio chat APP: the agent-core spine + console logger + readline UI + a pre-created `main` agent, with a `bin` | (composition + `bin`) | diff --git a/packages/ui/acp-agent/README.md b/packages/ui/acp-agent/README.md index d81c9cc091..a9622f1eeb 100644 --- a/packages/ui/acp-agent/README.md +++ b/packages/ui/acp-agent/README.md @@ -29,11 +29,11 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | -The leaf supplies the swappable backends: an LLM adapter (`llm-deepseek` for the real model, `llm-replay` for keyless snapshot replay) and a bash executor (`bash-local`). +The leaf supplies the swappable backends: an LLM adapter (`llm-deepseek` for the real model, `llm-replay` for keyless snapshot replay) and a bash executor. ## The bin -`dsh-acp-agent [path-to-cordis.yml]` (default `./cordis.yml`): +`dsh-acp-agent [--config path-to-cordis.yml]` (short form `-c`; default `./cordis.yml`): - loads a gitignored `.env` from the cwd — **skipped** in snapshot REPLAY so a stray key can never trigger a live call; - honors `DSH_SNAPSHOT=replay` by booting the sibling `cordis.snapshot.yml` (the keyless replay tree, `llm-replay` in place of `llm-deepseek`); diff --git a/packages/ui/acp-agent/src/bin.ts b/packages/ui/acp-agent/src/bin.ts index 1cbdff64d1..ddad5f0d21 100644 --- a/packages/ui/acp-agent/src/bin.ts +++ b/packages/ui/acp-agent/src/bin.ts @@ -22,11 +22,13 @@ * STDERR only (the app plugin loads no stdout logger, and the shared guards * write to stderr); a stray stdout write corrupts the protocol frames. * - * Usage: `dsh-acp-agent [path-to-cordis.yml]` (default `./cordis.yml`). + * Usage: `dsh-acp-agent [--config path-to-cordis.yml]` (default + * `./cordis.yml`). * * @module @deepseek-ai/dsh-acp-agent/bin */ +import { parseArgs } from 'node:util' import { boot, installFailLoud, loadEnv, resolveConfigPath } from '@deepseek-ai/dsh-app-boot' const NAME = 'dsh-acp-agent' @@ -37,7 +39,12 @@ const NAME = 'dsh-acp-agent' installFailLoud(NAME) const snapshotMode = process.env['DSH_SNAPSHOT'] if (snapshotMode !== 'replay') loadEnv(NAME) -const ctx = await boot(NAME, resolveConfigPath(process.argv[2] ?? './cordis.yml', snapshotMode)) +const { values } = parseArgs({ + args: process.argv.slice(2), + options: { config: { type: 'string', short: 'c' } }, + strict: true, +}) +const ctx = await boot(NAME, resolveConfigPath(values.config ?? './cordis.yml', snapshotMode)) if (snapshotMode !== undefined) { process.stdin.on('end', () => { void ctx.fiber.dispose().then(() => { process.exit(0) }) diff --git a/packages/ui/acp-agent/tests/built-bin.e2e.ts b/packages/ui/acp-agent/tests/built-bin.e2e.ts index de4612a40a..ac6965ff65 100644 --- a/packages/ui/acp-agent/tests/built-bin.e2e.ts +++ b/packages/ui/acp-agent/tests/built-bin.e2e.ts @@ -117,7 +117,7 @@ afterEach(async () => { describe.skipIf(!existsSync(acpBin))('dsh-acp-agent BUILT bin (node lib/bin.js, no tsx)', () => { it('boots the published bin and answers an initialize JSON-RPC frame on stdout', async () => { consumer = await makeConsumer() - child = spawn(process.execPath, ['--expose-internals', acpBin, './cordis.yml'], { + child = spawn(process.execPath, ['--expose-internals', acpBin, '--config', './cordis.yml'], { cwd: consumer, // Dummy key: initialize never reaches the model, so it is never used. env: { @@ -183,7 +183,7 @@ describe.skipIf(!existsSync(acpBin))('dsh-acp-agent BUILT bin (node lib/bin.js, /** Spawn the built acp bin against `configArg` and resolve with its exit code + stderr. */ function runBinExpectingExit(configArg: string, cwd: string = tmpdir()): Promise<{ code: number; stderr: string }> { return new Promise((resolve, reject) => { - const proc = spawn(process.execPath, ['--expose-internals', acpBin, configArg], { + const proc = spawn(process.execPath, ['--expose-internals', acpBin, '--config', configArg], { cwd, env: { ...process.env, diff --git a/packages/ui/acp-agent/tests/load-path.e2e.ts b/packages/ui/acp-agent/tests/load-path.e2e.ts index ec251a6e6b..963b440373 100644 --- a/packages/ui/acp-agent/tests/load-path.e2e.ts +++ b/packages/ui/acp-agent/tests/load-path.e2e.ts @@ -82,7 +82,7 @@ async function boot(): Promise { await writeFile(configPath, CORDIS_YML) const child = spawn( process.execPath, - ['--import', tsxLoader, binScript, configPath], + ['--import', tsxLoader, binScript, '--config', configPath], { cwd, env: { diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 403f8aac68..aa4e06d670 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -32,7 +32,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: | `session/update` | `session/event` | `agent_message_chunk` (text-delta), `agent_thought_chunk` (reasoning-delta), `user_message_chunk` (load replay), `tool_call`/`tool_call_update` (the render intent — a `card`-tagged `ToolCallView`/`ToolResultView` — owned by the TOOL via `presentCall`/`presentResult`, which the bridge switches on to build the wire shape — see Tool-call presentation) | | `elicitation/create` | `ctx.userInteraction.ask()` | maps `ask_user_question` questions to ACP form elicitations; option descriptions are shown in enum titles, `multi_select` uses ACP array enums, optionless requests use a required `custom` field, and a non-empty custom answer overrides any selected choice | | `session/request_permission` | `approval/request` listener | the bridge is the [`ctx.approval`](../user-approval/README.md) answerer for the agents it owns: an `ask` (a hook or `tools/pre-execute` plugin) becomes an editor prompt attached to the streamed tool call, offering one-shot `allow_once`/`reject_once` options only; a foreign or call-less request delegates down the answerer chain (fail-closed `unavailable` default). See "Permission prompts" | -| `session/set_config_option` | `setSandboxMode` / `setApprovalPolicy` | per-session knob switching over [session config options](https://agentclientprotocol.com/protocol/session-config-options) — see "Session config options" | +| `session/set_config_option` | `ctx.permission.set()` | per-session permission-preset switching over [session config options](https://agentclientprotocol.com/protocol/session-config-options) — see "Session config options" | ## Multi-session @@ -40,7 +40,7 @@ The bridge multiplexes N sessions over one connection. Live sessions are held in ## Session config options -The bridge advertises one independent `select` per composable knob in the `session/new`/`session/load` responses — `sandbox-mode` (`read-only`/`workspace-write`/`danger-full-access`, category `mode`) iff the mounted executor confines (`ctx.get('bash')?.sandboxMode` defined), `approval-policy` (`ask`/`never`) iff the approval seam is composed — with each session's `currentValue` folded from its OWN log (`effectiveSandboxMode`/`effectiveApprovalPolicy` ?? the composition default), so `session/load` reports a resumed session's overrides with no catch-up machinery. `session/set_config_option` validates the value against the same closed vocabulary, routes to the domain's write path (`setSandboxMode`/`setApprovalPolicy` — ONE log-only event on that session's log), and returns the complete refreshed state per the spec. Anchoring honors turn-enclosure: a switch while a turn is open appends immediately (openness read from the LOG — `agent.status` stays `running` between queued turns); an idle switch is held on the session record and anchored at the next turn's `agent/prompt-submit` (inside the turn, before anything assembles, last write per knob — an idle flip-flop anchors as one event), because appending from inside a `session/event` listener would reorder events for later-registered peers. Until anchored the switch lives in bridge memory only: responses overlay it truthfully, and a crash before the next turn reverts it — `session/load` then reports the fold's truth. Design: [the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md); protocol matrix: [acp-feature-support.md](acp-feature-support.md) § 6. +When `ctx.permission` is composed, the bridge advertises one `permission` select (category `mode`) in `session/new` and `session/load`; its options come from the deployment's preset table and its current value is `PermissionService.current(session.events)`, including the derived, switch-away-only `custom` state when the effective knobs match no preset. `session/set_config_option` accepts only advertised preset names, calls `PermissionService.set()` to write the preset through to the sandbox-mode and approval-policy events, and returns the complete refreshed state. A switch during an open turn appends immediately; an idle switch stays on the session record and anchors at the next turn's `agent/prompt-submit`, inside the turn and before request assembly. Until that anchor, responses overlay the pending value and a crash reverts to the durable fold. Design: [the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md); preset contract: [`dsh-permission`](../permission/README.md); protocol matrix: [acp-feature-support.md](acp-feature-support.md) § 6. Background-task isolation rides on `dsh-tool-bash`: bash task ids are global and predictable, so each task carries an opaque owner token — the owning agent's `session.header.id` — stored on the task inside the executor (`dsh-bash`'s `ownerOf(id)` seam). `bash_output`/`bash_kill` reject a task whose token differs from the caller's session token, so one session's agent can't read or kill another's task. Ownership is by session TOKEN, not `Agent` object identity — a different `Agent` object on the same session may access the task — and because the token lives on the executor's task it survives a `tool-bash` HMR reload. diff --git a/packages/ui/acp/acp-feature-support.md b/packages/ui/acp/acp-feature-support.md index be14fe6237..36ed963b14 100644 --- a/packages/ui/acp/acp-feature-support.md +++ b/packages/ui/acp/acp-feature-support.md @@ -10,7 +10,7 @@ Legend: ✅ supported · ⚠️ partial / fallback · ❌ not yet · — n/a. Th ## At a glance -The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), resumable session replay, one-shot permission prompts, and per-session sandbox/approval config options. The largest **unbuilt** areas are **MCP passthrough**, runtime model selection, **slash commands**, and **agent