From 709cc7200eb2b3ac64090c67833a25a367a1b3df Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:59:21 +0800 Subject: [PATCH 01/39] refactor: unify agent and session identity --- docs/config-catalog.md | 18 +- docs/cookbook/extension-cookbook.md | 4 +- docs/cordis-catalog/events.md | 34 +-- docs/cordis-catalog/services.md | 12 +- docs/core-data-structures/approval.md | 2 +- docs/core-data-structures/bash.md | 2 +- docs/core-data-structures/core.md | 8 +- docs/core-data-structures/subagent.md | 2 +- docs/event-producer-consumer.md | 34 +-- .../2026-06-11-content-block-vocabulary.md | 2 +- .../2026-06-14-session-persistence.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 10 +- .../2026-06-30-event-domain-semantics.md | 2 +- .../2026-07-08-agent-scope-contexts.md | 3 +- .../feature/2026-07-08-repeat-tool-guard.md | 5 +- ...-20-remove-agent-boundary-mirror-events.md | 8 +- ...claude-code-and-codex-subagent-backends.md | 2 +- .../2026-06-20-unify-agent-and-session-id.md | 6 +- examples/coding-agent/tests/code-mode.e2e.ts | 7 +- .../coding-agent/tests/coding-task.e2e.ts | 4 +- examples/coding-agent/tests/compaction.e2e.ts | 4 +- examples/coding-agent/tests/full-loop.e2e.ts | 4 +- examples/coding-agent/tests/resume.e2e.ts | 3 - examples/coding-agent/tests/todo-write.e2e.ts | 4 +- .../cordis-agent/tests/cordis-tools.e2e.ts | 8 +- .../bash/tool-bash/tests/integration.spec.ts | 11 +- packages/bash/tool-bash/tests/tools.spec.ts | 2 +- .../tests/compact-loop-repro.spec.ts | 7 +- .../cordis/tool-cordis/src/api-catalog.ts | 16 +- .../tool-cordis/tests/integration.spec.ts | 7 +- packages/core/agent-core/README.md | 2 +- .../core/agent-core/tests/agent-core.spec.ts | 12 +- packages/core/agent-loop/README.md | 10 +- packages/core/agent-loop/src/agent.ts | 8 +- packages/core/agent-loop/src/index.ts | 29 ++- packages/core/agent-loop/tests/agent.spec.ts | 53 +++-- packages/core/agent-loop/tests/cancel.spec.ts | 35 ++-- .../tests/config-session-id.spec.ts | 29 +-- .../agent-loop/tests/coverage-edges.spec.ts | 21 +- .../agent-loop/tests/interception.spec.ts | 62 +++--- packages/core/agent-loop/tests/loop.spec.ts | 85 ++++---- .../core/agent-loop/tests/properties.spec.ts | 11 +- .../agent-loop/tests/request-cache.e2e.ts | 7 +- .../tests/request-reconstruction.spec.ts | 22 +- packages/core/agent-loop/tests/resume.spec.ts | 85 ++++---- .../agent-loop/tests/review-fixes.spec.ts | 83 ++++---- .../agent-loop/tests/scope-lifecycle.spec.ts | 193 ++++++++---------- .../core/agent-loop/tests/tool-order.spec.ts | 9 +- .../core/agent-loop/tests/turn-stop.spec.ts | 19 +- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 28 ++- packages/core/agent/src/types.ts | 20 +- packages/core/agent/tests/agent.spec.ts | 29 +-- packages/core/session/src/index.ts | 7 +- packages/core/tools/tests/code-mode.spec.ts | 3 +- packages/core/tools/tests/scoped.spec.ts | 14 +- packages/fs/tool-fs/tests/fs-tools.e2e.ts | 4 +- packages/guard/repeat-tool-guard/README.md | 4 +- packages/guard/repeat-tool-guard/src/index.ts | 19 +- .../tests/repeat-tool-guard.spec.ts | 39 ++-- .../hooks/hooks-claude/tests/bridge.spec.ts | 31 +-- .../hooks/hooks-claude/tests/coverage.spec.ts | 73 +++---- .../hooks/hooks-codex/tests/bridge.spec.ts | 17 +- .../hooks/hooks-codex/tests/coverage.spec.ts | 73 +++---- packages/subagent/subagent-acp/src/run.ts | 4 +- .../tests/multi-subagent.spec.ts | 7 +- .../subagent-fork/tests/subagent-fork.spec.ts | 7 +- .../subagent/subagent-inprocess/src/index.ts | 7 +- .../tests/structured.spec.ts | 9 +- .../tests/subagent-inprocess.spec.ts | 7 +- .../subagent-spawn/tests/spawn.e2e.ts | 4 +- .../tests/subagent-spawn.spec.ts | 13 +- packages/subagent/subagent/src/index.ts | 7 +- packages/subagent/subagent/src/types.ts | 5 +- .../subagent/subagent/tests/service.spec.ts | 12 +- .../tool-subagent/tests/tool-subagent.spec.ts | 24 ++- packages/support/subagent-mock/src/index.ts | 4 +- .../subagent-mock/tests/subagent-mock.spec.ts | 6 +- .../todo/tool-todo/tests/integration.spec.ts | 9 +- .../todo/tool-todo/tests/tool-todo.spec.ts | 5 +- packages/ui/acp/src/index.ts | 3 - packages/ui/acp/tests/approval.spec.ts | 6 +- packages/ui/acp/tests/bridge.spec.ts | 24 +-- packages/ui/acp/tests/dispose.spec.ts | 43 ++-- packages/ui/acp/tests/edges.spec.ts | 3 +- packages/ui/acp/tests/load.spec.ts | 9 +- packages/ui/acp/tests/multi-session.spec.ts | 6 +- packages/ui/acp/tests/turns.spec.ts | 6 +- packages/ui/jsonrpc/src/server.ts | 2 - packages/ui/jsonrpc/tests/server.spec.ts | 27 +-- packages/ui/stdio-agent/README.md | 8 +- packages/ui/stdio-agent/src/index.ts | 23 +-- packages/ui/stdio-agent/src/stdio-chat.ts | 40 ++-- .../ui/stdio-agent/tests/readline.spec.ts | 2 +- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 16 +- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 60 +++--- packages/util/brand/README.md | 4 +- packages/util/brand/src/index.ts | 8 +- .../tool-workflow/tests/tool-workflow.spec.ts | 6 +- .../workflow-workerthread/src/runtime.ts | 4 +- .../tests/integration.spec.ts | 9 +- .../tests/source-worker.compat.spec.ts | 4 +- .../tests/workflow-workerthread.e2e.ts | 8 +- .../tests/workflow-workerthread.spec.ts | 20 +- packages/workflow/workflow/src/types.ts | 5 +- 105 files changed, 899 insertions(+), 948 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..94d613bc4e 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:250`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:249`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` @@ -117,8 +117,8 @@ Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt` export interface Config { /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { - /** Registry identity for the live agent. */ - id: AgentId + /** Stable config label used in logs and as the fresh combined-id prefix. */ + id: string /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -127,9 +127,9 @@ export interface Config { } ``` -Depends on: [`AgentId`](../packages/core/agent/src/index.ts) · [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) +Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:325`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -611,7 +611,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l ```ts config-catalog /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `model`/`resumeSessionId` configure the pre-created agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -620,7 +620,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l * `welcome` is the UI banner. */ export interface Config { - /** Model name for the `main` agent (must have a registered adapter). */ + /** Model name for the pre-created agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string @@ -635,7 +635,7 @@ export interface Config { /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ skills?: agentCore.SkillConfig /** - * If set, the `main` agent RESUMES this persisted session id instead of + * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`). */ @@ -645,7 +645,7 @@ export interface Config { Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts) +Source: [`packages/ui/stdio-agent/src/index.ts:64`](../packages/ui/stdio-agent/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index e2677e463a..1db5e85828 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -36,7 +36,7 @@ A UI plugin renders from the `session/event` feed (the assistant token stream as ```ts import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' declare function render(text: string): void declare function onUserInput(handler: (text: string) => void): void @@ -50,7 +50,7 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) } ``` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 5a3398f9a8..a5e018079a 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:304`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:331`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:605`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:593`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:438`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:426`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:456`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:444`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:348`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:473`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:537`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:525`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:381`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:369`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:345`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:552`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:540`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:570`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:558`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:588`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) ## `approval/*` @@ -317,7 +317,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:90`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:91`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -327,7 +327,7 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): void ``` -Source: [`packages/subagent/subagent/src/index.ts:66`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:67`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -337,7 +337,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:72`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:73`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -347,7 +347,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:82`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index bfb31749d5..4d162a55f5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -14,12 +14,12 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary Concrete ReactLoopAgent factory and driver service. ```ts cordis-catalog -create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent +create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:338`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` @@ -32,13 +32,13 @@ async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void enter(agent: Agent): () => void announce(agent: Agent): void -get(id: AgentId): Agent | undefined +get(id: SessionId): Agent | undefined list(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:203`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:199`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` @@ -218,7 +218,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:592`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:597`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` @@ -244,7 +244,7 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` -Source: [`packages/subagent/subagent/src/index.ts:123`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:124`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` diff --git a/docs/core-data-structures/approval.md b/docs/core-data-structures/approval.md index c5fa1fe13b..e8820ccfeb 100644 --- a/docs/core-data-structures/approval.md +++ b/docs/core-data-structures/approval.md @@ -6,7 +6,7 @@ Source: [`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approv ## Identity and outcome -Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call, session, or agent ids. +Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call or agent/session ids. ```ts type-equiv type ApprovalRequestId = Branded<'ApprovalRequestId'> diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index 51f7cb0696..df6c5ab16b 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -110,7 +110,7 @@ The `owner` token is the isolation key: the executor stores it but never interpr `stdin` and `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload on stdin and its `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` env. The model-facing `dsh-tool-bash` tool does not expose them as parameters — its request is built from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only — because a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), so duplicating them as tool params would be redundant. This is NOT a security boundary: the credential scrub in `dsh-bash-local` is what stops the harness's ambient secrets reaching a spawned command, and it works regardless of these fields (a model cannot read a value the scrub removed, and tool-call args are static JSON, never shell-evaluated). A guard test asserts the tool doesn't forward model `env`/`stdin` — to catch a future `...args` spread, not to defend a trust wall. `env` is merged AFTER the scrub so an explicit caller entry (a value it already holds) wins even on a credential-shaped name. See [the bash-stdin-env RFC](../rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). -Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`/`AgentId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. +Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. ## Foreground runs: `BashRunResult` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 168d727c8d..c6b74ed3c0 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -73,7 +73,7 @@ Two large discriminated unions are the ones consumers `switch` over most: **`Str ## Branded IDs -IDs that cross package boundaries are **branded** — structurally strings, but non-interchangeable at the type level (an `AgentId` can't be passed where a `CallId` is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings. +IDs that cross package boundaries are **branded** — structurally strings, but non-interchangeable at the type level (a `SessionId` cannot be passed where a `CallId` is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings. The `Branded` primitive lives in its own type-only package, [dsh-brand](../../packages/util/brand) (no runtime code, no harness-package dependency), so any package can brand the ids it owns without depending on an unrelated capability package (e.g. dsh-bash brands `BashTaskId`/`OwnerToken` via dsh-brand alone, never pulling in dsh-llm). @@ -83,7 +83,7 @@ Source: [`packages/util/brand/src/index.ts`](../../packages/util/brand/src/index type Branded = string & { readonly [BRAND]: B } ``` -The three core IDs: `CallId` (correlates a tool call with its result; dsh-llm), `SessionId` (dsh-session), `AgentId` (dsh-agent). Each is `Branded<'CallId'>` etc. plus a same-named factory function. Capability seams brand their own ids too — see `BashTaskId`/`OwnerToken` in [bash.md](bash.md). +The two core IDs are `CallId` (correlates a tool call with its result; dsh-llm) and `SessionId` (the shared live agent and durable session identity; dsh-session). Each is a `Branded<'…'>` plus a same-named factory function. Capability seams brand their own ids too — see `BashTaskId`/`OwnerToken` in [bash.md](bash.md). ## Content blocks and messages @@ -254,7 +254,7 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types ```ts type-equiv interface Agent { - readonly id: AgentId + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus @@ -353,7 +353,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. +`AgentStatus` is `'idle' | 'running' | 'disposed'`. `Agent.id` and `Agent.session.id` are the same branded `SessionId`. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. ## Interception decisions diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 5454f326b3..883c33020a 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -68,7 +68,7 @@ The handle the consumer holds after a provider has established a ready child. Th ```ts type-equiv interface SubagentRun { - readonly id: AgentId + readonly id: SessionId readonly result: Promise dispose(): Promise sendMessage?(content: ContentBlock[]): void diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index a7e2c8bb37..80389608cc 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:456`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:537`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:381`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:345`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:552`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:576`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `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) | @@ -31,10 +31,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `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) | | `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:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | -| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | +| `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) | +| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:67`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:73`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md index 42efb34774..fb272c5df9 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md +++ b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md @@ -21,4 +21,4 @@ In-session context injection (`context/message`, `steering/message`) renders as - Reasoning has a home without provider contortions. Multimodal content deliberately has NO core block type: the core set is limited to blocks every shipping path honors, and a multimodal feature adds its block type through the merge-extensible map in the same coordinated change that maps it in the adapters, surfaces it in the UI bridges, and prices it in compaction — see [the drop-image RFC](../simplification/2026-07-04-drop-image-content-block.md). Block cache hints likewise have no core field: DeepSeek prompt caching is automatic, so no shipping adapter can transmit a hint; a caching feature adds a `cache` field together with the adapter that honors it — see [the producer-less-variants RFC](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md). Assistant-prefix continuation (prefill) likewise has no request field: DeepSeek's chat-prefix completion is a Beta feature on a base URL neither shipping adapter targets, so a prefill feature adds `GenerateOptions.prefill` together with the adapter that honors it — see [the inert-request-knobs RFC](../simplification/2026-07-04-drop-inert-request-knobs.md). - Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests. -- IDs that cross package boundaries are branded (`CallId`, `SessionId`, `AgentId`) — nominal typing at zero runtime cost. +- IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost. diff --git a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md index 03d8a30b37..824e59a172 100644 --- a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md +++ b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md @@ -23,7 +23,7 @@ Key choices recorded here because they are durable, contested, and surprising: - **Append-only; a crashed turn is closed, never truncated.** Committed events — those at or below a flushed `turn/end` — are never rewritten. The loop only flushes at `turn/end`, so a crash can leave a durable log whose final turn never closed: real, fully-written events sit after the last `turn/end`. **A single turn can be huge in a long-horizon task** (many steps, large tool output spanning a long autonomous run), so discarding the interrupted turn would silently destroy a large amount of real work — truncating a turn is wrong. Instead, on reload `load` PRESERVES those events and CLOSES the orphaned turn by durably appending the minimal synthetic boundary events: an error `tool/result` for every `tool-call` the crash left unanswered, then a `step/end` if a step was still open, then a `turn/end` carrying the merge-extensible `{ kind: 'interrupted' }` reason (a marker that records the turn was cut short by a crash, not completed by the model — no loop ever emits it). The synthetic tool results matter for resume correctness: the loop logs the `assistant/message` (carrying the `tool-call` blocks) BEFORE running the tools, so a crash mid-tool leaves calls without results; `deriveMessages()` would then replay a dangling assistant tool-call, which every provider rejects as an invalid transcript on the next request. Answering each orphaned call with an error result keeps the rehydrated history valid. `load` returns the balanced log, so a resumed session is immediately usable. The ONLY thing discarded is a never-fully-written **torn tail fragment** — a final record whose bytes (JSONL) or row were never completely flushed; that fragment is not a valid event and is dropped before the synthetic closers are written. A parse error or `seq` gap in the COMMITTED region (at or before the last real `turn/end`) is genuine corruption and makes the session unloadable. - **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows. - **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) -- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and starts a fresh agent on the resumed id (NOT `${agentId}-session`). The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. +- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and registers the fresh agent under the exact resumed id. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 8171a05d30..5fe8224644 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -4,23 +4,23 @@ Status: implemented ## Problem -The harness already brands three identifiers — `CallId` (`packages/llm/llm/src/brand.ts`), `SessionId` (`packages/core/session/src/types.ts`), and `AgentId` (`packages/core/agent/src/types.ts`) — using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. +The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared agent/session `SessionId` (`packages/core/session/src/types.ts`) using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". -**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId`/`SessionId`/`AgentId` decay back to bare `string` at exactly the places confusion is most likely: the registry/store `Map` key types and most public method params. Representative sites: `SessionStore.store = new Map()` and `create`/`prepare(id?: string)`/`get(id: string)` (`packages/core/session/src/index.ts`); `AgentRegistry.store = new Map()` and `register`/`get(id: string)` (`packages/core/agent/src/index.ts`); `ToolPresenter.pending = new Map()` keyed by call id and `call(callId: string)`/`result(callId: string)` (`packages/ui/acp/src/index.ts`); the ACP session-id surface beyond the store map — `SessionRecord.sessionId: string`, `bySession = new WeakMap()`, `loadingIds = new Set()`, `requireSession(sessionId: string)`, and the exported `streamSessionEventUpdate(sessionId: string, …)` (`packages/ui/acp/src/index.ts`); and the persistence coordinator's `Map` keyed by session id (`packages/session-persistence/session-persistence/src/coordinator.ts`). A brand that is dropped at the `Map` key buys nothing on lookups — the value of the existing brands is partly unrealized. +**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. ## Decision A type-only change. Brands are zero-cost casts; nothing about runtime behavior, serialization, comparison, or the wire format changes. The work is in three parts, all honoring the existing "not every string" policy. -- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId`/`AgentId` already do. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). +- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). - **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) -- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `get(id: SessionId)`, `Map`, `Map`, the ACP `SessionRecord.sessionId: SessionId` surface, the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on the struct fields. +- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. Illustrative shape (the factory pattern is identical to the three existing brands): @@ -58,7 +58,7 @@ Kept deliberately narrow per the "not every string needs a brand" policy. Each o ## Verification -The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`AgentId`/`BashTaskId`) is keyed by bare `string` — `Map` keys, `WeakMap` value slots, `Set` membership (the ACP `bySession`/`loadingIds`), public method params, and exported signatures (`streamSessionEventUpdate`) all take the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. +The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`BashTaskId`) is keyed by bare `string`; public method params and exported signatures keep the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md index f0ab95ca80..f785851237 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md +++ b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md @@ -24,7 +24,7 @@ This is the foundational change in a stack that adds a Hooks subsystem; it estab **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit. -**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) was migrated to render boundaries from `session/event`, recovering the short agent label from an `agent/created`→id map. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). +**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) renders boundaries from `session/event` while retaining its live target object for the fixed `main` label. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md b/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md index dcff4d3220..15477e023a 100644 --- a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md +++ b/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md @@ -60,8 +60,7 @@ The ordinary contributor pattern is to register the complete local world during ```js const handle = await ctx.agents.create({ - agentId: AgentId('reviewer'), - sessionId: SessionId('reviewer-session'), + sessionId: SessionId('reviewer'), agentOptions: { model: 'model-name' }, setup(agentCtx) { agentCtx.systemPrompt.section({ diff --git a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md b/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md index 9d0446dcad..6961883318 100644 --- a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md +++ b/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md @@ -12,11 +12,10 @@ The harness already has every seam the pi extension uses, and better ones: [the The guard is a loop-hygiene plugin, not a model-facing tool: it never appears in the tool list, never vetoes or rewrites a call, and adds exactly one behavior — it watches each agent's stream of tool calls, counts runs of consecutive calls to the same tool with identical canonicalized arguments, and at configured run lengths injects an escalating advisory reminder telling the model to stop repeating itself, re-read the last result, and either change approach or conclude. The purpose is to break unproductive loops within a few wasted steps instead of letting them run to the turn's natural end — while leaving the decision (retry differently, gather more evidence, or finish) entirely with the model, so a legitimately repeated call is delayed by nothing and blocked by nothing. -The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers three listeners and holds all state in plugin-local maps keyed by `AgentId` — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish. +The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers two listeners and holds state in a `WeakMap` keyed by the live `Agent` object — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish; weak object keys also make a disposal-only cleanup listener unnecessary. - **`tools/post-execute` (waterfall)** — the one detection point. The listener receives `(exec, result)` together, so counting and reminder delivery need no cross-event pending map (the pi extension needs one only because its `tool_call`/`tool_result` hooks are separate events). It always delegates via `next()` and, when a threshold is hit, folds a reminder onto the downstream decision's `additionalContext` — the observe-and-enrich posture [the hooks bridges](2026-06-30-hook-bridges.md) already use, honoring the waterfall contract. Counting happens here rather than in `tools/pre-execute` because post-execute also runs for denied calls (`ToolRegistry.execute` routes a deny through the same pipeline), and a model hammering a denied call is exactly the loop worth breaking. - **`agent/prompt-submit` (waterfall)** — pure reset hook: delegate via `next()`, clear the submitting agent's chain. A user interjection changes the context; repetition across it is not a loop. -- **`agent/status` (emit)** — on `disposed`, drop the agent's state, bounding the maps over harness lifetime. ### Detection semantics @@ -25,7 +24,7 @@ The chain key is `(tool name, canonical arguments)`; a call identical to the pre Two deliberate rules, both documented in [the package README](../../../../packages/guard/repeat-tool-guard/README.md) because they are behavior a reader would otherwise guess at: - **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful — bookkeeping tools interleaved into a loop must not launder it — and it is the pi extension's (undocumented) semantics, kept on purpose and written down. -- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller (tests, non-loop consumers) has no model to remind and no `AgentId` to key on. +- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller (tests, non-loop consumers) has no model to remind and no live agent object to key on. ### Reminder delivery diff --git a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md b/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md index dbef22f3a3..f4b49281ea 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md +++ b/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md @@ -21,9 +21,9 @@ This duplication is not free. Every lifecycle change had to update the session e Make `session/event` the single live boundary/transcript stream. Consumers that render turns, tool calls, tool results, assistant messages, and durable boundaries subscribe to `session/event` and derive their UI from the same event vocabulary persistence uses. -The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle (or its short id) at a boundary keeps a small map from session id to agent id built from `agent/created`/`agent/disposed`; `dsh-ui-stdio` does exactly this to label its `[ turn N]` header, since the `turn/start` session event carries only the turn number. The canonical record remains the event-sourced session log. +The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle at a boundary retains the live target object from `agent/created`/`agent/disposed` and compares its session directly; `dsh-ui-stdio` uses this to label the app-owned agent's `[main turn N]` header while other sessions render their durable id. The canonical record remains the event-sourced session log. -The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it was migrated to `session/event` + the id map, and the turn mirrors were removed too. +The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it reads `session/event` and retains only its live target object. ## Scope: what is and isn't removed @@ -38,8 +38,8 @@ RETAINED — NOT durable-boundary mirrors, so out of scope for this decision: ## Alternatives considered - **Bundling `agent/steering` into the removal** — the original proposal's shape; narrowed out as scope creep: it mirrors the durable `steering/message` control record, not a boundary, and was removed by [its own later decision](2026-07-04-remove-agent-steering-mirror.md) (as was `agent/stream-chunk`, by [the stream-chunk-mirror RFC](2026-07-02-remove-stream-chunk-mirror.md)). -- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` + the id map instead. +- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` plus its live target object instead. ## Consequences -A plugin can no longer observe turn/step boundaries from a convenient `Agent`-first event. It must either subscribe to `session/event` or maintain a session-to-agent association. That is an acceptable trade: boundary consumers should not depend on a second event feed that can drift from the durable log. +A plugin can no longer observe turn/step boundaries from a convenient `Agent`-first event. It subscribes to `session/event` and, if it needs the live object, resolves the shared id through `ctx.agents` or retains the object it already owns. That is an acceptable trade: boundary consumers should not depend on a second event feed that can drift from the durable log. diff --git a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index 3de3c7d9be..911d28cf1f 100644 --- a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -14,7 +14,7 @@ Two sibling provider packages, structural variants of the ACP backend, plus one - `@deepseek-ai/dsh-subagent-codex` — spawns `codex app-server` and drives one thread/turn over its JSON-RPC-over-stdio protocol with a hand-rolled newline-JSON client (~200–300 lines) in the package. - `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`SENSITIVE_ENV_PATTERN`/`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. -Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = AgentId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. +Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = SessionId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. ## Verified interface facts (pinned versions) diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md index 1a69f9ebe6..6e3eea1515 100644 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md @@ -16,13 +16,13 @@ Session itself repeats the same fact as `Session.id` and `Session.header.id`. Co Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. -The config-driven path must first settle its currently hidden resume-or-create policy. Today it uses a stable agent label and fresh UUID-suffixed session id to avoid colliding with a durable log on the next run. Under unification it must deliberately resume the fixed id, mint a fresh combined id, or expose an explicit policy; implementation must not pick silently. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. ## Alternatives considered -**Keep separate routing and log identities.** The config-driven loop uses a stable configured agent id with a fresh UUID session on each fresh process start. That is a real use of the distinction: a stable routing/display label plus a new durable conversation. Unification can proceed only after choosing whether this path resumes a fixed identity, mints a combined per-run identity, or exposes the policy explicitly. If the stable label is a required product contract, reject this proposal rather than hiding it in another map. +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. ## Acceptance criteria @@ -35,4 +35,4 @@ The config-driven path must first settle its currently hidden resume-or-create p ## Risks -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. The config restart decision is blocking, not mechanical. If separate routing identity is a real requirement, reject this RFC and retain the current caller-supplied pair plus final-entry arbitration. +This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 512688d88d..22446f0dc3 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -4,11 +4,12 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -72,7 +73,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-')) ctx = await codeModeHarness(workdir) - const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/coding-task.e2e.ts b/examples/coding-agent/tests/coding-task.e2e.ts index ce716bdb2c..e1ae9804ac 100644 --- a/examples/coding-agent/tests/coding-task.e2e.ts +++ b/examples/coding-agent/tests/coding-task.e2e.ts @@ -4,8 +4,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The swebench-style smoke test: a real model fixes a real bug in a temp @@ -54,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test expect(before.status).not.toBe(0) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-task'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/coding-agent/tests/compaction.e2e.ts index 854cf49d2a..a0e71aacc4 100644 --- a/examples/coding-agent/tests/compaction.e2e.ts +++ b/examples/coding-agent/tests/compaction.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The compaction smoke test: a real model runs a multi-step bash task with a @@ -64,7 +64,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa }, persistenceRoot: join(workdir, '.sessions'), }) - const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/full-loop.e2e.ts b/examples/coding-agent/tests/full-loop.e2e.ts index 8718139ced..9a01713222 100644 --- a/examples/coding-agent/tests/full-loop.e2e.ts +++ b/examples/coding-agent/tests/full-loop.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The first place a REAL model meets the REAL bash tool: the cheap canary @@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas it('runs a bash command on request and reports its output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-')) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }]) await waitForIdle(ctx, agent) diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 70382b4beb..48e135ad92 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -4,7 +4,6 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' @@ -40,7 +39,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // log on disk survives. ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root }) const first = (await ctx.agents.create({ - agentId: AgentId('resume-1'), sessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent @@ -54,7 +52,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // run 1's exchange as conversation history. ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root }) const resumed = (await ctx.agents.resume({ - agentId: AgentId('resume-2'), resumeSessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent diff --git a/examples/coding-agent/tests/todo-write.e2e.ts b/examples/coding-agent/tests/todo-write.e2e.ts index 698fbd9e9e..7f3c3c1e4a 100644 --- a/examples/coding-agent/tests/todo-write.e2e.ts +++ b/examples/coding-agent/tests/todo-write.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * A REAL model drives the REAL todo_write tool: verify the WORLD (the session @@ -26,7 +26,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a it('appends a todo/write event with the model-produced task list', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-')) ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Use the todo_write tool to record a plan of exactly two steps: first ' diff --git a/examples/cordis-agent/tests/cordis-tools.e2e.ts b/examples/cordis-agent/tests/cordis-tools.e2e.ts index 388fcb0058..ffe9a290eb 100644 --- a/examples/cordis-agent/tests/cordis-tools.e2e.ts +++ b/examples/cordis-agent/tests/cordis-tools.e2e.ts @@ -1,8 +1,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import type { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' -import { AgentId } from '@deepseek-ai/dsh-agent' import { cordisHarness, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * With-key smoke for the self-referential cordis tools: a REAL model drives @@ -38,7 +38,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('mounts a status listener whose tagged output actually fires, then unmounts it', async () => { ctx = await cordisHarness() const log = vi.spyOn(console, 'log').mockImplementation(() => {}) - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -66,7 +66,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('builds itself a reverse_text tool and actually calls it', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -114,7 +114,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('composes two mounts through provide/inject, and unmounting the provider parks the consumer', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index a22e86bd99..3ab3ae6628 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { BashTaskId } from '@deepseek-ai/dsh-bash' @@ -74,7 +75,7 @@ describe('bash tool through the agent loop', () => { textResponse('The command printed integration-ok.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-fg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-fg'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) @@ -106,7 +107,7 @@ describe('bash tool through the agent loop', () => { textResponse('It failed with code 9.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-exit'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-exit'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) @@ -128,7 +129,7 @@ describe('bash tool through the agent loop', () => { let taskId = '' const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-bg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-bg'), { model: 'mock' }) // Capture the generated id so the deterministic fixture is checked against // the real executor instead of silently assuming it. diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index 12b4a53958..c68c445f0a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -57,7 +57,7 @@ async function setup() { const fakeAgentDisposers = new Map Promise | void)[]>() function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent { // The registry KEY (agent.id) is deliberately DIFFERENT from the session - // token (session.header.id) — a config agent has `agentId !== sessionId`. The + // token (session.header.id), which is also the agent's durable id. The // owner token IS the session id, so the notice path must find the agent by // `session.header.id`, NOT the registry key. Using distinct values here makes // the test fail if a regression matched on the wrong field (a same-value fake diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index bb77e44a9c..52a2ecd134 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -3,11 +3,12 @@ import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' @@ -119,7 +120,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () it('the head checkpoint the loop lands is a balanced cut on both sides', async () => { const { ctx } = await harness(8) try { - const agent = ctx.agentLoop.create(AgentId('repro'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('repro'), { model: 'mock' }) agent.send([{ type: 'text', text: 'do a long multi-step task' }]) await waitForIdle(ctx, agent) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 3d6ade301f..5721bd97d9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -56,7 +56,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'agentLoop', summary: 'Concrete ReactLoopAgent factory and driver service.', methods: [ - 'create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', + 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', ], @@ -71,7 +71,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'register(agent: Agent): () => void', 'enter(agent: Agent): () => void', 'announce(agent: Agent): void', - 'get(id: AgentId): Agent | undefined', + 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', ], }, @@ -488,7 +488,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ export const TYPE_API: readonly TypeApiEntry[] = [ { name: 'Agent', - declaration: 'export interface Agent {\n readonly id: AgentId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', + declaration: 'export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', }, { name: 'AgentFactory', @@ -498,10 +498,6 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AgentHandle', declaration: 'export interface AgentHandle {\n agent: Agent;\n dispose(): Promise;\n}', }, - { - name: 'AgentId', - declaration: 'export type AgentId = Branded<\'AgentId\'>;', - }, { name: 'AgentOptions', declaration: 'export interface AgentOptions {\n model?: string;\n}', @@ -644,7 +640,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CreateAgentOptions', - declaration: 'export interface CreateAgentOptions {\n readonly agentId: AgentId;\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface CreateAgentOptions {\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'CreateSessionOptions', @@ -756,7 +752,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'ResumeAgentOptions', - declaration: 'export interface ResumeAgentOptions {\n readonly agentId: AgentId;\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface ResumeAgentOptions {\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'SandboxEnforcement', @@ -868,7 +864,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SubagentRun', - declaration: 'export interface SubagentRun {\n readonly id: AgentId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', + declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', }, { name: 'SubagentStartRequest', diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 94331df7c0..0d4c6c5c18 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -51,7 +52,7 @@ describe('cordis tools through the agent loop', () => { textResponse('Done.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-cordis'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-cordis'), { model: 'mock' }) agent.send([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }]) await waitForIdle(ctx, agent) diff --git a/packages/core/agent-core/README.md b/packages/core/agent-core/README.md index 33cd0faddd..accbf66a7c 100644 --- a/packages/core/agent-core/README.md +++ b/packages/core/agent-core/README.md @@ -43,7 +43,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-core' // so validation and defaulting can never drift from the owners. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates one under the `main` config label; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. ## Why a code bundle, not a shared YAML include diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index 855bb28d49..058191c88f 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -6,8 +6,10 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as agentCore from '../src/index.ts' -import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' + import type { Message } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' async function composePrefix(ctx: Context, cwd: string): Promise { const agent = { session: { header: { cwd } } } as unknown as Agent @@ -102,16 +104,18 @@ describe('dsh-agent-core bundle', () => { it('defaults the agents list to empty (no pre-created agents)', async () => { const ctx = await mount() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.get(SessionId('main'))).toBeUndefined() await ctx.fiber.dispose() }) it('forwards a pre-created agent to the loop and the persona to system-prompt', async () => { const ctx = await mount({ - agents: [{ id: AgentId('main'), model: 'mock' }], + agents: [{ id: 'main', model: 'mock' }], persona: 'You are main.', }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + const agent = ctx.get('agents')?.list()[0] + expect(agent?.id).toBe(agent?.session.id) + expect(agent?.id).toMatch(/^main-session-/) const assembly = await ctx.get('systemPrompt')!.assemble() expect(assembly.sections.find(s => s.name === 'deployment:persona')?.text).toBe('You are main.') await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 6832800d2e..f40577bb95 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -12,14 +12,14 @@ Creation and resume are one rollback-covered transaction: construct a private se The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createAgent(ownerCtx, options)` and `resume(ownerCtx, options)` receive caller ownership explicitly, while the factory keeps its own dependency context for `sessions`/`llm`/`tools`/`systemPrompt`; this lets a caller inject only `agents` without shrinking the new agent's service surface. Caller unload, handle disposal, or provider unload converge on one memoized quiescence boundary. Provider shutdown waits both resource teardown and the public create/resume wrapper that observed deactivation, so no continuation can publish after dependencies disappear. -IDs are caller-chosen and assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same agent or session id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; IDs become reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. +Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: string, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create, used directly by programs and by `cordis.yml`-configured agents. It creates a fresh per-run session id `${id}-session-` with optional metadata; the uuid avoids colliding with a prior durable log. Each call is a new session (a deliberate demo simplification — a real resume-or-create policy is a TODO). Disposed with the calling fiber. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): -- `ctx.agents.create({ agentId, sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise` — programmatic create on a caller-supplied `sessionId`, NOT `${id}-session`. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. -- `ctx.agents.resume({ agentId, resumeSessionId, agentOptions?, setup?, signal? }): Promise` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. The live session id is the resumed id; turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. +- `ctx.agents.create({ sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise` — programmatic create under the caller-supplied shared id. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. +- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle). For a programmatic agent, the handle holder is the only consumer-facing teardown capability; AgentLoop provider unload is the independent structural teardown edge, not another handle exposed to application code. @@ -32,7 +32,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo ```ts interface Config { agents: Array<{ - id: string // required + id: string // required stable label; prefixes fresh combined ids model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index ff66f942be..d54baab597 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -8,11 +8,11 @@ import type { Context } from 'cordis' import { agentEvents } from '@deepseek-ai/dsh-agent' -import type { AgentId, AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' +import type { AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { deepFreeze } from '@deepseek-ai/dsh-llm' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' -import { snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session' +import { snapshotJsonValue, type Session, type SessionId } from '@deepseek-ai/dsh-session' import { Inbox, type InboxMessage } from './inbox.ts' import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts' @@ -59,7 +59,7 @@ export interface PreparedReactLoopAgent { * @returns the agent and closures bound only to that exact instance. */ export function prepareReactLoopAgent( - ctx: Context, id: AgentId, options: AgentOptions, session: Session, + ctx: Context, id: SessionId, options: AgentOptions, session: Session, ): PreparedReactLoopAgent { if (claimedDriverSessions.has(session)) { throw new Error(`session "${session.id}" already has a concrete agent driver`) @@ -163,7 +163,7 @@ export class ReactLoopAgent implements Agent { constructor( private loopCtx: Context, - public readonly id: AgentId, + public readonly id: SessionId, public readonly options: AgentOptions, public readonly session: Session, ) { diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 4ad4779176..33276c01f8 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -14,7 +14,6 @@ import { agentEvents } from '@deepseek-ai/dsh-agent' import type { AgentFactory, AgentHandle, - AgentId, AgentOptions, CreateAgentOptions, ResumeAgentOptions, @@ -68,7 +67,7 @@ class FactoryOwnership { } /** Build the public cancellation error while preserving a caller-supplied cause. */ -function signalAbortError(id: AgentId, signal: AbortSignal): Error { +function signalAbortError(id: SessionId, signal: AbortSignal): Error { if (signal.reason instanceof Error) return signal.reason return new Error(`agent "${id}" creation aborted`, { cause: signal.reason }) } @@ -108,7 +107,7 @@ class AgentCreationTransaction { private readonly loopCtx: Context, private readonly ownerCtx: Context, private readonly ownership: FactoryOwnership, - readonly id: AgentId, + readonly id: SessionId, signal?: AbortSignal, ) { ownerCtx.fiber.assertActive() @@ -325,8 +324,8 @@ declare module 'cordis' { export interface Config { /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { - /** Registry identity for the live agent. */ - id: AgentId + /** Stable config label used in logs and as the fresh combined-id prefix. */ + id: string /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -363,13 +362,13 @@ export class AgentLoop extends Service implements AgentFactory { for (const { id, cwd, resumeSessionId, ...options } of config.agents) { if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(id, options, cwd === undefined ? {} : { cwd }) + const sessionId = SessionId(`${id}-session-${randomUUID()}`) + this.create(sessionId, options, cwd === undefined ? {} : { cwd }) continue } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { - agentId: id, resumeSessionId, agentOptions: options, }).catch((error: unknown) => { @@ -382,19 +381,19 @@ export class AgentLoop extends Service implements AgentFactory { } /** - * Create an agent on a fresh per-run session, owned by the accessing fiber. - * Constructor-driven config calls use the loop fiber itself. - * @param id - agent registry id. + * Create an agent and session under one caller-supplied identity, owned by + * the accessing fiber. Constructor-driven config calls mint a fresh combined + * id before entering this boundary. + * @param id - shared agent/session identity. * @param options - concrete loop options. * @param meta - optional fresh-session workspace metadata. * @returns the published running agent. */ - create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { + create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { - const sessionId = SessionId(`${id}-session-${randomUUID()}`) - const session = loopCtx.sessions.prepare(sessionId, { meta }) + const session = loopCtx.sessions.prepare(id, { meta }) const agent = transaction.prepare(options, session) transaction.publish('startup') return agent @@ -417,7 +416,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.sessionId, options.signal, ) try { @@ -461,7 +460,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.resumeSessionId, options.signal, ) try { diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7f65bbc5f3..56d6489fbe 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -1,6 +1,5 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' @@ -53,10 +52,10 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) - const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('first-driver'), { model: 'mock' }, session) expect(() => prepared.agent.ctx).toThrow('context is not bound') - expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { model: 'mock' }, session)) + expect(() => prepareReactLoopAgent(ctx, SessionId('second-driver'), { model: 'mock' }, session)) .toThrow('already has a concrete agent driver') await prepared.dispose() @@ -66,11 +65,11 @@ describe('ReactLoopAgent', () => { it('borrows caller options and binds its scoped context exactly once', async () => { const ctx = await harness(new MockAdapter([textResponse('unused')])) const options = { model: 'mock' } - const agent = ctx.agentLoop.create(AgentId('owned-bindings'), options) + const agent = ctx.agentLoop.create(SessionId('owned-bindings'), options) expect(agent.options).toBe(options) expect(agent.id).toBe('owned-bindings') - expect(agent.session.id).toMatch(/^owned-bindings-session-/) + expect(agent.session.id).toBe(agent.id) expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/) await ctx.fiber.dispose() @@ -81,7 +80,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -96,7 +95,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -111,7 +110,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -124,7 +123,7 @@ describe('ReactLoopAgent', () => { it('inject() decides enclosure from the LOG (open turn), not agent status', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Simulate an OPEN turn in the log while the agent is idle (status is not a // reliable open-turn signal). inject must append into that open turn, NOT @@ -150,7 +149,7 @@ describe('ReactLoopAgent', () => { // A persistence-like listener whose flush rejects. ctx.on('session/flush', () => { throw new Error('disk gone') }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // inject() is synchronous and fires a fire-and-forget flush; a rejecting // flush must be contained (logged), never thrown into the caller. @@ -163,7 +162,7 @@ describe('ReactLoopAgent', () => { it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) @@ -183,7 +182,7 @@ describe('ReactLoopAgent', () => { it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) // Session contains a throwing post-commit turn/end observer. The accepted @@ -206,7 +205,7 @@ describe('ReactLoopAgent', () => { // A non-Error rejection exercises the String() normalization branch. ctx.on('session/flush', () => { throw 'disk gone' }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: { turn: number; step: number; message: string }[] = [] ctx.on('agent/error', (_a, turn, step, error) => void errors.push({ turn, step, message: error.message })) @@ -225,7 +224,7 @@ describe('ReactLoopAgent', () => { it('idle inject() with a non-serializable source opens no turn (nothing to close)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A non-serializable source makes the turn/start append throw BEFORE the // event is pushed (Session.append validates before push), so NO turn opens. @@ -240,7 +239,7 @@ describe('ReactLoopAgent', () => { it('steer() when idle falls through to send() and starts a turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // steer while idle delegates to send agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } }) @@ -258,7 +257,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('bare'), { model: 'mock' }, session) const { agent } = prepared // Start the loop to get the disposer; the agent waits for messages @@ -280,7 +279,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('pre-start-dispose')) - const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('pre-start-dispose'), { model: 'mock' }, session) await prepared.dispose() expect(prepared.agent.status).toBe('disposed') @@ -294,7 +293,7 @@ describe('ReactLoopAgent', () => { it('setting the same status does not emit agent/status again', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const statuses: string[] = [] ctx.on('agent/status', (subject, status) => { @@ -313,7 +312,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() resolves immediately when the agent is not running', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Fresh agent is idle — whenIdle() takes the not-running fast path and // resolves without subscribing. await must not hang. @@ -324,7 +323,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() waits for queued work that has not flipped status yet', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'queued') let settled = false @@ -342,8 +341,8 @@ describe('ReactLoopAgent', () => { it('whenIdle() awaits the running→idle transition, ignoring other subjects/running events', async () => { const adapter = new MockAdapter([textResponse('ok'), textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) // Drive `agent` into `running`, then await whenIdle() — it subscribes to // agent/status and resolves on the first transition out of running. @@ -379,7 +378,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter(['hang']) ctx.llm.registerAdapter(['mock'], adapter) const session = ctx.sessions.create(SessionId('bare')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('bare'), { model: 'mock' }, session) const { agent } = prepared prepared.markPublished() const dispose = prepared.startDriver() @@ -404,7 +403,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -425,7 +424,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -446,7 +445,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'running') throw new Error('bad running listener') }) @@ -464,7 +463,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'idle') throw new Error('bad idle listener') }) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 56376b69a7..82b1f6c58c 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -16,7 +16,8 @@ import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -57,7 +58,7 @@ describe('Agent.cancel()', () => { it('cancel() on an idle agent with nothing queued is a no-op; the next prompt runs (F2 leak guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // The loop is parked at the idle wait with nothing queued. A cancel here must // NOT arm the marker — otherwise the next legitimate prompt would be dropped. @@ -74,7 +75,7 @@ describe('Agent.cancel()', () => { it('pre-step cancel drops the about-to-start turn (no turn is opened)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // send() queues synchronously (status still idle, loop microtask not yet // resumed). Cancel in that pre-step window: the queued turn must not run. @@ -93,7 +94,7 @@ describe('Agent.cancel()', () => { it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => { const adapter = new MockAdapter([textResponse('x')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Queue work, then register a whenIdle() waiter while in the pre-step window // (status idle, hasQueued true) — it does NOT take the fast path. Then cancel. @@ -114,7 +115,7 @@ describe('Agent.cancel()', () => { it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -131,7 +132,7 @@ describe('Agent.cancel()', () => { it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -147,7 +148,7 @@ describe('Agent.cancel()', () => { it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => { const adapter = new MockAdapter(['hang', textResponse('second reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // First turn hangs; cancel it mid-step. send(agent, 'first') @@ -169,7 +170,7 @@ describe('Agent.cancel()', () => { it('cancel from inside the agent/session-prefix waterfall drops the step (prefix-composition window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Prefix composition runs before the pre-step seam on the instance's first // step; a cancel landing inside it must drop the about-to-start step @@ -203,7 +204,6 @@ describe('Agent.cancel()', () => { ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('a-dispose-prefix'), sessionId: SessionId('dispose-prefix-session'), agentOptions: { model: 'mock' }, }) @@ -232,7 +232,7 @@ describe('Agent.cancel()', () => { it('a cancel-interrupted prefix composition is discarded: the next send recomposes and ships the fresh prefix (stale-cache guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // The first composition is interrupted mid-waterfall and — like an // abort-aware listener bailing on a firing signal — contributes nothing. @@ -266,7 +266,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous turn/start session-event listener drops the step (step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A turn/start listener fires right after turn/start is appended, BEFORE any // AbortController is installed for the step. Cancelling there must still drop @@ -295,7 +295,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous step/start session-event listener drops the step (post-step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A step/start session-event listener fires AFTER step/start is appended // (and after the pre-step seam), so cancelling there lands in the SECOND @@ -334,7 +334,6 @@ describe('Agent.cancel()', () => { ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('a-dispose-step-start'), sessionId: SessionId('dispose-step-start-session'), agentOptions: { model: 'mock' }, }) @@ -366,7 +365,7 @@ describe('Agent.cancel()', () => { // `aborted` and run NO second step. const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 const reasons: TurnEndReason[] = [] @@ -398,7 +397,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous agent/status(running) listener drops the turn (window 2)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // setStatus('running') emits agent/status SYNCHRONOUSLY, so a running // listener can cancel in the gap between the loop's pre-step check and @@ -428,7 +427,7 @@ describe('Agent.cancel()', () => { // so whenIdle() resolves on the replacement turn's running→idle, not before. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let replaced = false const dispose = ctx.on('agent/status', (subject, status) => { @@ -458,7 +457,7 @@ describe('Agent.cancel()', () => { // settle (the quiescence contract), not resolve before B's first event. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'A') // queues A (status still idle, loop microtask pending) const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path) @@ -478,7 +477,7 @@ describe('Agent.cancel()', () => { it("cancel clears the turn's steering — it is not re-enqueued as a fresh turn", async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 07d6cd9e9b..134ea68c32 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -7,7 +7,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -32,7 +33,7 @@ describe('config-driven session id', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) const loopFiber = await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }], + agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('deferred') }], }) const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)') @@ -53,11 +54,13 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) - await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx1.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) - const a1 = ctx1.agents.get(AgentId('cfg')) as ReactLoopAgent + const a1 = ctx1.agents.list()[0] as ReactLoopAgent + expect(a1.id).toBe(a1.session.id) expect(a1.session.id).toMatch(idPattern) + expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined() a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -70,10 +73,11 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) - const a2 = ctx2.agents.get(AgentId('cfg')) as ReactLoopAgent + const a2 = ctx2.agents.list()[0] as ReactLoopAgent + expect(a2.id).toBe(a2.session.id) expect(a2.session.id).toMatch(idPattern) expect(a2.session.id).not.toBe(a1.session.id) a2.send([{ type: 'text', text: 'q2' }], { source: { kind: 'user' } }) @@ -96,7 +100,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) - const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -110,7 +114,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -118,11 +122,12 @@ describe('config-driven session id', () => { let resumed: ReactLoopAgent | undefined for (let i = 0; i < 50 && !resumed; i++) { await new Promise(r => setTimeout(r, 5)) - resumed = ctx2.agents.get(AgentId('main')) as ReactLoopAgent | undefined + resumed = ctx2.agents.get(SessionId('sticky-1')) as ReactLoopAgent | undefined } expect(resumed).toBeDefined() // The live session id IS the resumed id (NOT a fresh ${id}-session-), // and the prior turn's user message is in the derived history. + expect(resumed!.id).toBe(SessionId('sticky-1')) expect(resumed!.session.id).toBe('sticky-1') const derived = resumed!.session.deriveMessages() expect(JSON.stringify(derived)).toContain('remember me') @@ -138,16 +143,16 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) + await ctx.plugin(AgentLoop, { agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) await ctx.plugin(SessionPersistenceJsonl, { root }) ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('x')])) // The deferred resume fails (no such session on disk). It must be contained: - // a warning is logged, no 'main' agent is registered, and the app stays up. + // a warning is logged, no agent is registered, and the app stays up. await new Promise(r => setTimeout(r, 200)) - expect(ctx.agents.get(AgentId('main'))).toBeUndefined() + expect(ctx.agents.list()).toEqual([]) expect(warn).toHaveBeenCalledWith(expect.stringContaining('config-driven resume of "does-not-exist" failed')) warn.mockRestore() await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 23e5670f85..4e82e398f1 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm' -import SessionStore, { TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -40,7 +41,7 @@ describe('inbox acceptance', () => { it('rejects non-serializable content or source synchronously before notification or enqueue', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let queued = 0 ctx.on('agent/queued', () => { queued += 1 }) @@ -80,7 +81,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: typeof args === 'string' ? `raw: ${args}` : JSON.stringify(args) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -113,7 +114,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: 'ran with empty args' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -126,7 +127,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from pre-commit dispatch validation via the runLoop backstop', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('internal/dispatch', (_mode, name, args) => { @@ -152,7 +153,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => { const adapter = new MockAdapter([textResponse('irrelevant')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, _next) => { @@ -180,7 +181,7 @@ describe('coded error data emission', () => { it('errorData includes code when a coded error (LlmError) is thrown from a plugin', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, next) => { @@ -214,7 +215,7 @@ describe('disposed vs aborted branching', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -242,7 +243,7 @@ describe('structured tool error propagation (the runtime-validation RFC, part 2) textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'boom', description: 'always fails', diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 1ec48e553f..8c95be0d82 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -1,15 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { - AgentId, - type ContinuationDecision, - type PromptDecision, - type SessionStartSource, -} from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -57,7 +53,7 @@ describe('agent/prompt-submit', () => { it('allow (default via next) records the user/message unchanged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const seen: string[] = [] ctx.on('agent/prompt-submit', async (_agent, content, _source, next) => { @@ -76,7 +72,7 @@ describe('agent/prompt-submit', () => { it('allow with content REWRITES the prompt before it is recorded', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'allow', content: [{ type: 'text', text: 'REWRITTEN' }] })) @@ -94,7 +90,7 @@ describe('agent/prompt-submit', () => { it('allow with additionalContext injects a separate context/message into the turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -127,7 +123,7 @@ describe('agent/prompt-submit', () => { // elsewhere; this asserts they see each other's effects on the same turn). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -157,7 +153,7 @@ describe('agent/prompt-submit', () => { it('block drops the (only) prompt → zero-step turn ends rejected, model never called', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'block', reason: 'blocked by policy' })) @@ -194,7 +190,7 @@ describe('agent/prompt-submit', () => { // vetoed prompt and its reason would vanish from the log entirely. const adapter = new MockAdapter([textResponse('ran once')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise => { const text = content.map(b => (b.type === 'text' ? b.text : '')).join('') @@ -230,7 +226,7 @@ describe('agent/prompt-submit', () => { it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => { const adapter = new MockAdapter([textResponse('after')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threw = false ctx.on('agent/prompt-submit', async () => { @@ -263,7 +259,7 @@ describe('agent/session-start', () => { const sources: SessionStartSource[] = [] ctx.on('agent/session-start', (_agent, source) => void sources.push(source)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // fires synchronously at create, before any turn expect(sources).toEqual(['startup']) expect(events(agent).some(e => e.type === 'turn/start')).toBe(false) @@ -282,7 +278,7 @@ describe('agent/session-start', () => { agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } }) }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -300,8 +296,8 @@ describe('agent/session-start', () => { ctx.on('agent/session-start', () => { throw new Error('session-start hook broke') }) // create must not throw — the listener error is contained/logged - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - expect(agent.id).toBe(AgentId('a1')) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + expect(agent.id).toBe(SessionId('a1')) // and the agent still runs send(agent, 'go') @@ -314,8 +310,8 @@ describe('agent/session-prefix', () => { it('dispatches to global and matching agent-scope listeners only', async () => { const adapter = new MockAdapter([textResponse('a done'), textResponse('b done')]) const ctx = await harness(adapter) - const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { model: 'mock' }) - const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { model: 'mock' }) + const agentA = ctx.agentLoop.create(SessionId('prefix-a'), { model: 'mock' }) + const agentB = ctx.agentLoop.create(SessionId('prefix-b'), { model: 'mock' }) const seen: string[] = [] ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => { seen.push(`global:${agent.id}`) @@ -352,7 +348,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'catalog' }] } let composed = 0 @@ -385,7 +381,7 @@ describe('agent/session-prefix', () => { it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] } const order: string[] = [] @@ -412,7 +408,7 @@ describe('agent/session-prefix', () => { it('the canonical prepend pattern composes contributions in registration order', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Both listeners use the canonical `[mine, ...await next()]` prepend: the // waterfall unwinds innermost-first (the second listener's array is built @@ -434,7 +430,7 @@ describe('agent/session-prefix', () => { it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A listener that delegates without contributing — the canonical no-op. ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next()) @@ -450,7 +446,7 @@ describe('agent/session-prefix', () => { it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let mutationError: unknown ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise => { @@ -479,7 +475,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] } ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise => [...await next(), held]) @@ -500,7 +496,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { it('a continue decision with a reason records next-step steering in the same turn', async () => { const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let forced = false ctx.on('agent/turn-continuation', async (_agent, _turn, _default, next): Promise => { @@ -533,7 +529,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/turn-continuation', async (): Promise => ({ action: 'stop' })) @@ -563,7 +559,7 @@ describe('tools/post-execute additionalContext buffering across a multi-call ste name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Each call attaches additionalContext naming itself. ctx.on('tools/post-execute', async (exec, _result): Promise => @@ -599,7 +595,7 @@ describe('tools/pre-execute gate (native-plugin permission pattern, end-to-end t name: 'danger', description: 'danger', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('tools/pre-execute', async (exec, next): Promise => { if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' } @@ -663,7 +659,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'please echo hi') await waitForIdle(ctx, agent) @@ -686,7 +682,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) await ctx.plugin(NativeGuard) - const agent = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -705,7 +701,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se await fiber.dispose() // After disposal, a destructive prompt is NOT blocked (the listener is gone). - const agent = ctx.agentLoop.create(AgentId('a3'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a3'), { model: 'mock' }) send(agent, 'run rm -rf /') await waitForIdle(ctx, agent) // the prompt ran (not rejected) — proving the prompt-submit listener was disposed diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 71be5b339e..c4e49e0fa5 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -4,7 +4,8 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -44,7 +45,7 @@ describe('agent loop', () => { it('runs a simple turn: queued message → model → idle, with ordered events', async () => { const adapter = new MockAdapter([textResponse('hello there')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // All boundaries — turn and step — are durable session events on the // session/event feed (no agent/* mirror). Record them in fire order to @@ -92,7 +93,7 @@ describe('agent loop', () => { return [{ type: 'text', text: `echo: ${args.text}` }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -131,7 +132,7 @@ describe('agent loop', () => { return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -155,7 +156,7 @@ describe('agent loop', () => { return [] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -169,7 +170,6 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter, 'Working in {{cwd}}.') const handle = await ctx.agents.create({ - agentId: AgentId('a-cwd'), sessionId: SessionId('s-cwd'), meta: { cwd: '/work/space' }, agentOptions: { model: 'mock' }, @@ -192,7 +192,7 @@ describe('agent loop', () => { const ctx = await harness(adapter, 'In {{cwd}}.') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -233,7 +233,7 @@ describe('agent loop', () => { ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, model: 'mock' } }) - const agent = ctx.agentLoop.create(AgentId('a-late-model'), {}) + const agent = ctx.agentLoop.create(SessionId('a-late-model'), {}) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -259,7 +259,7 @@ describe('agent loop', () => { parameters: {}, execute: () => Promise.resolve({ content: [{ type: 'text' as const, text: 'apparent success' }], meta }), })) - const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-meta-agent'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -288,7 +288,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} })) - const agent = ctx.agentLoop.create(AgentId('a-no-system'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-no-system'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -300,7 +300,7 @@ describe('agent loop', () => { it('records raw chunks for replay as assistant/chunk session events', async () => { const adapter = new MockAdapter([textResponse('abc')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -324,7 +324,7 @@ describe('agent loop', () => { ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'slow', description: '', @@ -356,7 +356,7 @@ describe('agent loop', () => { it('steering while idle behaves like send (starts a turn)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.steer([{ type: 'text', text: 'hello' }]) await waitForIdle(ctx, agent) @@ -366,7 +366,7 @@ describe('agent loop', () => { it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } }) // The idle inject records a self-contained turn (turn/start → context/message @@ -393,7 +393,7 @@ describe('agent loop', () => { textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A tool that injects mid-execution: at this point the agent is running, so // inject must append the context/message into the ALREADY-open turn rather // than wrap it in its own one-shot turn. @@ -427,7 +427,7 @@ describe('agent loop', () => { textResponse('step 3'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -453,7 +453,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const) @@ -469,7 +469,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.llm.registerAdapter(['other-model'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { // The seed is frozen — config is not a mutable per-call knob; a switch @@ -502,7 +502,7 @@ describe('agent loop', () => { name: 'echo', description: 'echo', parameters: {}, async execute() { return [{ type: 'text', text: 'echoed' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { @@ -527,7 +527,7 @@ describe('agent loop', () => { // the derived request for that step (derive happens after step/start). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let injected = false ctx.on('agent/pre-step', (subject) => { @@ -563,7 +563,7 @@ describe('agent loop', () => { // The loop survives and a follow-up prompt still runs. const adapter = new MockAdapter([textResponse('second turn ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let throwOnce = true ctx.on('agent/pre-step', () => { @@ -597,7 +597,7 @@ describe('agent loop', () => { it('cancel() mid-stream ends the turn with reason aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -617,7 +617,7 @@ describe('agent loop', () => { // turn stops by default and ends max-tokens, not completed. const adapter = new MockAdapter([maxTokensResponse('truncat')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -642,7 +642,7 @@ describe('agent loop', () => { textResponse('second half'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -673,7 +673,7 @@ describe('agent loop', () => { // stop. The per-turn reason must be independent — turn 2 ends completed. const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -706,7 +706,7 @@ describe('agent loop', () => { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -748,7 +748,7 @@ describe('agent loop', () => { parameters: { text: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -767,7 +767,7 @@ describe('agent loop', () => { // on the normal step path suppresses a pure trace-only empty assistant/message. const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -797,7 +797,7 @@ describe('agent loop', () => { expect(message.content).toEqual([{ type: 'text', text: 'partial text' }]) return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -824,7 +824,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threw = false // Post-commit session observers cannot control the loop. The tool call still // drives the second model request, and the turn completes normally. @@ -843,7 +843,7 @@ describe('agent loop', () => { it('chains queued messages into consecutive turns', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const turns: number[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) }) @@ -868,7 +868,7 @@ describe('agent loop', () => { it('awaits session/flush at turn end (persistence checkpoint)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushed = 0 let flushedBeforeIdle = false @@ -888,7 +888,7 @@ describe('agent loop', () => { it('errors from the model surface as agent/error and end the turn', async () => { const adapter = new MockAdapter([]) // script exhausted → throws const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: Error[] = [] const reasons: TurnEndReason[] = [] @@ -913,10 +913,10 @@ describe('agent loop', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) - expect(ctx.agents.get(AgentId('scoped'))).toBe(agent) + expect(ctx.agents.get(SessionId('scoped'))).toBe(agent) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -925,7 +925,7 @@ describe('agent loop', () => { await agent.done expect(agent.status).toBe('disposed') - expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() + expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() expect(() => { send(agent, 'too late') }).toThrow('disposed') }) @@ -938,13 +938,14 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock' }], + agents: [{ id: 'config-agent', model: 'mock' }], }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent + const agent = ctx.agents.list()[0]! as ReactLoopAgent expect(agent).toBeDefined() - expect(agent.id).toBe('config-agent') + expect(agent.id).toBe(agent.session.id) + expect(agent.id).toMatch(/^config-agent-session-/) expect(agent.options.model).toBe('mock') // the agent is alive: send triggers a turn @@ -961,10 +962,10 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock', cwd: '/work/project' }], + agents: [{ id: 'config-agent', model: 'mock', cwd: '/work/project' }], }) - const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent + const agent = ctx.agents.list()[0]! as ReactLoopAgent expect(agent.session.header.cwd).toBe('/work/project') }) @@ -982,7 +983,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'run') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 1e603a1cc4..b3653d6540 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -14,10 +14,11 @@ import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' @@ -95,7 +96,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) const { seen: trace } = recordStatus(ctx, agent) const idle = nextIdle(ctx, agent) // Send all in one synchronous tick: they queue before the loop wakes. @@ -120,7 +121,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) for (const text of texts) { const idle = nextIdle(ctx, agent) agent.send([{ type: 'text', text }]) @@ -145,7 +146,7 @@ describe('agent loop scheduling properties', () => { async (steps) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) // Capture an idle waiter before EACH send; the last one is guaranteed // to resolve because the final send always triggers (or joins) a turn // that ends idle. Awaiting an already-resolved waiter is a no-op, so a diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 5ccaa7e797..7eddb6be39 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -71,7 +72,7 @@ function waitForIdle(context: Context, agent: Agent): Promise { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => { it('every request after the first hits the provider prefix cache', async () => { ctx = await loopHarness() - const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { model: 'deepseek-v4-flash' }) // Turn 1: forces a tool call → at least two steps (two model requests). agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }]) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 7054b683cb..202a8f6795 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -15,7 +15,8 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -74,7 +75,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -95,7 +96,7 @@ describe('request stability across the loop', () => { it('a later turn append-extends the previous turn (one conversation, one log)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -109,7 +110,7 @@ describe('request stability across the loop', () => { it('a compaction replace rewrites the resend, and the log explains it', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -142,7 +143,7 @@ describe('request stability across the loop', () => { it('a real system-prompt change is a full changed-header snapshot; a stable prompt logs nothing', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -166,7 +167,7 @@ describe('request stability across the loop', () => { it('an inject() during the agent/request waterfall joins the NEXT request (the step/start boundary)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let injected = false ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { @@ -194,7 +195,7 @@ describe('request stability across the loop', () => { it('a mutation attempt on the frozen request content throws into the step (loud, not silent)', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -215,7 +216,7 @@ describe('request stability across the loop', () => { it('a fresh loop instance over a seeded log anchors with a resume snapshot and stays cache-aligned', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('gen1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('gen1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -224,7 +225,6 @@ describe('request stability across the loop', () => { const adapter2 = new MockAdapter([textResponse('two')]) const ctx2 = await harness(adapter2) const handle = await ctx2.agents.create({ - agentId: AgentId('gen2'), sessionId: SessionId('gen2-session'), seed: [...agent.session.events], agentOptions: { model: 'mock' }, @@ -244,7 +244,7 @@ describe('request stability across the loop', () => { it('a delegating listener cannot mutate the seed through next() — the fold stays log-true', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { const config = await next() @@ -278,7 +278,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 93605008ec..f5809575ab 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -8,7 +8,8 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -83,11 +84,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => throwUnknown(failure)) await expect(ctx.agents.resume({ - agentId: AgentId('unknown-resume-failure'), resumeSessionId: sessionId, })).rejects.toBe(failure) - expect(ctx.agents.get(AgentId('unknown-resume-failure'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-resume-failure'))).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() await ctx.fiber.dispose() }) @@ -95,27 +95,26 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('createAgent uses the caller-supplied sessionId (not ${id}-session)', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - const { agent } = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('custom-session'), meta: { cwd: '/w' } }) + const { agent } = await ctx.agents.create({ sessionId: SessionId('custom-session'), meta: { cwd: '/w' } }) expect(agent.session.id).toBe('custom-session') expect(agent.session.header.cwd).toBe('/w') await ctx.fiber.dispose() }) - it('createAgent rejects a duplicate agent id BEFORE creating the session (no orphan)', async () => { + it('createAgent rejects a duplicate identity without orphaning a session', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - await ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-a') }) - // A second create with the SAME agent id but a fresh session id must reject - // up front — and must NOT leave an orphaned 'sess-b' session behind. - await expect(ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-b') })).rejects.toThrow(/already registered/) - expect(ctx.sessions.get(SessionId('sess-b'))).toBeUndefined() + const sessionId = SessionId('sess-a') + await ctx.agents.create({ sessionId }) + await expect(ctx.agents.create({ sessionId })).rejects.toThrow(/already exists/) + expect(ctx.sessions.list()).toHaveLength(1) await ctx.fiber.dispose() }) it('createAgent works without meta (no cwd)', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - const { agent } = await ctx.agents.create({ agentId: AgentId('a-nometa'), sessionId: SessionId('nometa-session') }) + const { agent } = await ctx.agents.create({ sessionId: SessionId('nometa-session') }) expect(agent.session.id).toBe('nometa-session') expect(agent.session.header.cwd).toBeUndefined() await ctx.fiber.dispose() @@ -125,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: create a no-cwd session and run a turn. const adapter1 = new MockAdapter([textResponse('a')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -141,7 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent expect(a2.session.header.cwd).toBeUndefined() await ctx2.fiber.dispose() }) @@ -152,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const { ctx: ctx1, root } = await persistentHarness(adapter1) const sources1: string[] = [] ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source)) - const a1 = (await ctx1.agents.create({ agentId: AgentId('s'), sessionId: SessionId('start-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent as ReactLoopAgent expect(sources1).toEqual(['startup']) a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) @@ -171,7 +170,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx2.llm.registerAdapter(['mock'], adapter2) const sources2: string[] = [] ctx2.on('agent/session-start', (_agent, source) => void sources2.push(source)) - await ctx2.agents.resume({ agentId: AgentId('s'), resumeSessionId: SessionId('start-sess') }) + await ctx2.agents.resume({ resumeSessionId: SessionId('start-sess') }) expect(sources2).toEqual(['resume']) await ctx2.fiber.dispose() }) @@ -186,7 +185,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', (session) => { expect(ctx.sessions.get(session.id)).toBe(session) - expect(ctx.agents.get(AgentId('resumed-atomic'))?.session).toBe(session) + expect(ctx.agents.get(sessionId)?.session).toBe(session) order.push('session/created') }) ctx.on('agent/created', (agent) => { @@ -199,11 +198,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { }) const resuming = ctx.agents.resume({ - agentId: AgentId('resumed-atomic'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async (agentCtx) => { - expect(agentCtx.agent?.id).toBe(AgentId('resumed-atomic')) + expect(agentCtx.agent?.id).toBe(sessionId) expect(agentCtx.agent?.session.events).toHaveLength(2) agentCtx.on('session/created', () => void order.push('setup-listener:session/created')) agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created')) @@ -215,7 +213,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { }) await setupStarted.promise - expect(ctx.agents.get(AgentId('resumed-atomic'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() expect(order).toEqual(['setup:start']) @@ -236,17 +234,15 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('successful resume disposal retires its caller-owned transaction effects', async () => { const sessionId = SessionId('resume-retired-effects-s') - const agentId = AgentId('resume-retired-effects') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) const handle = await ctx.agents.resume({ - agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' }, }) const transactionLabels = [ - `agentLoop.owner(${agentId})`, - `agentLoop.lifecycle(${agentId})`, + `agentLoop.owner(${sessionId})`, + `agentLoop.lifecycle(${sessionId})`, ] expect(ctx.fiber.getEffects().map(effect => effect.label)).toEqual(expect.arrayContaining(transactionLabels)) @@ -255,7 +251,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('resume setup rejection publishes nothing, unwinds, and releases both identities', async () => { + it('resume setup rejection publishes nothing, unwinds, and releases the identity', async () => { const sessionId = SessionId('resume-setup-reject') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) @@ -265,7 +261,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('agent/session-start', () => void published.push('agent/session-start')) await expect(ctx.agents.resume({ - agentId: AgentId('resume-reject'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async () => { @@ -275,10 +270,9 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { })).rejects.toThrow('resume setup failed') expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('resume-reject'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() const retry = await ctx.agents.resume({ - agentId: AgentId('resume-reject'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, }) @@ -299,7 +293,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { resuming = inner.agents.resume({ - agentId: AgentId('resume-owner-race'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async () => { @@ -313,7 +306,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await owner.dispose() await expect(resuming).rejects.toThrow(/owner disposed during setup/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('resume-owner-race'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() gate.resolve(undefined) @@ -322,9 +315,8 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('owner unload aborts a never-settling persistence load, releases identities, and blocks late publication', async () => { + it('owner unload aborts a never-settling persistence load, releases the identity, and blocks late publication', async () => { const sessionId = SessionId('resume-load-owner-unload') - const agentId = AgentId('resume-load-race') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) const snapshot = await ctx.sessionPersistence.load(sessionId) @@ -348,19 +340,19 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { - resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + resuming = inner.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/owner disposed during setup/) await promptly(owner.dispose()) expect(published).toEqual([]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - // owner.dispose() awaited transaction settlement, so the same identities - // can be reused before awaiting the public rejection. - const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) + // owner.dispose() awaited transaction settlement, so the identity can be + // reused before awaiting the public rejection. + const retry = await promptly(ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) await rejection expect(loads).toBe(2) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -370,7 +362,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { lateLoad.resolve(structuredClone(snapshot)) await Promise.resolve() await Promise.resolve() - expect(ctx.agents.get(agentId)).toBe(retry.agent) + expect(ctx.agents.get(sessionId)).toBe(retry.agent) expect(ctx.sessions.get(sessionId)).toBe(retry.agent.session) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -380,7 +372,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('AgentLoop unload aborts persistence load and awaits wrapper settlement', async () => { const sessionId = SessionId('resume-load-factory-unload') - const agentId = AgentId('resume-load-factory-race') const root = await persistSession(sessionId) const ctx = new Context() await ctx.plugin(LlmService) @@ -404,14 +395,14 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => void published.push('session/created')) ctx.on('agent/created', () => void published.push('agent/created')) - const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + const resuming = ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/agent loop is not active/) await promptly(loopFiber.dispose()) await rejection expect(published).toEqual([]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() lateLoad.resolve(structuredClone(snapshot)) await Promise.resolve() @@ -452,7 +443,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent expect(a2.session.header.parentSession).toBe('parent-sess') expect(a2.session.header.cwd).toBe('/w') expect(a2.session.header.seedLength).toBe(seed.length) @@ -466,7 +457,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // disk, since a crash before the next turn would otherwise lose it. const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -491,7 +482,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // drop it on reload (the bug this guards). const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -509,7 +500,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent const flat = JSON.stringify(a2.session.deriveMessages()) expect(flat).toContain('background task 42 finished') await ctx2.fiber.dispose() @@ -519,7 +510,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: run one full turn, persisting it. const adapter1 = new MockAdapter([textResponse('first answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) const events1 = [...a1.session.events] @@ -539,7 +530,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('main'), resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent // The resumed session carries the prior history… expect(a2.session.id).toBe('sess-resume') expect(a2.session.events.length).toBe(events1.length) @@ -567,7 +558,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) - await expect(ctx.