diff --git a/docs/architecture.md b/docs/architecture.md index d4abf10283..ccc18e7371 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -56,12 +56,15 @@ Waterfall events behave like around-middleware: a listener delegates by calling The shipped loop drains work from prompt through checkpoint. Every pause is a service call or event available to plugins. -A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. +A **session** is an append-only event log. A **turn** drains queued input until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. + +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 ```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 await unpublished setup +choose declarative identity and fresh/resume path + -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 await unpublished setup -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 53e5142dff..f8d6182e7a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -27,7 +27,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:208`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:207`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-demo` @@ -87,8 +87,10 @@ export interface Config { maxParallelToolCalls?: number /** 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 stable identity; remounts resume its materialized history, while first use creates it fresh. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -97,9 +99,9 @@ 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:334`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:370`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-agent-spine-demo` @@ -597,7 +599,7 @@ export interface Config { } ``` -Source: [`packages/guard/repeat-tool-guard/src/index.ts:27`](../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` @@ -767,12 +769,12 @@ Requires: `agents` · `userInteraction` export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - /** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */ - agent?: string + /** Exact shared agent/session identity stdin drives. Defaults to `'main'`. */ + sessionId?: string } ``` -Source: [`packages/ui/stdio/src/index.ts:30`](../packages/ui/stdio/src/index.ts) +Source: [`packages/ui/stdio/src/index.ts:33`](../packages/ui/stdio/src/index.ts) ## `@deepseek-ai/dsh-stdio-demo` @@ -813,7 +815,7 @@ export interface Config { /** Generic background-task control-tool config forwarded through agent-core. */ toolTasks?: NonNullable /** - * 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`). */ @@ -825,7 +827,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/stdio-demo/src/index.ts:37`](../packages/examples/stdio-demo/src/index.ts) +Source: [`packages/examples/stdio-demo/src/index.ts:38`](../packages/examples/stdio-demo/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 207ea114e0..b44b0e51b4 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: 3474bc116b43f9be57b52e947f9cf99730f7e796 -extension-cookbook.zh.md: 1a605b20fe4e171a948ac2a046193a2f4d884e44 +extension-cookbook.md: 995ecd879faec02044b55ce3d53f7fe1b2aed270 +extension-cookbook.zh.md: e3fe3103e13c359e77e0202df223aae35bcdd525 diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 3474bc116b..995ecd879f 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -40,7 +40,7 @@ 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 @@ -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 }])) } ``` diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 1a605b20fe..e3fe3103e1 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 }])) } ``` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 6fbffc1798..be88e1eaaa 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ A fully configured agent and live session were published. Setup is composition-o Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:154`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:141`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:163`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:150`](../../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:298`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -59,7 +59,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:217`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:204`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -71,7 +71,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca 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:227`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:214`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -83,7 +83,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already 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:182`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:169`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -95,7 +95,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:226`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -107,7 +107,7 @@ Compose request-only messages placed before derived history. The frozen result i Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:254`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:241`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -119,7 +119,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:195`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:182`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -131,7 +131,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:172`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:159`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -143,7 +143,7 @@ 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:265`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:252`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -155,7 +155,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:275`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:262`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -167,7 +167,19 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:272`](../../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. 