plans**, plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary). +The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), resumable session replay, one-shot permission prompts, and per-session permission presets. The largest **unbuilt** areas are **MCP passthrough**, runtime model selection, **slash commands**, and **agent plans**, plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary). ## 1. Agent methods (client → agent) @@ -25,8 +25,8 @@ The bridge implements the **core prompt-turn loop** for N concurrent sessions: i | `session/close` | S | ❌ | ✅ | ✅ | No `session/close` handler — the SDK dispatch returns `method_not_found`. The bridge tears sessions down on client disconnect / Cordis disposal (cross-cutting, see [§8](#8-cross-cutting)), but that is not the on-demand per-session method. | | `session/prompt` | S | ✅ | ✅ | ✅ | Maps to `agent.send`; one in-flight prompt per session; settles on the owning turn's end. | | `session/cancel` | S | ✅ | ✅ | ✅ | Queue-aware `agent.cancel`; settles the in-flight prompt `cancelled`, scoped to the one session. | -| `session/set_mode` | S | ❌ | ✅ | ✅ | Session modes deliberately skipped: config options are the spec's replacement (modes are slated for removal in ACP v2), and one mode list cannot carry the two orthogonal knobs (see [§6](#6-session-modes--config-options--models)). | -| `session/set_config_option` | S | ✅ | ✅ | ✅ | Two capability-gated selects — `sandbox-mode` (confining executor mounted) and `approval-policy` (approval seam composed); values validated against the domain vocabularies, one log-only event per switch on the session's own log, complete refreshed state in the response ([sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). | +| `session/set_mode` | S | ❌ | ✅ | ✅ | Session modes deliberately skipped: config options are the spec's replacement and modes are slated for removal in ACP v2 (see [§6](#6-session-modes--config-options--models)). | +| `session/set_config_option` | S | ✅ | ✅ | ✅ | One `permission` select when `ctx.permission` is composed; values come from the deployment preset table, a switch writes its preset event through to both knob events, and the response carries the complete refreshed state ([sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). | | model selection | S | ❌ | ✅ | ✅ | No distinct stable `session/set_model` — model is the `model`-category `session/set_config_option`. The bridge fixes the model per-bridge via config; no runtime switch. Codex still uses the legacy `unstable_setSessionModel` ext method. | | `session/list` | S | ❌ | ✅ | ✅ | Gated by `sessionCapabilities.list`. The harness HAS `sessionPersistence.list()` (used internally for load-cwd validation) but does not expose it over ACP. | | `session/delete` | S | ❌ | ✅ | ✅ | Gated by `sessionCapabilities.delete`. | @@ -111,7 +111,7 @@ Tool-call presentation is **owned by each tool** (`presentCall` / `presentResult ## 6. Session modes / config options / models -Config options ✅ (the [sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): the bridge advertises one independent `select` per composable knob — `sandbox-mode` iff the mounted executor confines, `approval-policy` iff the approval seam is composed — with per-session current values folded from each session's own log, and honors `session/set_config_option` end to end (idle switches anchor at the next turn under the turn-enclosure contract). Session MODES stay deliberately unmodeled: config options are the spec's replacement (modes are slated for removal in ACP v2), and one mode list cannot carry two orthogonal knobs. Runtime model selection is still not modeled — the harness fixes the model per-bridge via `AcpConfig.model` (both reference adapters ship a model selector). +Config options ✅ (the [sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): when `ctx.permission` is composed, the bridge advertises one `permission` select whose values come from the deployment preset table and whose current value derives from the session log; `session/set_config_option` switches the preset end to end, with idle switches anchoring at the next turn under the turn-enclosure contract. Session modes stay deliberately unmodeled because config options replace them in ACP v2. Runtime model selection is still not modeled — the harness fixes the model per bridge via `AcpConfig.model` (both reference adapters ship a model selector). ## 7. Content blocks diff --git a/packages/ui/acp/package.json b/packages/ui/acp/package.json index a916722c52..b0b038760b 100644 --- a/packages/ui/acp/package.json +++ b/packages/ui/acp/package.json @@ -28,36 +28,38 @@ }, "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", - "@deepseek-ai/dsh-user-approval": "^0.0.1", "@deepseek-ai/dsh-bash": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-permission": "^0.0.1", "@deepseek-ai/dsh-sandbox": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-session-persistence": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", + "@deepseek-ai/dsh-user-approval": "^0.0.1", "@deepseek-ai/dsh-user-interaction": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", - "@deepseek-ai/dsh-user-approval": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", "@deepseek-ai/dsh-fs-policy": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-permission": "workspace:^", "@deepseek-ai/dsh-sandbox": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", + "@deepseek-ai/dsh-tool-ask-user": "workspace:^", "@deepseek-ai/dsh-tool-bash": "workspace:^", "@deepseek-ai/dsh-tool-fs": "workspace:^", "@deepseek-ai/dsh-tool-todo": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", - "@deepseek-ai/dsh-tool-ask-user": "workspace:^", + "@deepseek-ai/dsh-user-approval": "workspace:^", "@deepseek-ai/dsh-user-interaction": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 7c97ad715c..7566d992be 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -72,10 +72,8 @@ import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { assertNever, CallId } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' -import { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-bash' -import { APPROVAL_POLICIES, effectiveApprovalPolicy, setApprovalPolicy } from '@deepseek-ai/dsh-user-approval' -import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' -import type { ApprovalPolicy } from '@deepseek-ai/dsh-user-approval' +// Side-effect type import: resolves `ctx.get('permission')` to the service. +import type {} from '@deepseek-ai/dsh-permission' import type { SessionEvent, TodoItem, TurnEndReason } from '@deepseek-ai/dsh-session' import type { ToolCallView, ToolRegistry, ToolResultView, TerminalResultView } from '@deepseek-ai/dsh-tools' // Side-effect type import: declaration-merges `ctx.sessionPersistence` onto @@ -323,7 +321,7 @@ interface SessionRecord { * overlay it truthfully, and a restart before the next turn reverts it — * which `session/load` then reports honestly from the log's fold. */ - pendingSwitches: { sandboxMode?: SandboxMode; approvalPolicy?: ApprovalPolicy } + pendingSwitches: { preset?: string } } /** @@ -544,46 +542,37 @@ export function apply(ctx: Context, config: AcpConfig): void { // --- The ACP Agent method surface ----------------------------------------- /** - * The session config options this composition can honor, with current - * values folded from the AGENT'S OWN session log (`effectiveSandboxMode` / - * `effectiveApprovalPolicy` — the log is the per-session store, so a - * `session/load` reports a resumed session's overrides with no catch-up - * machinery), overlaid with the record's not-yet-anchored pending switches - * (see {@link SessionRecord.pendingSwitches}). Capability-gated like every - * advertised lever: the sandbox option exists only when the mounted - * executor confines (`ctx.get('bash')?.sandboxMode` defined), the approval - * option only when the approval seam is composed — both read + * The session config options this composition can honor: ONE `Mode` + * select over the composed preset table (`ctx.permission` — the product + * layer bundling the sandbox-mode and approval-policy knobs), its current + * value folded from the AGENT'S OWN session log (the log is the + * per-session store, so a `session/load` reports a resumed session's + * preset with no catch-up machinery), overlaid with the record's + * not-yet-anchored pending switch (see + * {@link SessionRecord.pendingSwitches}). Capability-gated like every + * advertised lever: no preset service composed, no options — read * opportunistically so this bridge keeps working in compositions without - * them. + * it. */ const configOptionsFor = (agent: Agent, pending: SessionRecord['pendingSwitches'] = {}): SessionConfigOption[] => { - const options: SessionConfigOption[] = [] - const defaultMode = ctx.get('bash')?.sandboxMode - if (defaultMode !== undefined) { - options.push({ - id: 'sandbox-mode', - name: 'Sandbox', - description: 'The file sandbox mode bash commands in this session run under.', - category: 'mode', - type: 'select', - currentValue: pending.sandboxMode ?? effectiveSandboxMode(agent.session.events) ?? defaultMode, - options: SANDBOX_MODES.map(mode => ({ value: mode, name: mode })), - }) - } - const approval = ctx.get('approval') - if (approval !== undefined) { - options.push({ - id: 'approval-policy', - name: 'Approvals', - description: 'ask: permission prompts reach you; never: they are rejected automatically.', - type: 'select', - // `?? 'ask'` also shields against a provided stand-in whose config - // never went through the plugin schema (tests do this). - currentValue: pending.approvalPolicy ?? effectiveApprovalPolicy(agent.session.events) ?? approval.config.policy ?? 'ask', - options: APPROVAL_POLICIES.map(policy => ({ value: policy, name: policy })), - }) - } - return options + const presets = ctx.get('permission') + if (presets === undefined) return [] + const currentValue = pending.preset ?? presets.current(agent.session.events) + return [{ + id: 'permission', + name: 'Permissions', + description: 'The session permission preset: each choice bundles a sandbox mode and an approval policy.', + category: 'mode', + type: 'select', + currentValue, + options: [ + ...presets.names.map((name: string) => presets.optionOf(name)), + // The derived not-a-preset state: visible exactly while it IS the + // current value (a knob state outside the table), switchable FROM, + // never a target — set() below rejects it like any unknown name. + ...currentValue === 'custom' ? [presets.optionOf('custom')] : [], + ], + }] } /** @@ -613,15 +602,12 @@ export function apply(ctx: Context, config: AcpConfig): void { const flushPendingSwitches = (rec: SessionRecord): void => { const pending = rec.pendingSwitches rec.pendingSwitches = {} - const events = rec.agent.session.events - if (pending.sandboxMode !