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nope') })) + await expect(ctx.agents.resume({ resumeSessionId: SessionId('nope') })) .rejects.toThrow(/session persistence is not configured/) await ctx.fiber.dispose() }) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 5898a82ee2..942199e9eb 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -4,7 +4,8 @@ import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@d import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationDecision } from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -53,7 +54,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( return [{ type: 'text', text: 'ran' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Plugin rewrites the message: replaces the text AND adds a tool call. let rewritten = false @@ -104,7 +105,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { ]) const ctx = await harness(adapter) const executed: string[] = [] - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -148,7 +149,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('continued because of steering'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steeredOnce = false ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => { @@ -188,7 +189,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('after goal reminder'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steeredOnce = false ctx.on('session/event', (subject, event) => { @@ -218,7 +219,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steer() from a turn/end session-event listener becomes a queued message for the next turn', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const turns: number[] = [] let steeredOnce = false @@ -244,7 +245,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steering queued during an aborted step is re-delivered, not silently consumed', async () => { const adapter = new MockAdapter(['hang', textResponse('recovered')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -267,7 +268,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/turn-continuation', async (): Promise => { @@ -295,7 +296,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a rejecting session/flush listener is reported but does not kill the agent', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let rejectedOnce = false ctx.on('session/flush', async () => { @@ -325,7 +326,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const statuses: string[] = [] @@ -348,7 +349,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) ctx.on('agent/status', (_agent, status) => { @@ -361,7 +362,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { await agent.done // must not hang expect(agent.status).toBe('disposed') - expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() // unregistered despite the throw + expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw }) }) @@ -380,7 +381,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => { const adapter = new MockAdapter([textResponse('never')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model + const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -395,7 +396,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('the agent/request waterfall can supply the model for a model-less agent', async () => { const adapter = new MockAdapter([textResponse('routed')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model — router plugin decides + const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model — router plugin decides ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, model: 'mock' } @@ -410,7 +411,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('agent/queued carries the resolved source; steering/message records its source', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'noop', description: '', @@ -438,7 +439,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('send() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-send'), { model: 'mock' }) const content = [{ type: 'text' as const, text: 'accepted-send' }] const source = { kind: 'plugin' as const, plugin: 'accepted-source' } let notifiedContent: ContentBlock[] | undefined @@ -474,7 +475,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('running steer() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'gate', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-steer'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-steer'), { model: 'mock' }) const entered = Promise.withResolvers() const release = Promise.withResolvers() ctx.tools.register(defineTool({ @@ -528,7 +529,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -544,7 +545,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () ctx2.llm.registerAdapter(['mock'], second) const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] }) - const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded) + const prepared = prepareReactLoopAgent(ctx2, SessionId('forked-agent'), { model: 'mock' }, seeded) const forked = prepared.agent prepared.markPublished() ctx2.effect(() => prepared.startDriver()) @@ -591,7 +592,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -616,7 +617,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([abortedStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-aborted'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -634,7 +635,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error-nocode'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -650,7 +651,7 @@ describe('step boundary publication order', () => { it('the step/start event is in session.events when its session/event listener fires', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-step-order'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-step-order'), { model: 'mock' }) // Session.append pushes the event BEFORE notifying session/event listeners, // so a step/start listener always finds the matching event already in the @@ -711,7 +712,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/start observer cannot change a successful turn', async () => { const adapter = new MockAdapter([textResponse('request completed')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart'), { model: 'mock' }) // Session owns post-commit containment. The loop sees a successful append, // runs the request, and balances the ordinary step and turn boundaries. @@ -740,7 +741,7 @@ describe('turn and step boundary recovery', () => { it('a pre-commit step/start validation failure does not invent a step boundary', async () => { const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -771,7 +772,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider failed' } }] const adapter = new MockAdapter([errorStream]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnend-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -805,7 +806,7 @@ describe('turn and step boundary recovery', () => { it('a one-shot step/end validation failure keeps the step open until retry succeeds', async () => { const adapter = new MockAdapter([textResponse('completed before close validation')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -839,7 +840,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-errorlistener'), { model: 'mock' }) let threw = false ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } }) @@ -872,7 +873,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -901,7 +902,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { model: 'mock' }) }, { inject: ['agentLoop'] })) let threw = false @@ -935,7 +936,7 @@ describe('turn and step boundary recovery', () => { it('a throwing turn/start observer cannot starve the loop or later turns', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-preturn'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-preturn'), { model: 'mock' }) let threw = false ctx.on('session/event', (_session, event) => { @@ -966,7 +967,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/end observer cannot rewrite the turn outcome', async () => { const adapter = new MockAdapter([textResponse('all good'), textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-throw'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1008,7 +1009,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stependthrow'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1038,7 +1039,7 @@ describe('turn and step boundary recovery', () => { // boundary stays authoritative and the loop continues normally. const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnendappend'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1085,7 +1086,7 @@ describe('tool result call identity', () => { return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] }) }, { prepend: true }) - const agent = ctx.agentLoop.create(AgentId('a-callid'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-callid'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -1120,7 +1121,7 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream const adapter = new MockAdapter([[]]) const ctx = await harness(adapter) await ctx.plugin(Invariants) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({ role: 'assistant' as const, @@ -1171,7 +1172,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1227,7 +1228,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1282,7 +1283,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1334,7 +1335,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1384,7 +1385,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 2c478ad1f0..c68d96e525 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -4,7 +4,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' + import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' @@ -57,33 +58,31 @@ function disposeCurrentLifecycle(ownerCtx: Context): void { } describe('agent scope lifecycle', () => { - it('rejects an already-aborted creation signal before publishing either identity', async () => { + it('rejects an already-aborted creation signal before publishing either object', async () => { const ctx = await harness() const reason = new Error('cancelled before creation') const controller = new AbortController() controller.abort(reason) await expect(ctx.agents.create({ - agentId: AgentId('pre-aborted'), sessionId: SessionId('pre-aborted-s'), signal: controller.signal, })).rejects.toBe(reason) - expect(ctx.agents.get(AgentId('pre-aborted'))).toBeUndefined() + expect(ctx.agents.get(SessionId('pre-aborted-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('pre-aborted-s'))).toBeUndefined() const valueController = new AbortController() valueController.abort('plain cancellation reason') await expect(ctx.agents.create({ - agentId: AgentId('pre-aborted-value'), sessionId: SessionId('pre-aborted-value-s'), signal: valueController.signal, })).rejects.toMatchObject({ - message: 'agent "pre-aborted-value" creation aborted', + message: 'agent "pre-aborted-value-s" creation aborted', cause: 'plain cancellation reason', }) - expect(ctx.agents.get(AgentId('pre-aborted-value'))).toBeUndefined() + expect(ctx.agents.get(SessionId('pre-aborted-value-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('pre-aborted-value-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -100,12 +99,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('prepare-abort'), sessionId: SessionId('prepare-abort-s'), signal: controller.signal, })).rejects.toBe(reason) - expect(ctx.agents.get(AgentId('prepare-abort'))).toBeUndefined() + expect(ctx.agents.get(SessionId('prepare-abort-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('prepare-abort-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -124,7 +122,7 @@ describe('agent scope lifecycle', () => { thrown = createFailure let createCaught: unknown try { - ctx.agentLoop.create(AgentId('unknown-create')) + ctx.agentLoop.create(SessionId('unknown-create')) } catch (error: unknown) { createCaught = error } @@ -133,28 +131,27 @@ describe('agent scope lifecycle', () => { const ownedFailure = { source: 'createAgent' } thrown = ownedFailure await expect(ctx.agents.create({ - agentId: AgentId('unknown-owned-create'), sessionId: SessionId('unknown-owned-create-s'), })).rejects.toBe(ownedFailure) - expect(ctx.agents.get(AgentId('unknown-create'))).toBeUndefined() - expect(ctx.agents.get(AgentId('unknown-owned-create'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-create'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-owned-create-s'))).toBeUndefined() await ctx.fiber.dispose() }) it('wires agent.ctx: tagged with the agent, DX field set, ctx.agent safe elsewhere', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) expect(scopeOf(agent.ctx)).toBe(agent) expect(agent.ctx.agent).toBe(agent) // The root accessor default: a plain context answers undefined, not a throw. expect(ctx.agent).toBeUndefined() - await ctx.agents.get(AgentId('a1'))?.whenIdle() + await ctx.agents.get(SessionId('a1'))?.whenIdle() }) it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) const { agent } = handle agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' }) agent.ctx.tools.register({ @@ -179,8 +176,8 @@ describe('agent scope lifecycle', () => { it('agent.ctx listeners hear only their own agent (scoped dispatch end to end)', async () => { const ctx = await harness(new MockAdapter([textResponse('one'), textResponse('two')])) - const a = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) - const b = ctx.agentLoop.create(AgentId('b'), { model: 'mock' }) + const a = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) + const b = ctx.agentLoop.create(SessionId('b'), { model: 'mock' }) const heard: string[] = [] a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`)) @@ -210,7 +207,6 @@ describe('agent scope lifecycle', () => { }) const handle = await ctx.agents.create({ - agentId: AgentId('child'), sessionId: SessionId('child-s'), agentOptions: { model: 'mock' }, setup: async (agentCtx) => { @@ -224,14 +220,14 @@ describe('agent scope lifecycle', () => { await handle.dispose() }) - it('keeps both identities unpublished until async setup completes, then announces in order', async () => { + it('keeps both objects unpublished until async setup completes, then announces in order', async () => { const ctx = await harness() const gate = Promise.withResolvers() const setupStarted = Promise.withResolvers() const order: string[] = [] ctx.on('session/created', (session) => { expect(ctx.sessions.get(session.id)).toBe(session) - expect(ctx.agents.get(AgentId('atomic'))?.session).toBe(session) + expect(ctx.agents.get(session.id)?.session).toBe(session) order.push('session/created') }) ctx.on('agent/created', () => void order.push('agent/created')) @@ -239,11 +235,10 @@ describe('agent scope lifecycle', () => { const acceptedOptions = { model: 'mock' } const creating = ctx.agents.create({ - agentId: AgentId('atomic'), - sessionId: SessionId('atomic-s'), + sessionId: SessionId('atomic'), agentOptions: acceptedOptions, setup: async (agentCtx) => { - expect(agentCtx.agent?.id).toBe(AgentId('atomic')) + expect(agentCtx.agent?.id).toBe(SessionId('atomic')) agentCtx.on('session/created', () => void order.push('setup-listener:session/created')) agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created')) order.push('setup:start') @@ -253,7 +248,7 @@ describe('agent scope lifecycle', () => { }, }) await setupStarted.promise - expect(ctx.agents.get(AgentId('atomic'))).toBeUndefined() + expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) @@ -281,16 +276,14 @@ describe('agent scope lifecycle', () => { if (started === 2) bothStarted.resolve(undefined) await gate.promise } - const agentId = AgentId('concurrent-final-enter') + const sessionId = SessionId('concurrent-final-enter') const first = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-a'), + sessionId, agentOptions: { model: 'mock' }, setup, }) const second = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-b'), + sessionId, agentOptions: { model: 'mock' }, setup, }) @@ -304,7 +297,7 @@ describe('agent scope lifecycle', () => { const rejected = outcomes.filter((outcome): outcome is PromiseRejectedResult => outcome.status === 'rejected') expect(fulfilled).toHaveLength(1) expect(rejected).toHaveLength(1) - expect(String(rejected[0]!.reason)).toMatch(/already registered/) + expect(String(rejected[0]!.reason)).toMatch(/already exists/) expect(ctx.agents.list()).toEqual([fulfilled[0]!.value.agent]) expect(ctx.sessions.list()).toEqual([fulfilled[0]!.value.agent.session]) @@ -318,7 +311,6 @@ describe('agent scope lifecycle', () => { const pendingController = new AbortController() const setupStarted = Promise.withResolvers() const pending = ctx.agents.create({ - agentId: AgentId('signal-pending'), sessionId: SessionId('signal-pending-s'), agentOptions: { model: 'mock' }, signal: pendingController.signal, @@ -330,12 +322,11 @@ describe('agent scope lifecycle', () => { await setupStarted.promise pendingController.abort(new Error('cancel pending creation')) await expect(pending).rejects.toThrow('cancel pending creation') - expect(ctx.agents.get(AgentId('signal-pending'))).toBeUndefined() + expect(ctx.agents.get(SessionId('signal-pending-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('signal-pending-s'))).toBeUndefined() const liveController = new AbortController() const live = await ctx.agents.create({ - agentId: AgentId('signal-live'), sessionId: SessionId('signal-live-s'), agentOptions: { model: 'mock' }, signal: liveController.signal, @@ -358,7 +349,6 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { creating = inner.agents.create({ - agentId: AgentId('owner-race'), sessionId: SessionId('owner-race-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -372,7 +362,7 @@ describe('agent scope lifecycle', () => { await owner.dispose() await expect(creating).rejects.toThrow(/owner disposed during setup/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('owner-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('owner-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('owner-race-s'))).toBeUndefined() // Let the losing callback settle; Promise.race already observes it. gate.resolve(undefined) @@ -386,7 +376,6 @@ describe('agent scope lifecycle', () => { let creating2!: ReturnType const owner2 = await ctx.plugin(Object.assign((inner: Context) => { creating2 = inner.agents.create({ - agentId: AgentId('owner-race-2'), sessionId: SessionId('owner-race-s-2'), agentOptions: { model: 'mock' }, setup: async () => { @@ -400,7 +389,7 @@ describe('agent scope lifecycle', () => { const unload2 = owner2.dispose() await expect(creating2).rejects.toThrow(/owner disposed during setup/) await unload2 - expect(ctx.agents.get(AgentId('owner-race-2'))).toBeUndefined() + expect(ctx.agents.get(SessionId('owner-race-s-2'))).toBeUndefined() expect(ctx.sessions.get(SessionId('owner-race-s-2'))).toBeUndefined() }) @@ -413,7 +402,6 @@ describe('agent scope lifecycle', () => { ctx.on('agent/created', () => void published.push('agent/created')) const creating = ctx.agents.create({ - agentId: AgentId('factory-setup-race'), sessionId: SessionId('factory-setup-race-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -426,7 +414,7 @@ describe('agent scope lifecycle', () => { await loopFiber.dispose() await expect(creating).rejects.toThrow(/agent loop is not active/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('factory-setup-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-setup-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-setup-race-s'))).toBeUndefined() gate.resolve(undefined) @@ -444,7 +432,6 @@ describe('agent scope lifecycle', () => { }) const creating = ctx.agents.create({ - agentId: AgentId('factory-scope-race'), sessionId: SessionId('factory-scope-race-s'), agentOptions: { model: 'mock' }, setup: () => { setupCalls += 1 }, @@ -452,7 +439,7 @@ describe('agent scope lifecycle', () => { await expect(creating).rejects.toThrow(/agent loop is not active/) await loopFiber.dispose() expect(setupCalls).toBe(0) - expect(ctx.agents.get(AgentId('factory-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-scope-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-scope-race-s'))).toBeUndefined() await ctx.fiber.dispose() @@ -479,7 +466,6 @@ describe('agent scope lifecycle', () => { const owner = ctx.plugin(Object.assign((inner: Context) => { ownerFiber = inner.fiber creating = inner.agents.create({ - agentId: AgentId('caller-scope-race'), sessionId: SessionId('caller-scope-race-s'), agentOptions: { model: 'mock' }, }) @@ -495,7 +481,7 @@ describe('agent scope lifecycle', () => { await ownerDisposal await owner expect(scopeFiber?.uid).toBeNull() - expect(ctx.agents.get(AgentId('caller-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('caller-scope-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('caller-scope-race-s'))).toBeUndefined() await owner.dispose() await ctx.fiber.dispose() @@ -511,17 +497,17 @@ describe('agent scope lifecycle', () => { void loopFiber.dispose() }) - expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-scope-race'), { model: 'mock' })) .toThrow(/agent loop is not active/) await loopFiber.dispose() - expect(ctx.agents.get(AgentId('config-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('config-scope-race'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) await ctx.fiber.dispose() }) it('synchronous create leaves no lifecycle state when session preparation fails', async () => { const ctx = await harness() - const id = AgentId('config-prepare-failure') + const id = SessionId('config-prepare-failure') expect(() => ctx.agentLoop.create(id, { model: 'mock' }, { cwd: 'relative' })) .toThrow(/absolute path/) @@ -542,12 +528,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('factory-scope-throw'), sessionId: SessionId('factory-scope-throw-s'), agentOptions: { model: 'mock' }, })).rejects.toThrow('scope preparation failed') await loopFiber.dispose() - expect(ctx.agents.get(AgentId('factory-scope-throw'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-scope-throw-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-scope-throw-s'))).toBeUndefined() await ctx.fiber.dispose() @@ -556,23 +541,21 @@ describe('agent scope lifecycle', () => { it('AgentLoop unload is a structural co-owner of every live programmatic agent', async () => { const { ctx, loopFiber } = await harnessWithLoop() const loop = ctx.agentLoop - const agentId = AgentId('factory-live') + const sessionId = SessionId('factory-live') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('factory-live-s'), + sessionId, agentOptions: { model: 'mock' }, }) await loopFiber.dispose() expect(handle.agent.status).toBe('disposed') - expect(ctx.agents.get(agentId)).toBeUndefined() - expect(ctx.sessions.get(SessionId('factory-live-s'))).toBeUndefined() - expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([]) + expect(ctx.agents.get(sessionId)).toBeUndefined() + expect(ctx.sessions.get(sessionId)).toBeUndefined() + expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([]) // The consumer handle shares the provider's completed quiescence boundary. await handle.dispose() await expect(loop.createAgent(ctx, { - agentId: AgentId('factory-inactive'), sessionId: SessionId('factory-inactive-s'), })).rejects.toThrow('agent loop is not active') await ctx.fiber.dispose() @@ -583,7 +566,6 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { creating = inner.agents.create({ - agentId: AgentId('dependency-origin'), sessionId: SessionId('dependency-origin-s'), agentOptions: { model: 'mock' }, setup: (agentCtx) => { @@ -623,7 +605,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('session/created', (session) => { if (session.id !== SessionId('session-created-barrier-s')) return - const agent = ctx.agents.get(AgentId('session-created-barrier'))! + const agent = ctx.agents.get(SessionId('session-created-barrier-s'))! expect(ctx.sessions.get(session.id)).toBe(session) expect(agent.session).toBe(session) agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') }) @@ -638,7 +620,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('session-created-barrier'), sessionId: SessionId('session-created-barrier-s'), agentOptions: { model: 'mock' }, }) @@ -652,7 +633,7 @@ describe('agent scope lifecycle', () => { 'session-disposed', 'scope-disposed', ]) - expect(ctx.agents.get(AgentId('session-created-barrier'))).toBeUndefined() + expect(ctx.agents.get(SessionId('session-created-barrier-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('session-created-barrier-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -666,19 +647,19 @@ describe('agent scope lifecycle', () => { if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-created') }) ctx.on('agent/created', (agent) => { - if (agent.id !== AgentId('agent-created-barrier')) return + if (agent.id !== SessionId('agent-created-barrier-s')) return lifecycle.push('agent-created:dispose') disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/created', (agent) => { - if (agent.id !== AgentId('agent-created-barrier')) return + if (agent.id !== SessionId('agent-created-barrier-s')) return expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.sessions.get(agent.session.id)).toBe(agent.session) agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') }) lifecycle.push('agent-created:observer') }) ctx.on('agent/disposed', (agent) => { - if (agent.id === AgentId('agent-created-barrier')) lifecycle.push('agent-disposed') + if (agent.id === SessionId('agent-created-barrier-s')) lifecycle.push('agent-disposed') }) ctx.on('session/disposed', (session) => { if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-disposed') @@ -687,7 +668,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('agent-created-barrier'), sessionId: SessionId('agent-created-barrier-s'), agentOptions: { model: 'mock' }, }) @@ -703,7 +683,7 @@ describe('agent scope lifecycle', () => { 'session-disposed', 'scope-disposed', ]) - expect(ctx.agents.get(AgentId('agent-created-barrier'))).toBeUndefined() + expect(ctx.agents.get(SessionId('agent-created-barrier-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('agent-created-barrier-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -715,13 +695,12 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType ctx.on('agent/session-start', agent => void starts.push(agent.id)) ctx.on('agent/created', (agent) => { - if (agent.id === AgentId('listener-dispose')) void ownerCtx.fiber.dispose() + if (agent.id === SessionId('listener-dispose-s')) void ownerCtx.fiber.dispose() }) const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('listener-dispose'), sessionId: SessionId('listener-dispose-s'), agentOptions: { model: 'mock' }, }) @@ -730,7 +709,7 @@ describe('agent scope lifecycle', () => { await expect(creating).rejects.toThrow(/owner disposed during setup/) await owner.dispose() expect(starts).toEqual([]) - expect(ctx.agents.get(AgentId('listener-dispose'))).toBeUndefined() + expect(ctx.agents.get(SessionId('listener-dispose-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('listener-dispose-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -744,15 +723,15 @@ describe('agent scope lifecycle', () => { let scopeDisposed = false let observerSawLive = false ctx.on('agent/status', (agent, status) => { - if (agent.id === AgentId('session-start-dispose')) statuses.push(status) + if (agent.id === SessionId('session-start-dispose-s')) statuses.push(status) }) ctx.on('agent/session-start', (agent) => { - if (agent.id !== AgentId('session-start-dispose')) return + if (agent.id !== SessionId('session-start-dispose-s')) return announced = agent as ReactLoopAgent disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/session-start', (agent) => { - if (agent.id !== AgentId('session-start-dispose')) return + if (agent.id !== SessionId('session-start-dispose-s')) return expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.sessions.get(agent.session.id)).toBe(agent.session) agent.ctx.effect(() => () => { scopeDisposed = true }) @@ -762,7 +741,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('session-start-dispose'), sessionId: SessionId('session-start-dispose-s'), agentOptions: { model: 'mock' }, }) @@ -775,7 +753,7 @@ describe('agent scope lifecycle', () => { expect(observerSawLive).toBe(true) expect(scopeDisposed).toBe(true) expect(announced.session.events).toEqual([]) - expect(ctx.agents.get(AgentId('session-start-dispose'))).toBeUndefined() + expect(ctx.agents.get(SessionId('session-start-dispose-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('session-start-dispose-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -787,7 +765,6 @@ describe('agent scope lifecycle', () => { ctx.on('agent/created', () => void published.push('agent/created')) ctx.on('agent/session-start', () => void published.push('agent/session-start')) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -798,13 +775,13 @@ describe('agent scope lifecycle', () => { // Nothing leaked: no agent, no session, and the ids are reusable. expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) await retry.dispose() }) - it('rejects an exotic durable seed before publishing either identity', async () => { + it('rejects an exotic durable seed before publishing either object', async () => { const ctx = await harness() const published: string[] = [] ctx.on('session/created', () => { published.push('session') }) @@ -817,17 +794,15 @@ describe('agent scope lifecycle', () => { }] as unknown as SessionEvent[] await expect(ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { model: 'mock' }, seed, })).rejects.toThrow(/seed event at index 0 is not losslessly JSON-serializable/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('exotic-seed'))).toBeUndefined() + expect(ctx.agents.get(SessionId('exotic-seed-session'))).toBeUndefined() expect(ctx.sessions.get(SessionId('exotic-seed-session'))).toBeUndefined() const retry = await ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { model: 'mock' }, }) @@ -843,13 +818,13 @@ describe('agent scope lifecycle', () => { if (boom) { boom = false; throw new Error('boom created') } }) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, + sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, })).rejects.toThrow('boom created') - expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() expect(disposed).toEqual([]) // inserted but never announced: no impossible disposed edge // The rollback also disposed the scope fiber: re-creating works cleanly. - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) expect(scopeOf(retry.agent.ctx)).toBe(retry.agent) await retry.dispose() }) @@ -866,18 +841,17 @@ describe('agent scope lifecycle', () => { ctx.on('agent/disposed', (agent) => { lifecycle.push(`agent-disposed:${agent.id}`) }) await expect(ctx.agents.create({ - agentId: AgentId('partial-agent'), sessionId: SessionId('partial-session'), agentOptions: { model: 'mock' }, })).rejects.toThrow('agent observer failed') expect(lifecycle).toEqual([ 'session-created:partial-session', - 'agent-created:partial-agent', - 'agent-disposed:partial-agent', + 'agent-created:partial-session', + 'agent-disposed:partial-session', 'session-disposed:partial-session', ]) - expect(ctx.agents.get(AgentId('partial-agent'))).toBeUndefined() + expect(ctx.agents.get(SessionId('partial-session'))).toBeUndefined() expect(ctx.sessions.get(SessionId('partial-session'))).toBeUndefined() }) @@ -892,23 +866,23 @@ describe('agent scope lifecycle', () => { } }) - expect(() => ctx.agentLoop.create(AgentId('config-bad'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-bad'), { model: 'mock' })) .toThrow('config publish failed') - expect(ctx.agents.get(AgentId('config-bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('config-bad'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) }) it('registrations through a disposed agent ctx throw INACTIVE_EFFECT', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) await handle.dispose() expect(() => handle.agent.ctx.on('agent/status', () => {})).toThrow(/inactive context/) }) it('agentEvents fuses carrier and subject for custom drivers', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) const heard: string[] = [] agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`)) @@ -921,7 +895,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) const { agent } = handle @@ -930,7 +904,7 @@ describe('agent scope lifecycle', () => { if (event.type === 'turn/end') order.push('turn-end') }) ctx.on('agent/disposed', () => { - order.push(`disposed(listed=${ctx.agents.get(AgentId('o1')) !== undefined})`) + order.push(`disposed(listed=${ctx.agents.get(SessionId('o1-s')) !== undefined})`) order.push(`session-still-stored=${ctx.sessions.get(SessionId('o1-s')) !== undefined}`) }) @@ -955,7 +929,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) const teardownDone: string[] = [] @@ -967,23 +941,22 @@ describe('agent scope lifecycle', () => { // actually finished (the raw wrapper returns undefined on a repeat call). await handle.dispose() expect(teardownDone).toContain('unregistered') - expect(ctx.agents.get(AgentId('h1'))).toBeUndefined() + expect(ctx.agents.get(SessionId('h1-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('h1-s'))).toBeUndefined() await unload }) it('successful handle disposal retires its caller ownership effect', async () => { const ctx = await harness() - const agentId = AgentId('retired-owner-effect') + const sessionId = SessionId('retired-owner-effect') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('retired-owner-effect-s'), + sessionId, agentOptions: { model: 'mock' }, }) - expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${agentId})`) + expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${sessionId})`) await handle.dispose() - expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([]) + expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([]) await ctx.fiber.dispose() }) @@ -994,7 +967,6 @@ describe('agent scope lifecycle', () => { let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { handle = await inner.agents.create({ - agentId: AgentId('manual-first'), sessionId: SessionId('manual-first-s'), agentOptions: { model: 'mock' }, setup(agentCtx) { @@ -1014,7 +986,7 @@ describe('agent scope lifecycle', () => { expect(ownerSettled).toBe(false) gate.resolve(undefined) await Promise.all([disposing, unloading]) - expect(ctx.agents.get(AgentId('manual-first'))).toBeUndefined() + expect(ctx.agents.get(SessionId('manual-first-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('manual-first-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -1024,13 +996,11 @@ describe('agent scope lifecycle', () => { const gate = Promise.withResolvers() const cleanupStarted = Promise.withResolvers() const sessionDisposed = Promise.withResolvers() - const agentId = AgentId('quiescent-reuse') - const sessionId = SessionId('quiescent-reuse-s') + const sessionId = SessionId('quiescent-reuse') ctx.on('session/disposed', (session) => { if (session.id === sessionId) sessionDisposed.resolve(undefined) }) const first = await ctx.agents.create({ - agentId, sessionId, agentOptions: { model: 'mock' }, setup(agentCtx) { @@ -1043,10 +1013,10 @@ describe('agent scope lifecycle', () => { const disposing = first.dispose() await Promise.all([sessionDisposed.promise, cleanupStarted.promise]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { model: 'mock' } }) - expect(ctx.agents.get(agentId)).toBe(replacement.agent) + const replacement = await ctx.agents.create({ sessionId, agentOptions: { model: 'mock' } }) + expect(ctx.agents.get(sessionId)).toBe(replacement.agent) expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session) gate.resolve(undefined) @@ -1058,7 +1028,6 @@ describe('agent scope lifecycle', () => { it('handle.dispose() awaits an idle-injection flush before unregistering or detaching', async () => { const ctx = await harness() const handle = await ctx.agents.create({ - agentId: AgentId('idle-flush'), sessionId: SessionId('idle-flush-s'), agentOptions: { model: 'mock' }, }) @@ -1077,12 +1046,12 @@ describe('agent scope lifecycle', () => { const disposal = handle.dispose().then(() => { disposed = true }) await new Promise(resolve => setTimeout(resolve, 0)) expect(disposed).toBe(false) - expect(ctx.agents.get(AgentId('idle-flush'))).toBe(handle.agent) + expect(ctx.agents.get(SessionId('idle-flush-s'))).toBe(handle.agent) expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBe(handle.agent.session) gate.resolve(undefined) await disposal - expect(ctx.agents.get(AgentId('idle-flush'))).toBeUndefined() + expect(ctx.agents.get(SessionId('idle-flush-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBeUndefined() }) }) diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index d9b0a87e1d..1085f01a4c 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -10,11 +10,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { foldRequestHeader } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -57,7 +58,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter, toolOrder) for (const name of registrationOrder) registerNamed(ctx, name) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { ctx, agent, adapter } @@ -103,7 +104,7 @@ describe('loop-level canonical tool order', () => { registerNamed(ctx, 'alpha') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c275fee88c..c7823a2aa5 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type ContinuationStop } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationStop } from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -45,7 +46,7 @@ describe('agent/turn-stop', () => { textResponse('must not be requested'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-steering'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let steered = false @@ -72,7 +73,7 @@ describe('agent/turn-stop', () => { textResponse('must not become a late-steering turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-steering'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let injected = false @@ -98,7 +99,7 @@ describe('agent/turn-stop', () => { textResponse('queued follow-up answer'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-send'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let queued = false @@ -124,8 +125,8 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const stopped = ctx.agentLoop.create(AgentId('stopped'), { model: 'mock' }) - const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { model: 'mock' }) + const stopped = ctx.agentLoop.create(SessionId('stopped'), { model: 'mock' }) + const ordinary = ctx.agentLoop.create(SessionId('ordinary'), { model: 'mock' }) stopped.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(stopped) @@ -145,7 +146,7 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('owned-listener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-listener'), { model: 'mock' }) const disposeStop = agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(agent, 'first turn') @@ -162,7 +163,7 @@ describe('agent/turn-stop', () => { textResponse('healthy later turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('bad-policy'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-policy'), { model: 'mock' }) const reasons: TurnEndReason[] = [] const errors: string[] = [] ctx.on('session/event', (session, event) => { diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 9ee324b0c3..4eddb050d5 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -12,7 +12,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent): () => void` performs the authoritative ID collision check and inserts without announcing; `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. -- `ctx.agents.get(id: AgentId): Agent | undefined` +- `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index edb7f59a37..1306e8004d 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -9,7 +9,7 @@ import { Context, getTraceable, Service, symbols } from 'cordis' import { scopeTarget } from '@deepseek-ai/dsh-scope' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' -import type { Agent, AgentId, AgentOptions } from './types.ts' +import type { Agent, AgentOptions } from './types.ts' export * from './types.ts' export { agentEvents, assembleContextFor } from './dispatch.ts' @@ -33,15 +33,13 @@ declare module 'cordis' { /** * Options for programmatically creating an agent through the registry factory - * ({@link AgentRegistry.create}). The caller supplies the live `sessionId` - * (e.g. an ACP-generated id) and optional session metadata (the validated - * `cwd`, fork lineage); the factory creates the session, the agent, and wires - * them together. + * ({@link AgentRegistry.create}). The caller supplies the single live + * `sessionId` shared by the agent registry and session log (e.g. an + * ACP-generated id), plus optional session metadata (the validated `cwd`, fork + * lineage); the factory creates the session and agent under that identity. */ export interface CreateAgentOptions { - /** The agent's id (the registry handle). */ - readonly agentId: AgentId - /** The live session's id (NOT derived from agentId). */ + /** The live agent/session identity. */ readonly sessionId: SessionId /** * Session creation metadata: validated absolute `cwd`, `parentSession` @@ -93,9 +91,7 @@ export interface CreateAgentOptions { * ({@link AgentRegistry.resume}). */ export interface ResumeAgentOptions { - /** The agent's id (the registry handle). */ - readonly agentId: AgentId - /** The persisted session id to load and resume on. */ + /** The persisted session id to load and use as the live agent/session identity. */ readonly resumeSessionId: SessionId /** Per-agent options (model, …). */ readonly agentOptions?: AgentOptions @@ -180,7 +176,7 @@ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plug /** All mutable lifecycle state for one exact registry entry. */ interface AgentEntry { - readonly id: AgentId + readonly id: SessionId readonly agent: Agent readonly carrier: Scoped announced: boolean @@ -201,7 +197,7 @@ interface FactorySlot { * {@link setFactory}. */ export class AgentRegistry extends Service { - private store = new Map() + private store = new Map() private factory: FactorySlot | undefined constructor(ctx: Context) { @@ -257,7 +253,7 @@ export class AgentRegistry extends Service { * agent): this constructs the agent and its session. Rejects if no factory is * registered or creation/setup fails. The resolved {@link AgentHandle} lets * the owner tear down exactly this agent. - * @param options - agent id, session id/seed/metadata, and agent options. + * @param options - shared identity, session seed/metadata, and agent options. * @returns the handle after setup, rollback-covered publication, and loop start complete. */ async create(options: CreateAgentOptions): Promise { @@ -428,10 +424,10 @@ export class AgentRegistry extends Service { /** * Look up a live agent. - * @param id - the agent id to look up. + * @param id - the shared agent/session id to look up. * @returns the agent, or undefined when no live agent has that id. */ - get(id: AgentId): Agent | undefined { + get(id: SessionId): Agent | undefined { return this.store.get(id)?.agent } diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index a990f0d67d..b0fb78ad66 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -32,7 +32,7 @@ * event. A turn/step boundary is a durable fact: it lives in the session log * and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` * emit. A consumer that needs the `Agent` handle (or its short id) at a boundary - * keeps a session-id→agent map from `agent/created`/`agent/disposed`. + * looks up the agent directly by the event's session id. * See `docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md` * and `docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md`. * @@ -45,25 +45,12 @@ * @module @deepseek-ai/dsh-agent/types */ -import type { Branded } from '@deepseek-ai/dsh-brand' import type { Context } from 'cordis' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { ContentBlock, LlmCallConfig, Message, MessageSource } from '@deepseek-ai/dsh-llm' +import type { Session, SessionId } from '@deepseek-ai/dsh-session' import type {} from '@deepseek-ai/dsh-system-prompt' -/** Identifies one live agent in the registry. */ -export type AgentId = Branded<'AgentId'> - -/** - * Brand a string as an {@link AgentId}. - * @param id - the raw agent id string. - * @returns the same string, branded (a compile-time cast — no runtime cost). - */ -export function AgentId(id: string): AgentId { - return id as AgentId -} -import type { Session } from '@deepseek-ai/dsh-session' - declare module '@deepseek-ai/dsh-system-prompt' { interface AssembleContext { /** @@ -186,7 +173,8 @@ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' * package should depend on the implementation. */ export interface Agent { - readonly id: AgentId + /** The single identity shared with {@link session}. */ + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5d541d56a8..cba833b212 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -2,11 +2,12 @@ import { describe, expect, expectTypeOf, it } from 'vitest' import { Context, Service, symbols } from 'cordis' import type { Events } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry, { AgentId, agentEvents } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent' + import type { Agent, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent' function stubAgent(rawId: string): Agent { - const id = AgentId(rawId) + const id = SessionId(rawId) return { id, options: {}, @@ -57,7 +58,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) expect(() => ctx.agents.register(stubAgent('vetoed'))).toThrow('creation veto') - expect(ctx.agents.get(AgentId('vetoed'))).toBeUndefined() + expect(ctx.agents.get(SessionId('vetoed'))).toBeUndefined() expect(lifecycle).toEqual(['created:vetoed', 'disposed:vetoed']) }) @@ -158,11 +159,11 @@ describe('AgentRegistry factory seam', () => { const factory: AgentFactory = { async createAgent(ownerCtx, options) { calls.create.push({ ownerCtx, options }) - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() } }, async resume(ownerCtx, options) { calls.resume.push({ ownerCtx, options }) - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() } }, } return { factory, calls } @@ -171,15 +172,15 @@ describe('AgentRegistry factory seam', () => { it('requires a factory and delegates through the calling context', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) - await expect(ctx.agents.create({ agentId: AgentId('a'), sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/) + await expect(ctx.agents.create({ sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/) const { factory, calls } = stubFactory() ctx.agents.setFactory(factory) let callerFiber: Context['fiber'] | undefined await ctx.plugin(Object.assign(async (inner: Context) => { callerFiber = inner.fiber - await inner.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') }) - await inner.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') }) + await inner.agents.create({ sessionId: SessionId('create-s') }) + await inner.agents.resume({ resumeSessionId: SessionId('resume-s') }) }, { inject: ['agents'] })) expect(calls.create[0]?.ownerCtx.fiber).toBe(callerFiber) expect(calls.resume[0]?.ownerCtx.fiber).toBe(callerFiber) @@ -192,9 +193,9 @@ describe('AgentRegistry factory seam', () => { inner.agents.setFactory(stubFactory().factory) expect(() => inner.agents.setFactory(stubFactory().factory)).toThrow(/already registered/) }, { inject: ['agents'] })) - await expect(ctx.agents.create({ agentId: AgentId('before'), sessionId: SessionId('before-s') })).resolves.toBeDefined() + await expect(ctx.agents.create({ sessionId: SessionId('before-s') })).resolves.toBeDefined() await owner.dispose() - await expect(ctx.agents.create({ agentId: AgentId('after'), sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/) + await expect(ctx.agents.create({ sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/) }) it('canonicalizes an already traced Service before tracing it for the caller', async () => { @@ -214,18 +215,18 @@ describe('AgentRegistry factory seam', () => { } async createAgent(_ownerCtx: Context, options: CreateAgentOptions) { this.calls().push('create') - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() } } async resume(_ownerCtx: Context, options: ResumeAgentOptions) { this.calls().push('resume') - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() } } } await ctx.plugin(TracedFactory) const traced = (ctx as Context & { tracedFactory: TracedFactory }).tracedFactory ctx.agents.setFactory(traced) - await ctx.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') }) - await ctx.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') }) + await ctx.agents.create({ sessionId: SessionId('create-s') }) + await ctx.agents.resume({ resumeSessionId: SessionId('resume-s') }) const raw = (traced as unknown as { [symbols.original]?: TracedFactory })[symbols.original] expect(states.get(raw!)).toEqual(['create', 'resume']) }) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 06669ca85c..cb6e1304c3 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -288,7 +288,12 @@ export class Session { */ readonly header: SessionHeader - constructor(public readonly id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) { + /** The session identity, derived from its durable header's single copy. */ + get id(): SessionId { + return this.header.id + } + + constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) { if (seed) { // Validate the seed to the SAME invariants `append` enforces, so a // replay/fork (`ctx.sessions.create(id, { seed })`) cannot construct a diff --git a/packages/core/tools/tests/code-mode.spec.ts b/packages/core/tools/tests/code-mode.spec.ts index f9d84aadbf..2339657ec8 100644 --- a/packages/core/tools/tests/code-mode.spec.ts +++ b/packages/core/tools/tests/code-mode.spec.ts @@ -8,7 +8,6 @@ import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime' import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime' import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools' import type { Config, PostToolDecision, ToolExecutionResult } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEventMap } from '@deepseek-ai/dsh-session' @@ -59,7 +58,7 @@ async function setup(options: SetupOptions = {}) { /** Mint one production-shaped agent scope that can register scoped tool policy. */ async function mintAgentScope(ctx: Context, name = 'scoped'): Promise<{ scope: Scope; agent: Agent }> { - const agent = { id: AgentId(name) } as Agent + const agent = { id: SessionId(name) } as Agent let scope!: Scope await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, agent) }, { inject: ['tools', 'systemPrompt'] })) diff --git a/packages/core/tools/tests/scoped.spec.ts b/packages/core/tools/tests/scoped.spec.ts index 6599112c2a..8b8e1cfead 100644 --- a/packages/core/tools/tests/scoped.spec.ts +++ b/packages/core/tools/tests/scoped.spec.ts @@ -6,9 +6,11 @@ import type { Scope } from '@deepseek-ai/dsh-scope' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import type { PreToolDecision, ToolDefinition, ToolExecution, ToolExecutionInput, ToolExecutionToken } from '@deepseek-ai/dsh-tools' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' + import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { SessionId } from '@deepseek-ai/dsh-session' /** Mount the registry (with its systemPrompt dependency) on a fresh context. */ async function mount(): Promise { @@ -20,7 +22,7 @@ async function mount(): Promise { /** Mint a scope whose key doubles as a minimal Agent-like object. */ async function mintAgentScope(ctx: Context, name: string): Promise<{ scope: Scope; key: Agent }> { - const key = { id: name as AgentId } as Agent + const key = { id: name as SessionId } as Agent let scope!: Scope // The scoped context resolves services through the MINTING plugin's // dependency chain — the minter must inject what scope holders will reach @@ -62,7 +64,7 @@ describe('scoped tool registration', () => { it('files a scoped tool in its layer: visible/executable for that scope only', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent ctx.tools.register(tool('shared')) scope.ctx.tools.register(tool('mine')) @@ -195,7 +197,7 @@ describe('scoped execution dispatch', () => { it('an agent.ctx pre-execute listener gates only its own agent (and never subject-less calls)', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent ctx.tools.register(tool('t')) const seen: (string | undefined)[] = [] @@ -213,7 +215,7 @@ describe('scoped execution dispatch', () => { it('applies scoped guards after pre-execute and unwinds duplicate registrations independently', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent let bodyCalls = 0 ctx.tools.register({ ...tool('t'), @@ -428,7 +430,7 @@ describe('scoped execution dispatch', () => { it('uses one input snapshot for the normalized error shell', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'accepted') - const driftAgent = { id: 'drift' as AgentId } as Agent + const driftAgent = { id: 'drift' as SessionId } as Agent ctx.tools.register(tool('parent')) ctx.tools.register(tool('t')) let parent!: ToolExecutionToken diff --git a/packages/fs/tool-fs/tests/fs-tools.e2e.ts b/packages/fs/tool-fs/tests/fs-tools.e2e.ts index a270e7c6d8..dca48d65ab 100644 --- a/packages/fs/tool-fs/tests/fs-tools.e2e.ts +++ b/packages/fs/tool-fs/tests/fs-tools.e2e.ts @@ -3,7 +3,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { fsHarness, waitForIdle } from './harness.ts' @@ -35,7 +34,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => ctx = await fsHarness(workdir, SYSTEM) // agentLoop.create prepares a session with no cwd, so the provider default // (config.cwd = workdir) is the workspace. - const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('fs-e2e'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Create a file named note.txt containing exactly the line: status: draft. ' @@ -65,7 +64,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => try { ctx = await fsHarness(configDir, SYSTEM) const handle = await ctx.agents.create({ - agentId: AgentId('fs-e2e-cwd'), sessionId: SessionId(`fs-e2e-cwd-${Date.now()}`), meta: { cwd: sessionDir }, agentOptions: { model: 'deepseek-v4-flash' }, diff --git a/packages/guard/repeat-tool-guard/README.md b/packages/guard/repeat-tool-guard/README.md index dc385bc033..e46f113301 100644 --- a/packages/guard/repeat-tool-guard/README.md +++ b/packages/guard/repeat-tool-guard/README.md @@ -24,8 +24,8 @@ The chain key is `(tool name, canonical arguments)` — canonicalization is a de - **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful: bookkeeping tools interleaved into a loop must not launder it. - **Denied calls count.** Detection sits on `tools/post-execute`, which also runs for calls a `tools/pre-execute` listener denied — a model hammering a denied call is exactly the loop worth breaking. -- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no `AgentId` to key on. -- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so chains are keyed by `AgentId`; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain; agent disposal drops its state. +- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no live agent object to key on. +- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so a `WeakMap` keys each chain by the live agent object; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain, and object lifetime bounds the weak entry without a disposal listener. - **In-memory only.** A session resumed from persistence starts with a fresh chain — the guard is a heuristic nudge, not a logged invariant, later reminders are the accepted cost. ## Reminder delivery diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index 6a5662d693..d51df1d829 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -22,7 +22,7 @@ * exclude: [todo_write] # tool-name patterns transparent to the chain * ``` * - * Chain state is keyed per {@link AgentId} — the tool registry is a + * Chain state is keyed by the live agent object — the tool registry is a * context-level singleton whose waterfalls interleave every agent's calls, so * a shared counter would let one agent's repetition trip another's reminder. * State is in-memory only: a session resumed from persistence starts with a @@ -37,7 +37,7 @@ import type { Context } from 'cordis' import z from 'schemastery' -import type { AgentId, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' +import type { Agent, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' import type { MessageSource } from '@deepseek-ai/dsh-llm' import type { PostToolDecision, ToolExecution } from '@deepseek-ai/dsh-tools' @@ -202,9 +202,7 @@ export function apply(ctx: Context, config: Config): void { throw new Error(`repeat-tool-guard: invalid argumentsPreviewChars ${argumentsPreviewChars} — must be an integer >= 1`) } - // TODO(agent-keyed-repeat-chain): key a WeakMap by the Agent itself; that - // removes the disposal-only status listener and cannot collide on id reuse. - const chains = new Map() + const chains = new WeakMap() /** Whether a tool participates in the chain (untracked calls are transparent: they neither count nor reset). */ function tracked(toolName: string): boolean { @@ -227,9 +225,9 @@ export function apply(ctx: Context, config: Config): void { if (!tracked(exec.name)) return undefined const canonical = canonicalize(exec.arguments) const key = JSON.stringify([exec.name, canonical]) - const chain = chains.get(exec.agent.id) + const chain = chains.get(exec.agent) const count = chain !