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:363`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` @@ -289,7 +301,7 @@ 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:108`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:109`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -299,7 +311,7 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): 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) ### `subagent/provider-removed` — emit @@ -309,7 +321,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:88`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:89`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -319,7 +331,7 @@ 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:99`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:100`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e0f07cfce7..67f6e284e8 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:352`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:408`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` @@ -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: AgentId): Agent | undefined +get(id: SessionId): Agent | undefined list(): Agent[] +roots(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:133`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:201`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` @@ -220,7 +221,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:580`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:585`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` @@ -262,7 +263,7 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` -Source: [`packages/subagent/subagent/src/index.ts:141`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:142`](../../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/core.md b/docs/core-data-structures/core.md index c1ecdcc6a5..88ca9bf8f7 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -76,7 +76,7 @@ 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. @@ -86,7 +86,7 @@ Source: [`packages/util/brand/src/index.ts`](../../packages/util/brand/src/index type Branded = string & { readonly [BRAND]: B } ``` -The three core IDs are `CallId`, `SessionId`, and `AgentId`. Capability packages brand their own ids too, such as `TaskId` in [tasks.md](tasks.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). Capability packages brand their own ids too, such as `TaskId` in [tasks.md](tasks.md). ## Content blocks and messages @@ -303,7 +303,7 @@ interface InjectOptions extends SendOptions { ```ts type-equiv interface Agent { - readonly id: AgentId + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus @@ -409,7 +409,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `AgentId` is branded. `AgentOptions` is merge-extensible and currently includes `provider?` and `model?`; dispatch requires both after `agent/request`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. +`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `SessionId` is branded. `AgentOptions` is merge-extensible and currently includes `provider?` and `model?`; dispatch requires both after `agent/request`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits. diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 28093165bd..e6e2ae2ebe 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -68,7 +68,7 @@ interface SubagentStopReasonMap { ```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 acd90d4423..439c07fb25 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,32 +7,33 @@ 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:154`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:163`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:298`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:217`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:227`](../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:182`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp) | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:254`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:195`](../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) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:172`](../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`](../packages/ui/stdio) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:265`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:275`](../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:285`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:363`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:141`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:150`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`stdio`](../packages/ui/stdio) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:285`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:204`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:214`](../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:169`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:226`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp) | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:241`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:182`](../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), [`stdio`](../packages/ui/stdio) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:159`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio`](../packages/ui/stdio) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:252`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:262`](../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:272`](../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:31`](../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:61`](../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:70`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:53`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:40`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | -| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`workspace-context`](../packages/context/workspace-context) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | -| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:108`](../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:82`](../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:88`](../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:99`](../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:109`](../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:83`](../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:89`](../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:100`](../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:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`acp`](../packages/ui/acp) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 