== undefined - && pending.sandboxMode !== (effectiveSandboxMode(events) ?? ctx.get('bash')?.sandboxMode)) { - setSandboxMode(rec.agent.session, pending.sandboxMode) - } - if (pending.approvalPolicy !== undefined - && pending.approvalPolicy !== (effectiveApprovalPolicy(events) ?? ctx.get('approval')?.config.policy ?? 'ask')) { - setApprovalPolicy(rec.agent.session, pending.approvalPolicy) - } + if (pending.preset === undefined) return + const presets = ctx.get('permission') + /* v8 ignore next -- a pending preset exists only if the service answered the + switch; it cannot unmount between that and the next turn in any composition. */ + if (presets === undefined) return + presets.set(rec.agent.session, pending.preset) } // Idle-accepted switches anchor at the next turn's prompt-submit: the turn @@ -856,7 +842,7 @@ export function apply(ctx: Context, config: AcpConfig): void { setSessionConfigOption(params: SetSessionConfigOptionRequest): Promise { assertOpen() const rec = requireSession(SessionId(params.sessionId)) - // Both advertised options are selects, so the boolean-shaped variant of + // The advertised option is a select, so the boolean-shaped variant of // the request is a protocol misuse regardless of configId. if (typeof params.value !== 'string') { throw invalidParams(`config option ${params.configId} is a select; boolean values are not accepted`) @@ -873,32 +859,22 @@ export function apply(ctx: Context, config: AcpConfig): void { // advertised; an id this composition never advertised (or an unknown // one) rejects. switch (params.configId) { - case 'sandbox-mode': { - const defaultMode = ctx.get('bash')?.sandboxMode - if (defaultMode === undefined || !SANDBOX_MODES.includes(params.value as SandboxMode)) { - throw invalidParams(`unknown sandbox-mode value ${JSON.stringify(params.value)}`) + case 'permission': { + const presets = ctx.get('permission') + if (presets === undefined) { + throw invalidParams(`unknown permission value ${JSON.stringify(params.value)}`) } - const value = params.value as SandboxMode // A no-op switch (the value the session already shows — pending, - // else fold, else default) is acknowledged without recording - // anything: clients that re-push current selections on session - // start must not mint override events out of thin air. - const current = rec.pendingSwitches.sandboxMode ?? effectiveSandboxMode(rec.agent.session.events) ?? defaultMode - if (value === current) break - if (isTurnOpen(rec.agent)) setSandboxMode(rec.agent.session, value) - else rec.pendingSwitches.sandboxMode = value - break - } - case 'approval-policy': { - const approval = ctx.get('approval') - if (approval === undefined || !APPROVAL_POLICIES.includes(params.value as ApprovalPolicy)) { - throw invalidParams(`unknown approval-policy value ${JSON.stringify(params.value)}`) + // else derived) is acknowledged FIRST and records nothing: + // clients re-push current selections on session start, and the + // derived 'custom' current is only ever valid as such an echo. + const current = rec.pendingSwitches.preset ?? presets.current(rec.agent.session.events) + if (params.value === current) break + if (!presets.names.includes(params.value)) { + throw invalidParams(`unknown permission value ${JSON.stringify(params.value)}`) } - const value = params.value as ApprovalPolicy - const current = rec.pendingSwitches.approvalPolicy ?? effectiveApprovalPolicy(rec.agent.session.events) ?? approval.config.policy ?? 'ask' - if (value === current) break - if (isTurnOpen(rec.agent)) setApprovalPolicy(rec.agent.session, value) - else rec.pendingSwitches.approvalPolicy = value + if (isTurnOpen(rec.agent)) presets.set(rec.agent.session, params.value) + else rec.pendingSwitches.preset = params.value break } default: diff --git a/packages/ui/acp/tests/config-options.spec.ts b/packages/ui/acp/tests/config-options.spec.ts index 1202e44bd3..fb39b2a0de 100644 --- a/packages/ui/acp/tests/config-options.spec.ts +++ b/packages/ui/acp/tests/config-options.spec.ts @@ -1,10 +1,10 @@ /** - * Session config options over the bridge: the two per-session knobs - * (`sandbox-mode`, `approval-policy`) advertised from composition capability, - * their current values folded from each session's own log, switching via - * `session/set_config_option` (one log-only event per switch — the log is the - * store), and a resumed session reporting its overrides back on - * `session/load` with no catch-up machinery. + * Session config options over the bridge: ONE user-facing `Permissions` + * select (`ctx.permission`'s preset table — each choice bundles a sandbox + * mode and an approval policy), its current value folded from each session's + * own log, switching via `session/set_config_option` (the preset event plus + * its knob write-throughs — the log is the store), and a resumed session + * reporting its preset back on `session/load` with no catch-up machinery. */ import { afterEach, beforeEach, describe, expect, it } from 'vitest' @@ -14,50 +14,37 @@ import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import * as Invariants from '@deepseek-ai/dsh-invariants' import ApprovalService from '@deepseek-ai/dsh-user-approval' -import type { ApprovalPolicy } from '@deepseek-ai/dsh-user-approval' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' +import PermissionService from '@deepseek-ai/dsh-permission' import { makeBridgeHarness, textResponse, type BridgeHarness } from './harness.ts' /** * The REAL local executor reporting a confining default — `sandboxMode` is * the documented capability override point (`dsh-bash-sandbox` overrides it * the same way), so the bridge sees exactly what a sandboxing composition - * advertises without this suite dragging in a kernel sandbox stack. + * advertises without this suite dragging in a kernel sandbox stack. It + * reports `workspace-write`: the shipped preset's bundle, which + * the permission service validates the composition defaults against. */ class SandboxedLocalExecutor extends LocalBashExecutor { override get sandboxMode(): SandboxMode { - return 'read-only' + return 'workspace-write' } } -/** The exact option payloads the bridge advertises (pinned verbatim). */ -function sandboxOption(currentValue: SandboxMode): object { +/** The exact option payload the bridge advertises (pinned verbatim). */ +function permissionOption(currentValue: string): object { return { - id: 'sandbox-mode', - name: 'Sandbox', - description: 'The file sandbox mode bash commands in this session run under.', + id: 'permission', + name: 'Permissions', + description: 'The session permission preset: each choice bundles a sandbox mode and an approval policy.', category: 'mode', type: 'select', currentValue, options: [ - { value: 'read-only', name: 'read-only' }, - { value: 'workspace-write', name: 'workspace-write' }, - { value: 'danger-full-access', name: 'danger-full-access' }, - ], - } -} - -function approvalOption(currentValue: ApprovalPolicy): object { - return { - id: 'approval-policy', - name: 'Approvals', - description: 'ask: permission prompts reach you; never: they are rejected automatically.', - type: 'select', - currentValue, - options: [ - { value: 'ask', name: 'ask' }, - { value: 'never', name: 'never' }, + { value: 'workspace-write', name: 'workspace-write', description: 'Write inside the workspace; anything wider asks for your approval.' }, + { value: 'danger-full-access', name: 'danger-full-access', description: 'Full file access, no approval prompts.' }, ], } } @@ -75,144 +62,113 @@ describe('acp bridge — session config options', () => { await rm(storageDir, { recursive: true, force: true }) }) - /** A harness whose composition can honor both knobs (sandboxed executor + approval seam). */ - async function bothKnobs(options: { policy?: ApprovalPolicy; script?: NonNullable[0]>['script'] } = {}): Promise { + /** A harness composing the full preset stack (confining executor + approval seam + permission presets). */ + async function presetStack(options: { script?: NonNullable[0]>['script'] } = {}): Promise { const harness = await makeBridgeHarness({ storageDir, ...options.script !== undefined ? { script: options.script } : {} }) // The dev invariants police turn-enclosure: an idle switch that appended // outside a turn would throw right here in the suite, not in production. await harness.ctx.plugin(Invariants) await harness.ctx.plugin(SandboxedLocalExecutor, { timeoutMs: 10_000 }) - await harness.ctx.plugin(ApprovalService, options.policy !