== undefined && chain.key === key ? chain.count + 1 : 1 - chains.set(exec.agent.id, { key, count }) + chains.set(exec.agent, { key, count }) if (!thresholdSet.has(count)) return undefined const text = count === thresholds[0] ? GENTLE_REMINDER @@ -259,12 +257,7 @@ export function apply(ctx: Context, config: Config): void { // loop. Pure reset hook: always delegates (attaching nothing, vetoing // nothing). ctx.on('agent/prompt-submit', (agent, _content, _source, next): Promise => { - chains.delete(agent.id) + chains.delete(agent) return next() }) - - // Drop state when an agent goes away, bounding the map over harness lifetime. - ctx.on('agent/status', (agent, status) => { - if (status === 'disposed') chains.delete(agent.id) - }) } diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 565f1076b5..9538166fc4 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' @@ -57,7 +58,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -78,7 +79,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -100,7 +101,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +125,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -142,7 +143,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -163,7 +164,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -179,7 +180,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -195,7 +196,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -215,8 +216,8 @@ describe('chain semantics', () => { toolCallResponse('b3', 'probe', { q: 1 }), textResponse('done'), ])) - const agentA = ctx.agentLoop.create(AgentId('a'), { model: 'mock-a' }) - const agentB = ctx.agentLoop.create(AgentId('b'), { model: 'mock-b' }) + const agentA = ctx.agentLoop.create(SessionId('a'), { model: 'mock-a' }) + const agentB = ctx.agentLoop.create(SessionId('b'), { model: 'mock-b' }) agentA.send([{ type: 'text', text: 'go' }]) agentB.send([{ type: 'text', text: 'go' }]) await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)]) @@ -235,7 +236,7 @@ describe('chain semantics', () => { textResponse('turn two done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) agent.send([{ type: 'text', text: 'again' }]) @@ -256,14 +257,14 @@ describe('chain semantics', () => { // (the loop.spec pattern): a child plugin fiber owns `first`. let first!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - first = inner.agentLoop.create(AgentId('reused'), { model: 'mock' }) + first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() await first.done - const second = ctx.agentLoop.create(AgentId('reused'), { model: 'mock' }) + const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, second) @@ -279,7 +280,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -295,7 +296,7 @@ describe('chain semantics', () => { toolCallResponse('c1', 'probe', { q: 1 }), // if the direct call had counted, this would be #2 textResponse('done'), ])) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -317,7 +318,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -348,7 +349,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2cbc995ce3..2f0a2666c9 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -5,10 +5,11 @@ import { join } from 'node:path' import { Context, type Fiber } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -95,7 +96,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'do something' }]) await waitForIdle(ctx, agent) @@ -118,7 +119,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -143,7 +144,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'use danger' }]) await waitForIdle(ctx, agent) @@ -166,7 +167,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'use safe' }]) await waitForIdle(ctx, agent) @@ -188,7 +189,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -209,7 +210,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -233,7 +234,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -257,7 +258,7 @@ describe('hooks-claude bridge — SessionStart', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // session-start fires async (detached .then → agent.inject); wait for the // injected context/message to actually land before sending, rather than a // fixed sleep that flakes under load. @@ -294,8 +295,8 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => // Drive the observe-only lifecycle events directly (no real child needed — the // bridge just listens). No child agent is registered, so SubagentStart's // child lookup yields undefined and it simply runs the hook. - ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') }) - ctx.emit('subagent/end', { provider: 'inproc', id: AgentId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) + ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) + ctx.emit('subagent/end', { provider: 'inproc', id: SessionId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) // Both hooks run async (detached .then); poll for their marker files rather // than a fixed sleep that flakes under load. @@ -330,7 +331,7 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const { ctx, hooks } = await harnessWithFiber(dir, new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') }) + ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await hooks.dispose() @@ -359,7 +360,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The turn ran normally — no hooks, no crash. @@ -385,7 +386,7 @@ describe('hooks-claude bridge — load resilience', () => { const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 7feb46df05..16c48aa149 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -4,10 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -72,7 +73,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d }) ctx.logger.warn = warn as never ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) // substituted command ran @@ -88,7 +89,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war ctx.logger.warn = warn as never let sawArgs: unknown ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // updatedInput is NOT honored — the tool ran with the ORIGINAL args. @@ -104,7 +105,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ran')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The prompt proceeded unchanged; no context/message injected. @@ -134,7 +135,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -159,7 +160,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -175,7 +176,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) @@ -192,7 +193,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // A second model request ran → the empty-reason block forced continuation. @@ -208,9 +209,9 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const ctx = await harness(path, new MockAdapter([])) // Register a fake child agent under the id the event carries. const injected: string[] = [] - const child = { id: AgentId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-x') }) + ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) await waitFor(() => injected.includes('child guidance')) expect(injected).toContain('child guidance') }) @@ -224,9 +225,9 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: AgentId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-y') }) + ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) }) @@ -240,7 +241,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -254,7 +255,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -270,7 +271,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) - ctx.emit('subagent/end', { provider: 'p', id: AgentId('child-z'), stopReason: 'completed' }) + ctx.emit('subagent/end', { provider: 'p', id: SessionId('child-z'), stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) }) @@ -283,7 +284,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') @@ -298,7 +299,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // ask (no reason) → degrades to deny with the registry's generic message. @@ -313,7 +314,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -342,7 +343,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () // the protocol lib's reference default, not a config knob). HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) @@ -357,7 +358,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) @@ -372,7 +373,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -393,7 +394,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -410,7 +411,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -430,7 +431,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran @@ -448,7 +449,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) // NB: no projectDir // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' @@ -466,7 +467,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(path, adapter) // A later listener that blocks every prompt (registered AFTER the bridge). - const { AgentId: AId } = await import('@deepseek-ai/dsh-agent') + const { SessionId: AId } = await import('@deepseek-ai/dsh-session') ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) @@ -492,7 +493,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) @@ -514,7 +515,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -533,7 +534,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -557,7 +558,7 @@ describe('hooks-claude coverage — executor reject + no-open-turn', () => { const bash = ctx.bash bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -573,7 +574,7 @@ describe('hooks-claude coverage — detached-listener catch handlers', () => { const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Make inject throw, forcing the SessionStart .catch path. const original = agent.inject.bind(agent) let threw = false @@ -613,7 +614,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) @@ -649,7 +650,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server // Register a live child on its own session cwd; emit subagent/end with its id. const { SessionId } = await import('@deepseek-ai/dsh-session') - const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) + const childHandle = await ctx.agents.create({ sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) @@ -670,7 +671,7 @@ describe('hooks-claude coverage — systemMessage is warned, not surfaced', () = const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) @@ -691,7 +692,7 @@ describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait) const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Send immediately — do NOT wait for the session-start inject. agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index e0677306b0..4aa678c36e 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -5,10 +5,11 @@ import { join } from 'node:path' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -82,7 +83,7 @@ describe('hooks-codex bridge', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run ls' }]) await waitForIdle(ctx, agent) @@ -107,7 +108,7 @@ describe('hooks-codex bridge', () => { // Step 1 has no tool calls → would stop; the Stop hook forces step 2. const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +125,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // Ran normally; the unknown event was dropped at parse. @@ -135,7 +136,7 @@ describe('hooks-codex bridge', () => { const dir = configDir() // no hooks.json written const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) @@ -161,7 +162,7 @@ describe('hooks-codex bridge', () => { const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone @@ -190,7 +191,7 @@ describe('hooks-codex bridge', () => { ctx.llm.registerAdapter(['mock'], new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) // fires agent/session-start + ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // fires agent/session-start await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await fiber.dispose() diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 774b308fa1..75b04d4c57 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -4,10 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -52,7 +53,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) const te = events(agent).findLast(e => e.type === 'turn/end') @@ -64,7 +65,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') }) @@ -78,7 +79,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) expect(events(agent).some(e => e.type === 'user/message')).toBe(false) @@ -96,7 +97,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) expect(req).toContain('from-bridge') @@ -111,7 +112,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) @@ -125,7 +126,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) @@ -138,7 +139,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -151,7 +152,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -164,7 +165,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) }) @@ -176,7 +177,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' }) @@ -187,7 +188,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) @@ -200,7 +201,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) @@ -223,7 +224,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') @@ -246,7 +247,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) @@ -259,7 +260,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -273,7 +274,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => existsSync(marker)) // the clean no-output hook has finished agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message')).toBe(false) @@ -285,7 +286,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.inject = (() => { throw new Error('inject boom') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed')) @@ -298,7 +299,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -311,7 +312,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) @@ -327,7 +328,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded @@ -340,7 +341,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) @@ -352,7 +353,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -369,7 +370,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } expect(payload.tool_input.command).toBe('') @@ -405,7 +406,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) @@ -419,7 +420,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') @@ -432,7 +433,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') }) @@ -448,7 +449,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => existsSync(marker)) // the exit-2 hook has finished expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) @@ -462,7 +463,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') @@ -473,7 +474,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -487,7 +488,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') }) @@ -502,7 +503,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } expect(payload.tool_name).toBe('shell') @@ -518,7 +519,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(false) // the matcher fired → the hook denied the tool expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) @@ -530,7 +531,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') @@ -553,7 +554,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { ctx.llm.registerAdapter(['mock'], adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(existsSync(marker)).toBe(true) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 5222906a2d..1e82ef85b0 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -37,8 +37,8 @@ import { type SessionNotification, type StopReason, } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentResult, SubagentRun, SubagentStartRequest, SubagentStopReason } from '@deepseek-ai/dsh-subagent' import { buildChildEnv, disposeChildProcess, spawnFailure } from '@deepseek-ai/dsh-subagent-subprocess' @@ -190,7 +190,7 @@ function toError(value: unknown): Error { * @returns the ready run handle for the child subprocess. */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { - const id = AgentId(randomUUID()) + const id = SessionId(randomUUID()) if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') diff --git a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts index 8060a77fd4..d1b9065c60 100644 --- a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts +++ b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -37,7 +38,7 @@ async function setup(script: Script) { await ctx.plugin(Spawn, { providerName: 'spawn' }) await ctx.plugin(fork, { providerName: 'fork' }) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index e089cebe5f..360098e369 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -2,10 +2,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -43,7 +44,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(fork, { providerName: 'fork' }) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index f6de7200cf..965d9c8e78 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -9,7 +9,7 @@ import { randomUUID } from 'node:crypto' import type { Context } from 'cordis' -import { AgentId, type Agent, type AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { assertSubagentMaxDepth } from '@deepseek-ai/dsh-subagent' @@ -104,7 +104,7 @@ export async function startInProcessRun( throw new SubagentDepthError(childDepth, request.maxDepth) } - const childId = AgentId(randomUUID()) + const childId = SessionId(randomUUID()) const seedLength = options.seed?.length ?? 0 const parentHeader = parent.session.header const parentModel = parent.options.model @@ -127,8 +127,7 @@ export async function startInProcessRun( const flags = { cancelled: false } const handle = await parent.ctx.agents.create({ - agentId: childId, - sessionId: SessionId(randomUUID()), + sessionId: childId, meta: { ...parentHeader.cwd !== undefined ? { cwd: parentHeader.cwd } : {}, parentSession: parentHeader.id, diff --git a/packages/subagent/subagent-inprocess/tests/structured.spec.ts b/packages/subagent/subagent-inprocess/tests/structured.spec.ts index 3e23123622..93da5b1d51 100644 --- a/packages/subagent/subagent-inprocess/tests/structured.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/structured.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, type ContentBlock, type GenerateOptions } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import type { ContinuationDecision } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -68,7 +69,7 @@ async function setup(script: Script, options: SetupOptions = {}) { start: (request: SubagentStartRequest) => startInProcessRun(request, {}), }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter, disposeProvider } } @@ -333,7 +334,7 @@ describe('in-process structured output', () => { await expect(ctx.subagents.start('spawn', structuredRequest(parent, { outputSchema: { type: 'object', oneOf: [] } as unknown as StructuredOutputSchema, }))).rejects.toThrow(/unsupported output schema/) - expect(ctx.agents.get(AgentId('parent'))).toBeDefined() + expect(ctx.agents.get(SessionId('parent'))).toBeDefined() }) it('a schema carrying non-JSON values fails as OutputSchemaError at the validation boundary', async () => { diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 0005246523..aa0f946c89 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -24,7 +25,7 @@ async function setup(script: Script) { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts index daa032199e..b156f951ed 100644 --- a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts +++ b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { spawnHarness, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * With-key smoke for the in-process spawn backend: a REAL parent agent delegates @@ -29,7 +29,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('spawn backend with-key smoke', ( it('a parent delegates to a child that writes a file on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-subagent-spawn-e2e-')) ctx = await spawnHarness(workdir) - const parent = ctx.agentLoop.create(AgentId('e2e-parent'), { model: 'deepseek-v4-flash' }) + const parent = ctx.agentLoop.create(SessionId('e2e-parent'), { model: 'deepseek-v4-flash' }) parent.send([{ type: 'text', text: 'Use the subagent tool to delegate this exact task: "Use the bash tool to write the text ' diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 9e4e489882..06aa40ca9f 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -5,7 +5,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -36,7 +37,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter } } @@ -237,7 +238,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([textResponse('x')]) // A parent WITH a cwd (config agents have none, so create one explicitly). const parentHandle = await ctx.agents.create({ - agentId: AgentId('cwd-parent'), sessionId: SessionId('cwd-parent-session'), meta: { cwd: '/tmp/parent-workspace' }, agentOptions: { model: 'mock' }, @@ -254,7 +254,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([textResponse('explicit model child')]) // A parent with NO model (its own turns would need one supplied per-request). const parentHandle = await ctx.agents.create({ - agentId: AgentId('modelless-parent'), sessionId: SessionId('modelless-parent-session'), agentOptions: {}, }) @@ -318,7 +317,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) const controller = new AbortController() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'q' }], @@ -349,7 +348,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) const parentEffects = parent.ctx.fiber.getEffects().length const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) @@ -442,7 +441,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([]) // A handle-owned parent we can dispose (config agents dispose with the loop fiber). const parentHandle = await ctx.agents.create({ - agentId: AgentId('doomed-parent'), sessionId: SessionId('doomed-s'), agentOptions: { model: 'mock' }, }) @@ -465,7 +463,6 @@ describe('dsh-subagent-spawn', () => { it('parent disposal during the child setup transaction prevents every publication notification', async () => { const { ctx } = await setup([]) const parentHandle = await ctx.agents.create({ - agentId: AgentId('setup-race-parent'), sessionId: SessionId('setup-race-parent-session'), agentOptions: { model: 'mock' }, }) diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 4635de9697..e885c16469 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -18,7 +18,8 @@ import type { Scoped } from '@deepseek-ai/dsh-scope' import { assertSupportedOutputSchema } from '@deepseek-ai/dsh-tools' import { HarnessError } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentCapabilities, SubagentProvider, @@ -96,7 +97,7 @@ export interface SubagentRunInfo { /** The provider that established the run. */ readonly provider: string /** The child agent's id. */ - readonly id: AgentId + readonly id: SessionId } /** Observe-only outcome detail for a settled subagent run. */ @@ -104,7 +105,7 @@ export interface SubagentRunEndInfo { /** The provider that ran it. */ readonly provider: string /** The child agent's id. */ - readonly id: AgentId + readonly id: SessionId /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] /** The child's final assistant output, absent on infrastructure rejection. */ diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 3bdc78569a..8d360b1182 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -6,8 +6,9 @@ * @module @deepseek-ai/dsh-subagent/types */ -import type { Agent, AgentId, AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { StructuredOutputSchema, ToolRestriction } from '@deepseek-ai/dsh-tools' /** @@ -147,7 +148,7 @@ export interface SubagentResult { */ export interface SubagentRun { /** The child agent's id (local in-process runs are already published in `ctx.agents`; remote transports need not publish locally). */ - readonly id: AgentId + readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run * settles. Does NOT reject on a child-level failure — a model/transport diff --git a/packages/subagent/subagent/tests/service.spec.ts b/packages/subagent/subagent/tests/service.spec.ts index 3d10b425ed..ad7dbaafff 100644 --- a/packages/subagent/subagent/tests/service.spec.ts +++ b/packages/subagent/subagent/tests/service.spec.ts @@ -1,6 +1,7 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import { HarnessError } from '@deepseek-ai/dsh-llm' import { carrierKeyOf } from '@deepseek-ai/dsh-scope' import SubagentService, { @@ -12,9 +13,10 @@ import SubagentService, { type SubagentRun, type SubagentStartRequest, } from '@deepseek-ai/dsh-subagent' +import { SessionId } from '@deepseek-ai/dsh-session' function fakeParent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } const ALL_CAPS: SubagentCapabilities = { outputSchema: true, depthLimit: true, toolFilter: true, persona: true } @@ -45,7 +47,7 @@ class StubProvider implements SubagentProvider { async start(request: SubagentStartRequest): Promise { this.startCount += 1 return { - id: AgentId(`child:${this.name}:${request.parent.id}`), + id: SessionId(`child:${this.name}:${request.parent.id}`), result: Promise.resolve(this.outcome), async dispose() {}, } @@ -141,7 +143,7 @@ describe('SubagentService', () => { const starting = subagents.start('deferred', baseRequest({ parent })) await Promise.resolve() expect(events).toEqual([]) - ready.resolve({ id: AgentId('child'), result: result.promise, async dispose() {} }) + ready.resolve({ id: SessionId('child'), result: result.promise, async dispose() {} }) const run = await starting expect(events).toEqual(['start']) result.resolve({ output: [{ type: 'text', text: 'answer' }], stopReason: 'completed' }) @@ -190,7 +192,7 @@ describe('SubagentService', () => { capabilities: NO_CAPS, inheritsParentContext: false, async start() { - return { id: AgentId('infra-child'), result: failure.promise, async dispose() {} } + return { id: SessionId('infra-child'), result: failure.promise, async dispose() {} } }, }) const failedRun = await subagents.start('infra', baseRequest()) diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 5830513cf4..79df080657 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -4,10 +4,12 @@ import Loader from '@cordisjs/plugin-loader' import { CallId } from '@deepseek-ai/dsh-llm' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import SubagentService from '@deepseek-ai/dsh-subagent' import * as mock from '@deepseek-ai/dsh-subagent-mock' import * as tool from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * Drives the REAL plugin body: mounts `dsh-tool-subagent` on a real @@ -20,7 +22,7 @@ import * as tool from '../src/index.ts' /** A minimal parent Agent — the tool reads `agent.id` for `parent`. */ function fakeAgent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } async function setup(toolConfig: tool.Config, mockConfig: Partial = {}) { @@ -114,7 +116,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('weird-child'), + id: SessionId('weird-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'partial' }], stopReason: 'frobnicated' as never }), dispose: async () => {}, }), @@ -141,7 +143,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture-child'), + id: SessionId('capture-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -170,7 +172,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('bare-child'), + id: SessionId('bare-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -297,7 +299,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('spy-child'), + id: SessionId('spy-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => void disposed(), }), @@ -319,7 +321,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('spy-child'), + id: SessionId('spy-child'), result: Promise.resolve({ output: [], stopReason: 'error' as const }), dispose: async () => void disposed(), }), @@ -350,7 +352,7 @@ describe('dsh-tool-subagent', () => { resolveResult({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('spy-child'), + id: SessionId('spy-child'), result, dispose: async () => {}, } @@ -442,7 +444,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture2-child'), + id: SessionId('capture2-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -499,7 +501,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture3-child'), + id: SessionId('capture3-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -528,7 +530,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture4-child'), + id: SessionId('capture4-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts index abc1a6c5e9..bf7bcbe2fb 100644 --- a/packages/support/subagent-mock/src/index.ts +++ b/packages/support/subagent-mock/src/index.ts @@ -13,8 +13,8 @@ import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentCapabilities, SubagentProvider, @@ -65,7 +65,7 @@ class MockSubagentProvider implements SubagentProvider { // A deterministic child id derived from the parent — no clock/random (both // banned in deterministic paths here, and unnecessary for a scripted run). - const id = AgentId(`mock-subagent:${this.name}:${request.parent.id}`) + const id = SessionId(`mock-subagent:${this.name}:${request.parent.id}`) const resultFor = (): SubagentResult => ({ output, diff --git a/packages/support/subagent-mock/tests/subagent-mock.spec.ts b/packages/support/subagent-mock/tests/subagent-mock.spec.ts index 7fd93c62bc..b5e7180782 100644 --- a/packages/support/subagent-mock/tests/subagent-mock.spec.ts +++ b/packages/support/subagent-mock/tests/subagent-mock.spec.ts @@ -1,13 +1,15 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import * as mock from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A minimal parent — the mock provider only reads `parent.id`. */ function fakeParent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } function baseRequest(over: Partial = {}): SubagentStartRequest { diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 739367a699..8376a70425 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -64,7 +65,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Plan recorded.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo'), { model: 'mock' }) agent.send([{ type: 'text', text: 'plan a two-step task' }]) await waitForIdle(ctx, agent) @@ -92,7 +93,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Done planning.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo-2'), { model: 'mock' }) agent.send([{ type: 'text', text: 'plan then update' }]) await waitForIdle(ctx, agent) diff --git a/packages/todo/tool-todo/tests/tool-todo.spec.ts b/packages/todo/tool-todo/tests/tool-todo.spec.ts index 86e8814633..b426b6760c 100644 --- a/packages/todo/tool-todo/tests/tool-todo.spec.ts +++ b/packages/todo/tool-todo/tests/tool-todo.spec.ts @@ -6,7 +6,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { TodoItem } from '@deepseek-ai/dsh-session' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import * as tool from '../src/index.ts' /** @@ -20,7 +21,7 @@ import * as tool from '../src/index.ts' /** A parent Agent backed by a real Session — the tool reads `agent.session`. */ function agentWithSession(id = 'parent-1'): Agent & { session: Session } { const session = new Session(SessionId(id)) - return { id: AgentId(id), session } as unknown as Agent & { session: Session } + return { id: SessionId(id), session } as unknown as Agent & { session: Session } } async function setup(): Promise { diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index a3fdc38f97..e795c7e177 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -72,7 +72,6 @@ import { 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 { AgentId } 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' @@ -686,7 +685,6 @@ export function apply(ctx: Context, config: AcpConfig): void { validateMcpServers(params) const sessionId = SessionId(randomUUID()) const handle = await agents.create({ - agentId: AgentId(sessionId), sessionId, meta: { cwd: params.cwd }, agentOptions: agentOptions(config), @@ -757,7 +755,6 @@ export function apply(ctx: Context, config: AcpConfig): void { } } const handle = await agents.resume({ - agentId: AgentId(sessionId), resumeSessionId: sessionId, agentOptions: agentOptions(config), }) diff --git a/packages/ui/acp/tests/approval.spec.ts b/packages/ui/acp/tests/approval.spec.ts index ed035aaf80..36846ac728 100644 --- a/packages/ui/acp/tests/approval.spec.ts +++ b/packages/ui/acp/tests/approval.spec.ts @@ -4,9 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { CallId } from '@deepseek-ai/dsh-llm' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import ApprovalService, { type ApprovalRequest } from '@deepseek-ai/dsh-user-approval' import { makeBridgeHarness, type BridgeHarness } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The bridge's `approval/request` answerer: an ask for an agent the bridge @@ -31,7 +33,7 @@ describe('acp bridge — approval answerer', () => { ): Promise<{ agent: Agent; request: ApprovalRequest }> { await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = h.ctx.agents.get(AgentId(sessionId)) + const agent = h.ctx.agents.get(SessionId(sessionId)) if (agent === undefined) throw new Error('newSession created no agent') // In production an ask always fires mid-turn (tool execution); open one so // request()'s turn-enclosure precondition holds for the direct drive below. diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index be05a09644..7e780348ba 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -3,8 +3,8 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * End-to-end bridge specs over an in-memory transport: a real @@ -98,7 +98,7 @@ describe('acp bridge', () => { required: [], }, }) - const toolResult = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'tool/result') + const toolResult = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'tool/result') const toolResultBlock = toolResult?.type === 'tool/result' ? toolResult.data.content[0] : undefined const toolResultText = toolResultBlock?.type === 'text' ? toolResultBlock.text : undefined expect(toolResultText).toBe('{"answers":[{"id":"language","selected":["Python"]}]}') @@ -127,7 +127,7 @@ describe('acp bridge', () => { required: ['custom'], }, }) - const toolResult = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'tool/result') + const toolResult = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'tool/result') expect(JSON.stringify(toolResult)).toContain('apollo') }) @@ -136,7 +136,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { custom: 'Use Zig' } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! const result = await harness.ctx.userInteraction.ask({ agent, @@ -167,7 +167,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { choice: 'TypeScript', custom: 'Use Zig' } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ agent, @@ -184,7 +184,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { choice: ['Tests', 'Docs'] } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ agent, @@ -201,7 +201,7 @@ describe('acp bridge', () => { harness = await makeBridgeHarness({ storageDir, withAskUser: true }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] })) .rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' }) @@ -225,7 +225,7 @@ describe('acp bridge', () => { harness = await makeBridgeHarness({ storageDir, withAskUser: true }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! const alreadyAborted = new AbortController() alreadyAborted.abort() @@ -265,8 +265,8 @@ describe('acp bridge', () => { expect(b.sessionId).toBeTruthy() expect(a.sessionId).not.toBe(b.sessionId) // Both agents are live and independently registered. - expect(harness.ctx.agents.get(AgentId(a.sessionId))).toBeDefined() - expect(harness.ctx.agents.get(AgentId(b.sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(a.sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(b.sessionId))).toBeDefined() }) it('rejects a non-absolute cwd but accepts any absolute cwd (per-session workspace)', async () => { @@ -281,7 +281,7 @@ describe('acp bridge', () => { const res = await harness.client.newSession({ cwd: '/tmp', mcpServers: [] }) expect(res.sessionId).toBeTruthy() // The session header records that cwd, so its bash tools run there. - expect(harness.ctx.agents.get(AgentId(res.sessionId))!.session.header.cwd).toBe('/tmp') + expect(harness.ctx.agents.get(SessionId(res.sessionId))!.session.header.cwd).toBe('/tmp') }) it('rejects non-empty additionalDirectories', async () => { @@ -321,7 +321,7 @@ describe('acp bridge', () => { ], }) expect(result.stopReason).toBe('end_turn') - const user = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'user/message') + const user = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'user/message') expect(JSON.stringify(user)).toContain('resource_link') }) diff --git a/packages/ui/acp/tests/dispose.spec.ts b/packages/ui/acp/tests/dispose.spec.ts index f02a7b0649..b5d98c0881 100644 --- a/packages/ui/acp/tests/dispose.spec.ts +++ b/packages/ui/acp/tests/dispose.spec.ts @@ -4,7 +4,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { SessionId } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse } from './harness.ts' describe('acp bridge — disposal & HMR safety', () => { @@ -17,7 +16,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // Start a prompt that hangs in the model stream. const promptDone = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) @@ -62,10 +61,10 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeDefined() await harness.acpFiber.dispose() // tear down ONLY the bridge - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() await harness.dispose() }) @@ -92,7 +91,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // Start a prompt that hangs in the model stream. The prompt RPC will never // return (its transport is severed), so do not await it. void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) @@ -115,7 +114,7 @@ describe('acp bridge — disposal & HMR safety', () => { // and its session removed from the store, not merely idled (the old // behavior). The services live on the root ctx, so they survive this. await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId(sessionId))).toBeUndefined() await harness.dispose() }) @@ -128,7 +127,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -145,7 +144,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const session = harness.ctx.agents.get(AgentId(sessionId))!.session + const session = harness.ctx.agents.get(SessionId(sessionId))!.session await harness.ctx.fiber.dispose() const before = harness.updates.length @@ -169,12 +168,12 @@ describe('acp bridge — disposal & HMR safety', () => { await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) - const liveEvents = harness.ctx.agents.get(AgentId(sessionId))!.session.events.length + const liveEvents = harness.ctx.agents.get(SessionId(sessionId))!.session.events.length expect(liveEvents).toBeGreaterThan(0) // Tear down JUST the bridge (the AgentHandle dispose runs to quiescence). await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() // Re-load the session from disk: every live event (incl. the closing // turn/end) was flushed before the session was detached. @@ -201,7 +200,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -211,7 +210,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Dispose JUST the bridge: a fiber unload that must STILL honor the ordered // teardown (the composite effect runs its disposer chain as a unit). await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() // The loop's own `turn/end {disposed}` is on disk (re-load: the world, not // self-report) — NOT a crash-recovery `interrupted` substitute. @@ -230,21 +229,21 @@ describe('acp bridge — disposal & HMR safety', () => { // queryable, with its session still in the store. const harness = await makeBridgeHarness({ storageDir, script: [] }) const handleA = await harness.ctx.agents.create({ - agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, }) const handleB = await harness.ctx.agents.create({ - agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, + sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, }) - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBe(handleA.agent) - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBe(handleA.agent) + expect(harness.ctx.agents.get(SessionId('sib-b'))).toBe(handleB.agent) await handleA.dispose() // A is gone — unregistered AND its session removed from the store. - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('sib-a'))).toBeUndefined() expect(handleA.agent.status).toBe('disposed') // B is wholly unaffected. - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + expect(harness.ctx.agents.get(SessionId('sib-b'))).toBe(handleB.agent) expect(harness.ctx.sessions.get(SessionId('sib-b'))).toBeDefined() expect(handleB.agent.status).not.toBe('disposed') await harness.dispose() @@ -262,7 +261,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] }) harness.ctx.on('agent/disposed', () => { throw new Error('boom disposed listener') }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, }) handle.agent.send([{ type: 'text', text: 'go' }]) await handle.agent.whenIdle() @@ -270,7 +269,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Dispose: the throwing listener must NOT break the chain before detach. await handle.dispose() - expect(harness.ctx.agents.get(AgentId('guard-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('guard-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('guard-a'))).toBeUndefined() // detach still ran await harness.dispose() }) @@ -283,7 +282,7 @@ describe('acp bridge — disposal & HMR safety', () => { // observe the same quiescence boundary. const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, }) // Drive a turn that hangs in the model stream, so the loop is mid-turn when // disposed — its exit runs a final session/flush we can gate to hold the @@ -313,7 +312,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Release the flush; both resolve together and the session is gone. releaseFlush() await Promise.all([first, second]) - expect(harness.ctx.agents.get(AgentId('conc-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('conc-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('conc-a'))).toBeUndefined() await harness.dispose() }) diff --git a/packages/ui/acp/tests/edges.spec.ts b/packages/ui/acp/tests/edges.spec.ts index e86fb9fc94..329016a69e 100644 --- a/packages/ui/acp/tests/edges.spec.ts +++ b/packages/ui/acp/tests/edges.spec.ts @@ -3,7 +3,6 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { makeBridgeHarness, textResponse, type BridgeHarness } from './harness.ts' @@ -27,7 +26,7 @@ describe('acp bridge — demux & config edges', () => { await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const before = harness.updates.length - const { agent: foreign } = await harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) + const { agent: foreign } = await harness.ctx.agents.create({ sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) foreign.send([{ type: 'text', text: 'hi' }]) await foreign.whenIdle() await new Promise(r => setTimeout(r, 10)) diff --git a/packages/ui/acp/tests/load.spec.ts b/packages/ui/acp/tests/load.spec.ts index 2fbc95b3d9..efc9399c75 100644 --- a/packages/ui/acp/tests/load.spec.ts +++ b/packages/ui/acp/tests/load.spec.ts @@ -4,7 +4,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { SESSION_FORMAT_VERSION, SessionId } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness, type CapturedUpdate } from './harness.ts' /** Concatenate the text of all agent_message_chunk updates. */ @@ -194,7 +193,7 @@ describe('acp bridge — session/load replay', () => { release() // resume() finishes AFTER teardown expect(await loadResult).toBe('rejected') // No live agent was installed for the closed connection. - expect(loader.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId(sessionId))).toBeUndefined() }) it('rejects load when the requested cwd does not match the persisted session cwd', async () => { @@ -215,11 +214,11 @@ describe('acp bridge — session/load replay', () => { await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) await expect(loader.client.loadSession({ sessionId: 'elsewhere', cwd: process.cwd(), mcpServers: [] })) .rejects.toThrow(/cwd mismatch/) - expect(loader.ctx.agents.get(AgentId('elsewhere'))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId('elsewhere'))).toBeUndefined() const res = await loader.client.loadSession({ sessionId: 'elsewhere', cwd: `${otherCwd}/.`, mcpServers: [] }) expect(res).toBeDefined() - expect(loader.ctx.agents.get(AgentId('elsewhere'))!.session.header.cwd).toBe(otherCwd) + expect(loader.ctx.agents.get(SessionId('elsewhere'))!.session.header.cwd).toBe(otherCwd) }) it('rejects load for a non-absolute cwd (still required to be absolute)', async () => { @@ -254,7 +253,7 @@ describe('acp bridge — session/load replay', () => { // Rejected BEFORE resume (metadata-only check) — no agent was registered, so // the id is not wedged: a later attempt hits the same clean rejection, not a // duplicate-registration error. - expect(loader.ctx.agents.get(AgentId('legacy'))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId('legacy'))).toBeUndefined() await expect(loader.client.loadSession({ sessionId: 'legacy', cwd: process.cwd(), mcpServers: [] })) .rejects.toThrow(/no absolute persisted cwd/) }) diff --git a/packages/ui/acp/tests/multi-session.spec.ts b/packages/ui/acp/tests/multi-session.spec.ts index ca11934046..0881fe4199 100644 --- a/packages/ui/acp/tests/multi-session.spec.ts +++ b/packages/ui/acp/tests/multi-session.spec.ts @@ -3,8 +3,8 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, type BridgeHarness, type CapturedUpdate } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** Text of the agent_message_chunk updates scoped to one session id. */ function messageTextFor(updates: { sessionId?: string; update: CapturedUpdate }[], sessionId: string): string { @@ -102,8 +102,8 @@ describe('acp bridge — RFC 011 multi-session isolation', () => { await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId const b = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId - const agentA = harness.ctx.agents.get(AgentId(a))! - const agentB = harness.ctx.agents.get(AgentId(b))! + const agentA = harness.ctx.agents.get(SessionId(a))! + const agentB = harness.ctx.agents.get(SessionId(b))! // Wait deterministically for BOTH agents to enter `running` (not a fixed // sleep — agent startup latency is unbounded on a loaded worker). diff --git a/packages/ui/acp/tests/turns.spec.ts b/packages/ui/acp/tests/turns.spec.ts index f559ca36d9..000b80336d 100644 --- a/packages/ui/acp/tests/turns.spec.ts +++ b/packages/ui/acp/tests/turns.spec.ts @@ -3,7 +3,6 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { errorResponse, @@ -13,6 +12,7 @@ import { toolCallResponse, type BridgeHarness, } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** Boilerplate: initialize + create one session, returning its id. */ async function newSession(h: BridgeHarness, clientCapabilities: Record = {}): Promise { @@ -279,7 +279,7 @@ describe('acp bridge — turn outcomes', () => { // OWN turn with the real model answer. harness = await makeBridgeHarness({ storageDir, script: [textResponse('real answer')] }) const sessionId = await newSession(harness) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // On the queued prompt, synchronously inject a one-shot context turn (idle // inject writes turn/start{injection} → context/message → turn/end). Fire // once so it lands between install and the prompt turn. @@ -335,7 +335,7 @@ describe('acp bridge — turn outcomes', () => { await harness.client.cancel({ sessionId }) const res = await promptDone expect(res.stopReason).toBe('cancelled') - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await agent.whenIdle() // At most ONE turn ran (the cancelled one) — the cancel cleared the queue, so // no second turn was batched or leaked. (A best-effort abort that left queued diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 86af6645f3..4dbfeb0fa2 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -16,7 +16,6 @@ import type { Context } from 'cordis' import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { AgentHandle } from '@deepseek-ai/dsh-agent' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -255,7 +254,6 @@ export class HarnessSdkServer { private async createSession(sessionId: string): Promise { const handle = await this.ctx.agents.create({ - agentId: AgentId(sessionId), sessionId: SessionId(sessionId), meta: { cwd: this.cwd }, agentOptions: { model: this.model }, diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 1cde550f2e..9260a59aae 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -5,7 +5,8 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' +import { type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' + import { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-core' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' @@ -135,7 +136,6 @@ describe('HarnessSdkServer', () => { expect(llmServer.requests).toHaveLength(2) const orphanHandle = await ctx.agents.create({ - agentId: AgentId('orphan-agent'), sessionId: SessionId('orphan-session'), meta: { cwd: storageDir }, agentOptions: { model: 'dsagent-model' }, @@ -170,8 +170,8 @@ describe('HarnessSdkServer', () => { } as unknown as Agent const mainHandle = { agent: mainAgent, dispose: vi.fn(() => Promise.resolve()) } const otherHandle = { agent: otherAgent, dispose: vi.fn(() => Promise.resolve()) } - const create = vi.fn(async (options: { agentId: AgentId }) => - String(options.agentId) === 'main' ? mainHandle : otherHandle) + const create = vi.fn(async (options: { sessionId: SessionId }) => + String(options.sessionId) === 'main' ? mainHandle : otherHandle) const ctx = { on: vi.fn(() => () => undefined), agents: { create, get: () => undefined }, @@ -263,20 +263,18 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, transport) const parentHandle = await ctx.agents.create({ - agentId: AgentId('parent-agent'), sessionId: SessionId('main'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) const handle = await ctx.agents.create({ - agentId: AgentId('child-agent'), sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', - id: AgentId('child-agent'), + id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }) @@ -285,7 +283,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'spawn', - agentId: 'child-agent', + agentId: 'child-session', parentSessionId: 'main', childSessionId: 'child-session', status: 'ok', @@ -311,19 +309,16 @@ describe('HarnessSdkServer', () => { let failedHandle: AgentHandle | undefined try { parentHandle = await ctx.agents.create({ - agentId: AgentId('fallback-parent-agent'), sessionId: SessionId('fallback-parent'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) handle = await ctx.agents.create({ - agentId: AgentId('fallback-child-agent'), sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { model: 'deepseek' }, }) failedHandle = await ctx.agents.create({ - agentId: AgentId('failed-child-agent'), sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, @@ -333,18 +328,18 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('fallback-child-agent'), + id: SessionId('fallback-child-session'), stopReason: 'max-tokens', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('failed-child-agent'), + id: SessionId('failed-child-session'), stopReason: 'error', }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('missing-child-agent'), + id: SessionId('missing-child-agent'), stopReason: 'error', }) @@ -352,7 +347,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'fork', - agentId: 'fallback-child-agent', + agentId: 'fallback-child-session', parentSessionId: 'fallback-parent', childSessionId: 'fallback-child-session', status: 'error', @@ -364,7 +359,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'fork', - agentId: 'failed-child-agent', + agentId: 'failed-child-session', childSessionId: 'failed-child-session', status: 'error', stopReason: 'error', diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 27f0d20be7..82da64cd81 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -11,11 +11,11 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | Plugin | Why it is here | |---|---| | `@cordisjs/plugin-logger-console` | the console logger — stdout is just the terminal here, so logging to it is correct (the ACP app must NOT have this) | -| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's `model` with `process.cwd()` as the fresh session cwd and carrying its `persona` | +| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating one agent under the `main` config label from this app's `model`, with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | -| `stdio-chat` (in-package module) | the readline UI, bound to the `main` agent | +| `stdio-chat` (in-package module) | the readline UI, holding the app-owned agent object directly and rendering it as `main` | `@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, NOT baked in here: it is a Loader-only, subprocess-only dev plugin — its constructor throws without `node --expose-internals` + a live `loader`, and the in-process test tier cannot even import it (so a package whose `apply` statically pulled it in could never carry the per-file coverage gate). Unlike the console logger, a stray `hmr` is not a stdout-purity footgun, so leaving it at the leaf costs no safety. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`. @@ -25,14 +25,14 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | Key | Default | Routed to | |---|---|---| -| `model` | (required) | the pre-created `main` agent's model | +| `model` | (required) | the pre-created agent's model | | `persona` | — | the deployment persona template (may reference `{{model}}`), routed to `dsh-system-prompt` | | `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 | | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd`, so project-scoped features such as skill discovery and default bash workdir follow the directory where `dsh-stdio-agent` was started. Resumed sessions keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id. Resumed sessions register under the exact `resumeSessionId` and keep the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 127851eaf5..f01c48a615 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -3,11 +3,11 @@ * @deepseek-ai/dsh-agent-core}) plus the coupled front-door cluster a terminal * chat needs — a console logger, the readline UI (the in-package `stdio-chat` * module), JSONL session - * persistence, and a pre-created `main` agent the UI drives. + * persistence, and one pre-created agent the UI drives under its `main` label. * * The cluster is BAKED IN, not left to the leaf: a stdio app always logs to the - * console (stdout is just the terminal) and always pre-creates the `main` agent - * the readline UI sends to. The leaf supplies the swappable backends (the LLM + * console (stdout is just the terminal) and always pre-creates one agent the + * readline UI labels `main`. The leaf supplies the swappable backends (the LLM * adapter, the bash executor), optional product tools, the optional `hmr` * dev-reload plugin, and this app's {@link Config} (model, prompt, persistence * root, welcome banner). @@ -41,7 +41,6 @@ import type { Context } from 'cordis' import ConsoleExporter from '@cordisjs/plugin-logger-console' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' import * as agentCore from '@deepseek-ai/dsh-agent-core' @@ -54,7 +53,7 @@ export const name = 'stdio-agent' /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `model`/`resumeSessionId` configure the pre-created agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -63,7 +62,7 @@ export const name = 'stdio-agent' * `welcome` is the UI banner. */ export interface Config { - /** Model name for the `main` agent (must have a registered adapter). */ + /** Model name for the pre-created agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string @@ -78,7 +77,7 @@ export interface Config { /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ skills?: agentCore.SkillConfig /** - * If set, the `main` agent RESUMES this persisted session id instead of + * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`). */ @@ -103,9 +102,9 @@ export const Config: z = z.object({ /** * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-core bundle pre-creating the `main` agent from this - * app's `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI bound to `main`. The `hmr` dev-reload plugin is + * (infra), then the agent-core bundle pre-creating one agent from this app's + * `model`/`resumeSessionId` with the deployment `persona`, then the JSONL + * backend, then the readline UI rendering that object as `main`. The `hmr` dev-reload plugin is * a leaf concern (see the module doc), so it is not mounted here. */ export function apply(ctx: Context, config: Config): void { @@ -115,7 +114,7 @@ export function apply(ctx: Context, config: Config): void { ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, ...config.tools !== undefined ? { tools: config.tools } : {}, agents: [{ - id: AgentId('main'), + id: 'main', model: config.model, cwd: process.cwd(), ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, @@ -125,5 +124,5 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', agent: 'main' }) + ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.' }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 8e3c1f467b..cb9ce0bc10 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -19,7 +19,7 @@ import { createInterface } from 'node:readline' import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' import { UserInteractionError, type AskUserQuestionAnswer, @@ -36,15 +36,10 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - // TODO(fixed-stdio-agent): this app-internal plugin is mounted only for the - // precreated `main` agent; remove configurability and its config-only test. - /** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */ - agent?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - agent: z.string().default('main'), }) /** @@ -98,23 +93,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // Loader validation, so it must be self-contained rather than trusting the // cast — `config.welcome as string` would otherwise be `undefined` on `{}`. const welcome = config.welcome ?? 'ready.' - const agentId = AgentId(config.agent ?? 'main') const { input, output, exit } = runtime - // Render label lookup: the `turn/start` session event carries only the turn - // number, so to print the short agent id (`[main turn 1]`) we map the - // session's id to its agent's id. The session id is not reliably the agent id - // (a session can be created with an explicit/client-supplied id), so build the - // map from `agent/created` rather than parsing the id string. Seed from the - // registry's current agents first: an agent registered before this plugin - // installed (e.g. the pre-created `main` agent, or any agent surviving an HMR - // reload of just this fiber) already fired its `agent/created`, so the live - // listener alone would miss it and its turns would fall back to the raw - // session id. - const labelBySession = new Map() - for (const agent of ctx.agents.list()) labelBySession.set(agent.session.header.id, agent.id) - ctx.on('agent/created', (agent) => { labelBySession.set(agent.session.header.id, agent.id) }) - ctx.on('agent/disposed', (agent) => { labelBySession.delete(agent.session.header.id) }) + // This app owns exactly one pre-created agent. Hold the live object directly: + // its per-run id is intentionally fresh, while `main` remains only the + // terminal's fixed display label. + let target: Agent | undefined = ctx.agents.list()[0] + ctx.on('agent/created', (agent) => { target ??= agent }) + ctx.on('agent/disposed', (agent) => { + if (target === agent) target = undefined + }) // Transcript rendering off the durable `session/event` feed — the assistant // token stream, turn/step boundaries, tool activity, and todos all come from @@ -136,7 +124,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt output.write(chunk.text) } } else if (event.type === 'turn/start') { - const label = labelBySession.get(session.header.id) ?? session.header.id + const label = target?.session === session ? 'main' : session.id output.write(`\n[${label} turn ${event.data.turn}] `) } else if (event.type === 'turn/end') { if (inReasoning) output.write('\x1B[0m') @@ -187,7 +175,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // Work submitted: wait until a turn has run and the agent is idle. if (submittedWork) { if (!sawRunning) return - const agent = ctx.agents.get(agentId) + const agent = target if (agent && agent.status !== 'idle') return // a turn is still running } // Let any final output flush, then exit. The handle is tracked so the @@ -201,7 +189,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const disposeStatusListener = ctx.on('agent/status', (subject, status) => { - if (subject.id !== agentId) return + if (subject !== target) return if (status === 'running') sawRunning = true if (status === 'idle') maybeExit() }) @@ -354,9 +342,9 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return - const agent = ctx.agents.get(agentId) + const agent = target if (!agent) { - ctx.logger.error('ui-stdio: agent "%s" is not running', agentId) + ctx.logger.error('ui-stdio: main agent is not running') return } submittedWork = true diff --git a/packages/ui/stdio-agent/tests/readline.spec.ts b/packages/ui/stdio-agent/tests/readline.spec.ts index a958c435c1..6116aa356f 100644 --- a/packages/ui/stdio-agent/tests/readline.spec.ts +++ b/packages/ui/stdio-agent/tests/readline.spec.ts @@ -16,7 +16,7 @@ function fakeContext(): Context { return { on: vi.fn(() => vi.fn()), effect: vi.fn((callback: () => () => void) => callback()), - // The UI seeds its label map from the registry at install; this suite only + // The UI seeds its target object from the registry at install; this suite only // exercises readline terminal-mode selection, so an empty roster suffices. agents: { list: vi.fn(() => []) }, userInteraction: { registerProvider: vi.fn(() => vi.fn()) }, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 0668d25fb0..5c5c0d2667 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -4,7 +4,8 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' + import type { Message } from '@deepseek-ai/dsh-llm' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as stdioAgent from '../src/index.ts' @@ -82,9 +83,12 @@ describe('dsh-stdio-agent app', () => { expect(ctx.get('sessionPersistence')).toBeDefined() expect(ctx.get('userInteraction')).toBeDefined() expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() - // The pre-created `main` agent the UI drives. - const agent = ctx.get('agents')?.get(AgentId('main')) + // The sole pre-created agent the UI drives. `main` is its stable config + // label; each fresh process mints a durable combined agent/session id. + const agent = ctx.get('agents')?.list()[0] expect(agent).toBeDefined() + expect(agent?.id).toBe(agent?.session.id) + expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) await ctx.fiber.dispose() }) @@ -99,7 +103,7 @@ describe('dsh-stdio-agent app', () => { stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) await new Promise(resolve => setTimeout(resolve, 80)) expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + expect(ctx.get('agents')?.list()).toHaveLength(1) await ctx.fiber.dispose() }) @@ -116,7 +120,7 @@ describe('dsh-stdio-agent app', () => { it('forwards resumeSessionId onto the pre-created agent when set', async () => { // A resume id defers agent creation until persistence loads; with no backing - // session the resume is contained + logged, so no `main` agent registers — + // session the resume is contained + logged, so no agent registers — // the branch that maps resumeSessionId through is what this covers. const ctx = await mount({ model: 'mock', @@ -125,7 +129,7 @@ describe('dsh-stdio-agent app', () => { resumeSessionId: 'no-such-session', skills: await isolatedSkillsConfig(), }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.list()).toEqual([]) await ctx.fiber.dispose() }) diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 93683d0768..69ca5f8837 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -57,17 +57,16 @@ function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & { status, sent, steered, - // A minimal session stub: the UI reads only `session.header.id` (to map the - // session back to its agent id for the turn-boundary label). - session: { header: { id: `${id}-session` } }, + // A minimal session stub with the agent's shared durable identity. + session: { id, header: { id } }, send: (content: ContentBlock[]) => void sent.push(content), steer: (content: ContentBlock[]) => void steered.push(content), } as never } /** A session stub whose `header.id` matches an agent's, for `session/event` emits. */ -function makeSession(agentId: string): Session { - return { header: { id: `${agentId}-session` } } as Session +function makeSession(id: string): Session { + return { id, header: { id } } as Session } /** An `assistant/chunk` session event carrying one raw stream chunk. */ @@ -75,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there', agent: 'main' } +const CONFIG: Config = { welcome: 'hi there' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -99,12 +98,11 @@ describe('createStdioChat rendering', () => { expect(out.text()).toBe('hi there\n> ') }) - it('falls back to default welcome/agent when called with empty config', async () => { + it('falls back to the default welcome when called with empty config', async () => { // createStdioChat is exported and may be driven directly (bypassing the - // Loader's schemastery validation), so it must default welcome/agent itself. + // Loader's schemastery validation), so it must default the welcome itself. const { out } = await setup({}) expect(out.text()).toBe('ready.\n> ') - // And it drives the default agent id 'main'. }) it('detects readline terminal mode from both stream TTY flags', async () => { @@ -156,9 +154,9 @@ describe('createStdioChat rendering', () => { it('renders turn/start and turn/end markers from the session feed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - // agent/created populates the session-id → agent-id label map. + // agent/created supplies the app-owned target object. ctx.emit('agent/created', agent) - const session = makeSession('main') + const session = agent.session ctx.emit('session/event', session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } }, } as SessionEvent) @@ -169,21 +167,20 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('\n> ') }) - it('falls back to the session id as the label when no agent is mapped', async () => { + it('uses the session id as the label for a non-target session', async () => { const { ctx, out } = await setup() - // No agent/created emitted, so the label map is empty — the header id shows. + // No target exists, so the event's durable identity is the label. ctx.emit('session/event', makeSession('orphan'), { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, } as SessionEvent) - expect(out.text()).toContain('[orphan-session turn 1] ') + expect(out.text()).toContain('[orphan turn 1] ') }) - it('seeds labels for agents already registered before the UI installs', async () => { + it('uses an agent already registered before the UI installs as its target', async () => { // The pre-created `main` agent (and any agent surviving an HMR reload of just // this fiber) fired its `agent/created` before the UI's listener existed, so // the live listener alone would miss it. Seeding from `ctx.agents.list()` at - // install time is what keeps its turn header showing `[main turn N]` instead - // of the raw session id. + // install time preserves the terminal's fixed `[main turn N]` label. const ctx = new Context() await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) @@ -193,7 +190,7 @@ describe('createStdioChat rendering', () => { await ctx.plugin(Object.assign((inner: Context) => { createStdioChat(inner, CONFIG, runtime) }, { inject: ['agents', 'userInteraction'] })) - ctx.emit('session/event', makeSession('main'), { + ctx.emit('session/event', agent.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 5, trigger: { kind: 'message' } }, } as SessionEvent) expect(out.text()).toContain('[main turn 5] ') @@ -209,17 +206,28 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('\x1B[2mmid\x1B[0m') }) - it('drops the label mapping on agent/disposed', async () => { + it('drops the target object on agent/disposed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') ctx.emit('agent/created', agent) ctx.emit('agent/disposed', agent) - // After disposal the map no longer resolves the agent id — fall back to the - // session header id. - ctx.emit('session/event', makeSession('main'), { + // After disposal the event belongs to a non-target session, so its durable + // identity is rendered directly. + ctx.emit('session/event', agent.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, } as SessionEvent) - expect(out.text()).toContain('[main-session turn 1] ') + expect(out.text()).toContain('[main turn 1] ') + }) + + it('keeps the target when a different agent is disposed', async () => { + const { ctx, out } = await setup() + const target = makeAgent('target') + ctx.emit('agent/created', target) + ctx.emit('agent/disposed', makeAgent('other')) + ctx.emit('session/event', target.session, { + type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, + } as SessionEvent) + expect(out.text()).toContain('[main turn 1] ') }) it('renders tool/call and tool/result session events', async () => { @@ -666,11 +674,11 @@ describe('createStdioChat input', () => { const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) input.feed('nobody home') await new Promise(r => setImmediate(r)) - expect(spy).toHaveBeenCalledWith('ui-stdio: agent "%s" is not running', 'main') + expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') }) - it('drives the agent named in config, not a hardcoded id', async () => { - const { ctx, input } = await setup({ welcome: 'w', agent: 'worker' }) + it('drives the app-owned agent without a duplicate id config', async () => { + const { ctx, input } = await setup({ welcome: 'w' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') diff --git a/packages/util/brand/README.md b/packages/util/brand/README.md index 8f7943def7..be25edd55e 100644 --- a/packages/util/brand/README.md +++ b/packages/util/brand/README.md @@ -4,7 +4,7 @@ The `Branded` nominal-typing primitive — a tiny, **type-only** package (no ## What `Branded` is -A brand makes structurally-identical strings non-interchangeable at the type level: an `AgentId` cannot be passed where a `CallId` is expected, even though both are plain `string`s at runtime. +A brand makes structurally-identical strings non-interchangeable at the type level: a `SessionId` cannot be passed where a `CallId` is expected, even though both are plain `string`s at runtime. ```ts import type { Branded } from '@deepseek-ai/dsh-brand' @@ -21,6 +21,6 @@ Construction goes through the per-id factory in the OWNING package (a plain cast ## Policy: brand ids that cross package boundaries -A package brands the ids it OWNS — `CallId` in `dsh-llm` (tool-call correlation), `SessionId` in `dsh-session`, `AgentId` in `dsh-agent`, `BashTaskId`/`OwnerToken` in `dsh-bash`. Branding is for ids that cross package boundaries and could plausibly be confused; **not every string needs a brand.** +A package brands the ids it OWNS — `CallId` in `dsh-llm` (tool-call correlation), the shared agent/session `SessionId` in `dsh-session`, and `BashTaskId`/`OwnerToken` in `dsh-bash`. Branding is for ids that cross package boundaries and could plausibly be confused; **not every string needs a brand.** This package owns ONLY the primitive — no concrete id, no runtime code beyond the (erased) type. Keeping the primitive dependency-free is the point: a capability package can brand its ids without depending on an unrelated package. `dsh-bash`, for example, brands `BashTaskId`/`OwnerToken` by depending on `dsh-brand` alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. diff --git a/packages/util/brand/src/index.ts b/packages/util/brand/src/index.ts index 051ced94b7..d8c28846b3 100644 --- a/packages/util/brand/src/index.ts +++ b/packages/util/brand/src/index.ts @@ -4,15 +4,15 @@ * cross-boundary id. * * A brand makes structurally-identical strings non-interchangeable at the type - * level: an `AgentId` cannot be passed where a `CallId` is expected, even + * level: a `SessionId` cannot be passed where a `CallId` is expected, even * though both are plain strings at runtime. Construction goes through a per-id * factory in the OWNING package (a plain cast inside — zero runtime cost); * comparison, logging, and serialization all behave as ordinary strings. * * Policy: a package brands the ids it owns — `CallId` in dsh-llm (tool-call - * correlation), `SessionId` in dsh-session, `AgentId` in dsh-agent, - * `BashTaskId`/`OwnerToken` in dsh-bash. Branding is for ids that cross package - * boundaries and could plausibly be confused; not every string needs a brand. + * correlation), and `SessionId` in dsh-session; `BashTaskId`/`OwnerToken` live + * in dsh-bash. Branding is for ids that cross package boundaries and could + * plausibly be confused; not every string needs a brand. * This package owns ONLY the primitive — no concrete id, no runtime code beyond * the (erased) type — so the brand vocabulary stays dependency-free and a * package can brand its ids without depending on an unrelated capability diff --git a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts index 0585889617..ac7112a0f0 100644 --- a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts +++ b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts @@ -4,7 +4,6 @@ import Loader from '@cordisjs/plugin-loader' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { WorkflowRunId, WorkflowService } from '@deepseek-ai/dsh-workflow' import type { WorkflowResult, WorkflowRun, WorkflowStartRequest } from '@deepseek-ai/dsh-workflow' @@ -12,6 +11,7 @@ import { CallId } from '@deepseek-ai/dsh-llm' import SubagentService from '@deepseek-ai/dsh-subagent' import WorkerWorkflowEngine from '@deepseek-ai/dsh-workflow-workerthread' import * as toolWorkflow from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A controllable engine standing in behind ctx.workflows (the tool's only seam). */ class StubEngine extends WorkflowService { @@ -51,7 +51,7 @@ async function setup(config?: { toolName?: string; maxResultChars?: number }) { await ctx.plugin(StubEngine) await ctx.plugin(toolWorkflow, config ?? {}) const engine = ctx.workflows as StubEngine - const parent = { id: AgentId('caller'), options: {} } as unknown as Agent + const parent = { id: SessionId('caller'), options: {} } as unknown as Agent return { ctx, engine, parent } } @@ -237,7 +237,7 @@ describe('dsh-tool-workflow', () => { await ctx.plugin(SubagentService) await ctx.plugin(WorkerWorkflowEngine, { disposeGraceMs: 30 }) await ctx.plugin(toolWorkflow, {}) - const parent = { id: AgentId('caller'), options: {} } as unknown as Agent + const parent = { id: SessionId('caller'), options: {} } as unknown as Agent const controller = new AbortController() const pending = execute(ctx, { script: 'await new Promise(() => {})\nreturn 1', diff --git a/packages/workflow/workflow-workerthread/src/runtime.ts b/packages/workflow/workflow-workerthread/src/runtime.ts index 94282cb173..7dbdccbb43 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -38,8 +38,8 @@ */ import * as vm from 'node:vm' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import { assertSupportedOutputSchema, OutputSchemaError } from '@deepseek-ai/dsh-tools' import type { StructuredOutputSchema } from '@deepseek-ai/dsh-tools' import { isFatalWorkflowError, WorkflowError } from '@deepseek-ai/dsh-workflow' @@ -319,7 +319,7 @@ export class WorkflowExecution { await run.dispose() throw this.cancelledError() } - const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: AgentId(run.id) } + const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: SessionId(run.id) } this.observer.agentStart(info) try { let result diff --git a/packages/workflow/workflow-workerthread/tests/integration.spec.ts b/packages/workflow/workflow-workerthread/tests/integration.spec.ts index 0e1727f877..2e13ddcb8b 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -37,7 +38,7 @@ async function setup(script: Script) { await ctx.plugin(spawn, { providerName: 'spawn' }) await ctx.plugin(WorkerWorkflowEngine, {}) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter } } @@ -73,7 +74,7 @@ return { prose, verdict: judged.verdict, confidence: judged.confidence }`, // Both children were disposed to quiescence — no live child agents remain. expect(childIds.length).toBe(2) for (const childId of childIds) { - expect(ctx.agents.get(AgentId(childId))).toBeUndefined() + expect(ctx.agents.get(SessionId(childId))).toBeUndefined() } }) diff --git a/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts b/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts index 7f34396d52..673a43ee0a 100644 --- a/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts @@ -6,10 +6,10 @@ import { expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import WorkerWorkflowEngine from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' // A fresh thread compiles the source runtime. Leave contention headroom on // shared CI runners without weakening any engine-level timeout assertion. @@ -19,7 +19,7 @@ it('runs the default config through the source worker', async () => { const ctx = new Context() const subagents = await ctx.plugin(SubagentService) const engine = await ctx.plugin(WorkerWorkflowEngine, {}) - const parent = { id: AgentId('workflow-compat-parent'), options: {} } as unknown as Agent + const parent = { id: SessionId('workflow-compat-parent'), options: {} } as unknown as Agent try { const run = ctx.workflows.start({ script: 'return 6 * 7', diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index 1d6f61432a..169d80cda7 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -62,7 +63,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key it('runs a two-phase script in a worker thread over real children, one through the structured runtime', async () => { ctx = await harness() const parentHandle = await ctx.agents.create({ - agentId: AgentId('wf-worker-e2e-parent'), sessionId: 'wf-worker-e2e-session' as never, agentOptions: { model: 'deepseek-v4-flash' }, }) @@ -95,7 +95,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key expect(childIds.length).toBe(2) // The children were disposed to quiescence after collection. for (const childId of childIds) { - expect(ctx.agents.get(AgentId(childId))).toBeUndefined() + expect(ctx.agents.get(SessionId(childId))).toBeUndefined() } await parentHandle.dispose() }, 240_000) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 4ad00ee02f..09fb606d69 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -3,17 +3,17 @@ import { fileURLToPath } from 'node:url' import type { Worker } from 'node:worker_threads' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import type { SubagentCapabilities, SubagentProvider, SubagentResult, SubagentRun, SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import type { WorkflowMeta, WorkflowResult, WorkflowResultInfo, WorkflowRunInfo } from '@deepseek-ai/dsh-workflow' import * as workerEngineModule from '../src/index.ts' import WorkerWorkflowEngine, { HostToWorkerType, WorkerToHostType, type Config } from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A minimal parent stand-in: the engine only threads it through to the provider. */ function fakeParent(): Agent { - return { id: AgentId('workflow-parent'), options: {} } as unknown as Agent + return { id: SessionId('workflow-parent'), options: {} } as unknown as Agent } // Worker-thread startup is CPU-bound (a fresh thread compiles the runtime on @@ -117,7 +117,7 @@ class StubProvider implements SubagentProvider { } if (request.signal.aborted) throw new Error('child start aborted before publication') return { - id: AgentId(`stub-child-${index}`), + id: SessionId(`stub-child-${index}`), result: terminal.promise, dispose: () => { controlled.disposeCalls += 1 @@ -366,7 +366,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('reject-child'), + id: SessionId('reject-child'), result: Promise.reject(new Error('backend exploded')), dispose: () => Promise.resolve(), }), @@ -400,7 +400,7 @@ describe('dsh-workflow-workerthread', () => { stopReason: 'completed', } as unknown as SubagentResult const start = vi.spyOn(ctx.subagents, 'start').mockResolvedValue({ - id: AgentId('raw-invalid-child'), + id: SessionId('raw-invalid-child'), result: Promise.resolve(invalid), dispose: () => Promise.resolve(), }) @@ -423,7 +423,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('bad-dispose-child'), + id: SessionId('bad-dispose-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, dispose: () => { throw new Error('dispose exploded') }, @@ -444,7 +444,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('trap-child'), + id: SessionId('trap-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, // The rejection VALUE's own coercion throws: a warn built with bare @@ -771,7 +771,7 @@ describe('dsh-workflow-workerthread', () => { settle({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('signal-only-child'), + id: SessionId('signal-only-child'), result, dispose: () => Promise.resolve(), } @@ -1092,7 +1092,7 @@ describe('dsh-workflow-workerthread', () => { expect(request.signal.reason).toBe('workflow worker gone') ready.resolve({ - id: AgentId('late-ready-child'), + id: SessionId('late-ready-child'), result: Promise.resolve({ output: [], stopReason: 'aborted' }), dispose: () => { disposeCalls += 1 @@ -1128,7 +1128,7 @@ describe('dsh-workflow-workerthread', () => { handle.cancel('reentered from worker-death signal cleanup') }, { once: true }) return { - id: AgentId('doomed-child'), + id: SessionId('doomed-child'), result: new Promise(() => { /* never settles; the reap is the teardown */ }), dispose: () => Promise.reject(new Error('dispose exploded during reap')), } diff --git a/packages/workflow/workflow/src/types.ts b/packages/workflow/workflow/src/types.ts index 981a2da172..35ea4fb053 100644 --- a/packages/workflow/workflow/src/types.ts +++ b/packages/workflow/workflow/src/types.ts @@ -7,7 +7,8 @@ */ import type { Branded } from '@deepseek-ai/dsh-brand' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { SessionId } from '@deepseek-ai/dsh-session' /** Identifies one workflow run. */ export type WorkflowRunId = Branded<'WorkflowRunId'> @@ -145,7 +146,7 @@ export interface WorkflowAgentInfo { /** The phase this agent belongs to (the `phase` option, else the current `phase()` title). */ phase?: string /** The child agent's id on the subagent seam. */ - childId: AgentId + childId: SessionId } /** How one `agent()` call settled: clean result, child failure (script sees `null`), or run cancellation. */ From 17c99efcc14c76bbc548f64ec536d95a2dbb25c5 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:22:20 +0800 Subject: [PATCH 02/39] fix: complete unified subagent identity --- docs/module-graph.md | 12 ++++-- docs/rfc/INDEX.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 38 +++++++++++++++++++ .../2026-06-20-unify-agent-and-session-id.md | 38 ------------------- packages/subagent/subagent-acp/package.json | 2 + packages/subagent/subagent-acp/src/run.ts | 16 ++++---- .../subagent-acp/tests/mock-acp-server.ts | 2 +- .../subagent-acp/tests/subagent-acp.spec.ts | 3 +- packages/subagent/subagent/package.json | 2 + packages/support/subagent-mock/package.json | 2 + packages/workflow/workflow/package.json | 1 + pnpm-lock.yaml | 9 +++++ 13 files changed, 77 insertions(+), 54 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md delete mode 100644 docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md diff --git a/docs/module-graph.md b/docs/module-graph.md index e4d0b3367d..8ac71b11cc 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -179,6 +179,7 @@ flowchart TD pkg_workflow --> pkg_agent pkg_workflow --> pkg_brand pkg_workflow --> pkg_llm + pkg_workflow --> pkg_session pkg_tools --> pkg_agent pkg_tools --> pkg_code_runtime pkg_tools --> pkg_llm @@ -215,6 +216,7 @@ flowchart TD pkg_subagent --> pkg_agent pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope + pkg_subagent --> pkg_session pkg_subagent --> pkg_tools pkg_tool_web --> pkg_llm pkg_tool_web --> pkg_system_prompt @@ -265,6 +267,7 @@ flowchart TD pkg_agent_core --> pkg_tools pkg_subagent_acp --> pkg_agent pkg_subagent_acp --> pkg_llm + pkg_subagent_acp --> pkg_session pkg_subagent_acp --> pkg_subagent pkg_subagent_acp --> pkg_subagent_subprocess pkg_subagent_inprocess --> pkg_agent @@ -285,6 +288,7 @@ flowchart TD pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent pkg_subagent_mock --> pkg_llm + pkg_subagent_mock --> pkg_session pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm @@ -362,14 +366,14 @@ flowchart TD | [`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) | +| [`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) | | [`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) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | @@ -380,11 +384,11 @@ flowchart TD | [`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) | | [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tools`](../packages/core/tools) | -| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | +| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | +| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a5334a63e1..5ed8c6ae6d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -17,7 +17,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| -| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | @@ -87,6 +86,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | | [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | | [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | +| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | | [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | | [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 5fe8224644..4fe7f58168 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -62,6 +62,6 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal (both touch the session-id / owner-token boundary); if that proposal lands, `OwnerToken` still stays distinct from the unified id for the decoupling reason above. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. - **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. - **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md new file mode 100644 index 0000000000..be1052830a --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -0,0 +1,38 @@ +# RFC: Unify the agent id and the session id + +Status: implemented + +## Problem + +The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. + +ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. + +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. + +Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. + +## Decision + +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process and ACP subagent creation use the child session id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. + +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. + +`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. + +## Alternatives considered + +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. + +## Verification + +- Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. +- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id. +- The config-driven resume-or-create policy is explicit and covered across a durable restart. +- A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. +- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. + +## Consequences + +This forecloses latent multi-session-actor and session-handoff designs and makes persisted client-chosen session identity the registry identity. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md deleted file mode 100644 index 6e3eea1515..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,38 +0,0 @@ -# RFC: Unify the agent id and the session id - -Status: proposed - -## Problem - -The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately. - -ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. - -Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes. - -## Proposal - -Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. - -`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation. -- The config-driven resume-or-create policy is explicit and covered across a durable restart. -- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/packages/subagent/subagent-acp/package.json b/packages/subagent/subagent-acp/package.json index e73d861a79..4c34ebe3fc 100644 --- a/packages/subagent/subagent-acp/package.json +++ b/packages/subagent/subagent-acp/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "@deepseek-ai/dsh-subagent-subprocess": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -35,6 +36,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-subagent-subprocess": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.4", diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 1e82ef85b0..1cc220204f 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,7 +23,6 @@ */ import { spawn } from 'node:child_process' -import { randomUUID } from 'node:crypto' import { Readable, Writable } from 'node:stream' import { ClientSideConnection, @@ -190,8 +189,6 @@ function toError(value: unknown): Error { * @returns the ready run handle for the child subprocess. */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { - const id = SessionId(randomUUID()) - if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') // Spawn the child ACP agent. stdin = ACP request channel, stdout = ACP @@ -260,7 +257,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe ), ) - let sessionId: string | undefined + let sessionId: SessionId | undefined // Resolves when a cancel is requested, so `result` can settle `aborted` even // if the child never cooperates with `session/cancel` (it ignores the notify, // or the prompt wedges). The result path races this against the ACP drive: the @@ -309,7 +306,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = session.sessionId + sessionId = SessionId(session.sessionId) if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -321,6 +318,11 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe if (flags.cancelled) throw new Error('subagent request was aborted before the ACP child started') throw toError(error) } + // The startup race can fulfill only after newSession assigned the id; this + // guard keeps that cross-closure invariant explicit for TypeScript. + /* v8 ignore next */ + if (sessionId === undefined) throw new Error('ACP child published without a session id') + const runId = sessionId const result: Promise = (async (): Promise => { try { @@ -332,7 +334,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // succeeds, transport/process failure rejects the in-flight prompt RPC. const prompt = async (): Promise => { // The startup phase cannot fulfill without assigning the session id. - const promptResult = await conn.prompt({ sessionId: sessionId as string, prompt: toAcpPrompt(request.prompt) }) + const promptResult = await conn.prompt({ sessionId: runId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ @@ -366,7 +368,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { - id, + id: runId, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index fb200f3505..5145941526 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -99,7 +99,7 @@ function makeAgent(conn: AgentSideConnection): Agent { writeFileSync(NEWSESSION_GATE.ready, 'at-newSession') while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10)) } - return { sessionId: randomUUID() } + return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { // No auth methods advertised; nothing to do. diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index eed3cfe1ed..115d5c3e97 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -122,8 +122,9 @@ describe('buildChildEnv', () => { describe('dsh-subagent-acp', () => { it('drives a child process to completion and returns its streamed output', async () => { - const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn' }) + const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' }) const run = await ctx.subagents.start('acp', request('do X')) + expect(run.id).toBe('acp-child-session') const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('hello from acp child') diff --git a/packages/subagent/subagent/package.json b/packages/subagent/subagent/package.json index eb0dbf8da0..cf1ebf9485 100644 --- a/packages/subagent/subagent/package.json +++ b/packages/subagent/subagent/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -32,6 +33,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/support/subagent-mock/package.json b/packages/support/subagent-mock/package.json index 8980cc35d2..528691daef 100644 --- a/packages/support/subagent-mock/package.json +++ b/packages/support/subagent-mock/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -33,6 +34,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.4", "cordis": "^4.0.0-rc.6" diff --git a/packages/workflow/workflow/package.json b/packages/workflow/workflow/package.json index a6c004d6d0..4d79d672a1 100644 --- a/packages/workflow/workflow/package.json +++ b/packages/workflow/workflow/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index d02b4a9ca6..6214564eae 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -827,6 +827,9 @@ importers: '@deepseek-ai/dsh-scope': specifier: workspace:^ version: link:../../core/scope + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -852,6 +855,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../subagent @@ -1085,6 +1091,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../../subagent/subagent From 7d711c44a8a6202680f2801ba16b391858715163 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:41:01 +0800 Subject: [PATCH 03/39] fix: keep remote subagent ids parent-scoped --- .../2026-06-20-unify-agent-and-session-id.md | 4 ++-- .../core/agent-loop/tests/scope-lifecycle.spec.ts | 2 +- packages/subagent/subagent-acp/README.md | 2 ++ packages/subagent/subagent-acp/src/run.ts | 15 ++++++++++----- .../subagent-acp/tests/subagent-acp.spec.ts | 10 ++++++++-- packages/subagent/subagent/src/types.ts | 2 +- 6 files changed, 24 insertions(+), 11 deletions(-) diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index be1052830a..032eae4f7d 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -14,7 +14,7 @@ Session itself repeated the same fact as `Session.id` and `Session.header.id`. C ## Decision -An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process and ACP subagent creation use the child session id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index c68d96e525..e29e73c393 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -249,7 +249,7 @@ describe('agent scope lifecycle', () => { }) await setupStarted.promise expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() - expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() + expect(ctx.sessions.get(SessionId('atomic'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) const handle = await creating diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index c949685fcc..03b1a856ed 100644 --- a/packages/subagent/subagent-acp/README.md +++ b/packages/subagent/subagent-acp/README.md @@ -6,6 +6,8 @@ The ACP provider runs each subagent in a fresh subprocess and drives it as an Ag `start(request)` performs `spawn` → ACP `initialize` → `newSession` before it fulfills. Fulfillment therefore means a remote session is ready and ownership has transferred to the caller. A spawn, initialization, new-session, or pre-publication cancellation failure rejects only after the subprocess has been reaped. +The returned run id is minted in the parent namespace. The child server's session id remains private to ACP wire calls because ACP guarantees it only within that fresh child process; using it as the parent lifecycle id could collide with another remote run or a local agent. + After publication, the provider sends the prompt and collects streamed `agent_message_chunk` text into `SubagentResult.output`. A prompt/transport failure resolves with `stopReason: 'error'`, or `aborted` when the required request signal or disposal requested cancellation. `dispose()` is idempotent. It removes the signal listener, requests ACP cancellation when possible, closes stdin, waits `disposeEofGraceMs`, escalates to SIGTERM, waits `disposeGraceMs`, and finally uses SIGKILL if necessary. Every run uses a fresh process; process pooling is not implemented. diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 1cc220204f..7d0c11cbe1 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,6 +23,7 @@ */ import { spawn } from 'node:child_process' +import { randomUUID } from 'node:crypto' import { Readable, Writable } from 'node:stream' import { ClientSideConnection, @@ -190,6 +191,10 @@ function toError(value: unknown): Error { */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') + // ACP session ids are unique only within the child server. The lifecycle id + // is minted in the parent namespace so fresh processes cannot collide with + // each other or with a local agent that happens to use the same session id. + const id = SessionId(randomUUID()) // Spawn the child ACP agent. stdin = ACP request channel, stdout = ACP // response channel, stderr = INHERIT so the child's diagnostics surface on the @@ -257,7 +262,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe ), ) - let sessionId: SessionId | undefined + let sessionId: string | undefined // Resolves when a cancel is requested, so `result` can settle `aborted` even // if the child never cooperates with `session/cancel` (it ignores the notify, // or the prompt wedges). The result path races this against the ACP drive: the @@ -306,7 +311,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = SessionId(session.sessionId) + sessionId = session.sessionId if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -322,7 +327,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // guard keeps that cross-closure invariant explicit for TypeScript. /* v8 ignore next */ if (sessionId === undefined) throw new Error('ACP child published without a session id') - const runId = sessionId + const remoteSessionId = sessionId const result: Promise = (async (): Promise => { try { @@ -334,7 +339,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // succeeds, transport/process failure rejects the in-flight prompt RPC. const prompt = async (): Promise => { // The startup phase cannot fulfill without assigning the session id. - const promptResult = await conn.prompt({ sessionId: runId, prompt: toAcpPrompt(request.prompt) }) + const promptResult = await conn.prompt({ sessionId: remoteSessionId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ @@ -368,7 +373,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { - id: runId, + id, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index 115d5c3e97..e5fe05384e 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -121,16 +121,22 @@ describe('buildChildEnv', () => { }) describe('dsh-subagent-acp', () => { - it('drives a child process to completion and returns its streamed output', async () => { + it('drives child processes with parent-unique run ids and returns streamed output', async () => { const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' }) const run = await ctx.subagents.start('acp', request('do X')) - expect(run.id).toBe('acp-child-session') + expect(run.id).not.toBe('acp-child-session') const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('hello from acp child') const disposal = run.dispose() expect(run.dispose()).toBe(disposal) await disposal + + const nextRun = await ctx.subagents.start('acp', request('do X again')) + expect(nextRun.id).not.toBe(run.id) + expect(nextRun.id).not.toBe('acp-child-session') + await nextRun.result + await nextRun.dispose() }) it('maps a max_tokens stop reason', async () => { diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 8d360b1182..827c2db7a7 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -147,7 +147,7 @@ export interface SubagentResult { * presence of the method IS the capability — narrow before calling. */ export interface SubagentRun { - /** The child agent's id (local in-process runs are already published in `ctx.agents`; remote transports need not publish locally). */ + /** Parent-scoped run id. Local runs use the published child session id; remote providers mint an id unique in the parent namespace. */ readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run From 58e61ae20ba28101be0bed01505b03ec20cd6a7e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:37:58 +0800 Subject: [PATCH 04/39] fix: retain stdio target across agent replacement --- packages/ui/stdio-agent/src/stdio-chat.ts | 19 +++++++++++------ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 21 +++++++++++++++++++ 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index cb9ce0bc10..bfb58e3a57 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,13 +95,20 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns exactly one pre-created agent. Hold the live object directly: - // its per-run id is intentionally fresh, while `main` remains only the - // terminal's fixed display label. - let target: Agent | undefined = ctx.agents.list()[0] - ctx.on('agent/created', (agent) => { target ??= agent }) + // This app owns one root agent. Hold the live object directly: its per-run id + // is intentionally fresh, while `main` remains only the terminal's fixed + // display label. HMR may publish the replacement before old teardown emits + // disposed, so a target disposal reselects the surviving root from the live + // registry instead of leaving the terminal detached. Fork children carry + // parentSession lineage and must never become the terminal target. + const rootAgent = (): Agent | undefined => + ctx.agents.list().find(agent => agent.session.header.parentSession === undefined) + let target: Agent | undefined = rootAgent() + ctx.on('agent/created', (agent) => { + if (target === undefined && agent.session.header.parentSession === undefined) target = agent + }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = undefined + if (target === agent) target = rootAgent() }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 69ca5f8837..2b1df53921 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -230,6 +230,27 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 1] ') }) + it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { + const { ctx, input } = await setup() + const oldRoot = makeAgent('old-root') + const child = makeAgent('child') + ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id + const replacement = makeAgent('replacement') + const disposeOld = ctx.agents.register(oldRoot) + ctx.agents.register(child) + ctx.agents.register(replacement) + + // The replacement's created edge arrived while oldRoot was still targeted. + // Once oldRoot is removed, registry order is child then replacement; the + // UI must skip the surviving child and route input to the replacement root. + disposeOld() + input.feed('after hmr') + await new Promise(resolve => setImmediate(resolve)) + + expect(child.sent).toEqual([]) + expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) + }) + it('renders tool/call and tool/result session events', async () => { const { ctx, out } = await setup() const session = {} as Session From 3bd2052d7251b9500e8afca02aaee64ca8b2ad40 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:52:46 +0800 Subject: [PATCH 05/39] fix: allow lineage-bearing stdio targets --- packages/ui/stdio-agent/src/stdio-chat.ts | 24 +++++++++---------- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 17 ++++++++++++- 2 files changed, 27 insertions(+), 14 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index bfb58e3a57..2a4d620494 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,20 +95,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one root agent. Hold the live object directly: its per-run id - // is intentionally fresh, while `main` remains only the terminal's fixed - // display label. HMR may publish the replacement before old teardown emits - // disposed, so a target disposal reselects the surviving root from the live - // registry instead of leaving the terminal detached. Fork children carry - // parentSession lineage and must never become the terminal target. - const rootAgent = (): Agent | undefined => - ctx.agents.list().find(agent => agent.session.header.parentSession === undefined) - let target: Agent | undefined = rootAgent() - ctx.on('agent/created', (agent) => { - if (target === undefined && agent.session.header.parentSession === undefined) target = agent - }) + // This app owns one configured agent. Hold the live object directly: its + // per-run id is intentionally fresh, while `main` remains only the + // terminal's fixed display label. At install the configured agent is the + // earliest registry entry (it creates any subagents later). During HMR the + // replacement is published after the old tree, so when old teardown finally + // emits disposed, the newest survivor is the replacement. Persisted + // parentSession lineage is deliberately irrelevant: a resumed child session + // can itself be this process's configured top-level agent. + let target: Agent | undefined = ctx.agents.list()[0] + ctx.on('agent/created', (agent) => { target ??