8b67c73d27..555afdffea 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -230,6 +230,7 @@ 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 @@ -244,10 +245,6 @@ 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 @@ -284,6 +281,7 @@ 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 @@ -348,6 +346,7 @@ 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 @@ -370,12 +369,18 @@ 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_home @@ -412,6 +417,7 @@ flowchart TD pkg_acp_demo --> pkg_user_interaction pkg_acp_demo --> pkg_workspace_context 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 @@ -477,17 +483,16 @@ 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) | | [`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), [`home`](../packages/util/home), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session-persistence`](../packages/session-persistence/session-persistence), [`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-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`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) | | [`spill-policy`](../packages/spill/spill-policy) | `spill` | [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`tools`](../packages/core/tools) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | @@ -502,15 +507,16 @@ 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), [`session-persistence`](../packages/session-persistence/session-persistence), [`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), [`home`](../packages/util/home), [`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), [`workspace-context`](../packages/context/workspace-context) | | [`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), [`workspace-context`](../packages/context/workspace-context) | -| [`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), [`workspace-context`](../packages/context/workspace-context) | +| [`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), [`workspace-context`](../packages/context/workspace-context) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index ecb66326b3..fba361469c 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -20,7 +20,6 @@ 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 | ### Architecture @@ -99,6 +98,7 @@ 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/2026-06-11-content-block-vocabulary.md b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md index 1c22f9b7ca..77f521834c 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 @@ -23,4 +23,4 @@ In-session context injection (`context/message`, `steering/message`) renders as - Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image RFC](../simplification/2026-07-04-drop-image-content-block.md). - Cache hints and assistant prefill remain absent until a shipping adapter can honor them; see the [producer-less variants](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md) and [inert request knobs](../simplification/2026-07-04-drop-inert-request-knobs.md) RFCs. - 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 327aa8eac3..3bd3c3fdf1 100644 --- a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md +++ b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md @@ -21,7 +21,7 @@ Key choices recorded here because they are durable, contested, and surprising: - **Append-only; a crashed turn is closed, never truncated.** Events through a flushed `turn/end` are never rewritten, and the loop flushes only at turn end. Because one interrupted turn may contain substantial valid work, `load` preserves its contiguous, parseable events and appends error results for unanswered tool calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }`. The synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded; a parse error or sequence gap at or before the last real `turn/end` is 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/2026-06-18-agent-lifecycle-and-ownership-seams.md b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md index 665063399d..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 @@ -12,28 +12,30 @@ Three seams: the queue-aware cancel, the `AgentHandle` disposer, and the bash ow ### 1. Queue-aware `Agent.cancel(reason?)` -`cancel()` is the single public stop primitive. It clears queued and steering input, aborts an in-flight step, and arms a turn-scoped marker checked at each turn boundary. A queued prompt therefore cannot start after cancellation or absorb later input. `whenIdle()` waits for post-cancel quiescence, and ACP `session/cancel` maps to this method. An idle cancel does not arm the marker. +A new `cancel()` verb on the `Agent` interface — the single public stop primitive. (It originally shipped alongside a narrower step-only `abort()`; that verb was later removed as unused, leaving `cancel()` the only public way to stop work.) It clears the inbox's queued + steering FIFOs, aborts the in-flight step if any, and drives a **turn-scoped cancellation marker** the driver loop checks at every turn-decision point — so a prompt that is queued-but-not-yet-started never runs, a cancel landing in the pre-step / continuation window drops the about-to-run turn (ending it `aborted`), and a later prompt cannot be batched into the cancelled turn. `whenIdle()` reaches post-cancel quiescence. ACP `session/cancel` maps to `cancel()`. The marker is armed ONLY when there is something to cancel, so an idle no-op cancel cannot strand the next prompt. ### 2. `AgentHandle` async disposer -`ctx.agents.create`/`resume` and `AgentFactory` return `AgentHandle = { agent, dispose() }`. Disposal is a consumer capability; an observer holding only `Agent` cannot tear it down. The caller fiber and factory