== undefined ? { policy: options.policy } : {}) + await harness.ctx.plugin(ApprovalService) + await harness.ctx.plugin(PermissionService) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) return harness } - it('advertises no configOptions in a composition with neither knob', async () => { + it('advertises no configOptions without the permission service — even with both knobs composed', async () => { h = await makeBridgeHarness({ storageDir }) + await h.ctx.plugin(SandboxedLocalExecutor, { timeoutMs: 10_000 }) + await h.ctx.plugin(ApprovalService) await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) expect(res.configOptions).toBeUndefined() }) - it('a non-confining executor advertises no sandbox option (nothing would honor it)', async () => { - h = await makeBridgeHarness({ storageDir, withBash: true }) - await h.ctx.plugin(ApprovalService) - await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + it('advertises the Permissions select with the default preset current', async () => { + h = await presetStack() const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toEqual([approvalOption('ask')]) - }) - - it('advertises both knobs with capability-derived currents (config default included)', async () => { - h = await bothKnobs({ policy: 'never' }) - const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toEqual([sandboxOption('read-only'), approvalOption('never')]) + expect(res.configOptions).toEqual([permissionOption('workspace-write')]) }) it('an idle switch is pending (overlaid, not yet logged), then anchors INSIDE the next turn', async () => { - h = await bothKnobs({ script: [textResponse('ok')] }) + h = await presetStack({ script: [textResponse('ok')] }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const afterSandbox = await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'workspace-write' }) - expect(afterSandbox.configOptions).toEqual([sandboxOption('workspace-write'), approvalOption('ask')]) - const afterApproval = await h.client.setSessionConfigOption({ sessionId, configId: 'approval-policy', value: 'never' }) - expect(afterApproval.configOptions).toEqual([sandboxOption('workspace-write'), approvalOption('never')]) + const after = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) + expect(after.configOptions).toEqual([permissionOption('danger-full-access')]) - // Idle: nothing in the log yet — turn-enclosure forbids a bare append - // (the dev invariants in this suite would throw), so the switch lives on - // the record until a turn opens. + // Idle: nothing in the log yet — turn-enclosure forbids a bare append. const session = h.ctx.agents.list()[0]?.session - expect(session?.events.some(e => e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) + expect(session?.events.some(e => e.type === 'permission/preset' || e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) - // The next turn anchors both switches inside itself, one event per knob. await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = session?.events ?? [] - expect(events.filter(e => e.type === 'bash/sandbox-mode').map(e => e.data)).toEqual([{ mode: 'workspace-write' }]) + expect(events.filter(e => e.type === 'permission/preset').map(e => e.data)).toEqual([{ preset: 'danger-full-access' }]) + expect(events.filter(e => e.type === 'bash/sandbox-mode').map(e => e.data)).toEqual([{ mode: 'danger-full-access' }]) expect(events.filter(e => e.type === 'approval/policy').map(e => e.data)).toEqual([{ policy: 'never' }]) const turnStart = events.findIndex(e => e.type === 'turn/start') - const anchored = events.findIndex(e => e.type === 'bash/sandbox-mode') + const anchored = events.findIndex(e => e.type === 'permission/preset') expect(turnStart).toBeGreaterThanOrEqual(0) expect(anchored).toBeGreaterThan(turnStart) }) - it('an idle flip-flop anchors as ONE event (last write per knob wins)', async () => { - h = await bothKnobs({ script: [textResponse('ok')] }) + it('an idle flip-flop anchors as ONE switch (last write wins)', async () => { + h = await presetStack({ script: [textResponse('ok')] }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'workspace-write' }) - await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'danger-full-access' }) + await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) + const again = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) + expect(again.configOptions).toEqual([permissionOption('danger-full-access')]) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] - expect(events.filter(e => e.type === 'bash/sandbox-mode').map(e => e.data)).toEqual([{ mode: 'danger-full-access' }]) - // Idle again AFTER a completed turn (the log now ends in turn/end): a new - // switch pends rather than appending outside the closed turn. - const again = await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'read-only' }) - expect(again.configOptions?.find(option => option.id === 'sandbox-mode')).toMatchObject({ currentValue: 'read-only' }) - expect(events.filter(e => e.type === 'bash/sandbox-mode')).toHaveLength(1) - }) - - it('a no-op switch (the value already shown) records nothing and keeps a live pending', async () => { - h = await bothKnobs({ script: [textResponse('ok')] }) - const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - // Re-pushing the composition default (what clients that echo current - // selections on session start do) must not mint an override event. - const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'approval-policy', value: 'ask' }) - expect(echo.configOptions?.find(option => option.id === 'approval-policy')).toMatchObject({ currentValue: 'ask' }) - // Re-sending a PENDING value keeps the pending switch alive (it is what - // the session shows), rather than cancelling it. - await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'workspace-write' }) - const repeat = await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'workspace-write' }) - expect(repeat.configOptions?.find(option => option.id === 'sandbox-mode')).toMatchObject({ currentValue: 'workspace-write' }) - await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) - const events = h.ctx.agents.list()[0]?.session.events ?? [] - expect(events.filter(e => e.type === 'approval/policy')).toHaveLength(0) - expect(events.filter(e => e.type === 'bash/sandbox-mode').map(e => e.data)).toEqual([{ mode: 'workspace-write' }]) + expect(events.filter(e => e.type === 'permission/preset')).toHaveLength(1) + // Between turns (a closed turn in the log) a switch still pends — the + // enclosure fold walks past the turn/end — and anchors with the NEXT turn. + await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'workspace-write' }) + expect(h.ctx.agents.list()[0]?.session.events.filter(e => e.type === 'permission/preset')).toHaveLength(1) }) it('a net-zero idle flip-flop anchors NOTHING (switches are recorded, select clicks are not)', async () => { - h = await bothKnobs({ script: [textResponse('ok')] }) + h = await presetStack({ script: [textResponse('ok')] }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'workspace-write' }) - const back = await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'read-only' }) - expect(back.configOptions?.find(option => option.id === 'sandbox-mode')).toMatchObject({ currentValue: 'read-only' }) + await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) + const back = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'workspace-write' }) + expect(back.configOptions).toEqual([permissionOption('workspace-write')]) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] - expect(events.filter(e => e.type === 'bash/sandbox-mode')).toHaveLength(0) + expect(events.some(e => e.type === 'permission/preset' || e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) + }) + + it('a no-op switch (the value already shown) records nothing and keeps a live pending', async () => { + h = await presetStack({ script: [textResponse('ok')] }) + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'workspace-write' }) + expect(echo.configOptions).toEqual([permissionOption('workspace-write')]) + await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) + const repeat = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) + expect(repeat.configOptions).toEqual([permissionOption('danger-full-access')]) + await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) + const events = h.ctx.agents.list()[0]?.session.events ?? [] + expect(events.filter(e => e.type === 'permission/preset').map(e => e.data)).toEqual([{ preset: 'danger-full-access' }]) }) it('a mid-turn switch anchors immediately (the open turn encloses it)', async () => { - h = await bothKnobs({ script: ['hang'] }) + h = await presetStack({ script: ['hang'] }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const hung = h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) // Give the loop a tick to open the turn (the turns.spec hang idiom). await new Promise(resolve => setTimeout(resolve, 30)) - await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'workspace-write' }) - await h.client.setSessionConfigOption({ sessionId, configId: 'approval-policy', value: 'never' }) + await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) const events = h.ctx.agents.list()[0]?.session.events ?? [] const turnStart = events.findIndex(e => e.type === 'turn/start') - const anchored = events.findIndex(e => e.type === 'bash/sandbox-mode') + const anchored = events.findIndex(e => e.type === 'permission/preset') expect(turnStart).toBeGreaterThanOrEqual(0) expect(anchored).toBeGreaterThan(turnStart) + expect(events.some(e => e.type === 'bash/sandbox-mode')).toBe(true) expect(events.some(e => e.type === 'approval/policy')).toBe(true) await h.client.cancel({ sessionId }) await hung }) - it('tolerates a provided approval stand-in whose config skipped the plugin schema', async () => { - h = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] }) - h.ctx.provide('approval', { config: {} } as unknown as InstanceType) - await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) - const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toEqual([approvalOption('ask')]) - const sessionId = res.sessionId - // The schema-less config also shields the no-op guard ('ask' by the ?? fallback)… - const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'approval-policy', value: 'ask' }) - expect(echo.configOptions).toEqual([approvalOption('ask')]) - // …and the anchor-time comparison: a real switch under the stand-in still anchors. - await h.client.setSessionConfigOption({ sessionId, configId: 'approval-policy', value: 'never' }) - await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) - const events = h.ctx.agents.list()[0]?.session.events ?? [] - expect(events.filter(e => e.type === 'approval/policy').map(e => e.data)).toEqual([{ policy: 'never' }]) - }) - it('rejects unknown ids, unadvertised ids, boolean values, and out-of-vocabulary values', async () => { h = await makeBridgeHarness({ storageDir }) await h.ctx.plugin(ApprovalService) @@ -221,40 +177,72 @@ describe('acp bridge — session config options', () => { await expect(h.client.setSessionConfigOption({ sessionId, configId: 'reasoning-effort', value: 'max' })) .rejects.toThrow(/unknown config option/) - // sandbox-mode exists as a concept but THIS composition never advertised it. - await expect(h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'workspace-write' })) - .rejects.toThrow(/unknown sandbox-mode value/) - await expect(h.client.setSessionConfigOption({ sessionId, configId: 'approval-policy', type: 'boolean', value: true })) + // `permission` exists as a concept but THIS composition never advertised it. + await expect(h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' })) + .rejects.toThrow(/unknown permission value/) + await expect(h.client.setSessionConfigOption({ sessionId, configId: 'permission', type: 'boolean', value: true })) .rejects.toThrow(/select; boolean values are not accepted/) - await expect(h.client.setSessionConfigOption({ sessionId, configId: 'approval-policy', value: 'always' })) - .rejects.toThrow(/unknown approval-policy value/) + }) + + it('rejects an out-of-vocabulary preset on an advertising composition', async () => { + h = await presetStack() + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + await expect(h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'plan' })) + .rejects.toThrow(/unknown permission value/) }) it('a switch in one session never leaks into a concurrent one (state and pending both per-session)', async () => { - h = await bothKnobs() + h = await presetStack() const a = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const b = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'sandbox-mode', value: 'danger-full-access' }) - // B sees its own composition defaults, not A's pending switch... - const bAfter = await h.client.setSessionConfigOption({ sessionId: b.sessionId, configId: 'approval-policy', value: 'never' }) - expect(bAfter.configOptions).toEqual([sandboxOption('read-only'), approvalOption('never')]) + await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'permission', value: 'danger-full-access' }) + // B sees the composition default, not A's pending switch... + const bAfter = await h.client.setSessionConfigOption({ sessionId: b.sessionId, configId: 'permission', value: 'workspace-write' }) + expect(bAfter.configOptions).toEqual([permissionOption('workspace-write')]) // ...and A keeps its own state, untouched by B's. - const aAfter = await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'sandbox-mode', value: 'danger-full-access' }) - expect(aAfter.configOptions).toEqual([sandboxOption('danger-full-access'), approvalOption('ask')]) + const aAfter = await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'permission', value: 'danger-full-access' }) + expect(aAfter.configOptions).toEqual([permissionOption('danger-full-access')]) }) - it('session/load reports a resumed session\'s overrides from its own log', async () => { - h = await bothKnobs({ script: [textResponse('ok')] }) + it('a knob drifted outside the table derives a visible-but-untargetable custom current', async () => { + h = await presetStack() const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - await h.client.setSessionConfigOption({ sessionId, configId: 'sandbox-mode', value: 'danger-full-access' }) - await h.client.setSessionConfigOption({ sessionId, configId: 'approval-policy', value: 'never' }) + // Drift a knob out from under the table (a plugin writing the knob + // directly — the raw setters remain public mechanism), inside its own + // turn: the dev invariants enforce turn-enclosure here too. + const agent = h.ctx.agents.list()[0] + if (agent === undefined) throw new Error('expected an agent') + agent.session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + agent.session.append('bash/sandbox-mode', { mode: 'read-only' }) + agent.session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + // The echo of the derived current is a no-op, not an unknown-value error… + const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'custom' }) + const option = echo.configOptions?.[0] + expect(option).toMatchObject({ currentValue: 'custom' }) + if (option === undefined || !('options' in option)) throw new Error('expected a select option') + expect(option.options.map(o => 'value' in o ? o.value : o)).toEqual(['workspace-write', 'danger-full-access', 'custom']) + // …while custom as a TARGET from a real preset stays rejected: switching + // away is ordinary, and the custom entry disappears from the options. + const away = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) + const afterOption = away.configOptions?.[0] + expect(afterOption).toMatchObject({ currentValue: 'danger-full-access' }) + if (afterOption === undefined || !('options' in afterOption)) throw new Error('expected a select option') + expect(afterOption.options.map(o => 'value' in o ? o.value : o)).toEqual(['workspace-write', 'danger-full-access']) + await expect(h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'custom' })) + .rejects.toThrow(/unknown permission value/) + }) + + it('session/load reports a resumed session\'s preset from its own log', async () => { + h = await presetStack({ script: [textResponse('ok')] }) + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) // One turn checkpoints the log (the switch events flush with it). await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'persist me' }] }) await h.dispose() h = undefined - loader = await bothKnobs() + loader = await presetStack() const res = await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toEqual([sandboxOption('danger-full-access'), approvalOption('never')]) + expect(res.configOptions).toEqual([permissionOption('danger-full-access')]) }) }) diff --git a/packages/ui/acp/tsconfig.json b/packages/ui/acp/tsconfig.json index 0c82438277..387e0d0c53 100644 --- a/packages/ui/acp/tsconfig.json +++ b/packages/ui/acp/tsconfig.json @@ -38,6 +38,9 @@ { "path": "../user-approval" }, + { + "path": "../permission" + }, { "path": "../../sandbox/sandbox" }, diff --git a/packages/ui/jsonrpc-agent/README.md b/packages/ui/jsonrpc-agent/README.md index d1836c737d..01c8723893 100644 --- a/packages/ui/jsonrpc-agent/README.md +++ b/packages/ui/jsonrpc-agent/README.md @@ -4,7 +4,7 @@ The **JSON-RPC SDK server app bin** (`dsh-jsonrpc-agent`): boot a harness from a ## Config discovery -Two channels, environment first: `$DSH_CORDIS_CONFIG` (the existing SDK-client convention, wins), then the `argv[2]` positional path (`dsh-jsonrpc-agent `, the human channel, isomorphic to `dsh-acp-agent`). An empty value counts as absent on either channel. Neither given, or the path missing on disk: the bin prints a one-line usage naming both channels to stderr and exits 1 — there is no default `./cordis.yml` and no built-in fallback config. A config that names a plugin which fails to load fails loud through the shared [`dsh-app-boot`](../app-boot/README.md) guards (`assertEntriesLoaded` + the unhandled-rejection handler), never a silent half-boot. There is no `DSH_SNAPSHOT` handling: this protocol is not part of the ACP snapshot tier. +Two channels, environment first: `$DSH_CORDIS_CONFIG` (the existing SDK-client convention, wins), then the `argv[2]` positional path (`dsh-jsonrpc-agent `, the human channel). An empty value counts as absent on either channel. Neither given, or the path missing on disk: the bin prints a one-line usage naming both channels to stderr and exits 1 — there is no default `./cordis.yml` and no built-in fallback config. A config that names a plugin which fails to load fails loud through the shared [`dsh-app-boot`](../app-boot/README.md) guards (`assertEntriesLoaded` + the unhandled-rejection handler), never a silent half-boot. There is no `DSH_SNAPSHOT` handling: this protocol is not part of the ACP snapshot tier. Note the deliberate flip side of config-decides-everything: a config that loads no `dsh-jsonrpc` entry boots fine and serves nothing — the bin cannot know which plugin is "the server". diff --git a/packages/ui/jsonrpc-agent/src/bin.ts b/packages/ui/jsonrpc-agent/src/bin.ts index b2c9f0c3d2..a70251a2be 100644 --- a/packages/ui/jsonrpc-agent/src/bin.ts +++ b/packages/ui/jsonrpc-agent/src/bin.ts @@ -9,7 +9,7 @@ * * - Config discovery is `$DSH_CORDIS_CONFIG` (the existing SDK-client * convention, wins) or the `argv[2]` positional path (the human channel, - * isomorphic to `dsh-acp-agent`); an empty value counts as absent. Neither + * for direct launches); an empty value counts as absent. Neither * given, or the path missing on disk, prints the one-line usage to stderr * and exits 1. No built-in fallback — the external config IS the deployment * (docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). diff --git a/packages/ui/permission/README.md b/packages/ui/permission/README.md new file mode 100644 index 0000000000..2f6b12054b --- /dev/null +++ b/packages/ui/permission/README.md @@ -0,0 +1,7 @@ +# @deepseek-ai/dsh-permission + +User-facing permission presets. Owns the `ctx.permission` service ([`PermissionService`](src/index.ts)): a config-defined preset table — by default `workspace-write` (`workspace-write` + `ask`) and `danger-full-access` (`danger-full-access` + `never`) — where each name bundles the two mechanism knobs, `bash/sandbox-mode` and `approval/policy`. The product surface (the ACP bridge's single `Permissions` select) advertises `names` and calls `set()`; the mechanism tiers stay orthogonal capabilities that never learn the product vocabulary. + +A switch WRITES THROUGH: `set(session, name)` appends one log-only `permission/preset` event when the name differs from the session's current preset (the audit fact reverse-mapping cannot recover — two presets may share knob values and differ only in composed policy, the planned `agent` preset being the standing example), then each knob event through its own THE-write-path setter, skipping values the session already effectively has — a net-zero switch appends nothing. The current preset DERIVES from the effective knob values (fold ?? composition default per knob): the last-chosen preset when its bundle still matches (presets may share bundles — the fold breaks the tie), else the first matching table entry, else the reserved `custom` — the honest not-a-preset state, shown as the current value only while it holds, switchable FROM and never a target. Every existing knob consumer (executor stamping, the approval gate, narrators, resume) keeps reading its own fold, untouched. + +Composing it requires a confining `ctx.bash` executor and the `ctx.approval` seam; a table entry named `custom` throws at load (the name is reserved), while composition defaults outside the table are not an error — a zero-event session simply derives `custom`. See [the