= agent }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = rootAgent() + if (target === agent) target = ctx.agents.list().at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2b1df53921..2654a05680 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -185,6 +185,9 @@ describe('createStdioChat rendering', () => { await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) const agent = makeAgent('main') + // Durable lineage does not imply runtime child ownership: the stdio app + // may explicitly resume a persisted fork as its one configured agent. + ;(agent.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(agent) // registered BEFORE the UI plugin below const { runtime, out } = makeRuntime() await ctx.plugin(Object.assign((inner: Context) => { @@ -196,6 +199,18 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 5] ') }) + it('accepts a lineage-bearing configured agent created after the UI installs', async () => { + const { ctx, input } = await setup() + const resumed = makeAgent('resumed') + ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' + ctx.emit('agent/created', resumed) + + input.feed('continue') + await new Promise(resolve => setImmediate(resolve)) + + expect(resumed.sent).toEqual([[{ type: 'text', text: 'continue' }]]) + }) + it('resets dim styling at turn/end if a turn ends mid-reasoning', async () => { const { ctx, out } = await setup() const session = makeSession('main') @@ -242,7 +257,7 @@ describe('createStdioChat rendering', () => { // The replacement's created edge arrived while oldRoot was still targeted. // Once oldRoot is removed, registry order is child then replacement; the - // UI must skip the surviving child and route input to the replacement root. + // most recently published survivor is the HMR replacement. disposeOld() input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) From c2979322c8b938b1c2e91920740688788867e6d7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:13:42 +0800 Subject: [PATCH 06/39] fix: keep stdio targeting on runtime roots --- docs/cordis-catalog/services.md | 5 ++-- packages/core/agent-loop/src/index.ts | 2 +- .../agent-loop/tests/scope-lifecycle.spec.ts | 18 +++++++++++++ packages/core/agent/README.md | 3 ++- packages/core/agent/src/index.ts | 22 ++++++++++++++-- packages/core/agent/tests/agent.spec.ts | 24 +++++++++++++++--- packages/ui/stdio-agent/src/stdio-chat.ts | 20 +++++++-------- .../ui/stdio-agent/tests/readline.spec.ts | 4 +-- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 25 ++++++++++++------- 9 files changed, 92 insertions(+), 31 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 4d162a55f5..1366fcf6f6 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -30,15 +30,16 @@ setFactory(factory: AgentFactory): () => void async create(options: CreateAgentOptions): Promise async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void -enter(agent: Agent): () => void +enter(agent: Agent, owner: Agent | undefined): () => void announce(agent: Agent): void get(id: SessionId): Agent | undefined list(): Agent[] +roots(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:199`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:201`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33276c01f8..dbe503ff6a 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -229,7 +229,7 @@ class AgentCreationTransaction { this.publishing = true try { this.detachSession = agent.ctx.sessions.enter(session) - this.detachAgent = this.loopCtx.agents.enter(agent) + this.detachAgent = this.loopCtx.agents.enter(agent, this.ownerAgent) agent.ctx.sessions.announce(session) this.assertActive() diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index e29e73c393..610e077a67 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -149,6 +149,24 @@ describe('agent scope lifecycle', () => { await ctx.agents.get(SessionId('a1'))?.whenIdle() }) + it('records agents created through an agent context as non-root runtime children', async () => { + const ctx = await harness() + const root = await ctx.agents.create({ + sessionId: SessionId('runtime-root'), + agentOptions: { model: 'mock' }, + }) + const child = await root.agent.ctx.agents.create({ + sessionId: SessionId('runtime-child'), + agentOptions: { model: 'mock' }, + }) + + expect(ctx.agents.list()).toEqual([root.agent, child.agent]) + expect(ctx.agents.roots()).toEqual([root.agent]) + + await child.dispose() + await root.dispose() + }) + it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 4eddb050d5..643c15002b 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -11,9 +11,10 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. -- Advanced ordered lifecycle: `enter(agent): () => void` performs the authoritative ID collision check and inserts without announcing; `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. +- Advanced ordered lifecycle: `enter(agent, owner): () => void` performs the authoritative ID collision check and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` +- `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 1306e8004d..b25d1e3cac 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -178,6 +178,8 @@ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plug interface AgentEntry { readonly id: SessionId readonly agent: Agent + /** Runtime creator-agent ownership; independent of durable session lineage. */ + readonly owner: Agent | undefined readonly carrier: Scoped announced: boolean announcing: boolean @@ -303,7 +305,7 @@ export class AgentRegistry extends Service { */ register(agent: Agent): () => void { const dispose = this.ctx.effect(function* (this: AgentRegistry) { - yield this.enter(agent) + yield this.enter(agent, this.ctx.agent) this.announce(agent) }.bind(this), 'agents.register()') // eslint-disable-next-line @typescript-eslint/no-misused-promises -- synchronous cleanup; direct return preserves disposer identity @@ -317,12 +319,15 @@ export class AgentRegistry extends Service { * returned detach closure into its pre-installed composite teardown before * calling {@link announce}. Ordinary callers use {@link register}. * @param agent - the prepared, unpublished agent. + * @param owner - live agent whose scoped context created this agent, or + * undefined for a top-level runtime root. This is runtime ownership, not + * the resumed session's durable parent lineage. * @returns an idempotent closure that removes this exact entry and emits * `agent/disposed` with listener failures contained. When called from a * synchronous `agent/created` listener, removal and disposal wait until * that creation dispatch unwinds. */ - enter(agent: Agent): () => void { + enter(agent: Agent, owner: Agent | undefined): () => void { const id = agent.id const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume @@ -331,6 +336,7 @@ export class AgentRegistry extends Service { const entry: AgentEntry = { id, agent, + owner, carrier, announced: false, announcing: false, @@ -438,6 +444,18 @@ export class AgentRegistry extends Service { list(): Agent[] { return [...this.store.values()].map(entry => entry.agent) } + + /** + * All live top-level agents in registration order. A top-level agent was + * created without an owning agent context; durable session lineage does not + * affect this runtime relation, so a resumed fork may still be a root. + * @returns a fresh array; mutating it does not affect the registry. + */ + roots(): Agent[] { + return [...this.store.values()] + .filter(entry => entry.owner === undefined) + .map(entry => entry.agent) + } } export default AgentRegistry diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index cba833b212..5563d01cad 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -42,6 +42,7 @@ describe('AgentRegistry', () => { const dispose = ctx.agents.register(agent) expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.agents.list()).toEqual([agent]) + expect(ctx.agents.roots()).toEqual([agent]) expect(() => ctx.agents.register(stubAgent('a1'))).toThrow(/already registered/) dispose() @@ -49,6 +50,23 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('tracks runtime creator ownership separately from registry order', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const root = stubAgent('root') + const child = stubAgent('child') + const detachRoot = ctx.agents.enter(root, undefined) + ctx.agents.announce(root) + const detachChild = ctx.agents.enter(child, root) + ctx.agents.announce(child) + + expect(ctx.agents.list()).toEqual([root, child]) + expect(ctx.agents.roots()).toEqual([root]) + + detachChild() + detachRoot() + }) + it('rolls an entry back and pairs a partially delivered creation when a listener throws', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -94,7 +112,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) const first = stubAgent('split') - const detachFirst = ctx.agents.enter(first) + const detachFirst = ctx.agents.enter(first, undefined) expect(lifecycle).toEqual([]) ctx.agents.announce(first) expect(() => { ctx.agents.announce(first) }).toThrow(/already announced/) @@ -102,7 +120,7 @@ describe('AgentRegistry', () => { detachFirst() const replacement = stubAgent('split') - const detachReplacement = ctx.agents.enter(replacement) + const detachReplacement = ctx.agents.enter(replacement, undefined) detachFirst() expect(ctx.agents.get(replacement.id)).toBe(replacement) expect(() => { ctx.agents.announce(first) }).toThrow(/not live/) @@ -122,7 +140,7 @@ describe('AgentRegistry', () => { }) ctx.on('agent/created', () => void order.push(`second:${ctx.agents.get(agent.id) === agent}`)) ctx.on('agent/disposed', () => void order.push('disposed')) - const detach = ctx.agents.enter(agent) + const detach = ctx.agents.enter(agent, undefined) ctx.agents.announce(agent) expect(order).toEqual(['first:true', 'after-detach:true', 'second:true', 'disposed']) expect(ctx.agents.get(agent.id)).toBeUndefined() diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 2a4d620494..a295274786 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,18 +95,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one configured agent. Hold the live object directly: its - // per-run id is intentionally fresh, while `main` remains only the - // terminal's fixed display label. At install the configured agent is the - // earliest registry entry (it creates any subagents later). During HMR the - // replacement is published after the old tree, so when old teardown finally - // emits disposed, the newest survivor is the replacement. Persisted - // parentSession lineage is deliberately irrelevant: a resumed child session - // can itself be this process's configured top-level agent. - let target: Agent | undefined = ctx.agents.list()[0] - ctx.on('agent/created', (agent) => { target ??= agent }) + // This app owns one configured top-level agent. Hold the live object + // directly: its per-run id is intentionally fresh, while `main` remains only + // the terminal's fixed display label. Runtime creator ownership distinguishes + // that root from its subagents even if a child is registered after an HMR + // replacement. Persisted parentSession lineage is deliberately irrelevant: + // a resumed child session can itself be this process's configured root. + let target: Agent | undefined = ctx.agents.roots()[0] + ctx.on('agent/created', () => { target ??= ctx.agents.roots()[0] }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = ctx.agents.list().at(-1) + if (target === agent) target = ctx.agents.roots().at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/readline.spec.ts b/packages/ui/stdio-agent/tests/readline.spec.ts index 6116aa356f..fa82db4d96 100644 --- a/packages/ui/stdio-agent/tests/readline.spec.ts +++ b/packages/ui/stdio-agent/tests/readline.spec.ts @@ -16,9 +16,9 @@ function fakeContext(): Context { return { on: vi.fn(() => vi.fn()), effect: vi.fn((callback: () => () => void) => callback()), - // The UI seeds its target object from the registry at install; this suite only + // The UI seeds its root target from the registry at install; this suite only // exercises readline terminal-mode selection, so an empty roster suffices. - agents: { list: vi.fn(() => []) }, + agents: { roots: vi.fn(() => []) }, userInteraction: { registerProvider: vi.fn(() => vi.fn()) }, } as unknown as Context } diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2654a05680..2600fdb24f 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -154,8 +154,7 @@ describe('createStdioChat rendering', () => { it('renders turn/start and turn/end markers from the session feed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - // agent/created supplies the app-owned target object. - ctx.emit('agent/created', agent) + ctx.agents.register(agent) const session = agent.session ctx.emit('session/event', session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } }, @@ -203,7 +202,7 @@ describe('createStdioChat rendering', () => { const { ctx, input } = await setup() const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' - ctx.emit('agent/created', resumed) + ctx.agents.register(resumed) input.feed('continue') await new Promise(resolve => setImmediate(resolve)) @@ -224,8 +223,8 @@ describe('createStdioChat rendering', () => { it('drops the target object on agent/disposed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - ctx.emit('agent/created', agent) - ctx.emit('agent/disposed', agent) + const dispose = ctx.agents.register(agent) + dispose() // After disposal the event belongs to a non-target session, so its durable // identity is rendered directly. ctx.emit('session/event', agent.session, { @@ -237,7 +236,7 @@ describe('createStdioChat rendering', () => { it('keeps the target when a different agent is disposed', async () => { const { ctx, out } = await setup() const target = makeAgent('target') - ctx.emit('agent/created', target) + ctx.agents.register(target) ctx.emit('agent/disposed', makeAgent('other')) ctx.emit('session/event', target.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, @@ -251,19 +250,27 @@ describe('createStdioChat rendering', () => { const child = makeAgent('child') ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id const replacement = makeAgent('replacement') + const lateChild = makeAgent('late-child') const disposeOld = ctx.agents.register(oldRoot) - ctx.agents.register(child) + const disposeChild = ctx.agents.enter(child, oldRoot) + ctx.agents.announce(child) ctx.agents.register(replacement) + const disposeLateChild = ctx.agents.enter(lateChild, replacement) + ctx.agents.announce(lateChild) // The replacement's created edge arrived while oldRoot was still targeted. - // Once oldRoot is removed, registry order is child then replacement; the - // most recently published survivor is the HMR replacement. + // A replacement-owned child then arrived even later. Once oldRoot is + // removed, runtime ownership still identifies replacement as the only + // surviving root instead of selecting either newer child by insertion order. disposeOld() input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) expect(child.sent).toEqual([]) + expect(lateChild.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) + disposeLateChild() + disposeChild() }) it('renders tool/call and tool/result session events', async () => { From 99b5f04c9bb5ff2ac78d9cc30ce22d65a181c097 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:26:46 +0800 Subject: [PATCH 07/39] fix: use unified identity for bash ownership --- docs/core-data-structures/bash.md | 2 +- ...-18-agent-lifecycle-and-ownership-seams.md | 4 +- .../architecture/2026-06-20-branded-ids.md | 4 +- packages/bash/bash/src/types.ts | 2 +- packages/bash/tool-bash/README.md | 4 +- packages/bash/tool-bash/src/index.ts | 22 ++++----- packages/bash/tool-bash/tests/tools.spec.ts | 46 +++++++++---------- .../cordis/tool-cordis/src/api-catalog.ts | 3 +- 8 files changed, 40 insertions(+), 47 deletions(-) diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index df6c5ab16b..0cc82e5165 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -37,7 +37,7 @@ interface BashExecRequest { env?: Record | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key - * (the tool layer passes the owning agent's `session.header.id`). The + * (the tool layer passes the owning agent's shared `id`). The * executor stores it on the task and exposes it via {@link BashExecutor.ownerOf}; * the executor itself NEVER interprets it (no access policy lives in the * seam — that is the consumer's job). Absent for foreground runs and for an diff --git a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md index d64329262e..d75ec379fc 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +++ b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md @@ -22,7 +22,7 @@ A new `cancel()` verb on the `Agent` interface — the single public stop primit ### 3. Bash owner token in the seam -Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.session.header.id` as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.session.header.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.id` (the shared registry/session id) as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## Verification @@ -35,7 +35,7 @@ These invariants hold and are pinned by tests: ## Session owner tokens are unique among live agents -The bash owner-token comparison relies on `session.header.id` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. +The bash owner-token comparison relies on the shared `Agent.id`/`SessionId` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 4fe7f58168..fd5c5bf953 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's shared `Agent.id`/`SessionId` (`callerToken = (exec) => exec.agent?.id` in `packages/bash/tool-bash/src/index.ts`) wearing a different seam-local name. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the shared id alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -18,7 +18,7 @@ A type-only change. Brands are zero-cost casts; nothing about runtime behavior, - **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). -- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) +- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's shared `id` (`SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) - **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index 39dbc162c6..c4c48645e1 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -117,7 +117,7 @@ export interface BashExecRequest { env?: Record | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key - * (the tool layer passes the owning agent's `session.header.id`). The + * (the tool layer passes the owning agent's shared `id`). The * executor stores it on the task and exposes it via {@link BashExecutor.ownerOf}; * the executor itself NEVER interprets it (no access policy lives in the * seam — that is the consumer's job). Absent for foreground runs and for an diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index 800de0132c..c4ea498e07 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -34,7 +34,7 @@ Result text: stdout, then a `[stderr]` section, then status markers — `[sandbo ### Task ownership (cross-session isolation) -The owning agent's session token (`session.header.id`) is stamped onto the task at spawn — passed to the executor via `resolve({ …, owner })` and stored ON THE TASK inside the executor (the `dsh-bash` `ownerOf(id)` seam), **not** in a plugin-local map. `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token (`session.header.id`) with `!== undefined` semantics and reject a task owned by a *different* session with `task belongs to another session` (a task started with no agent — a non-loop caller — has no owner token and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this token check is the fence that stops one session's agent from reading or killing another session's background task. Because ownership lives on the task in the executor (disposed with the `dsh-bash` fiber), it **survives an independent `tool-bash` HMR reload** — closing the old plugin-local-map gap where a reload orphaned pre-reload tasks. (The `onTaskDone` listener is still effect-scoped to this plugin's `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +The owning agent's shared registry/session id (`agent.id`) is stamped onto the task at spawn — passed to the executor via `resolve({ …, owner })` and stored ON THE TASK inside the executor (the `dsh-bash` `ownerOf(id)` seam), **not** in a plugin-local map. `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's shared id with `!== undefined` semantics and reject a task owned by a *different* session with `task belongs to another session` (a task started with no agent — a non-loop caller — has no owner token and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this token check is the fence that stops one session's agent from reading or killing another session's background task. Because ownership lives on the task in the executor (disposed with the `dsh-bash` fiber), it **survives an independent `tool-bash` HMR reload** — closing the old plugin-local-map gap where a reload orphaned pre-reload tasks. (The `onTaskDone` listener is still effect-scoped to this plugin's `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## UI presentation @@ -42,7 +42,7 @@ These tools own how their calls render in a UI (an editor's tool-call card) via ## Background completion notices -When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). The owning agent is found by its session token: the listener reads `ctx.bash.ownerOf(task.id)` and scans `ctx.get('agents')?.list()` for an agent whose `session.header.id` matches (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, so the `ctx.agents` proxy would throw). If no live agent carries that token — e.g. the owning session disconnected and its agent was disposed while the task ran on — the notice is dropped cleanly. Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`. +When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). The listener reads `ctx.bash.ownerOf(task.id)` and scans `ctx.get('agents')?.list()` for that shared agent/session id (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, so the `ctx.agents` proxy would throw). If no live agent carries that token — e.g. the owning session disconnected and its agent was disposed while the task ran on — the notice is dropped cleanly. Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`. ## The tool builds its request from named args only diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 31e6512ae0..fe07b80989 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -12,7 +12,7 @@ * `bash_output`. * * Task ownership: a background task's OWNER is an opaque token — the owning - * agent's `session.header.id` — passed to the executor at spawn + * agent's shared `id` — passed to the executor at spawn * (`resolve({ …, owner })`) and stored ON THE TASK inside the executor * (`@deepseek-ai/dsh-bash`'s `ownerOf(id)` seam), NOT in a plugin-local map. * `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token @@ -414,16 +414,12 @@ export function apply(ctx: Context): void { }) /** - * The caller's owner TOKEN — the owning agent's `session.header.id`, or - * `undefined` for a non-agent caller. Read `session.header.id` (NOT - * `session.id`): every other subsystem keys off the header id (the ACP bridge, - * both persistence backends), and the sibling `resolveWorkdir` already reads - * `session.header.cwd`, so using `session.id` here would be the asymmetry smell - * the conventions flag. The two are equal in production, but the header is the - * canonical identity. + * The caller's owner TOKEN — the owning agent's shared registry/session id, + * or `undefined` for a non-agent caller. Agent and Session deliberately have + * one live identity; workdir remains separate session metadata. */ const callerToken = (exec: { agent?: Agent }): OwnerToken | undefined => - exec.agent ? OwnerToken(exec.agent.session.header.id) : undefined + exec.agent ? OwnerToken(exec.agent.id) : undefined /** * Authorize a `bash_output`/`bash_kill` call against the task's stored owner @@ -443,18 +439,16 @@ export function apply(ctx: Context): void { } // Background completion → inject a notice into the owning agent's session. - // Find the live agent by its session id token via the agent registry, read + // Find the live agent by its shared registry/session token, read // opportunistically with `ctx.get('agents')` (NOT `ctx.agents`/static inject): // this listener runs from `task.done.then` on the bash fiber — a foreign // fiber — where the `ctx.agents` property proxy would throw through the // traceable shadow; `ctx.get(name)` is the topology-independent lookup. No - // registry mounted (`undefined`) → drop the notice. Match on - // `agent.session.header.id`, NOT the registry key: a config agent's id differs - // from its session id, and the owner token IS the session id. + // registry mounted (`undefined`) → drop the notice. ctx.bash.onTaskDone((task) => { const ownerToken = ctx.bash.ownerOf(task.id) if (ownerToken === undefined) return - const agent = ctx.get('agents')?.list().find(a => OwnerToken(a.session.header.id) === ownerToken) + const agent = ctx.get('agents')?.list().find(a => OwnerToken(a.id) === ownerToken) if (!agent) return try { agent.inject( diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index c68c445f0a..639dd8631a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -47,22 +47,16 @@ async function setup() { } /** - * Build a fake {@link Agent} whose session token is `sessionId`, REGISTER it in - * `ctx.agents` (the completion-notice path finds the owning agent by scanning - * the registry for a matching `session.header.id`), and return it. The returned + * Build a fake {@link Agent} with the shared registry/session `sessionId`, + * REGISTER it in `ctx.agents`, and return it. The returned * agent is also passed to `execute` as `exec.agent` so it owns the spawned task. * The registration disposer is tracked so {@link unregisterFakeAgents} can drop * it (simulating the owning session disconnecting before a task completes). */ const fakeAgentDisposers = new Map Promise | void)[]>() function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent { - // The registry KEY (agent.id) is deliberately DIFFERENT from the session - // token (session.header.id), which is also the agent's durable id. The - // owner token IS the session id, so the notice path must find the agent by - // `session.header.id`, NOT the registry key. Using distinct values here makes - // the test fail if a regression matched on the wrong field (a same-value fake - // would pass either way — the "hits the line but not the scenario" trap). - const agent = { id: `agent-${sessionId}`, inject, session: { header: { version: 0, id: sessionId, createdAt: 0 } } } as unknown as Agent + const id = SessionId(sessionId) + const agent = { id, inject, session: new Session(id) } as unknown as Agent const dispose = ctx.agents.register(agent) const list = fakeAgentDisposers.get(ctx) ?? [] list.push(dispose) @@ -418,9 +412,9 @@ describe('background tools', () => { it('injects a completion notice into the owning agent (found via the registry by session token)', async () => { const ctx = await setup() const inject = vi.fn() - // The notice path looks the agent up in ctx.agents by its session token, so + // The notice path looks the agent up in ctx.agents by its shared id, so // the agent must be REGISTERED (not merely passed to execute). Mount a - // registry and register a fake whose session.header.id IS the owner token. + // registry and register a fake whose agent/session id IS the owner token. const agent = registerFakeAgent(ctx, 'bg', inject) const started = await ctx.tools.execute({ @@ -517,13 +511,14 @@ describe('background task ownership (cross-session isolation)', () => { function callAs(ctx: Context, agent: import('@deepseek-ai/dsh-agent').Agent | undefined, name: string, args: unknown) { return ctx.tools.execute({ callId: CallId(`own-${++callCounter}`), name, arguments: args, ...agent ? { agent } : {} }) } - // Ownership is by TOKEN (session.header.id), NOT agent object identity — so - // each agent needs a DISTINCT session id, else every fake yields the same + // Ownership is by the shared agent/session TOKEN, NOT agent object identity — + // so each agent needs a DISTINCT id, else every fake yields the same // token and the isolation tests pass for the wrong reason (all tasks owned by - // the same token). The impl reads `session.header.id`, so the fakes MUST carry - // it. - const fakeAgent = (sessionId: string) => - ({ inject: () => undefined, session: { header: { version: 0, id: sessionId, createdAt: 0 } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent + // the same token). + const fakeAgent = (sessionId: string) => { + const id = SessionId(sessionId) + return { id, inject: () => undefined, session: new Session(id) } as unknown as import('@deepseek-ai/dsh-agent').Agent + } it('rejects bash_output/bash_kill for a task owned by a DIFFERENT session token', async () => { const ctx = await setup() @@ -548,7 +543,7 @@ describe('background task ownership (cross-session isolation)', () => { }) it('a DIFFERENT Agent object with the SAME session token may access the task (ownership is by token, not object identity)', async () => { - // Ownership fences by session.header.id, NOT Agent object identity. Two + // Ownership fences by the shared id, NOT Agent object identity. Two // distinct Agent objects sharing one session token (e.g. an agent re-created // on the same session) are the SAME owner. const ctx = await setup() @@ -638,8 +633,10 @@ describe('session-cwd routing (per-session workdir)', () => { return ctx.tools.execute({ callId: CallId(`cwd-${++callCounter}`), name: 'bash', arguments: args, ...agent ? { agent } : {} }) } // An agent whose session header carries a cwd (what session/new records). - const agentInCwd = (cwd: string) => - ({ inject: () => undefined, session: { header: { version: 0, id: 'c', createdAt: 0, cwd } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent + const agentInCwd = (cwd: string) => { + const id = SessionId('c') + return { id, inject: () => undefined, session: { header: { version: 0, id, createdAt: 0, cwd } } } as unknown as import('@deepseek-ai/dsh-agent').Agent + } it('defaults bash to the agent\'s session cwd (not the server launch dir)', async () => { const ctx = await setup() @@ -1188,10 +1185,11 @@ describe('sandbox escalation (sandbox_permissions / justification)', () => { * enforces the enclosure. */ function escalationAgent(events: Array<{ type: string; data: Record }>): Agent { + const id = SessionId('sess-esc') return { - id: 'agent-esc', + id, session: { - header: { version: 0, id: 'sess-esc', createdAt: 0 }, + header: { version: 0, id, createdAt: 0 }, events: [{ type: 'turn/start' }], append: (type: string, data: Record) => { events.push({ type, data }) }, }, @@ -1406,7 +1404,7 @@ describe('per-session sandbox mode (the bash/sandbox-mode fold)', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) const injected: string[] = [] const agent = { - id, + id: SessionId(id), session, inject: (content: { type: string; text: string }[]) => { injected.push(content[0]?.text ?? '') }, } as unknown as Agent diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..ff27f51067 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -69,10 +69,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', 'register(agent: Agent): () => void', - 'enter(agent: Agent): () => void', + 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { From f02005c832b450d65d372c935c612c7d83eec54d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:39:28 +0800 Subject: [PATCH 08/39] fix: enforce unified agent startup invariants --- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 3 +++ packages/core/agent/tests/agent.spec.ts | 12 ++++++++- .../hooks/hooks-claude/tests/coverage.spec.ts | 8 +++--- packages/subagent/subagent-acp/src/run.ts | 11 ++++---- .../subagent-acp/tests/mock-acp-server.ts | 3 +++ .../subagent-acp/tests/subagent-acp.spec.ts | 26 +++++++++++++++++++ 7 files changed, 55 insertions(+), 10 deletions(-) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 643c15002b..a45603f191 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -11,7 +11,7 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. -- Advanced ordered lifecycle: `enter(agent, owner): () => void` performs the authoritative ID collision check and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. +- Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index b25d1e3cac..abafa38e45 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -329,6 +329,9 @@ export class AgentRegistry extends Service { */ enter(agent: Agent, owner: Agent | undefined): () => void { const id = agent.id + if (id !== agent.session.id) { + throw new Error(`agent id "${id}" does not match session id "${agent.session.id}"`) + } const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume // operations may both prepare, but only one exact entry can publish. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5563d01cad..d2866cacb3 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -11,7 +11,7 @@ function stubAgent(rawId: string): Agent { return { id, options: {}, - session: new Session(SessionId(`${id}-session`)), + session: new Session(id), status: 'idle', ctx: new Context(), send() {}, @@ -50,6 +50,16 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('rejects an agent whose registry and session identities differ', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const agent = { ...stubAgent('agent-id'), session: new Session(SessionId('session-id')) } + + expect(() => ctx.agents.enter(agent, undefined)) + .toThrow('agent id "agent-id" does not match session id "session-id"') + expect(ctx.agents.list()).toEqual([]) + }) + it('tracks runtime creator ownership separately from registry order', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 16c48aa149..0b41fd0d10 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -4,7 +4,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { Session, SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' @@ -209,7 +209,8 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const ctx = await harness(path, new MockAdapter([])) // Register a fake child agent under the id the event carries. const injected: string[] = [] - const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + const childId = SessionId('child-x') + const child = { id: childId, inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: new Session(childId) } as unknown as Parameters[0] ctx.agents.register(child) ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) await waitFor(() => injected.includes('child guidance')) @@ -225,7 +226,8 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + const childId = SessionId('child-y') + const child = { id: childId, inject: () => { throw new Error('inject boom') }, session: new Session(childId) } as unknown as Parameters[0] ctx.agents.register(child) ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 7d0c11cbe1..8ef49f0f7d 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -311,7 +311,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = session.sessionId + const returnedSessionId: unknown = Reflect.get(session, 'sessionId') + if (typeof returnedSessionId !== 'string') throw new Error('ACP child published without a session id') + sessionId = returnedSessionId if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -323,10 +325,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe if (flags.cancelled) throw new Error('subagent request was aborted before the ACP child started') throw toError(error) } - // The startup race can fulfill only after newSession assigned the id; this - // guard keeps that cross-closure invariant explicit for TypeScript. - /* v8 ignore next */ - if (sessionId === undefined) throw new Error('ACP child published without a session id') + // The startup transaction validates the returned id before it can fulfill. + // This assertion carries that cross-closure invariant into TypeScript. + if (sessionId === undefined) throw new Error('unreachable: ACP startup fulfilled without a session id') const remoteSessionId = sessionId const result: Promise = (async (): Promise => { diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index 5145941526..f56404834b 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -19,6 +19,8 @@ * handler is in flight (it has streamed its chunk). A test * polls for this file to cancel on a CONDITION rather than * an arbitrary timeout (subprocess cold-start is variable). + * - `MOCK_MISSING_SESSION_ID` — if `1`, return a malformed empty `session/new` + * response to exercise startup rollback. * - `MOCK_FLUSH_ON_EOF` — if set, on stdin EOF the agent takes an async beat * (MOCK_FLUSH_DELAY_MS, default 150) simulating the real * acp-agent's EOF-driven quiesce+flush, then touches this @@ -99,6 +101,7 @@ function makeAgent(conn: AgentSideConnection): Agent { writeFileSync(NEWSESSION_GATE.ready, 'at-newSession') while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10)) } + if (process.env.MOCK_MISSING_SESSION_ID === '1') return {} as NewSessionResponse return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index e5fe05384e..daa037ca20 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -195,6 +195,32 @@ describe('dsh-subagent-acp', () => { } }) + it('reaps a child whose session/new response omits the session id', async () => { + const tmp = mkdtempSync(join(tmpdir(), 'acp-malformed-session-')) + const flushed = join(tmp, 'flushed') + try { + await expect(startAcpRun(request(), { + command: process.execPath, + args: ['--import', tsxLoader, mockServer], + cwd: process.cwd(), + permission: 'reject', + env: { + MOCK_MISSING_SESSION_ID: '1', + MOCK_FLUSH_ON_EOF: flushed, + MOCK_FLUSH_DELAY_MS: '20', + TSX_TSCONFIG_PATH: repoTsconfig, + }, + disposeEofGraceMs: 1000, + disposeGraceMs: 100, + })).rejects.toThrow('ACP child published without a session id') + // Startup rejects only after its private child reaches quiescence. The + // marker proves rollback closed stdin and allowed the child's EOF flush. + expect(existsSync(flushed)).toBe(true) + } finally { + rmSync(tmp, { recursive: true, force: true }) + } + }) + it('dispose escalates SIGTERM → SIGKILL for a child that traps SIGTERM (bounded quiescence)', async () => { // The child traps SIGTERM and keeps its event loop alive, so a graceful // term alone would hang dispose forever. With a short grace, dispose must From a9c4fe2c4ba9f92a85117d60ad01ce1ee5930c69 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:43:01 +0800 Subject: [PATCH 09/39] test: exclude validated ACP assertion --- packages/subagent/subagent-acp/src/run.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 8ef49f0f7d..e135beb210 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -327,6 +327,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe } // The startup transaction validates the returned id before it can fulfill. // This assertion carries that cross-closure invariant into TypeScript. + /* v8 ignore next */ if (sessionId === undefined) throw new Error('unreachable: ACP startup fulfilled without a session id') const remoteSessionId = sessionId From 2dea4afac0d49976700139a766d40734e3204f4e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:23:02 +0800 Subject: [PATCH 10/39] fix: bind stdio to its configured agent --- packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 5 ++- packages/ui/stdio-agent/src/stdio-chat.ts | 30 +++++++++++----- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 35 ++++++++++++++----- 4 files changed, 53 insertions(+), 19 deletions(-) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 82da64cd81..d7d30ee49d 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id. Resumed sessions register under the exact `resumeSessionId` and keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id; the UI binds to that fresh-id namespace, or to the exact `resumeSessionId` for a resumed run, and never selects unrelated registry roots. Resumed sessions keep the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index f01c48a615..2eca0cceb3 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -124,5 +124,8 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.' }) + ctx.plugin(uiStdio, { + welcome: config.welcome ?? 'ready.', + ...config.resumeSessionId !== undefined ? { resumeSessionId: config.resumeSessionId } : {}, + }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index a295274786..76347c91e4 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -36,10 +36,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string + /** Exact persisted session id the app configured for resume; absent selects the app's fresh `main-session-*` identity. */ + resumeSessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), + resumeSessionId: z.string(), }) /** @@ -95,16 +98,25 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one configured top-level agent. Hold the live object - // directly: its per-run id is intentionally fresh, while `main` remains only - // the terminal's fixed display label. Runtime creator ownership distinguishes - // that root from its subagents even if a child is registered after an HMR - // replacement. Persisted parentSession lineage is deliberately irrelevant: - // a resumed child session can itself be this process's configured root. - let target: Agent | undefined = ctx.agents.roots()[0] - ctx.on('agent/created', () => { target ??= ctx.agents.roots()[0] }) + // Bind only to this app's configured top-level agent. Fresh runs own the + // `main-session-*` namespace; resumed runs own the exact persisted id. The + // registry's runtime-root relation excludes subagents without confusing it + // with durable parentSession lineage. Keeping the matching candidates also + // covers HMR's publish-new-before-dispose-old ordering without ever falling + // through to an unrelated root owned by another app or test fixture. + const matchesConfiguredIdentity = (agent: Agent): boolean => config.resumeSessionId === undefined + ? agent.id.startsWith('main-session-') + : agent.id === config.resumeSessionId + const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) + let target: Agent | undefined = [...configuredRoots].at(-1) + ctx.on('agent/created', (agent) => { + if (!matchesConfiguredIdentity(agent) || !ctx.agents.roots().includes(agent)) return + configuredRoots.add(agent) + target ??= agent + }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = ctx.agents.roots().at(-1) + configuredRoots.delete(agent) + if (target === agent) target = [...configuredRoots].at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2600fdb24f..668068a72d 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -74,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there' } +const CONFIG: Config = { welcome: 'hi there', resumeSessionId: 'main' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -199,7 +199,9 @@ describe('createStdioChat rendering', () => { }) it('accepts a lineage-bearing configured agent created after the UI installs', async () => { - const { ctx, input } = await setup() + const { ctx, input } = await setup({ welcome: 'hi there', resumeSessionId: 'resumed' }) + const unrelated = makeAgent('unrelated') + ctx.agents.register(unrelated) const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(resumed) @@ -207,6 +209,7 @@ describe('createStdioChat rendering', () => { input.feed('continue') await new Promise(resolve => setImmediate(resolve)) + expect(unrelated.sent).toEqual([]) expect(resumed.sent).toEqual([[{ type: 'text', text: 'continue' }]]) }) @@ -235,7 +238,7 @@ describe('createStdioChat rendering', () => { it('keeps the target when a different agent is disposed', async () => { const { ctx, out } = await setup() - const target = makeAgent('target') + const target = makeAgent('main') ctx.agents.register(target) ctx.emit('agent/disposed', makeAgent('other')) ctx.emit('session/event', target.session, { @@ -245,11 +248,11 @@ describe('createStdioChat rendering', () => { }) it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { - const { ctx, input } = await setup() - const oldRoot = makeAgent('old-root') + const { ctx, input } = await setup({ welcome: 'hi there' }) + const oldRoot = makeAgent('main-session-old') const child = makeAgent('child') ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id - const replacement = makeAgent('replacement') + const replacement = makeAgent('main-session-replacement') const lateChild = makeAgent('late-child') const disposeOld = ctx.agents.register(oldRoot) const disposeChild = ctx.agents.enter(child, oldRoot) @@ -273,6 +276,22 @@ describe('createStdioChat rendering', () => { disposeChild() }) + it('does not retarget stdin to an unrelated root after the configured agent is disposed', async () => { + const { ctx, input } = await setup() + const unrelated = makeAgent('unrelated') + ctx.agents.register(unrelated) + const configured = makeAgent('main') + const disposeConfigured = ctx.agents.register(configured) + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + + disposeConfigured() + input.feed('must not leak') + await new Promise(resolve => setImmediate(resolve)) + + expect(unrelated.sent).toEqual([]) + expect(error).toHaveBeenCalledWith('ui-stdio: main agent is not running') + }) + it('renders tool/call and tool/result session events', async () => { const { ctx, out } = await setup() const session = {} as Session @@ -720,8 +739,8 @@ describe('createStdioChat input', () => { expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') }) - it('drives the app-owned agent without a duplicate id config', async () => { - const { ctx, input } = await setup({ welcome: 'w' }) + it('drives the exact app-configured resumed session', async () => { + const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: 'worker' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') From ccd810f84d74ce452d858b553eb0cbdb282d715c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:36:22 +0800 Subject: [PATCH 11/39] fix: normalize empty stdio resume identity --- packages/ui/stdio-agent/src/stdio-chat.ts | 5 +++-- packages/ui/stdio-agent/tests/stdio-chat.spec.ts | 9 +++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 76347c91e4..17a11168db 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -104,9 +104,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // with durable parentSession lineage. Keeping the matching candidates also // covers HMR's publish-new-before-dispose-old ordering without ever falling // through to an unrelated root owned by another app or test fixture. - const matchesConfiguredIdentity = (agent: Agent): boolean => config.resumeSessionId === undefined + const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId + const matchesConfiguredIdentity = (agent: Agent): boolean => resumeSessionId === undefined ? agent.id.startsWith('main-session-') - : agent.id === config.resumeSessionId + : agent.id === resumeSessionId const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) let target: Agent | undefined = [...configuredRoots].at(-1) ctx.on('agent/created', (agent) => { diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 668068a72d..2ebc51e14e 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -747,6 +747,15 @@ describe('createStdioChat input', () => { await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) }) + + it('treats an empty resume session id as a fresh configured identity', async () => { + const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: '' }) + const agent = makeAgent('main-session-fresh') + ctx.agents.register(agent) + input.feed('hi') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toHaveLength(1) + }) }) describe('createStdioChat EOF exit', () => { From 6b782b018927139ea07e5907488b0b948d90c813 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:54:34 +0800 Subject: [PATCH 12/39] fix: bind stdio to its exact fresh identity --- docs/config-catalog.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/core/agent-loop/README.md | 5 ++- packages/core/agent-loop/src/index.ts | 11 +++-- .../tests/config-session-id.spec.ts | 30 +++++++++++++ packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 7 ++- packages/ui/stdio-agent/src/stdio-chat.ts | 32 +++++--------- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 13 ++++++ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 44 +++++-------------- 10 files changed, 88 insertions(+), 62 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 94d613bc4e..66791edb0a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -119,6 +119,8 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string + /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -645,7 +647,7 @@ export interface Config { Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/ui/stdio-agent/src/index.ts:64`](../packages/ui/stdio-agent/src/index.ts) +Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 032eae4f7d..404ba83636 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -16,7 +16,7 @@ Session itself repeated the same fact as `Session.id` and `Session.header.id`. C An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f40577bb95..246c9cdc27 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary; an app may instead supply an exact fresh `sessionId` when another coupled component must bind to it. `resumeSessionId` loads and registers the exact persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -33,6 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required stable label; prefixes fresh combined ids + sessionId?: string // optional exact identity for a fresh session model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -40,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` and optional `sessionId` apply only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index dbe503ff6a..0041b984d1 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -326,6 +326,8 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string + /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -341,6 +343,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), + sessionId: z.string(), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), @@ -360,12 +363,14 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('model', context => context.agent?.options.model) ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) - for (const { id, cwd, resumeSessionId, ...options } of config.agents) { + for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { if (resumeSessionId === undefined || resumeSessionId === '') { - const sessionId = SessionId(`${id}-session-${randomUUID()}`) - this.create(sessionId, options, cwd === undefined ? {} : { cwd }) + this.create(sessionId ?? SessionId(`${id}-session-${randomUUID()}`), options, cwd === undefined ? {} : { cwd }) continue } + if (sessionId !