provider also own the instance, and every path shares one memoized teardown: stop the loop, await quiescence and flushes, detach the agent and session, then unwind its scope. IDs become reusable when their registry entries detach. Config-created agents belong to the loop fiber; ACP stores and disposes each session handle. +`ctx.agents.create`/`resume` (and the `AgentFactory` interface) return `AgentHandle = { agent: Agent; dispose(): Promise }`. The disposer is a **consumer capability** — a registry observer holding only the bare `Agent` cannot tear it down. The caller fiber and registered factory provider are structural co-owners: caller unload enforces structured ownership, while provider unload must stop old instances whose scoped dependency surface resolves through that provider. All three paths reach the same memoized teardown: stop the loop, await its exit and idle flushes (true quiescence, not just the `disposed` status flip), detach the agent, detach its session, and unwind its scope. Each public ID becomes reusable when its exact registry entry detaches; there is no separate reservation-release phase. Config-created agents are already owned by the `AgentLoop` fiber (the handle is discarded). ACP holds each session's disposer in its `SessionRecord` and runs it on disconnect/teardown, so a bare client disconnect leaves no registered agent and no session-store entry — even when `session/load` races teardown (the just-resumed handle is disposed before the closed-guard throw). -Teardown order is load-bearing for durability. The session lifecycle and loop share one composite Cordis effect so LIFO disposal stops the loop and awaits `agent.done` before detaching the session. Sibling effects would dispose concurrently and could remove append hooks before the closing flush. Disposal notifications are contained so they cannot interrupt the chain. +**Teardown ORDER is load-bearing for durability**, and the implementation folds the session lifecycle into the agent's SINGLE composite cordis effect (`SessionStore.prepare`/`enter`/`announce`, replacing a sibling-effect split). A fiber unload disposes sibling effects concurrently (`Promise.all`), which would race removing the session store's append publication hooks against the loop's closing `session/flush` and drop the closing `turn/end`; inside one effect the disposers run as an ordered LIFO chain (loop stopped + `await agent.done` BEFORE the session detaches), so the loop's final flush is captured on BOTH the handle's `dispose()` and a fiber unload. The contained `agent/disposed` and `session/disposed` notifications cannot reject the chain or skip later teardown. ### 3. Bash owner token in the seam -Background task ownership belongs to the executor. `BashExecSpec.owner` carries an optional opaque token, `ownerOf(id)` reads it, and `dsh-tool-bash` stamps the calling session token at start. `bash_output` and `bash_kill` reject mismatched callers; completion notices locate the live agent by session token through the registry. Keeping ownership on the task preserves the fence across tool-plugin reloads. The completion listener remains effect-scoped, so a notice that settles during the reload gap may still be dropped. +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 -- ACP disconnect or session close leaves no registered agent or session-store entry, including when `session/load` races teardown. -- Cancelling before a queued prompt starts prevents that prompt from running or absorbing the next prompt. -- Reloading `dsh-tool-bash` does not let another session read or kill an existing background task because ownership remains on the executor. -- Config-created agents remain loop-fiber-owned, so non-ACP demos need not manage handles explicitly. +These invariants hold and are pinned by tests: + +- ACP disconnect/session close leaves no registered agent AND no session-store entry for that session, even when `session/load` races teardown. +- `session/cancel` before a queued prompt starts prevents that prompt from running and cannot batch the next prompt into the cancelled turn. +- A `tool-bash` HMR reload does NOT make an existing background task readable or killable by a different session (ownership survives on the executor). +- Existing non-ACP demos still work without managing handles explicitly; config-created agents remain owned by the `AgentLoop` plugin fiber. ## Session owner tokens are unique among live agents -The bash owner token relies on `session.header.id` being unique among live agents. Concurrent same-ID operations may prepare privately, but `SessionStore.enter()` rejects duplicate publication and the losing transaction rolls back. `tool-bash` owns the comparison policy; the bash seam stores an opaque `owner` string without interpreting it. +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 9f83e46b24..fd5c5bf953 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 IDs in the bash seam.** `BashTask.id` and every executor/tool boundary used bare `string`, even though the generated value has the same `name-N` shape as default session ids. The model also returns this value through `task_id`, so confusing task and session ids was both type-correct and reachable. +**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 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 — erosion of existing brands.