acp-agent example's default tree](../../../examples/acp-agent/) for the composed leaf and [the sandbox RFC § Per-session modes](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md) for the switching design this layers over. diff --git a/packages/ui/permission/package.json b/packages/ui/permission/package.json new file mode 100644 index 0000000000..b6833791e4 --- /dev/null +++ b/packages/ui/permission/package.json @@ -0,0 +1,41 @@ +{ + "name": "@deepseek-ai/dsh-permission", + "description": "User-facing permission presets (ctx.permission) for the DeepSeek Harness: one product-level Permissions select bundling the sandbox-mode and approval-policy knobs, written through to their own session events", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-bash": "^0.0.1", + "@deepseek-ai/dsh-sandbox": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-user-approval": "^0.0.1", + "cordis": "^4.0.0-rc.6" + }, + "dependencies": { + "schemastery": "^3.18.0" + }, + "devDependencies": { + "@deepseek-ai/dsh-bash": "workspace:^", + "@deepseek-ai/dsh-sandbox": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-user-approval": "workspace:^", + "cordis": "^4.0.0-rc.6" + } +} diff --git a/packages/ui/permission/src/index.ts b/packages/ui/permission/src/index.ts new file mode 100644 index 0000000000..67e623052b --- /dev/null +++ b/packages/ui/permission/src/index.ts @@ -0,0 +1,237 @@ +/** + * User-facing PERMISSION PRESETS: one product-level knob over the two + * mechanism knobs. A preset names a bundle — its sandbox mode + * (`bash/sandbox-mode`) and its approval policy (`approval/policy`) — so a + * user picks `workspace-write` or `danger-full-access` while the mechanism + * tiers stay orthogonal capabilities. Switching a preset WRITES THROUGH: one `permission/preset` event + * records the chosen bundle (the audit fact reverse-mapping cannot recover — + * two presets may share knob values and differ only in composed policy, the + * planned `agent` preset being the standing example), then each knob event + * follows through its own THE-write-path setter, skipping values the session + * already effectively has. Every existing consumer (executor stamping, the + * approval gate, narrators, resume) keeps reading its own knob fold, + * untouched. + * + * @module dsh-permission + */ + +import { Context, Service } from 'cordis' +import z from 'schemastery' +import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' +import { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-bash' +import type { ApprovalPolicy } from '@deepseek-ai/dsh-user-approval' +import { APPROVAL_POLICIES, effectiveApprovalPolicy, setApprovalPolicy } from '@deepseek-ai/dsh-user-approval' + +declare module 'cordis' { + interface Context { + permission: PermissionService + } +} + +declare module '@deepseek-ai/dsh-session' { + interface SessionEventMap { + /** + * The session's permission preset was switched — log-only (the + * `bash/sandbox-mode` precedent): durable and replayable, never in the + * model transcript. The LAST such event is the session's preset + * ({@link effectivePermissionPreset}); the knob events the switch wrote + * through follow it in the same turn, and they — not this record of the + * user's choice — are what execution reads. + */ + 'permission/preset': { preset: string } + } +} + +/** + * One preset's knob bundle — the sandbox mode and approval policy a session + * runs under while the preset is active — plus its presentation. + */ +export interface PresetSpec { + /** The `bash/sandbox-mode` value the preset writes through. */ + sandbox: SandboxMode + /** The `approval/policy` value the preset writes through. */ + approval: ApprovalPolicy + /** The display label a client shows for this preset; the raw table key when omitted. */ + name?: string + /** One user-facing sentence on what the preset means; omitted when not configured. */ + description?: string +} + +/** The select-option shape a presentation layer advertises for one preset (or for the derived `custom` state). */ +export interface PresetOption { + /** The machine value (`session/set_config_option` vocabulary): the table key, or `custom`. */ + value: string + /** The display label. */ + name: string + /** One user-facing sentence on what the value means. */ + description?: string +} + +/** + * The derived not-a-preset state: the session's effective knob values match + * no table entry (composition defaults outside the table, or a knob moved + * out from under the last-chosen preset). Never a switch target and never + * an event payload — {@link PermissionService.current} derives it, and the + * presentation layer shows it as a selectable-FROM-only current value. + */ +export const CUSTOM_PRESET = 'custom' + +/** + * The session's permission-preset override: the last `permission/preset` event in the + * log, or undefined when the session never switched (callers apply the + * plugin's configured default). The pure fold — resume needs no catch-up + * machinery because replaying the log IS the state. + * @param events - session events in log order (other event types are skipped). + * @returns the preset of the last switch event, or undefined without one. + */ +export function effectivePermissionPreset(events: readonly SessionEvent[]): string | undefined { + for (let index = events.length - 1; index >= 0; index -= 1) { + const event = events[index] as SessionEvent + if (event.type === 'permission/preset') return event.data.preset + } + return undefined +} + +/** The {@link PermissionService} config: the deployment's preset table. */ +export interface Config { + /** + * The preset table: name → knob bundle. Defaults to `workspace-write` + * (workspace-write + ask) and `danger-full-access` (danger-full-access + + * never). The name `custom` is reserved for the derived not-a-preset state. + */ + presets?: Record +} + +/** + * The permission service (`ctx.permission`). Owns the deployment's preset + * table and THE write path for preset switches; presentation layers (the ACP + * bridge's single `Permissions` select) advertise {@link names} and call + * {@link set}. Composing it REQUIRES both mechanism knobs — a confining + * `ctx.bash` executor and the `ctx.approval` seam. A knob state matching no + * table entry is not an error but the derived {@link CUSTOM_PRESET} state: + * shown as the current value, never a switch target. + */ +export class PermissionService extends Service { + // Inline schema call: the config catalog walks `static Config` statically. + static Config: z = z.object({ + presets: z.dict(z.object({ + sandbox: z.union(SANDBOX_MODES as SandboxMode[]).required(), + approval: z.union(APPROVAL_POLICIES as ApprovalPolicy[]).required(), + name: z.string(), + description: z.string(), + })).default({ + // Keep the user-facing preset names explicit about filesystem reach. + 'workspace-write': { + sandbox: 'workspace-write', approval: 'ask', + name: 'workspace-write', description: 'Write inside the workspace; anything wider asks for your approval.', + }, + 'danger-full-access': { + sandbox: 'danger-full-access', approval: 'never', + name: 'danger-full-access', description: 'Full file access, no approval prompts.', + }, + }), + }) + + static inject = ['bash', 'approval'] + + private readonly presets: Record + + constructor(ctx: Context, config: Config) { + super(ctx, 'permission') + // The schema defaulted the table — the cast records that runtime fact. + this.presets = config.presets as Record + if (CUSTOM_PRESET in this.presets) { + throw new Error(`permission: "${CUSTOM_PRESET}" is reserved for the derived not-a-preset state and cannot name a table entry`) + } + if (ctx.bash.sandboxMode === undefined) { + throw new Error('permission: the mounted bash executor does not confine (no sandboxMode) — presets bundle a sandbox mode, so composing this plugin over an unconfined executor is a misconfiguration') + } + } + + /** + * The advertised preset names, in the preset table's declaration order. + * @returns every switchable preset name. + */ + get names(): readonly string[] { + return Object.keys(this.presets) + } + + /** + * The preset a session is on right now, derived from the EFFECTIVE knob + * values (fold ?? composition default per knob): the last-chosen preset + * when its bundle still matches (presets may share bundles — the fold + * breaks the tie), else the first table entry that matches, else + * {@link CUSTOM_PRESET} — a mismatch is a state, not an error. + * @param events - the session's events in log order. + * @returns the effective preset name, or `custom` when nothing matches. + */ + current(events: readonly SessionEvent[]): string { + const sandbox = effectiveSandboxMode(events) ?? this.ctx.bash.sandboxMode + const approval = effectiveApprovalPolicy(events) ?? this.ctx.approval.config.policy ?? 'ask' + const matches = (spec: PresetSpec): boolean => spec.sandbox === sandbox && spec.approval === approval + const folded = effectivePermissionPreset(events) + if (folded !== undefined) { + const spec = this.presets[folded] + if (spec !== undefined && matches(spec)) return folded + } + for (const [name, spec] of Object.entries(this.presets)) { + if (matches(spec)) return name + } + return CUSTOM_PRESET + } + + /** + * A preset's knob bundle, for consumers presenting or validating one. + * @param name - the preset name to resolve. + * @returns the bundle; throws on a name outside the table (fails loud — + * an unvalidated caller handed the service an unknown preset). + */ + resolve(name: string): PresetSpec { + const spec = this.presets[name] + if (spec === undefined) { + throw new Error(`permission: unknown preset "${name}" (known: ${Object.keys(this.presets).join(', ')})`) + } + return spec + } + + /** + * The select-option presentation of one advertisable value: a table entry + * (label/description from its spec, the raw key standing in for a missing + * label) or the derived {@link CUSTOM_PRESET} with its fixed presentation. + * @param name - a table key, or `custom`. + * @returns the option a client renders; throws on any other name. + */ + optionOf(name: string): PresetOption { + if (name === CUSTOM_PRESET) { + return { value: CUSTOM_PRESET, name: 'Custom', description: 'A hand-set knob combination outside the preset table.' } + } + const spec = this.resolve(name) + return { value: name, name: spec.name ?? name, ...spec.description !