== undefined) { + throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) + } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 134ea68c32..543335e5fd 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -24,7 +24,37 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } +async function makeCoreContext(): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + return ctx +} + describe('config-driven session id', () => { + it('accepts one exact fresh id and rejects it alongside a resume id', async () => { + const exact = await makeCoreContext() + await exact.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact'), model: 'mock' }], + }) + expect(exact.agents.get(SessionId('stdio-exact'))?.session.id).toBe('stdio-exact') + await exact.fiber.dispose() + + const conflicting = await makeCoreContext() + await expect(conflicting.plugin(AgentLoop, { + agents: [{ + id: 'main', + sessionId: SessionId('fresh'), + resumeSessionId: SessionId('persisted'), + model: 'mock', + }], + })).rejects.toThrow('sessionId and resumeSessionId are mutually exclusive') + await conflicting.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index d7d30ee49d..b509e46781 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id; the UI binds to that fresh-id namespace, or to the exact `resumeSessionId` for a resumed run, and never selects unrelated registry roots. Resumed sessions keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; the UI's `main` text is only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 2eca0cceb3..03f3d49555 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -39,6 +39,7 @@ */ import type { Context } from 'cordis' +import { randomUUID } from 'node:crypto' import ConsoleExporter from '@cordisjs/plugin-logger-console' import z from 'schemastery' import { SessionId } from '@deepseek-ai/dsh-session' @@ -108,6 +109,8 @@ export const Config: z = z.object({ * a leaf concern (see the module doc), so it is not mounted here. */ export function apply(ctx: Context, config: Config): void { + const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId + const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, @@ -117,7 +120,7 @@ export function apply(ctx: Context, config: Config): void { id: 'main', model: config.model, cwd: process.cwd(), - ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, + ...resumeSessionId === undefined ? { sessionId } : { resumeSessionId: sessionId }, }], ...config.skills !== undefined ? { skills: config.skills } : {}, }) @@ -126,6 +129,6 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(toolAskUser) ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', - ...config.resumeSessionId !== undefined ? { resumeSessionId: config.resumeSessionId } : {}, + sessionId, }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 17a11168db..93c8f9b4f1 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -36,13 +36,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - /** Exact persisted session id the app configured for resume; absent selects the app's fresh `main-session-*` identity. */ - resumeSessionId?: string + /** Exact shared agent/session identity this app instance created or resumed. */ + sessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - resumeSessionId: z.string(), + sessionId: z.string(), }) /** @@ -98,26 +98,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // Bind only to this app's configured top-level agent. Fresh runs own the - // `main-session-*` namespace; resumed runs own the exact persisted id. The - // registry's runtime-root relation excludes subagents without confusing it - // with durable parentSession lineage. Keeping the matching candidates also - // covers HMR's publish-new-before-dispose-old ordering without ever falling - // through to an unrelated root owned by another app or test fixture. - const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId - const matchesConfiguredIdentity = (agent: Agent): boolean => resumeSessionId === undefined - ? agent.id.startsWith('main-session-') - : agent.id === resumeSessionId - const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) - let target: Agent | undefined = [...configuredRoots].at(-1) + // Bind only to the exact identity this app passed to its config-created + // agent. Session ids are opaque: neither a prefix nor registry order can + // identify ownership. The root check rejects a child that somehow preempts + // the configured id; later recreation under the same id supports loop HMR. + const matchesConfiguredIdentity = (agent: Agent): boolean => + agent.id === config.sessionId && ctx.agents.roots().includes(agent) + let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === config.sessionId) ctx.on('agent/created', (agent) => { - if (!matchesConfiguredIdentity(agent) || !ctx.agents.roots().includes(agent)) return - configuredRoots.add(agent) - target ??= agent + if (matchesConfiguredIdentity(agent)) target = agent }) ctx.on('agent/disposed', (agent) => { - configuredRoots.delete(agent) - if (target === agent) target = [...configuredRoots].at(-1) + if (target === agent) target = undefined }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 5c5c0d2667..9a7bf10bad 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -93,6 +93,19 @@ describe('dsh-stdio-agent app', () => { await ctx.fiber.dispose() }) + it('normalizes an empty resume id to a fresh exact app identity', async () => { + const ctx = await mount({ + model: 'mock', + resumeSessionId: '', + persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', + skills: await isolatedSkillsConfig(), + }) + const agent = ctx.get('agents')?.list()[0] + expect(agent?.id).toMatch(/^main-session-[0-9a-f-]{36}$/) + expect(agent?.id).toBe(agent?.session.id) + await ctx.fiber.dispose() + }) + it('defaults persistenceRoot and welcome when omitted', async () => { // Direct apply (NOT via ctx.plugin, which validates+defaults the config // first) so the runtime `?? './.sessions'` / `?? 'ready.'` fallbacks on diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2ebc51e14e..f1ca914525 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -74,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there', resumeSessionId: 'main' } +const CONFIG: Config = { welcome: 'hi there', sessionId: 'main' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -199,7 +199,7 @@ describe('createStdioChat rendering', () => { }) it('accepts a lineage-bearing configured agent created after the UI installs', async () => { - const { ctx, input } = await setup({ welcome: 'hi there', resumeSessionId: 'resumed' }) + const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'resumed' }) const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) const resumed = makeAgent('resumed') @@ -247,33 +247,21 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 1] ') }) - it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { - const { ctx, input } = await setup({ welcome: 'hi there' }) - const oldRoot = makeAgent('main-session-old') - const child = makeAgent('child') - ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id - const replacement = makeAgent('main-session-replacement') - const lateChild = makeAgent('late-child') + it('retargets only the exact identity after loop HMR recreation', async () => { + const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'main-session-fixed' }) + const oldRoot = makeAgent('main-session-fixed') + const prefixCollision = makeAgent('main-session-unrelated') const disposeOld = ctx.agents.register(oldRoot) - const disposeChild = ctx.agents.enter(child, oldRoot) - ctx.agents.announce(child) - ctx.agents.register(replacement) - const disposeLateChild = ctx.agents.enter(lateChild, replacement) - ctx.agents.announce(lateChild) - - // The replacement's created edge arrived while oldRoot was still targeted. - // A replacement-owned child then arrived even later. Once oldRoot is - // removed, runtime ownership still identifies replacement as the only - // surviving root instead of selecting either newer child by insertion order. + ctx.agents.register(prefixCollision) disposeOld() + const replacement = makeAgent('main-session-fixed') + ctx.agents.register(replacement) + input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) - expect(child.sent).toEqual([]) - expect(lateChild.sent).toEqual([]) + expect(prefixCollision.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) - disposeLateChild() - disposeChild() }) it('does not retarget stdin to an unrelated root after the configured agent is disposed', async () => { @@ -740,7 +728,7 @@ describe('createStdioChat input', () => { }) it('drives the exact app-configured resumed session', async () => { - const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: 'worker' }) + const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') @@ -748,14 +736,6 @@ describe('createStdioChat input', () => { expect(agent.sent).toHaveLength(1) }) - it('treats an empty resume session id as a fresh configured identity', async () => { - const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: '' }) - const agent = makeAgent('main-session-fresh') - ctx.agents.register(agent) - input.feed('hi') - await new Promise(r => setImmediate(r)) - expect(agent.sent).toHaveLength(1) - }) }) describe('createStdioChat EOF exit', () => { From 2dca8e2151ef3745f88507fe2aac17cabd630eac Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:58:35 +0800 Subject: [PATCH 13/39] docs: refresh agent loop catalog location --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1366fcf6f6..6b456ef942 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From 816b6e4c68e26c38c4ac0aab1cad3ee14714a510 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:25:49 +0800 Subject: [PATCH 14/39] fix: restore exact config sessions on loop reload --- docs/config-catalog.md | 2 +- .../2026-06-20-unify-agent-and-session-id.md | 10 ++--- .../2026-07-02-remove-stream-chunk-mirror.md | 2 +- packages/core/agent-loop/README.md | 6 +-- packages/core/agent-loop/src/index.ts | 29 ++++++++++++++- .../tests/config-session-id.spec.ts | 37 +++++++++++++++++++ packages/ui/stdio-agent/README.md | 2 +- 7 files changed, 75 insertions(+), 13 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 66791edb0a..024d3b766b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -119,7 +119,7 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string - /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + /** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */ sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 404ba83636..20ba40c196 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -4,19 +4,19 @@ Status: implemented ## Problem -The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. +A live agent/session pair needs one identity for registry routing, event sourcing, and persistence. Giving the factory independent `agentId` and `sessionId` inputs would permit pairings no production path can use, while forcing every consumer to choose or translate between two names for the same lifecycle. -ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. +ACP uses the same value for both identities. Stdio and hooks also operate on the session event stream and need the corresponding live agent directly; no production path reattaches one live agent object to several sessions or drives one session through several agent ids. -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) uses one `AgentCreationTransaction` for create and resume, and agent/session entries share the same final-entry collision rule. A second identity would not represent separate liveness, rollback, or quiescence; it would only add API and translation state around the same transaction. -Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. +Session identity likewise has one home in `Session.header.id`; `Session.id` is a derived accessor rather than independent state that needs duplicate validation. ## Decision An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. An ordinary fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide. A coupled app may pre-mint and pass an exact `sessionId`: first use creates it, while an AgentLoop remount with an already-present persistence service resumes materialized history under that same identity. `resumeSessionId` instead requires an existing persisted identity. The two exact-id inputs are mutually exclusive. Stdio uses the resume-or-create form so its config-created agent and UI share one opaque identity across loop reloads instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. diff --git a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md b/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md index a272dfe0b2..6ca85b3d16 100644 --- a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md +++ b/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md @@ -42,4 +42,4 @@ Not touched: ## Consequences -A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event` and filters `assistant/chunk` (the `Agent` handle, if needed, is recovered from a session-id→agent map built from `agent/created`/`agent/disposed`, exactly as boundary consumers already do). No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made. +A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event`, filters `assistant/chunk`, and looks up the corresponding live handle directly with `ctx.agents.get(session.id)` when needed. No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 246c9cdc27..2db1a6c079 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary; an app may instead supply an exact fresh `sessionId` when another coupled component must bind to it. `resumeSessionId` loads and registers the exact persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary. An app may instead supply a stable exact `sessionId`: first use creates it, while a remount with persistence already present resumes its materialized history. `resumeSessionId` requires and loads an existing persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -33,7 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required stable label; prefixes fresh combined ids - sessionId?: string // optional exact identity for a fresh session + sessionId?: string // optional exact resume-or-create identity model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` and optional `sessionId` apply only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 0041b984d1..33e8c3c443 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -326,7 +326,7 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string - /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + /** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */ sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string @@ -364,8 +364,17 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { + const meta = cwd === undefined ? {} : { cwd } if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(sessionId ?? SessionId(`${id}-session-${randomUUID()}`), options, cwd === undefined ? {} : { cwd }) + const configuredId = sessionId ?? SessionId(`${id}-session-${randomUUID()}`) + const persistence = sessionId === undefined ? undefined : ctx.get('sessionPersistence') + if (persistence === undefined) { + this.create(configuredId, options, meta) + } else { + void this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) + }) + } continue } if (sessionId !== undefined) { @@ -385,6 +394,22 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Restore a materialized exact config identity on remount, or create it on first use. */ + private async restoreOrCreateConfigured( + ownerCtx: Context, + persistence: SessionPersistence, + sessionId: SessionId, + agentOptions: AgentOptions, + meta: Pick, + ): Promise { + const exists = (await persistence.list()).some(header => header.id === sessionId) + if (exists) { + await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) + return + } + this.create(sessionId, agentOptions, meta) + } + /** * Create an agent and session under one caller-supplied identity, owned by * the accessing fiber. Constructor-driven config calls mint a fresh combined diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 543335e5fd..9382804527 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -55,6 +55,43 @@ describe('config-driven session id', () => { await conflicting.fiber.dispose() }) + it('restores a materialized exact id across an AgentLoop-only reload', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first'), textResponse('second')])) + const config = { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-reload'), model: 'mock' }] } + + const firstLoop = await ctx.plugin(AgentLoop, config) + let first: ReactLoopAgent | undefined + for (let i = 0; i < 50 && first === undefined; i++) { + await new Promise(resolve => setTimeout(resolve, 5)) + first = ctx.agents.get(SessionId('stdio-exact-reload')) as ReactLoopAgent | undefined + } + expect(first).toBeDefined() + first!.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) + await waitForIdle(ctx, first!) + await firstLoop.dispose() + + const secondLoop = await ctx.plugin(AgentLoop, config) + let second: ReactLoopAgent | undefined + for (let i = 0; i < 50 && second === undefined; i++) { + await new Promise(resolve => setTimeout(resolve, 5)) + second = ctx.agents.get(SessionId('stdio-exact-reload')) as ReactLoopAgent | undefined + } + expect(second).toBeDefined() + expect(JSON.stringify(second!.session.deriveMessages())).toContain('remember me') + second!.send([{ type: 'text', text: 'continue' }], { source: { kind: 'user' } }) + await waitForIdle(ctx, second!) + await ctx.sessions.flush(second!.session) + const loaded = await ctx.sessionPersistence.load(SessionId('stdio-exact-reload')) + expect(loaded.events.filter(event => event.type === 'turn/start')).toHaveLength(2) + + await secondLoop.dispose() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index b509e46781..15b1c78f09 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; the UI's `main` text is only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin From 656ae95263cfd9f832bdeefbf9da6a91b8ce72bb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:28:04 +0800 Subject: [PATCH 15/39] test: await exact stdio startup condition --- packages/ui/stdio-agent/tests/stdio-agent.spec.ts | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 9a7bf10bad..a14848a549 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -114,9 +114,8 @@ describe('dsh-stdio-agent app', () => { const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) - await new Promise(resolve => setTimeout(resolve, 80)) - expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.list()).toHaveLength(1) + await expect.poll(() => ctx.get('sessionPersistence')).toBeDefined() + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) await ctx.fiber.dispose() }) From 949ee03377719aea96a26fd96ba0bc284cf740ec Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:38:53 +0800 Subject: [PATCH 16/39] test: cover exact session restore failure --- .../tests/config-session-id.spec.ts | 21 +++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 9382804527..dcde82efe2 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -92,6 +92,27 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('contains an exact-id persistence lookup failure', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const failure = new Error('persistence index failed') + vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-failure'), model: 'mock' }], + }) + + await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining( + 'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed', + )) + expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() + warn.mockRestore() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) From 46b8bce03acebd579cdcb4daf91c02e51eddf78e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:47:47 +0800 Subject: [PATCH 17/39] fix: join exact session startup on teardown --- docs/config-catalog.md | 2 +- docs/cordis-catalog/services.md | 2 +- packages/core/agent-loop/src/index.ts | 19 +++++++++++--- .../tests/config-session-id.spec.ts | 25 +++++++++++++++++++ 4 files changed, 42 insertions(+), 6 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 024d3b766b..d22bcca6f7 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:333`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 6b456ef942..e79422b94f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33e8c3c443..d2d8648595 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -45,6 +45,7 @@ const INACTIVE_STATES: ReadonlySet = new Set([ class FactoryOwnership { private accepting = true private transactions = new Set() + private startupTasks = new Set>() constructor(private readonly fiber: Context['fiber']) {} @@ -57,12 +58,20 @@ class FactoryOwnership { return () => { this.transactions.delete(transaction) } } + /** Join config startup work that begins before an agent transaction exists. */ + trackStartup(task: Promise): void { + this.startupTasks.add(task) + const forget = () => { this.startupTasks.delete(task) } + void task.then(forget, forget) + } + async dispose(): Promise { this.accepting = false const reason = new Error('agent loop is not active') - await Promise.all( - [...this.transactions].map(transaction => transaction.disposeForFactory(reason)), - ) + await Promise.all([ + ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), + ...this.startupTasks, + ]) } } @@ -371,9 +380,10 @@ export class AgentLoop extends Service implements AgentFactory { if (persistence === undefined) { this.create(configuredId, options, meta) } else { - void this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) }) + this.ownership.trackStartup(startup) } continue } @@ -403,6 +413,7 @@ export class AgentLoop extends Service implements AgentFactory { meta: Pick, ): Promise { const exists = (await persistence.list()).some(header => header.id === sessionId) + if (!this.ownership.isActive()) return if (exists) { await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) return diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index dcde82efe2..c1a04fadd0 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -113,6 +113,31 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const listing = Promise.withResolvers>>() + vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + const loop = await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], + }) + let disposed = false + const disposal = loop.dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) + + listing.resolve([]) + await disposal + expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(warn).not.toHaveBeenCalled() + warn.mockRestore() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) From e8f1bd41f5bd96c529c59ed524cfdeef7d3d1ce3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:02:18 +0800 Subject: [PATCH 18/39] fix: buffer stdio until exact session starts --- docs/event-producer-consumer.md | 2 +- packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/stdio-chat.ts | 65 ++++++++++++----- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 72 +++++++++++++++---- 4 files changed, 108 insertions(+), 33 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..1439873f69 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -15,7 +15,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 15b1c78f09..bbf175d92d 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 93c8f9b4f1..17d396c042 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -3,9 +3,10 @@ * `steer()`, and renders the durable transcript to stdout. A UI is "just a * plugin" — it consumes the `session/event` feed (the assistant token stream, * turn/step boundaries, tool activity, todos) plus a few `agent/*` control - * events (`agent/status`, `agent/created`/`agent/disposed`) and the `agents` - * service. Dimmed chain-of-thought rendering plus robust piped-stdin EOF→idle - * exit handling, configured via {@link Config}. + * events (`agent/status`, `agent/created`/`agent/disposed`, + * `agent/session-start`) and the `agents` service. Dimmed chain-of-thought + * rendering plus robust piped-stdin EOF→idle exit handling, configured via + * {@link Config}. * * An internal module of the stdio app, not a package of its own: the app's * front-door cluster always includes this UI, and nothing else composes it. @@ -105,12 +106,6 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const matchesConfiguredIdentity = (agent: Agent): boolean => agent.id === config.sessionId && ctx.agents.roots().includes(agent) let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === config.sessionId) - ctx.on('agent/created', (agent) => { - if (matchesConfiguredIdentity(agent)) target = agent - }) - ctx.on('agent/disposed', (agent) => { - if (target === agent) target = undefined - }) // Transcript rendering off the durable `session/event` feed — the assistant // token stream, turn/step boundaries, tool activity, and todos all come from @@ -158,7 +153,6 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt }) ctx.effect(() => { - const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) // Piped-input exit, once stdin reaches EOF: // - If no line ever submitted work (empty stdin, blank-only lines), exit // immediately — no turn will ever start, so there is nothing to wait @@ -176,6 +170,36 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt let exitTimer: ReturnType | undefined let activeQuestion: PendingQuestion | undefined const questionQueue: PendingQuestion[] = [] + const queuedInput: string[] = [] + let targetReady = target !== undefined + let hadReadyTarget = targetReady + + const submit = (agent: Agent, text: string): void => { + submittedWork = true + if (agent.status === 'running') { + agent.steer([{ type: 'text', text }]) + } else { + agent.send([{ type: 'text', text }]) + } + } + + const disposeCreatedListener = ctx.on('agent/created', (agent) => { + if (!matchesConfiguredIdentity(agent)) return + target = agent + targetReady = false + }) + const disposeSessionStartListener = ctx.on('agent/session-start', (agent) => { + if (agent !== target) return + targetReady = true + hadReadyTarget = true + for (const text of queuedInput.splice(0)) submit(agent, text) + }) + const disposeDisposedListener = ctx.on('agent/disposed', (agent) => { + if (target !== agent) return + target = undefined + targetReady = false + }) + const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) const maybeExit = (): void => { if (disposed || !stdinClosed) return @@ -351,16 +375,20 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const text = line.trim() if (!text) return const agent = target - if (!agent) { + if (agent === undefined || !targetReady) { + // Initial exact-id restoration is asynchronous. Preserve input until + // session-start, the first supported point for queueing agent work. + // After a previously ready target disappears, a line in the HMR gap + // still fails loud unless its exact replacement is already publishing. + if (!hadReadyTarget || agent !== undefined) { + submittedWork = true + queuedInput.push(text) + return + } ctx.logger.error('ui-stdio: main agent is not running') return } - submittedWork = true - if (agent.status === 'running') { - agent.steer([{ type: 'text', text }]) - } else { - agent.send([{ type: 'text', text }]) - } + submit(agent, text) }) reader.on('close', () => { // Fires for BOTH stdin EOF and plugin disposal (reader.close() below); @@ -376,6 +404,9 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposePendingQuestions() disposeUserInteractionProvider() disposeStatusListener() + disposeCreatedListener() + disposeSessionStartListener() + disposeDisposedListener() reader.close() } }, 'ui-stdio') diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index f1ca914525..943c48ef08 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -64,6 +64,13 @@ function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & { } as never } +/** Register a fake configured agent and cross the supported startup-work boundary. */ +function registerReady(ctx: Context, agent: Agent, source: 'startup' | 'resume' = 'startup'): () => void { + const dispose = ctx.agents.register(agent) + ctx.emit('agent/session-start', agent, source) + return dispose +} + /** A session stub whose `header.id` matches an agent's, for `session/event` emits. */ function makeSession(id: string): Session { return { id, header: { id } } as Session @@ -198,15 +205,21 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 5] ') }) - it('accepts a lineage-bearing configured agent created after the UI installs', async () => { + it('buffers input for a lineage-bearing configured agent until its session starts', async () => { const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'resumed' }) + input.feed('continue') + await new Promise(resolve => setImmediate(resolve)) + const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) + ctx.emit('agent/session-start', unrelated, 'startup') const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(resumed) + await new Promise(resolve => setImmediate(resolve)) + expect(resumed.sent).toEqual([]) - input.feed('continue') + ctx.emit('agent/session-start', resumed, 'resume') await new Promise(resolve => setImmediate(resolve)) expect(unrelated.sent).toEqual([]) @@ -256,9 +269,11 @@ describe('createStdioChat rendering', () => { disposeOld() const replacement = makeAgent('main-session-fixed') ctx.agents.register(replacement) - input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) + expect(replacement.sent).toEqual([]) + ctx.emit('agent/session-start', replacement, 'resume') + await new Promise(resolve => setImmediate(resolve)) expect(prefixCollision.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) @@ -269,7 +284,7 @@ describe('createStdioChat rendering', () => { const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) const configured = makeAgent('main') - const disposeConfigured = ctx.agents.register(configured) + const disposeConfigured = registerReady(ctx, configured) const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) disposeConfigured() @@ -693,7 +708,7 @@ describe('createStdioChat input', () => { it('sends a typed line to an idle agent', async () => { const { ctx, input } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('do a thing') await new Promise(r => setImmediate(r)) expect(agent.sent).toEqual([[{ type: 'text', text: 'do a thing' }]]) @@ -703,7 +718,7 @@ describe('createStdioChat input', () => { it('steers a typed line into a running agent', async () => { const { ctx, input } = await setup() const agent = makeAgent('main', 'running') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('steer me') await new Promise(r => setImmediate(r)) expect(agent.steered).toEqual([[{ type: 'text', text: 'steer me' }]]) @@ -719,18 +734,26 @@ describe('createStdioChat input', () => { expect(agent.sent).toEqual([]) }) - it('logs and drops a line when the target agent is not running', async () => { + it('buffers a line until the initial target session starts', async () => { const { ctx, input } = await setup() const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) input.feed('nobody home') await new Promise(r => setImmediate(r)) - expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') + expect(spy).not.toHaveBeenCalled() + + const agent = makeAgent('main') + ctx.agents.register(agent) + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([]) + ctx.emit('agent/session-start', agent, 'startup') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([[{ type: 'text', text: 'nobody home' }]]) }) it('drives the exact app-configured resumed session', async () => { const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') - ctx.agents.register(agent) + registerReady(ctx, agent, 'resume') input.feed('hi') await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) @@ -749,7 +772,7 @@ describe('createStdioChat EOF exit', () => { it('waits for the agent to settle idle after running before exiting', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) input.finish() @@ -764,10 +787,31 @@ describe('createStdioChat EOF exit', () => { expect(exit).toHaveBeenCalledWith(0) }) + it('keeps piped EOF pending until buffered startup input runs', async () => { + const { ctx, input, exit } = await setup() + input.feed('work') + input.finish() + await flushExit() + expect(exit).not.toHaveBeenCalled() + + const agent = makeAgent('main', 'idle') + ctx.agents.register(agent) + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([]) + ctx.emit('agent/session-start', agent, 'startup') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([[{ type: 'text', text: 'work' }]]) + ctx.emit('agent/status', agent, 'running') + ;(agent as { status: AgentStatus }).status = 'idle' + ctx.emit('agent/status', agent, 'idle') + await flushExit() + expect(exit).toHaveBeenCalledWith(0) + }) + it('schedules the exit only once when idle fires repeatedly', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'running') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) ctx.emit('agent/status', agent, 'running') // sawRunning = true @@ -785,7 +829,7 @@ describe('createStdioChat EOF exit', () => { it('does not exit on an idle transition for a different agent', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) input.finish() @@ -799,7 +843,7 @@ describe('createStdioChat EOF exit', () => { it('does not exit while a turn is still running at EOF', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) ctx.emit('agent/status', agent, 'running') @@ -848,7 +892,7 @@ describe('createStdioChat disposal (HMR safety)', () => { it('removes the agent/status listener on dispose', async () => { const { ctx, fiber, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) await fiber.dispose() From c1fb97c63a3ac7c3a6d4066ccc7615d292c0dfa7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:23:38 +0800 Subject: [PATCH 19/39] fix: surface config startup failures --- docs/architecture.md | 7 ++- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 12 +++++ docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 1 + docs/module-graph.md | 3 +- .../cordis/tool-cordis/src/api-catalog.ts | 6 +++ packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 30 +++++++++++- .../tests/config-session-id.spec.ts | 10 ++++ packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/package.json | 2 + packages/ui/stdio-agent/src/index.ts | 23 ++++----- packages/ui/stdio-agent/src/stdio-chat.ts | 20 ++++++++ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 47 ++++++++++++++++++- pnpm-lock.yaml | 3 ++ 16 files changed, 151 insertions(+), 21 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..06a3a86fb4 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -51,14 +51,17 @@ Waterfall events behave like around-middleware: a listener delegates by calling ## Default Loop Lifecycle -The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins. +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. +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. + ### Turn Flow ```text -prepare private session + agent.ctx -> await unpublished setup +choose declarative identity and fresh/resume path + -> prepare private session + agent.ctx -> await unpublished setup -> enter session + agent -> session/created -> agent/created -> enable driving -> agent/session-start(source) -> start driver forever: diff --git a/docs/config-catalog.md b/docs/config-catalog.md index d22bcca6f7..839e7967e6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:333`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:344`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a5e018079a..3c56882494 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -175,6 +175,18 @@ Types: [Agent](../core-data-structures/core.md) Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) +## `agent-loop/*` + +### `agent-loop/config-start-failed` — emit + +A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. + +```ts cordis-catalog +'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void +``` + +Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) + ## `approval/*` ### `approval/request` — waterfall diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e79422b94f..63375a46bf 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:359`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 1439873f69..0ab96fca31 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,6 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 8ac71b11cc..cc4cd86c47 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -316,6 +316,7 @@ flowchart TD pkg_acp_agent --> pkg_user_interaction pkg_stdio_agent --> pkg_agent pkg_stdio_agent --> pkg_agent_core + pkg_stdio_agent --> pkg_agent_loop pkg_stdio_agent --> pkg_app_boot pkg_stdio_agent --> pkg_llm pkg_stdio_agent --> pkg_session @@ -394,4 +395,4 @@ flowchart TD | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-agent`](../packages/ui/acp-agent) | `ui` | [`acp`](../packages/ui/acp), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-agent`](../packages/ui/stdio-agent) | `ui` | [`agent`](../packages/core/agent), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-agent`](../packages/ui/stdio-agent) | `ui` | [`agent`](../packages/core/agent), [`agent-core`](../packages/core/agent-core), [`agent-loop`](../packages/core/agent-loop), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index ff27f51067..a9d1d5acaa 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -237,6 +237,12 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ /** Every harness event, sorted by name. */ export const EVENT_API: readonly EventApiEntry[] = [ + { + name: 'agent-loop/config-start-failed', + mode: 'emit', + signature: '\'agent-loop/config-start-failed\'(sessionId: SessionId, error: unknown): void', + summary: 'A declarative agent entry failed before it could publish a live agent.', + }, { name: 'agent/created', mode: 'emit', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2db1a6c079..2593da7c47 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index d2d8648595..62c5d94b06 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -327,6 +327,17 @@ declare module 'cordis' { interface Context { agentLoop: AgentLoop } + interface Events { + /** + * A declarative agent entry failed before it could publish a live agent. + * Consumers that buffer work for the configured identity use this + * transient signal to reject that work instead of waiting forever. + * @param sessionId - exact shared agent/session identity that failed startup. + * @param error - persistence, setup, or publication failure. + * @mode emit + */ + 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void + } } /** Plugin configuration for declarative startup agents. */ @@ -381,7 +392,7 @@ export class AgentLoop extends Service implements AgentFactory { this.create(configuredId, options, meta) } else { const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'restore', configuredId, error) }) this.ownership.trackStartup(startup) } @@ -396,7 +407,7 @@ export class AgentLoop extends Service implements AgentFactory { resumeSessionId, agentOptions: options, }).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven resume of "${resumeSessionId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'resume', resumeSessionId, error) }) }) return fiber.dispose @@ -404,6 +415,21 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Report a contained declarative-start failure to identity-bound consumers. */ + private reportConfiguredStartupFailure( + configId: string, + action: 'restore' | 'resume', + sessionId: SessionId, + error: unknown, + ): void { + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) + try { + this.ctx.emit('agent-loop/config-start-failed', sessionId, error) + } catch (listenerError) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + } + } + /** Restore a materialized exact config identity on remount, or create it on first use. */ private async restoreOrCreateConfigured( ownerCtx: Context, diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index c1a04fadd0..ad9ec6b792 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -98,6 +98,12 @@ describe('config-driven session id', () => { const ctx = await makeCoreContext() await ctx.plugin(SessionPersistenceJsonl, { root }) const failure = new Error('persistence index failed') + const listenerFailure = new Error('failure observer failed') + const failures: { sessionId: SessionId; error: unknown }[] = [] + ctx.on('agent-loop/config-start-failed', (sessionId, error) => { + failures.push({ sessionId, error }) + }) + ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) @@ -108,6 +114,10 @@ describe('config-driven session id', () => { await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining( 'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed', )) + expect(failures).toEqual([{ sessionId: SessionId('stdio-exact-failure'), error: failure }]) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener threw: Error: failure observer failed', + ) expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index bbf175d92d..a91bef85a0 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt; `agent-loop/config-start-failed` instead drains and reports buffered input so a missing or corrupt persisted session cannot hang EOF. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/package.json b/packages/ui/stdio-agent/package.json index fcd432a9fd..60a9529d47 100644 --- a/packages/ui/stdio-agent/package.json +++ b/packages/ui/stdio-agent/package.json @@ -35,6 +35,7 @@ "@deepseek-ai/dsh-app-boot": "^0.0.1", "@cordisjs/plugin-logger-console": "^1.0.0", "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-agent-core": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -51,6 +52,7 @@ "@deepseek-ai/dsh-app-boot": "workspace:^", "@cordisjs/plugin-logger-console": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 03f3d49555..1278ded88a 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -102,16 +102,23 @@ export const Config: z = z.object({ }) /** - * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-core bundle pre-creating one agent from this app's - * `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI rendering that object as `main`. The `hmr` dev-reload plugin is - * a leaf concern (see the module doc), so it is not mounted here. + * Compose the spine with the stdio front door. Console logging, persistence, + * and user interaction mount first; the readline UI then waits on the agent + * registry and subscribes to config-start failures before agent-core can start + * the configured identity. The ask-user tool waits on the completed spine. + * The `hmr` dev-reload plugin is a leaf concern (see the module doc), so it is + * not mounted here. */ export function apply(ctx: Context, config: Config): void { const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(UserInteractionService) + ctx.plugin(uiStdio, { + welcome: config.welcome ?? 'ready.', + sessionId, + }) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, @@ -124,11 +131,5 @@ export function apply(ctx: Context, config: Config): void { }], ...config.skills !== undefined ? { skills: config.skills } : {}, }) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) - ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { - welcome: config.welcome ?? 'ready.', - sessionId, - }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 17d396c042..39d59dfdc0 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -21,6 +21,7 @@ import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' import type { Agent } from '@deepseek-ai/dsh-agent' +import type {} from '@deepseek-ai/dsh-agent-loop' import { UserInteractionError, type AskUserQuestionAnswer, @@ -173,6 +174,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const queuedInput: string[] = [] let targetReady = target !== undefined let hadReadyTarget = targetReady + let failedStartup: { error: unknown } | undefined const submit = (agent: Agent, text: string): void => { submittedWork = true @@ -187,6 +189,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt if (!matchesConfiguredIdentity(agent)) return target = agent targetReady = false + failedStartup = undefined }) const disposeSessionStartListener = ctx.on('agent/session-start', (agent) => { if (agent !== target) return @@ -220,6 +223,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt exitTimer = setTimeout(() => { exit(0) }, 200) } + const disposeStartupFailedListener = ctx.on('agent-loop/config-start-failed', (sessionId, error) => { + if (sessionId !== config.sessionId || targetReady) return + failedStartup = { error } + const dropped = queuedInput.length + queuedInput.length = 0 + submittedWork = sawRunning + if (dropped > 0) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${String(error)}`) + } + maybeExit() + }) + const disposeStatusListener = ctx.on('agent/status', (subject, status) => { if (subject !== target) return if (status === 'running') sawRunning = true @@ -374,6 +389,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return + if (failedStartup !== undefined) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${String(failedStartup.error)}`) + return + } const agent = target if (agent === undefined || !targetReady) { // Initial exact-id restoration is asynchronous. Preserve input until @@ -407,6 +426,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposeCreatedListener() disposeSessionStartListener() disposeDisposedListener() + disposeStartupFailedListener() reader.close() } }, 'ui-stdio') diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 943c48ef08..11e64ac19c 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -4,7 +4,7 @@ import { Context } from 'cordis' import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' -import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type Session, type SessionEvent } from '@deepseek-ai/dsh-session' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' import { createStdioChat, type Config, type StdioRuntime } from '../src/stdio-chat.ts' @@ -750,6 +750,32 @@ describe('createStdioChat input', () => { expect(agent.sent).toEqual([[{ type: 'text', text: 'nobody home' }]]) }) + it('drops later input after the configured startup fails', async () => { + const { ctx, input } = await setup() + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + const failure = new Error('persisted session is corrupt') + ctx.emit('agent-loop/config-start-failed', SessionId('main'), failure) + + input.feed('cannot run') + await new Promise(r => setImmediate(r)) + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: persisted session is corrupt', + ) + }) + + it('ignores a stale config-start failure after the exact target is ready', async () => { + const { ctx, input } = await setup() + const agent = makeAgent('main') + registerReady(ctx, agent) + ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('stale')) + + input.feed('still live') + await new Promise(r => setImmediate(r)) + + expect(agent.sent).toEqual([[{ type: 'text', text: 'still live' }]]) + }) + it('drives the exact app-configured resumed session', async () => { const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') @@ -808,6 +834,25 @@ describe('createStdioChat EOF exit', () => { expect(exit).toHaveBeenCalledWith(0) }) + it('drains buffered piped input and exits when configured startup fails', async () => { + const { ctx, input, exit } = await setup() + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + input.feed('work') + input.finish() + await new Promise(r => setImmediate(r)) + ctx.emit('agent-loop/config-start-failed', SessionId('other'), new Error('unrelated')) + await flushExit() + expect(exit).not.toHaveBeenCalled() + + ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('missing persisted session')) + await flushExit() + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: missing persisted session', + ) + expect(exit).toHaveBeenCalledWith(0) + }) + it('schedules the exit only once when idle fires repeatedly', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'running') diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..7a8fe5a6ea 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1328,6 +1328,9 @@ importers: '@deepseek-ai/dsh-agent-core': specifier: workspace:^ version: link:../../core/agent-core + '@deepseek-ai/dsh-agent-loop': + specifier: workspace:^ + version: link:../../core/agent-loop '@deepseek-ai/dsh-app-boot': specifier: workspace:^ version: link:../app-boot From 7d6ef0a47260a096a7594e54c797fde9e1ba8ca0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:33:36 +0800 Subject: [PATCH 20/39] fix: contain config failure observers --- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/src/index.ts | 14 ++++++++++---- .../agent-loop/tests/config-session-id.spec.ts | 7 ++++++- scripts/gen-doc-graphs.ts | 3 +++ 4 files changed, 20 insertions(+), 6 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 0ab96fca31..de89a69f18 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 62c5d94b06..5a7484a378 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -423,10 +423,16 @@ export class AgentLoop extends Service implements AgentFactory { error: unknown, ): void { this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) - try { - this.ctx.emit('agent-loop/config-start-failed', sessionId, error) - } catch (listenerError) { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] + for (const callback of this.ctx.events.dispatch('emit', args)) { + try { + const returned: unknown = callback(...args) + void Promise.resolve(returned).catch((listenerError: unknown) => { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${String(listenerError)}`) + }) + } catch (listenerError: unknown) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + } } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index ad9ec6b792..a7292b2284 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -99,11 +99,13 @@ describe('config-driven session id', () => { await ctx.plugin(SessionPersistenceJsonl, { root }) const failure = new Error('persistence index failed') const listenerFailure = new Error('failure observer failed') + const asyncListenerFailure = new Error('async failure observer failed') const failures: { sessionId: SessionId; error: unknown }[] = [] + ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) + ctx.on('agent-loop/config-start-failed', () => Promise.reject(asyncListenerFailure) as never) ctx.on('agent-loop/config-start-failed', (sessionId, error) => { failures.push({ sessionId, error }) }) - ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) @@ -118,6 +120,9 @@ describe('config-driven session id', () => { expect(warn).toHaveBeenCalledWith( 'agent "main": config-start-failed listener threw: Error: failure observer failed', ) + await expect.poll(() => warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener rejected: Error: async failure observer failed', + ) expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5144e388a2..fa7daed85e 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -245,6 +245,9 @@ const DYNAMIC_EVENT_DISPATCHERS: Array<{ event: string; pkg: string; method: str // Registry disposal reuses the stable carrier captured before entry commit // and contains each listener directly rather than rebuilding via agentEvents. { event: 'agent/disposed', pkg: 'agent', method: 'events.dispatch' }, + // Config startup failures have no live Agent carrier; AgentLoop resolves the + // callbacks directly to contain each synchronous throw and async rejection. + { event: 'agent-loop/config-start-failed', pkg: 'agent-loop', method: 'events.dispatch' }, { event: 'session/created', pkg: 'session', method: 'events.dispatch' }, // Session event callbacks are likewise resolved before the log push, then // invoked individually after commit so observer failures are contained. From a25c0f084f035f94a11292b17ec9a31e93349c2e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:25:30 +0800 Subject: [PATCH 21/39] fix: totalize configured startup failures --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/src/index.ts | 15 ++++++-- .../tests/config-session-id.spec.ts | 36 +++++++++++++++++++ 6 files changed, 52 insertions(+), 7 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index d7a973fd81..484ba1c632 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:344`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 088e60450d..e44df3c3b2 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -185,7 +185,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 8c00bd45ef..699c73fe2c 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:359`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 825f54b077..78a30bd4e1 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 5a7484a378..3c09ef2e7f 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -41,6 +41,15 @@ const INACTIVE_STATES: ReadonlySet = new Set([ FiberState.FAILED, ]) +/** Render an arbitrary thrown value without letting coercion escape containment. */ +function renderThrown(value: unknown): string { + try { + return String(value) + } catch { + return '' + } +} + /** Factory-level ownership of every preparing or live transaction. */ class FactoryOwnership { private accepting = true @@ -422,16 +431,16 @@ export class AgentLoop extends Service implements AgentFactory { sessionId: SessionId, error: unknown, ): void { - this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] for (const callback of this.ctx.events.dispatch('emit', args)) { try { const returned: unknown = callback(...args) void Promise.resolve(returned).catch((listenerError: unknown) => { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${String(listenerError)}`) + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${renderThrown(listenerError)}`) }) } catch (listenerError: unknown) { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${renderThrown(listenerError)}`) } } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index a7292b2284..b35dc71739 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -128,6 +128,42 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('contains startup and observer failures whose string coercion throws', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-unrenderable-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const unrenderable = { + [Symbol.toPrimitive](): never { + throw new Error('coercion escaped') + }, + } + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', () => { throw unrenderable }) + // Deliberately violate the normal Error-only rejection rule to exercise the unknown boundary. + // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors + ctx.on('agent-loop/config-start-failed', () => Promise.reject(unrenderable) as never) + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) + vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(unrenderable) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-unrenderable'), model: 'mock' }], + }) + + await expect.poll(() => failures).toEqual([unrenderable]) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-driven restore of "stdio-exact-unrenderable" failed: ', + ) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener threw: ', + ) + await expect.poll(() => warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener rejected: ', + ) + await ctx.fiber.dispose() + }) + it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) dirs.push(root) From b47e4c5276604dd1e5a400f5f60d2c16e195df10 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:45:12 +0800 Subject: [PATCH 22/39] fix: suppress teardown startup failures --- docs/architecture.md | 2 +- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 4 ++-- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 4 +++- packages/core/agent-loop/tests/config-session-id.spec.ts | 5 ++++- 8 files changed, 14 insertions(+), 9 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 41ab5c716b..0eb7f1fe55 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -56,7 +56,7 @@ Default loop processing remains exposed through plugin-visible services and even 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. -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. +Startup resolves identity. No id mints `-session-`; `sessionId` resumes or creates; `resumeSessionId` requires history. Active failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject work; teardown stays silent. ### Turn Flow diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 484ba1c632..173806572a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index e44df3c3b2..df3aec8b12 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -179,13 +179,13 @@ Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/t ### `agent-loop/config-start-failed` — emit -A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. +A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. Normal factory teardown suppresses failures from the cancelled startup attempt. ```ts cordis-catalog 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 965a640966..74496739e2 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 78a30bd4e1..cc155ebb16 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2593da7c47..e27e8b625a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 3c09ef2e7f..06c108d324 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -340,7 +340,8 @@ declare module 'cordis' { /** * A declarative agent entry failed before it could publish a live agent. * Consumers that buffer work for the configured identity use this - * transient signal to reject that work instead of waiting forever. + * transient signal to reject that work instead of waiting forever. Normal + * factory teardown suppresses failures from the cancelled startup attempt. * @param sessionId - exact shared agent/session identity that failed startup. * @param error - persistence, setup, or publication failure. * @mode emit @@ -431,6 +432,7 @@ export class AgentLoop extends Service implements AgentFactory { sessionId: SessionId, error: unknown, ): void { + if (!this.ownership.isActive()) return this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] for (const callback of this.ctx.events.dispatch('emit', args)) { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index b35dc71739..53782fe03c 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -172,6 +172,8 @@ describe('config-driven session id', () => { const listing = Promise.withResolvers>>() vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) const loop = await ctx.plugin(AgentLoop, { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], @@ -181,9 +183,10 @@ describe('config-driven session id', () => { await Promise.resolve() expect(disposed).toBe(false) - listing.resolve([]) + listing.reject(new Error('startup cancelled by teardown')) await disposal expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(failures).toEqual([]) expect(warn).not.toHaveBeenCalled() warn.mockRestore() await ctx.fiber.dispose() From 1f2c85c854985384febdf6829cc3d9eb2181b3ed Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 13:47:44 +0800 Subject: [PATCH 23/39] test: await fresh stdio agent publication --- packages/ui/stdio-agent/tests/stdio-agent.spec.ts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index a14848a549..4d555f5965 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -85,6 +85,7 @@ describe('dsh-stdio-agent app', () => { expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() // The sole pre-created agent the UI drives. `main` is its stable config // label; each fresh process mints a durable combined agent/session id. + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) const agent = ctx.get('agents')?.list()[0] expect(agent).toBeDefined() expect(agent?.id).toBe(agent?.session.id) @@ -100,6 +101,7 @@ describe('dsh-stdio-agent app', () => { persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', skills: await isolatedSkillsConfig(), }) + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) const agent = ctx.get('agents')?.list()[0] expect(agent?.id).toMatch(/^main-session-[0-9a-f-]{36}$/) expect(agent?.id).toBe(agent?.session.id) From b58cf7ec2fdb3ba7d88ec097766dd47f2a188a2a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 14:24:21 +0800 Subject: [PATCH 24/39] fix: coordinate overlapping configured reloads --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 35 +++++++++++++++ .../tests/config-session-id.spec.ts | 44 +++++++++++++++++++ packages/ui/stdio-agent/src/stdio-chat.ts | 13 +++++- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 12 +++-- 9 files changed, 103 insertions(+), 11 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 173806572a..9bebe62380 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:361`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index df3aec8b12..f913b95c36 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -185,7 +185,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:356`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d3e8b74edf..e4e68fe17f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:376`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index cc155ebb16..2b62ec93eb 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:356`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index e27e8b625a..881d60027a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. An overlapping remount waits for an already-disposed same-id agent to finish detaching both registries before it inspects persistence, so asynchronous teardown cannot strand the configured identity. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 06c108d324..3274e36587 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -53,6 +53,7 @@ function renderThrown(value: unknown): string { /** Factory-level ownership of every preparing or live transaction. */ class FactoryOwnership { private accepting = true + private readonly inactive = Promise.withResolvers() private transactions = new Set() private startupTasks = new Set>() @@ -74,8 +75,14 @@ class FactoryOwnership { void task.then(forget, forget) } + /** Resolve `task`, or stop waiting when factory teardown begins. */ + async waitWhileActive(task: Promise): Promise { + await Promise.race([task, this.inactive.promise]) + } + async dispose(): Promise { this.accepting = false + this.inactive.resolve() const reason = new Error('agent loop is not active') await Promise.all([ ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), @@ -455,6 +462,8 @@ export class AgentLoop extends Service implements AgentFactory { agentOptions: AgentOptions, meta: Pick, ): Promise { + await this.waitForDrainingConfiguredIdentity(ownerCtx, sessionId) + if (!this.ownership.isActive()) return const exists = (await persistence.list()).some(header => header.id === sessionId) if (!this.ownership.isActive()) return if (exists) { @@ -464,6 +473,32 @@ export class AgentLoop extends Service implements AgentFactory { this.create(sessionId, agentOptions, meta) } + /** Wait for an already-disposed same-id lifecycle to finish registry teardown. */ + private async waitForDrainingConfiguredIdentity(ownerCtx: Context, sessionId: SessionId): Promise { + const current = ownerCtx.agents.get(sessionId) + if (current?.status !== 'disposed') return + + const released = Promise.withResolvers() + const checkReleased = (): void => { + if (ownerCtx.agents.get(sessionId) === undefined && ownerCtx.sessions.get(sessionId) === undefined) { + released.resolve() + } + } + const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => { + if (agent.id === sessionId) checkReleased() + }) + const disposeSessionListener = ownerCtx.on('session/disposed', (session) => { + if (session.id === sessionId) checkReleased() + }) + try { + checkReleased() + await this.ownership.waitWhileActive(released.promise) + } finally { + disposeAgentListener() + disposeSessionListener() + } + } + /** * Create an agent and session under one caller-supplied identity, owned by * the accessing fiber. Constructor-driven config calls mint a fresh combined diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 53782fe03c..fda5681c29 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -92,6 +92,50 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('waits for a draining exact-id lifecycle during an overlapping reload', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-overlap-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const sessionId = SessionId('stdio-exact-overlap') + const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } + const firstLoop = await ctx.plugin(AgentLoop, config) + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const first = ctx.agents.get(sessionId) as ReactLoopAgent + + const flushGate = Promise.withResolvers() + let flushStarted = false + ctx.on('session/flush', (session) => { + if (session !== first.session) return + flushStarted = true + return flushGate.promise + }) + first.inject([{ type: 'text', text: 'persist before replacement' }], { + source: { kind: 'plugin', plugin: 'test' }, + }) + expect(flushStarted).toBe(true) + + const firstDisposal = firstLoop.dispose() + await expect.poll(() => first.status).toBe('disposed') + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_id, error) => { failures.push(error) }) + const secondLoop = await ctx.plugin(AgentLoop, config) + await new Promise(resolve => setTimeout(resolve, 0)) + expect(ctx.agents.get(sessionId)).toBe(first) + expect(failures).toEqual([]) + + flushGate.resolve(undefined) + await firstDisposal + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const second = ctx.agents.get(sessionId) as ReactLoopAgent + expect(second).not.toBe(first) + expect(JSON.stringify(second.session.deriveMessages())).toContain('persist before replacement') + expect(failures).toEqual([]) + + await secondLoop.dispose() + await ctx.fiber.dispose() + }) + it('contains an exact-id persistence lookup failure', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) dirs.push(root) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 39d59dfdc0..4505f19b98 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -67,6 +67,15 @@ function isTTYPair(input: Readable, output: Writable): boolean { return Boolean((input as { isTTY?: boolean }).isTTY && (output as { isTTY?: boolean }).isTTY) } +/** Render an arbitrary failure without allowing hostile coercion to escape the UI boundary. */ +function renderThrown(value: unknown): string { + try { + return String(value) + } catch { + return '' + } +} + interface PendingQuestion { request: AskUserQuestionRequest questionIndex: number @@ -230,7 +239,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt queuedInput.length = 0 submittedWork = sawRunning if (dropped > 0) { - ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${String(error)}`) + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${renderThrown(error)}`) } maybeExit() }) @@ -390,7 +399,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const text = line.trim() if (!text) return if (failedStartup !== undefined) { - ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${String(failedStartup.error)}`) + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${renderThrown(failedStartup.error)}`) return } const agent = target diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 11e64ac19c..c303577c48 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -83,6 +83,10 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { const CONFIG: Config = { welcome: 'hi there', sessionId: 'main' } +function unrenderableFailure(): unknown { + return { [Symbol.toPrimitive](): never { throw new Error('coercion escaped') } } +} + async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -753,14 +757,14 @@ describe('createStdioChat input', () => { it('drops later input after the configured startup fails', async () => { const { ctx, input } = await setup() const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) - const failure = new Error('persisted session is corrupt') + const failure = unrenderableFailure() ctx.emit('agent-loop/config-start-failed', SessionId('main'), failure) input.feed('cannot run') await new Promise(r => setImmediate(r)) expect(error).toHaveBeenCalledWith( - 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: persisted session is corrupt', + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', ) }) @@ -844,11 +848,11 @@ describe('createStdioChat EOF exit', () => { await flushExit() expect(exit).not.toHaveBeenCalled() - ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('missing persisted session')) + ctx.emit('agent-loop/config-start-failed', SessionId('main'), unrenderableFailure()) await flushExit() expect(error).toHaveBeenCalledWith( - 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: missing persisted session', + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', ) expect(exit).toHaveBeenCalledWith(0) }) From d83aa8d11aa217fdbee379dce37aa5146228dd21 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 15:31:00 +0800 Subject: [PATCH 25/39] test: cover exact-id reload cancellation --- packages/core/agent-loop/src/index.ts | 8 +- .../tests/config-session-id.spec.ts | 85 +++++++++++++------ 2 files changed, 62 insertions(+), 31 deletions(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 3274e36587..ff0c692928 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -484,12 +484,8 @@ export class AgentLoop extends Service implements AgentFactory { released.resolve() } } - const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => { - if (agent.id === sessionId) checkReleased() - }) - const disposeSessionListener = ownerCtx.on('session/disposed', (session) => { - if (session.id === sessionId) checkReleased() - }) + const disposeAgentListener = ownerCtx.on('agent/disposed', checkReleased) + const disposeSessionListener = ownerCtx.on('session/disposed', checkReleased) try { checkReleased() await this.ownership.waitWhileActive(released.promise) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index fda5681c29..ceaf6597cb 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -136,6 +136,37 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('cancels an exact-id reload while the prior lifecycle is still draining', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-cancel-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const sessionId = SessionId('stdio-exact-cancel') + const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } + const firstLoop = await ctx.plugin(AgentLoop, config) + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const first = ctx.agents.get(sessionId) as ReactLoopAgent + + const flushGate = Promise.withResolvers() + ctx.on('session/flush', (session) => { + if (session === first.session) return flushGate.promise + }) + first.inject([{ type: 'text', text: 'persist before cancellation' }], { + source: { kind: 'plugin', plugin: 'test' }, + }) + + const firstDisposal = firstLoop.dispose() + await expect.poll(() => first.status).toBe('disposed') + const secondLoop = await ctx.plugin(AgentLoop, config) + await secondLoop.dispose() + expect(ctx.agents.get(sessionId)).toBe(first) + + flushGate.resolve(undefined) + await firstDisposal + expect(ctx.agents.get(sessionId)).toBeUndefined() + await ctx.fiber.dispose() + }) + it('contains an exact-id persistence lookup failure', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) dirs.push(root) @@ -208,33 +239,37 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) - it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { - const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) - dirs.push(root) - const ctx = await makeCoreContext() - await ctx.plugin(SessionPersistenceJsonl, { root }) - const listing = Promise.withResolvers>>() - vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) - const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const failures: unknown[] = [] - ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) + it.each(['resolve', 'reject'] as const)( + 'joins an exact-id persistence lookup that will %s before AgentLoop disposal completes', + async (outcome) => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const listing = Promise.withResolvers>>() + vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) - const loop = await ctx.plugin(AgentLoop, { - agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], - }) - let disposed = false - const disposal = loop.dispose().then(() => { disposed = true }) - await Promise.resolve() - expect(disposed).toBe(false) + const loop = await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], + }) + let disposed = false + const disposal = loop.dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) - listing.reject(new Error('startup cancelled by teardown')) - await disposal - expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() - expect(failures).toEqual([]) - expect(warn).not.toHaveBeenCalled() - warn.mockRestore() - await ctx.fiber.dispose() - }) + if (outcome === 'resolve') listing.resolve([]) + else listing.reject(new Error('startup cancelled by teardown')) + await disposal + expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(failures).toEqual([]) + expect(warn).not.toHaveBeenCalled() + warn.mockRestore() + await ctx.fiber.dispose() + }, + ) it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() From 8be096c540c6b82187051eab9febd461a46e4fc2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:08:37 +0800 Subject: [PATCH 26/39] fix: preserve master bash guidance wording --- packages/bash/tool-bash/src/index.ts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 662b7a065f..4c699cd6c0 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -173,15 +173,15 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string { + 'poll it with `bash_output` and stop it with `bash_kill`.' if (escalationModes.length === 0) return base return base + ' 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 ' + + '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 ' + + '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 ' + + '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 ' + + '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.' } From 10fd0b4504b47285b67aed611e4cc0a2e86c5db4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:22:37 +0800 Subject: [PATCH 27/39] docs: align unified identity translation --- docs/cookbook/extension-cookbook.i18n.yaml | 4 ++-- docs/cookbook/extension-cookbook.zh.md | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index ef1d8d606f..2761b419e9 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 40ee22b352c884d7f295c87726c54ab8e166c844 -extension-cookbook.zh.md: 4e5bc68c973649574bcb2404bea00096eb9ca41f +extension-cookbook.md: 0b95866515efa1b28a95ed48de0fe20d76a62b82 +extension-cookbook.zh.md: 038bf093ce2d289fb59be165a154cbe4df831d9e diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 4e5bc68c97..038bf093ce 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -40,7 +40,7 @@ UI 插件从 `session/event` 事件流渲染（助手 token 流以 `assistant/ch ```ts import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' declare function render(text: string): void declare function onUserInput(handler: (text: string) => void): void @@ -54,7 +54,7 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) } ``` From 9745a0d43a979d34c44c2a42d8a485d03a25de71 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:36:04 +0800 Subject: [PATCH 28/39] fix: reject empty configured session ids --- packages/core/agent-loop/src/index.ts | 2 +- packages/core/agent-loop/tests/config-session-id.spec.ts | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 8d9a184cc7..325ba7b92d 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -377,7 +377,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), - sessionId: z.string(), + sessionId: z.string().min(1), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 096a6eff9e..bd2a5522df 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -35,6 +35,15 @@ async function makeCoreContext(): Promise { } describe('config-driven session id', () => { + it('rejects an empty exact id before publishing an agent', async () => { + const ctx = await makeCoreContext() + await expect(ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId(''), model: 'mock' }], + })).rejects.toThrow('expected string length >= 1') + expect(ctx.agents.get(SessionId(''))).toBeUndefined() + await ctx.fiber.dispose() + }) + it('accepts one exact fresh id and rejects it alongside a resume id', async () => { const exact = await makeCoreContext() await exact.plugin(AgentLoop, { From f8cc1af99b9b8a5681f93e8939bf8e93f98a4011 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:36:57 +0800 Subject: [PATCH 29/39] test(tasks): align tool fixtures with unified identity --- .../tasks/tool-tasks/tests/tool-tasks.spec.ts | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts index 1b5e221a3c..0a2d89431e 100644 --- a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts +++ b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts @@ -5,6 +5,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import TaskService from '@deepseek-ai/dsh-tasks' import type { TaskHooks, TaskOutcome, TaskSnapshot, TaskStart } from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' @@ -23,17 +24,17 @@ async function setup(config: ToolTasks.Config = {}) { } /** - * A fake agent whose session token is `sessionId`, registered in `ctx.agents`. - * The agent id is deliberately different so session authorization and exact - * lifecycle ownership cannot be confused in tests. + * A fake agent with the shared agent/session identity, registered in + * `ctx.agents` with a dedicated lifecycle scope. */ function fakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void = () => {}): Agent { const scopeFiber = ctx.plugin(() => {}) + const id = SessionId(sessionId) const agent = { - id: `agent-${sessionId}`, + id, ctx: scopeFiber.ctx, inject, - session: { header: { version: 0, id: sessionId, createdAt: 0 } }, + session: { id, header: { version: 0, id, createdAt: 0 } }, } as unknown as Agent agentRegistryDisposers.set(agent, ctx.agents.register(agent)) return agent @@ -276,7 +277,7 @@ describe('completion notices', () => { await tick() // Disposed owner: inject throws the disposed message — contained. - const inject = vi.fn(() => { throw new Error('agent "agent-sess-1" is disposed') }) + const inject = vi.fn(() => { throw new Error('agent "sess-1" is disposed') }) const owner = fakeAgent(ctx, 'sess-1', inject) const p = producer({ owner }) ctx.tasks.start(p.spec) @@ -287,7 +288,7 @@ describe('completion notices', () => { it('does not route an old owner completion notice to a same-session replacement', async () => { const { ctx } = await setup() - const oldInject = vi.fn(() => { throw new Error('agent "agent-shared" is disposed') }) + const oldInject = vi.fn(() => { throw new Error('agent "shared" is disposed') }) const oldOwner = fakeAgent(ctx, 'shared', oldInject) const p = producer({ owner: oldOwner }) ctx.tasks.start(p.spec) From 8e37abb6c9dffa1fa2d5a24d05aa9eef4dde88e3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:50:33 +0800 Subject: [PATCH 30/39] docs: refresh module graph for unified identity --- docs/module-graph.md | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 199f11e8d3..baa714bad1 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -205,6 +205,7 @@ flowchart TD pkg_workflow --> pkg_agent pkg_workflow --> pkg_brand pkg_workflow --> pkg_llm + pkg_workflow --> pkg_session pkg_tools --> pkg_agent pkg_tools --> pkg_code_runtime pkg_tools --> pkg_llm @@ -219,10 +220,6 @@ flowchart TD pkg_permission --> pkg_sandbox pkg_permission --> pkg_session pkg_permission --> pkg_user_approval - pkg_stdio --> pkg_agent - pkg_stdio --> pkg_llm - pkg_stdio --> pkg_session - pkg_stdio --> pkg_user_interaction pkg_agent_loop --> pkg_agent pkg_agent_loop --> pkg_llm pkg_agent_loop --> pkg_scope @@ -250,6 +247,7 @@ flowchart TD pkg_subagent --> pkg_agent pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope + pkg_subagent --> pkg_session pkg_subagent --> pkg_tools pkg_tool_web --> pkg_llm pkg_tool_web --> pkg_system_prompt @@ -296,6 +294,7 @@ flowchart TD pkg_tool_workflow --> pkg_workflow pkg_subagent_acp --> pkg_agent pkg_subagent_acp --> pkg_llm + pkg_subagent_acp --> pkg_session pkg_subagent_acp --> pkg_subagent pkg_subagent_acp --> pkg_subagent_subprocess pkg_subagent_inprocess --> pkg_agent @@ -317,12 +316,18 @@ flowchart TD pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent pkg_subagent_mock --> pkg_llm + pkg_subagent_mock --> pkg_session pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent + pkg_stdio --> pkg_agent + pkg_stdio --> pkg_agent_loop + pkg_stdio --> pkg_llm + pkg_stdio --> pkg_session + pkg_stdio --> pkg_user_interaction pkg_agent_spine_demo --> pkg_agent pkg_agent_spine_demo --> pkg_agent_loop pkg_agent_spine_demo --> pkg_invariants @@ -356,6 +361,7 @@ flowchart TD pkg_acp_demo --> pkg_tools pkg_acp_demo --> pkg_user_interaction pkg_stdio_demo --> pkg_agent + pkg_stdio_demo --> pkg_agent_loop pkg_stdio_demo --> pkg_agent_spine_demo pkg_stdio_demo --> pkg_app_boot pkg_stdio_demo --> pkg_llm @@ -412,16 +418,15 @@ flowchart TD | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | | [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) | | [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) | -| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`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) | -| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`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), [`tasks`](../packages/tasks/tasks), [`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) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | @@ -433,15 +438,16 @@ flowchart TD | [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) | | [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`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) | -| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | +| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | +| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | From 828d6004ba35737a5887def0ce3c32b1c84b77ea Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:51:12 +0800 Subject: [PATCH 31/39] fix(sdk): share generated session identity --- packages/sdk/create-sdk/tests/create.spec.ts | 1 + packages/sdk/helper/src/features/builtin/app.ts | 7 ++++--- .../sdk/helper/src/templates/assets/index.ts.tpl | 14 +++++++------- packages/sdk/helper/tests/project.spec.ts | 15 +++++++++++++-- 4 files changed, 25 insertions(+), 12 deletions(-) diff --git a/packages/sdk/create-sdk/tests/create.spec.ts b/packages/sdk/create-sdk/tests/create.spec.ts index 9d75700bb9..04a251351d 100644 --- a/packages/sdk/create-sdk/tests/create.spec.ts +++ b/packages/sdk/create-sdk/tests/create.spec.ts @@ -257,6 +257,7 @@ describe('CreateWizard and scaffolder', () => { expect(index).toContain('SdkBootContext') expect(index).toContain('ctx.agents.create') expect(index).toContain('agentOptions: { model: "deepseek-v4-flash" }') + expect(index).not.toContain('AgentId') const tsconfig = parseGeneratedTsConfig(await readFile(join(target, 'tsconfig.base.json'), 'utf8')) const manifest = parseGeneratedPackageManifest(await readFile(join(target, 'package.json'), 'utf8')) expect(tsconfig.compilerOptions.types).toEqual(['node']) diff --git a/packages/sdk/helper/src/features/builtin/app.ts b/packages/sdk/helper/src/features/builtin/app.ts index a89f2c84ae..e4ff11af20 100644 --- a/packages/sdk/helper/src/features/builtin/app.ts +++ b/packages/sdk/helper/src/features/builtin/app.ts @@ -4,6 +4,7 @@ * @module @deepseek-ai/dsh-helper/features/builtin/app */ +import { JsExpression } from '../../documents/cordis-yaml-file.ts' import { featureId } from '../../ids.ts' import type { ProjectProfile } from '../../project/types.ts' import { @@ -94,11 +95,11 @@ class AppOption extends FeatureOption { name: '@deepseek-ai/dsh-stdio', config: { welcome: 'agent REPL ready. Give it a coding task.', - agent: 'main', + sessionId: new JsExpression('process.env.DSH_SDK_SESSION_ID'), }, - }, ['welcome', 'agent'], config => [ + }, ['welcome', 'sessionId'], config => [ ...optionalString(config, 'welcome'), - ...requiredString(config, 'agent'), + ...config.sessionId instanceof JsExpression ? [] : requiredString(config, 'sessionId'), ]), ]) case 'embed': diff --git a/packages/sdk/helper/src/templates/assets/index.ts.tpl b/packages/sdk/helper/src/templates/assets/index.ts.tpl index d0315db80c..4c3099199c 100644 --- a/packages/sdk/helper/src/templates/assets/index.ts.tpl +++ b/packages/sdk/helper/src/templates/assets/index.ts.tpl @@ -2,14 +2,12 @@ import { startSDK, type SdkBootContext } from '@deepseek-ai/dsh-scripts' {{else}} import { randomUUID } from 'node:crypto' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { startSDK, type SdkBootContext } from '@deepseek-ai/dsh-scripts' {{/if}} /** Boot this project's cordis.yml when invoked by dsh-scripts. */ export async function main(boot: SdkBootContext) { - const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) {{#if isStdio}} const model = boot.args.model if (typeof model !== 'string' || model.length === 0) throw new Error('stdio startup requires --model=') @@ -17,24 +15,26 @@ export async function main(boot: SdkBootContext) { if (resume !== undefined && (typeof resume !== 'string' || resume.length === 0)) { throw new Error('stdio startup requires --resume=') } + const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`) + process.env.DSH_SDK_SESSION_ID = sessionId +{{/if}} + const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) +{{#if isStdio}} if (resume === undefined) { await ctx.agents.create({ - agentId: AgentId('main'), - sessionId: SessionId(`main-session-${randomUUID()}`), + sessionId, meta: { cwd: boot.cwd }, agentOptions: { model }, }) } else { await ctx.agents.resume({ - agentId: AgentId('main'), - resumeSessionId: SessionId(resume), + resumeSessionId: sessionId, agentOptions: { model }, }) } {{else}} {{#if isEmbed}} await ctx.agents.create({ - agentId: AgentId('main'), sessionId: SessionId(`main-session-${randomUUID()}`), meta: { cwd: boot.cwd }, agentOptions: { model: {{modelLiteral}} }, diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index d55bb16be9..13fc046a04 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -167,6 +167,10 @@ describe('SdkProject and ProjectEditSession', () => { expect(index).toContain('SdkBootContext') expect(index).toContain('agents.create') expect(index).toContain('boot.args.resume') + expect(index).not.toContain('AgentId') + expect(index).toContain('const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`)') + expect(index).toContain('process.env.DSH_SDK_SESSION_ID = sessionId') + expect(index).toContain('resumeSessionId: sessionId') expect(project.packageManifest().scripts).toEqual({ dev: 'dsh-sdk dev index.ts -- --model="deepseek-v4-flash"', build: 'dsh-sdk build', @@ -175,7 +179,11 @@ describe('SdkProject and ProjectEditSession', () => { config: 'dsh-sdk config', }) expect(await readFile(join(project.root, '.env.example'), 'utf8')).toContain('EXA_API_KEY=') - expect(project.cordis.entry('stdio')?.config).toMatchObject({ agent: 'main' }) + expect(project.cordis.entry('stdio')?.config?.sessionId).toMatchObject({ + source: 'process.env.DSH_SDK_SESSION_ID', + }) + expect(await readFile(join(project.root, 'cordis.yml'), 'utf8')) + .toContain('sessionId: !!js process.env.DSH_SDK_SESSION_ID') expect(project.cordis.entry('stdio')?.config).not.toHaveProperty('model') expect(project.cordis.entry('agent-loop')?.config).toEqual({ agents: [] }) expect(project.cordis.entry('system-prompt')?.config?.persona).toContain('{{cwd}}') @@ -286,7 +294,10 @@ describe('SdkProject and ProjectEditSession', () => { const embed = (await embedEdit.commit()).project expect(embed.profile.runInterface).toBe('embed') expect(await readFile(join(embed.root, 'README.md'), 'utf8')).toContain('Embed the harness') - expect(await readFile(join(embed.root, 'index.ts'), 'utf8')).toContain('agents.create') + const embedIndex = await readFile(join(embed.root, 'index.ts'), 'utf8') + expect(embedIndex).toContain('agents.create') + expect(embedIndex).toContain("import { SessionId } from '@deepseek-ai/dsh-session'") + expect(embedIndex).not.toContain('AgentId') await writeFile(join(embed.root, 'README.md'), '# Custom README\n') const modified = await SdkProject.open(embed.root) From c148090961bf8de680f6b210e5d0532b23c174b8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:07:59 +0800 Subject: [PATCH 32/39] test(sdk): cover invalid generated session ids --- packages/sdk/helper/tests/project.spec.ts | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index 13fc046a04..bfaa8cbf77 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -873,6 +873,12 @@ describe('extension points', () => { resource.kind === 'cordis-config-entry' && resource.entry.id === 'acp') expect(acpEntry?.entry.id).toBe('acp') expect(acpEntry?.validateConfig?.({ model: '' })).toHaveLength(1) + const stdioEntry = builtins.get(featureId('app')).contribution(selection('app', ['stdio']), profile).resources + .find((resource): resource is CordisConfigEntryResource => + resource.kind === 'cordis-config-entry' && resource.entry.id === 'stdio') + expect(stdioEntry?.validateConfig?.({ welcome: 'ready', sessionId: 1 })).toEqual([ + 'sessionId must be a non-empty string', + ]) const embedOption = app.options.find(option => option.id === 'embed') expect(embedOption?.markerConfigEntries(profile)).toEqual([]) expect(embedOption?.contribution(profile, {}).resources.map(resource => resource.kind)).toEqual([ From a6e406a7782303ea5838007e8e85401e95ce4e01 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:16:52 +0800 Subject: [PATCH 33/39] docs(agent-loop): correct identity limitations --- packages/core/agent-loop/README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 9a165fd66a..6028b2f97f 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -126,7 +126,6 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p ## Known Limitations and Deferred Work - **Tool calls within a step execute sequentially** — parallel execution waits on concurrency-safety metadata in the tool contract (see `dsh-tools`). -- **No resume-or-create policy on the config path** — config-driven `create()` starts a fresh `${id}-session-` every run (`TODO(demo)`), and a config `resumeSessionId` whose resume fails logs a warning and creates no agent. +- **Config labels are fresh by default** — omitting `sessionId` creates a fresh `${id}-session-` on every startup; exact resume-or-create behavior requires an explicit stable `sessionId`, while `resumeSessionId` requires existing persisted history. - **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options. - **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin. -- **`runLoop`/`Inbox`/`InboxMessage` stay exported with no outside consumer** — [removal is proposed](../../../docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md). From d56cc8d42417c45c835c2f7576d16bab980eb428 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:00:56 +0800 Subject: [PATCH 34/39] fix(stdio): close startup failure gaps --- .../helper/src/templates/assets/index.ts.tpl | 31 ++++++++++++------- packages/sdk/helper/tests/project.spec.ts | 2 ++ packages/ui/stdio/README.md | 6 ++-- packages/ui/stdio/package.json | 5 +++ 4 files changed, 30 insertions(+), 14 deletions(-) diff --git a/packages/sdk/helper/src/templates/assets/index.ts.tpl b/packages/sdk/helper/src/templates/assets/index.ts.tpl index 4c3099199c..a79818908c 100644 --- a/packages/sdk/helper/src/templates/assets/index.ts.tpl +++ b/packages/sdk/helper/src/templates/assets/index.ts.tpl @@ -20,17 +20,26 @@ export async function main(boot: SdkBootContext) { {{/if}} const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) {{#if isStdio}} - if (resume === undefined) { - await ctx.agents.create({ - sessionId, - meta: { cwd: boot.cwd }, - agentOptions: { model }, - }) - } else { - await ctx.agents.resume({ - resumeSessionId: sessionId, - agentOptions: { model }, - }) + try { + if (resume === undefined) { + await ctx.agents.create({ + sessionId, + meta: { cwd: boot.cwd }, + agentOptions: { model }, + }) + } else { + await ctx.agents.resume({ + resumeSessionId: sessionId, + agentOptions: { model }, + }) + } + } catch (error) { + try { + await ctx.fiber.dispose() + } catch (disposeError) { + throw new AggregateError([error, disposeError], 'stdio startup and cleanup failed') + } + throw error } {{else}} {{#if isEmbed}} diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index bfaa8cbf77..655b308911 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -171,6 +171,8 @@ describe('SdkProject and ProjectEditSession', () => { expect(index).toContain('const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`)') expect(index).toContain('process.env.DSH_SDK_SESSION_ID = sessionId') expect(index).toContain('resumeSessionId: sessionId') + expect(index).toContain('await ctx.fiber.dispose()') + expect(index).toContain("new AggregateError([error, disposeError], 'stdio startup and cleanup failed')") expect(project.packageManifest().scripts).toEqual({ dev: 'dsh-sdk dev index.ts -- --model="deepseek-v4-flash"', build: 'dsh-sdk build', diff --git a/packages/ui/stdio/README.md b/packages/ui/stdio/README.md index b7d320880d..f9cebe11e6 100644 --- a/packages/ui/stdio/README.md +++ b/packages/ui/stdio/README.md @@ -9,7 +9,7 @@ This package owns the terminal channel only. It injects `agents` and `userIntera | Key | Default | Meaning | |---|---|---| | `welcome` | `ready.` | Banner printed before the first prompt | -| `agent` | `main` | Agent id driven by stdin and observed for EOF shutdown | +| `sessionId` | `main` | Exact agent/session identity driven by stdin and observed for EOF shutdown | The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. Disposal closes readline and unregisters every listener/provider through Cordis effects. @@ -18,7 +18,7 @@ The plugin seeds display labels from the live agent registry, then tracks `agent name: '@deepseek-ai/dsh-stdio' config: welcome: 'agent REPL ready. Give it a coding task.' - agent: main + sessionId: main ``` ## Model Experience @@ -37,6 +37,6 @@ The plugin seeds display labels from the live agent registry, then tracks `agent ## Known Limitations and Deferred Work -- **One configured agent receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `agent` id rather than routing by the visible label. +- **One configured session receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `sessionId` rather than routing by the visible label. - **Terminal questions are text-only and sequential** — the provider queues asks, supports option labels plus custom text, and has no richer UI shapes such as file pickers or diff previews. - **Closed stdin ends the terminal channel** — EOF rejects active or queued questions and exits after submitted work reaches idle; there is no reconnect path for a long-lived process. diff --git a/packages/ui/stdio/package.json b/packages/ui/stdio/package.json index 1c7311d0cb..e1bffdf171 100644 --- a/packages/ui/stdio/package.json +++ b/packages/ui/stdio/package.json @@ -29,6 +29,11 @@ "@deepseek-ai/dsh-user-interaction": "^0.0.1", "cordis": "^4.0.0-rc.7" }, + "peerDependenciesMeta": { + "@deepseek-ai/dsh-agent-loop": { + "optional": true + } + }, "dependencies": { "schemastery": "^3.18.0" }, From b2064cba10f3a0c19ca24472f0ee7d7f81c1816f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:26:57 +0800 Subject: [PATCH 35/39] fix(agent-loop): reject duplicate configured identities --- packages/core/agent-loop/src/index.ts | 22 ++++++++++++++++--- .../tests/config-session-id.spec.ts | 19 ++++++++++++++++ 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 325ba7b92d..7144ae8dfb 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -369,6 +369,24 @@ export interface Config { })[] } +/** Reject self-contained identity conflicts before any configured agent starts. */ +function validateConfiguredAgents(agents: Config['agents']): void { + const exactIdentities = new Map() + for (const { id, sessionId, resumeSessionId } of agents) { + const hasResumeId = resumeSessionId !== undefined && resumeSessionId !== '' + if (sessionId !== undefined && hasResumeId) { + throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) + } + const exactIdentity = hasResumeId ? resumeSessionId : sessionId + if (exactIdentity === undefined) continue + const firstId = exactIdentities.get(exactIdentity) + if (firstId !== undefined) { + throw new Error(`agents "${firstId}" and "${id}" use duplicate exact session identity "${exactIdentity}"`) + } + exactIdentities.set(exactIdentity, id) + } +} + /** Concrete ReactLoopAgent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] @@ -390,6 +408,7 @@ export class AgentLoop extends Service implements AgentFactory { constructor(ctx: Context, public config: Config) { super(ctx, 'agentLoop') + validateConfiguredAgents(config.agents) this.ownership = new FactoryOwnership(ctx.fiber) this.runtime = { ctx } ctx.effect(() => () => this.ownership.dispose(), 'agentLoop.transactions()') @@ -412,9 +431,6 @@ export class AgentLoop extends Service implements AgentFactory { } continue } - if (sessionId !== undefined) { - throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) - } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index bd2a5522df..56cc0bee40 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -64,6 +64,25 @@ describe('config-driven session id', () => { await conflicting.fiber.dispose() }) + it('rejects duplicate exact ids before asynchronous configured startup', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-duplicate-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + + const outcome = await ctx.plugin(AgentLoop, { + agents: [ + { id: 'first', sessionId: SessionId('shared'), model: 'mock' }, + { id: 'second', sessionId: SessionId('shared'), model: 'mock' }, + ], + }).then(() => undefined, (error: unknown) => error) + const published = ctx.agents.get(SessionId('shared')) + await ctx.fiber.dispose() + + expect(outcome).toEqual(new Error('agents "first" and "second" use duplicate exact session identity "shared"')) + expect(published).toBeUndefined() + }) + it('restores a materialized exact id across an AgentLoop-only reload', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-')) dirs.push(root) From 042d752fd2ca7f8699011275b03a952935a0a54a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:26:57 +0800 Subject: [PATCH 36/39] docs(repeat-guard): trim module orientation --- packages/guard/repeat-tool-guard/src/index.ts | 37 ++----------------- 1 file changed, 4 insertions(+), 33 deletions(-) diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index d51df1d829..bd6c5a4404 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -1,37 +1,8 @@ /** - * Repeat-tool-call guard: advisory loop-breaker for agents stuck re-issuing - * the same tool call with identical arguments. - * - * Not a model-facing tool — it registers no tool, never vetoes or rewrites a - * call, and adds exactly one behavior: watch each agent's stream of tool calls - * through the `tools/post-execute` waterfall, count runs of consecutive calls - * to the same tool with identical canonicalized arguments, and at configured - * run lengths fold an escalating advisory reminder onto the decision's - * `additionalContext`. The loop appends that context as a logged - * `context/message` after the step's tool results, so the reminder is - * model-visible, source-attributed, and reconstructable from the session log - * with no new session event. Decision record: - * docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md. - * - * ```yaml - * - id: repeat-tool-guard - * name: '@deepseek-ai/dsh-repeat-tool-guard' - * config: - * thresholds: [3, 5, 8] # consecutive counts that trigger a reminder - * include: [] # tool-name patterns to track; empty = all tools - * exclude: [todo_write] # tool-name patterns transparent to the chain - * ``` - * - * Chain state is keyed by the live agent object — the tool registry is a - * context-level singleton whose waterfalls interleave every agent's calls, so - * a shared counter would let one agent's repetition trip another's reminder. - * State is in-memory only: a session resumed from persistence starts with a - * fresh chain (the guard is a heuristic nudge, not a logged invariant). - * - * Plugin export shape: named exports, NO default. The cordis Loader's - * `unwrapExports` does `exports.default ?? exports`, so a stray default would - * collapse the module to the bare `apply` (see docs/postmortem/0001). - * + * Advisory per-agent repeat-call detector. It enriches post-execute decisions + * with logged model context without vetoing or rewriting calls. Configuration + * and chain semantics live in the package README; rationale lives in the + * repeat-tool-guard RFC. * @module @deepseek-ai/dsh-repeat-tool-guard */ From 68b5c716b1265590f5f2936c33f9760b12c8d1db Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:29:08 +0800 Subject: [PATCH 37/39] docs(catalog): refresh AgentLoop source link --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 85e07f8191..f83f2bf616 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:373`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:391`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From b77cfd64a1cba70c1c2168d370aeab3108989a12 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:29:32 +0800 Subject: [PATCH 38/39] docs(catalog): refresh repeat guard source link --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 46645b0575..29d37dd6db 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -548,7 +548,7 @@ export interface Config { } ``` -Source: [`packages/guard/repeat-tool-guard/src/index.ts:55`](../packages/guard/repeat-tool-guard/src/index.ts) +Source: [`packages/guard/repeat-tool-guard/src/index.ts:26`](../packages/guard/repeat-tool-guard/src/index.ts) ## `@deepseek-ai/dsh-sandbox-local` From 9a25e44fbb4c192ad1912fa504d9b71e19820f36 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 12:54:45 +0800 Subject: [PATCH 39/39] test(agent-spine-demo): wait for exact agent identity --- .../examples/agent-spine-demo/tests/agent-core.spec.ts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts index 6081fff1a1..fb74e11b7d 100644 --- a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts +++ b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts @@ -86,10 +86,10 @@ async function withIsolatedSkillHomes(run: () => Promise): Promise { } } -function waitForMainIdle(ctx: Context): Promise { +function waitForIdle(ctx: Context, target: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (agent, status) => { - if (agent.id === 'main' && status === 'idle') { + if (agent === target && status === 'idle') { dispose() resolve() } @@ -177,7 +177,7 @@ describe('dsh-agent-spine-demo bundle', () => { const agent = handle.agent agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, agent) const sentText = adapter.requests[0]?.messages.map(messageText).join('\n') expect(sentText).toContain('hi') @@ -206,7 +206,7 @@ describe('dsh-agent-spine-demo bundle', () => { }) handle.agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, handle.agent) expect(adapter.requests[0]?.messages).toEqual([{ role: 'user', content: [{ type: 'text', text: 'hi' }] }]) await handle.dispose() @@ -295,7 +295,7 @@ describe('dsh-agent-spine-demo bundle', () => { }) handle.agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, handle.agent) expect(messageText(adapter.requests[0]?.messages[0])).toContain('workspace rule before skills') expect(messageText(adapter.requests[0]?.messages[1])).toContain('prefix-order-skill')