== undefined ? { description: spec.description } : {} } + } + + /** + * THE write path for a preset switch: appends one `permission/preset` event when + * `name` differs from the session's current preset, then writes each knob + * through its own setter, skipping values the session already effectively + * has — a net-zero switch appends nothing (the log records switches, not + * select clicks). + * @param session - the session the switch belongs to. + * @param name - the preset to switch to (validated via {@link resolve}). + */ + set(session: Session, name: string): void { + const spec = this.resolve(name) + if (this.current(session.events) !== name) { + session.append('permission/preset', { preset: name }) + } + const events = session.events + if (spec.sandbox !== (effectiveSandboxMode(events) ?? this.ctx.bash.sandboxMode)) { + setSandboxMode(session, spec.sandbox) + } + if (spec.approval !== (effectiveApprovalPolicy(events) ?? this.ctx.approval.config.policy ?? 'ask')) { + setApprovalPolicy(session, spec.approval) + } + } +} + +export default PermissionService diff --git a/packages/ui/permission/tests/permission.spec.ts b/packages/ui/permission/tests/permission.spec.ts new file mode 100644 index 0000000000..2852b2d96b --- /dev/null +++ b/packages/ui/permission/tests/permission.spec.ts @@ -0,0 +1,147 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { Session, SessionId } from '@deepseek-ai/dsh-session' +import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' +import type { ApprovalPolicy } from '@deepseek-ai/dsh-user-approval' +import PermissionService, { CUSTOM_PRESET, effectivePermissionPreset } from '@deepseek-ai/dsh-permission' +import type { Config } from '@deepseek-ai/dsh-permission' + +/** Mount the service over stand-in bash/approval capabilities (the two facts it validates against). */ +async function mounted(options: { + config?: Config + bashDefault?: SandboxMode | undefined + approvalDefault?: ApprovalPolicy | undefined +} = {}): Promise { + const ctx = new Context() + ctx.provide('bash', { sandboxMode: 'bashDefault' in options ? options.bashDefault : 'workspace-write' }) + ctx.provide('approval', { config: { policy: 'approvalDefault' in options ? options.approvalDefault : 'ask' } }) + await ctx.plugin(PermissionService, options.config ?? {}) + return ctx +} + +/** A real Session seeded with one opened turn (events append without ceremony in unit scope). */ +function freshSession(id: string): Session { + return new Session(SessionId(id)) +} + +describe('effectivePermissionPreset', () => { + it('folds to the last event, or undefined without one', () => { + const session = freshSession('sess-fold') + expect(effectivePermissionPreset(session.events)).toBeUndefined() + session.append('permission/preset', { preset: 'danger-full-access' }) + session.append('permission/preset', { preset: 'workspace-write' }) + expect(effectivePermissionPreset(session.events)).toBe('workspace-write') + }) +}) + +describe('PermissionService', () => { + it('advertises the preset table in declaration order and resolves bundles', async () => { + const ctx = await mounted() + expect(ctx.permission.names).toEqual(['workspace-write', 'danger-full-access']) + expect(ctx.permission.resolve('danger-full-access')).toMatchObject({ sandbox: 'danger-full-access', approval: 'never' }) + expect(() => ctx.permission.resolve('plan')).toThrow(/unknown preset "plan"/) + }) + + it('current() derives from the effective knobs: composition defaults hit workspace-write, a switch hits its preset', async () => { + const ctx = await mounted() + const session = freshSession('sess-current') + expect(ctx.permission.current(session.events)).toBe('workspace-write') + ctx.permission.set(session, 'danger-full-access') + expect(ctx.permission.current(session.events)).toBe('danger-full-access') + }) + + it('a knob state matching no table entry derives custom — a state, not an error', async () => { + const ctx = await mounted() + const session = freshSession('sess-custom') + session.append('bash/sandbox-mode', { mode: 'read-only' }) + expect(ctx.permission.current(session.events)).toBe(CUSTOM_PRESET) + // Switching FROM custom is an ordinary write-through; custom itself is + // never a target. + ctx.permission.set(session, 'danger-full-access') + expect(ctx.permission.current(session.events)).toBe('danger-full-access') + expect(() => ctx.permission.resolve(CUSTOM_PRESET)).toThrow(/unknown preset/) + }) + + it('composition defaults outside the table derive custom at zero events', async () => { + const ctx = await mounted({ approvalDefault: 'never' }) + const session = freshSession('sess-defaults-custom') + expect(ctx.permission.current(session.events)).toBe(CUSTOM_PRESET) + }) + + it('the fold breaks bundle ties; a stale fold no longer matching falls back to table order', async () => { + const ctx = await mounted({ config: { presets: { + 'workspace-write': { sandbox: 'workspace-write', approval: 'ask' }, + agentish: { sandbox: 'workspace-write', approval: 'ask' }, + 'danger-full-access': { sandbox: 'danger-full-access', approval: 'never' }, + } } }) + const session = freshSession('sess-tie') + // Same bundle as workspace-write, chosen explicitly: the fold names it. + ctx.permission.set(session, 'agentish') + expect(ctx.permission.current(session.events)).toBe('agentish') + // A knob drifts: the fold's bundle no longer matches → reverse map wins. + session.append('approval/policy', { policy: 'never' }) + session.append('bash/sandbox-mode', { mode: 'danger-full-access' }) + expect(ctx.permission.current(session.events)).toBe('danger-full-access') + }) + + it('set() writes through: one preset event plus both knob events', async () => { + const ctx = await mounted() + const session = freshSession('sess-set') + ctx.permission.set(session, 'danger-full-access') + expect(session.events.map(e => [e.type, e.data])).toEqual([ + ['permission/preset', { preset: 'danger-full-access' }], + ['bash/sandbox-mode', { mode: 'danger-full-access' }], + ['approval/policy', { policy: 'never' }], + ]) + }) + + it('set() to the current preset is a no-op when the knobs already match (clicks are not switches)', async () => { + const ctx = await mounted() + const session = freshSession('sess-noop') + ctx.permission.set(session, 'workspace-write') + expect(session.events).toHaveLength(0) + }) + + it('re-asserting a preset from a drifted (custom) state re-records the choice and repairs the knob', async () => { + const ctx = await mounted() + const session = freshSession('sess-drift') + ctx.permission.set(session, 'danger-full-access') + // A knob drifts out from under the preset (a direct setter call, a test + // scenario): the session derives custom, and re-asserting the preset is + // a real switch again — choice re-recorded, only the drifted knob moves. + session.append('bash/sandbox-mode', { mode: 'read-only' }) + ctx.permission.set(session, 'danger-full-access') + const tail = session.events.slice(4) + expect(tail.map(e => [e.type, e.data])).toEqual([ + ['permission/preset', { preset: 'danger-full-access' }], + ['bash/sandbox-mode', { mode: 'danger-full-access' }], + ]) + }) + + it('rejects composition over a non-confining executor at load', async () => { + await expect(mounted({ bashDefault: undefined })) + .rejects.toThrow(/does not confine/) + }) + + it('optionOf() presents shipped labels/descriptions, falls back to the raw key, and fixes custom', async () => { + const ctx = await mounted() + expect(ctx.permission.optionOf('danger-full-access')).toEqual({ value: 'danger-full-access', name: 'danger-full-access', description: 'Full file access, no approval prompts.' }) + expect(ctx.permission.optionOf('custom')).toEqual({ value: 'custom', name: 'Custom', description: 'A hand-set knob combination outside the preset table.' }) + const bare = await mounted({ config: { presets: { plain: { sandbox: 'workspace-write', approval: 'ask' } } } }) + expect(bare.permission.optionOf('plain')).toEqual({ value: 'plain', name: 'plain' }) + expect(() => ctx.permission.optionOf('plan')).toThrow(/unknown preset/) + }) + + it('rejects a table entry named custom (reserved for the derived state)', async () => { + await expect(mounted({ config: { presets: { custom: { sandbox: 'read-only', approval: 'ask' } } } })) + .rejects.toThrow(/reserved for the derived not-a-preset state/) + }) + + it('reads a schema-less approval stand-in as the ask default', async () => { + const ctx = await mounted({ approvalDefault: undefined }) + const session = freshSession('sess-standin') + ctx.permission.set(session, 'workspace-write') + expect(session.events).toHaveLength(0) + expect(ctx.permission.current(session.events)).toBe('workspace-write') + }) +}) diff --git a/packages/ui/permission/tsconfig.json b/packages/ui/permission/tsconfig.json new file mode 100644 index 0000000000..8b9cff62b4 --- /dev/null +++ b/packages/ui/permission/tsconfig.json @@ -0,0 +1,33 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../../vendor/schemastery" + }, + { + "path": "../../core/session" + }, + { + "path": "../../sandbox/sandbox" + }, + { + "path": "../../bash/bash" + }, + { + "path": "../user-approval" + } + ] +} diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 541f34d207..64b3249237 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -759,6 +759,25 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/session-query/session-query: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-session-persistence': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/skill/skill: dependencies: schemastery: @@ -1176,6 +1195,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-permission': + specifier: workspace:^ + version: link:../permission '@deepseek-ai/dsh-sandbox': specifier: workspace:^ version: link:../../sandbox/sandbox @@ -1267,6 +1289,28 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) + packages/ui/permission: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@deepseek-ai/dsh-bash': + specifier: workspace:^ + version: link:../../bash/bash + '@deepseek-ai/dsh-sandbox': + specifier: workspace:^ + version: link:../../sandbox/sandbox + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../user-approval + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/ui/jsonrpc: dependencies: schemastery: @@ -1724,6 +1768,9 @@ importers: '@deepseek-ai/dsh-llm-pi-ai': specifier: workspace:^ version: link:../../packages/llm/llm-pi-ai + '@deepseek-ai/dsh-permission': + specifier: workspace:^ + version: link:../../packages/ui/permission '@deepseek-ai/dsh-repeat-tool-guard': specifier: workspace:^ version: link:../../packages/guard/repeat-tool-guard diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index 76e6bf157f..a843b2f04a 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -32,6 +32,7 @@ "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", "@deepseek-ai/dsh-llm-pi-ai": "workspace:^", + "@deepseek-ai/dsh-permission": "workspace:^", "@deepseek-ai/dsh-repeat-tool-guard": "workspace:^", "@deepseek-ai/dsh-sandbox": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", diff --git a/scripts/demo-code-mode.mjs b/scripts/demo-code-mode.mjs index a93ea98173..d8c975190c 100644 --- a/scripts/demo-code-mode.mjs +++ b/scripts/demo-code-mode.mjs @@ -15,7 +15,7 @@ import { spawn } from 'node:child_process' // Loader's HMR path). const UIS = new Map([ ['repl', ['--expose-internals', '--import', 'tsx', 'packages/ui/stdio-agent/src/bin.ts', 'examples/coding-agent/code-mode.cordis.yml']], - ['acp', ['--import', 'tsx', 'packages/ui/acp-agent/src/bin.ts', 'examples/acp-agent/code-mode.cordis.yml']], + ['acp', ['--import', 'tsx', 'packages/ui/acp-agent/src/bin.ts', '--config', 'examples/acp-agent/code-mode.cordis.yml']], ]) const ui = process.argv[2] ?? 'repl' diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index fa7daed85e..3476399438 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -73,6 +73,7 @@ const GROUP_ORDER = [ 'cordis', 'hooks', 'session-persistence', + 'session-query', 'support', 'ui', ] @@ -92,7 +93,7 @@ const SERVICE_ROLES: ServiceRole[] = [ pkg: 'session', title: 'In-memory session store', mode: 'core', - consumers: ['agent-loop', 'agent', 'session-persistence', 'subagent-inprocess', 'invariants'], + consumers: ['agent-loop', 'agent', 'session-persistence', 'session-query', 'subagent-inprocess', 'invariants'], note: 'Owns append-only Session instances and emits the durable session event feed.', }, { @@ -101,9 +102,16 @@ const SERVICE_ROLES: ServiceRole[] = [ title: 'Durable session persistence seam', mode: 'seam', implementations: ['session-persistence-jsonl', 'session-persistence-sqlite'], - consumers: ['agent-loop', 'acp'], + consumers: ['agent-loop', 'acp', 'session-query'], note: 'Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time.', }, + { + key: 'sessionQuery', + pkg: 'session-query', + title: 'Exact session-history reads', + mode: 'seam', + note: 'Resolves live and optional persisted logs into one logical corpus for exact reads.', + }, { key: 'systemPrompt', pkg: 'system-prompt', @@ -181,6 +189,15 @@ const SERVICE_ROLES: ServiceRole[] = [ consumers: ['tools', 'tool-bash'], note: 'One-shot permission decisions dispatched over the `approval/request` waterfall; answerers are listeners (the ACP bridge for its own agents), absence fails closed to `unavailable`.', }, + { + key: 'permission', + pkg: 'permission', + title: 'Permission presets', + mode: 'core', + implementations: [], + consumers: ['acp'], + note: 'User-facing preset table (`workspace-write`/`danger-full-access`) bundling the sandbox-mode and approval-policy knobs; a switch writes one `permission/preset` event through to both knob events.', + }, { key: 'codeRuntime', pkg: 'code-runtime', diff --git a/scripts/gen-module-graph.ts b/scripts/gen-module-graph.ts index 2a687c8f26..97c462a5a6 100644 --- a/scripts/gen-module-graph.ts +++ b/scripts/gen-module-graph.ts @@ -46,6 +46,7 @@ const GROUP_ORDER = [ 'cordis', 'hooks', 'session-persistence', + 'session-query', 'support', 'ui', ] diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 874f0754a6..59daa559ce 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -39,10 +39,19 @@ { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceEventType", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceOp", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceIntent", "source": "packages/core/session/src/types.ts" }, + { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceFoldReplacement", "source": "packages/core/session/src/surface.ts" }, + { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceFoldResult", "source": "packages/core/session/src/surface.ts" }, { "doc": "docs/core-data-structures/persistence.md", "symbol": "SessionHeader", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/persistence.md", "symbol": "CreateSessionOptions", "source": "packages/core/session/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventSurface", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionRecord", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventRecord", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionQueryErrorCode", "source": "packages/session-query/session-query/src/config.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventReadRequest", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventWindow", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/tools.md", "symbol": "ToolDefinition", "source": "packages/core/tools/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "SchemaProp", "source": "packages/core/tools/src/schema.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "SchemaSpec", "source": "packages/core/tools/src/schema.ts" }, diff --git a/tsconfig.base.json b/tsconfig.base.json index 36401b77f7..c6dff7c732 100644 --- a/tsconfig.base.json +++ b/tsconfig.base.json @@ -57,6 +57,7 @@ "./packages/sandbox/*/src", "./packages/hooks/*/src", "./packages/session-persistence/*/src", + "./packages/session-query/*/src", "./packages/ui/*/src", "./packages/util/*/src", "./packages/support/*/src" diff --git a/tsconfig.build.json b/tsconfig.build.json index b3d904aa9b..6deb2c6e01 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -18,10 +18,12 @@ { "path": "./packages/session-persistence/session-persistence" }, { "path": "./packages/session-persistence/session-persistence-jsonl" }, { "path": "./packages/session-persistence/session-persistence-sqlite" }, + { "path": "./packages/session-query/session-query" }, { "path": "./packages/core/system-prompt" }, { "path": "./packages/core/agent" }, { "path": "./packages/ui/user-interaction" }, { "path": "./packages/ui/user-approval" }, + { "path": "./packages/ui/permission" }, { "path": "./packages/core/tools" }, { "path": "./packages/skill/skill" }, { "path": "./packages/skill/skill-local" }, diff --git a/tsconfig.json b/tsconfig.json index a52f21a86e..dd283ec5d7 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -29,10 +29,12 @@ { "path": "./packages/session-persistence/session-persistence" }, { "path": "./packages/session-persistence/session-persistence-jsonl" }, { "path": "./packages/session-persistence/session-persistence-sqlite" }, + { "path": "./packages/session-query/session-query" }, { "path": "./packages/core/system-prompt" }, { "path": "./packages/core/agent" }, { "path": "./packages/ui/user-interaction" }, { "path": "./packages/ui/user-approval" }, + { "path": "./packages/ui/permission" }, { "path": "./packages/core/tools" }, { "path": "./packages/skill/skill" }, { "path": "./packages/skill/skill-local" }, diff --git a/vendor/README.md b/vendor/README.md index 0a709495db..e27385f836 100644 --- a/vendor/README.md +++ b/vendor/README.md @@ -36,6 +36,7 @@ Keep this log exhaustive — every divergence from upstream must be listed. 4. **Vendored TypeScript source internal specifiers**: changed local relative imports/exports from upstream's specifier shape to explicit `.ts` specifiers so TypeScript rewrites emitted JS to `.js` while declarations keep explicit, NodeNext-safe `.ts` specifiers. This includes `loader/src/config/isolate.ts` using `declare module './entry.ts'`. 5. **`schemastery/tsdown.config.ts` and `logger-console/tsdown.config.ts`**: ours, not upstream files — per-package build-shape overrides (dual ESM+CJS output; separate node/browser entries) for the repo-root tsdown build. They read the JS emitted under `lib/types` and then write the publish runtime entries under `lib/`. Like the regenerated tsconfigs, they are not part of the upstream sync surface. 6. **`cordis/src/fiber.ts` lifecycle hardening**: locally closes three reentrant disposal gaps. An effect's owner-list wrapper is registered before its setup body runs, so an unload begun from inside setup awaits setup and every collected cleanup; synchronous setup failure removes the wrapper and rolls back collected cleanup. Async cleanup stays owner-visible until quiescence, and Cordis's internal effect composition joins an already-running cleanup while repeated public disposer calls retain their upstream single-shot result. Effect creation is rejected while the owner is `UNLOADING` (while `PENDING` and `LOADING` remain legal), preventing cleanup-time registrations from escaping the unload snapshot. Child fibers register and receive their parent-owned disposer before `internal/plugin` publication, resolve dependency declarations added by that notification before activation, drain effects attached while pending, skip plugin execution when reentrant disposal invalidates the load epoch before its first checkpoint, and contain teardown-notification failures per observer so one callback cannot starve peers or interrupt ownership cleanup. +7. **`cordis/src/events.ts`**: a `FIXME` documents the upstream `parallel()` bug where a synchronous listener throw aborts callback enumeration and starves later listeners; runtime behavior remains upstream-identical pending an upstream fix. ## Sync procedure diff --git a/vendor/cordis/src/events.ts b/vendor/cordis/src/events.ts index 4461816537..e483afadf5 100644 --- a/vendor/cordis/src/events.ts +++ b/vendor/cordis/src/events.ts @@ -106,6 +106,8 @@ export class EventsService { /** Run listeners concurrently and wait for all of them. */ async parallel(...args: any[]) { + // FIXME(cordis upstream): A synchronous listener throw aborts callback + // enumeration here and starves later parallel listeners. Fix upstream. await Promise.all(this.dispatch('emit', args).map(cb => cb(...args))) }