** `CallId`, `SessionId`, and `AgentId` became bare strings in registry maps, public lookup parameters, ACP session tracking, and the persistence coordinator. Dropping a brand at a lookup boundary defeats its main protection. +**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.) +- **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`, `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): @@ -44,7 +44,7 @@ export function OwnerToken(id: string): OwnerToken { ### Why not typing `owner` as `SessionId`? -The executor treats ownership as opaque and must not depend on the session model. A distinct `OwnerToken` preserves that boundary while preventing raw strings or task ids from being passed as owners. `dsh-tool-bash`, which owns the access policy, performs the single conversion from `SessionId`. +The obvious shortcut is to type `owner` as `SessionId` directly — it always *is* one. We reject that. The bash executor seam is a capability seam (interface `dsh-bash`, implementation `dsh-bash-local`, consumer `dsh-tool-bash`) and its owner token is *documented as deliberately opaque*: the executor "never interprets it (no access policy lives in the seam — that is the consumer's job)" (`packages/bash/bash/src/types.ts`). Typing the seam's field as `SessionId` would import `dsh-session`'s vocabulary into a package that must not know what an owner token *means* — it would couple a generic execution backend to the session model and contradict the opaque-token design. A sandboxed or remote executor that replaces `dsh-bash-local` should not inherit a session dependency. The distinct `OwnerToken` brand keeps the seam decoupled: `dsh-bash` knows only "an owner is some opaque branded token," and the `dsh-tool-bash` consumer — which already decides the access policy — is the single boundary that casts its `SessionId` into an `OwnerToken`. The brand still delivers the safety win (you cannot pass a `BashTaskId` or a raw string where an owner is expected) without the coupling. ## Out of scope / possible extensions @@ -58,10 +58,10 @@ Kept deliberately narrow per the "not every string needs a brand" policy. Each o ## Verification -`BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded through the executor, local implementation, and model-facing tool without adding a `dsh-session` dependency. Collections, public parameters, and exported signatures use the applicable brand for `CallId`, `SessionId`, `AgentId`, or `BashTaskId` rather than bare `string`; raw provider, ACP, and model inputs enter through the brand factory instead of scattered 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 -- **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/architecture/2026-06-30-event-domain-semantics.md b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md index 4cf055179c..b38777be38 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 vocabulary is the foundation for interception decisions, the durable `hook/ **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 4996fc2935..74f4216565 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 counts consecutive calls to the same tool with identical canonical arguments and injects advisory reminders at configured thresholds. It never delays, blocks, or rewrites a call; the model decides whether to retry differently or finish. -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, prepends a reminder to the downstream decision's `additionalContexts` — 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 e2a1165846..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 @@ -2,9 +2,18 @@ Status: implemented + + ## Problem -The loop exposed durable turn and step boundaries through both the replayable `SessionEvent` log and live `agent/*` mirrors. Consumers had to choose between two sources for the same fact and reconcile their timing. ACP and persistence already used the log; the stdio UI was the only remaining mirror consumer and already rendered tool calls and results from `session/event`. +The loop records the canonical transcript in `SessionEvent` and also emitted a parallel set of live `agent/*` boundary mirror events: `agent/turn-start`, `agent/turn-end`, `agent/step-start`, and `agent/step-end`. The mirrors made consumers choose between two sources of truth for the SAME durable fact. ACP already chose the session log for the editor-facing transcript because it is the one durable, replayable record; consuming a live mirror would require reconciling its timing with the boundary already stored in that log. The stdio UI was the only production consumer that still rendered turn boundaries from the mirror events; it already rendered tool calls and results from `session/event`. This duplication is not free. Every lifecycle change had to update the session event, the mirror event, docs, invariants, tests, and snapshot expectations. The duplicate boundary events also made failure ordering subtle: a turn can be durably closed before a live `agent/turn-end` listener runs, so a post-boundary listener failure has no valid in-log position left and must be reported out of band. @@ -12,19 +21,25 @@ 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. -Remove `agent/turn-start`, `agent/turn-end`, `agent/step-start`, and `agent/step-end`. Boundary consumers subscribe to `session/event`. A UI that needs an agent label maintains a session-to-agent map from `agent/created` and `agent/disposed`, because the durable `turn/start` carries the turn number but not the agent id. +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 had no consumers and were removed first by the [event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md). That decision retained the turn mirrors for the stdio UI; this RFC removes them after migrating that test REPL to `session/event` and the id map. +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 -This decision covers only durable turn and step boundaries. `agent/steering` mirrored a control record and `agent/stream-chunk` mirrored the token stream, so each was handled separately: [steering](2026-07-04-remove-agent-steering-mirror.md) and [stream chunks](2026-07-02-remove-stream-chunk-mirror.md). `agent/created`, `agent/disposed`, `agent/status`, `agent/error`, and `agent/queued` remain live lifecycle or control events rather than transcript mirrors; queued input may be cancelled before any durable event exists. +Removed (durable-boundary mirrors — the session log is authoritative for each): `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end`. + +RETAINED — NOT durable-boundary mirrors, so out of scope for this decision: + +- `agent/steering` — not a boundary, so out of scope for THIS decision (the original proposal bundled it into the removal; that would have been scope creep here). It mirrors the durable `steering/message` control record rather than a boundary, and was removed by its own follow-up: [Remove the `agent/steering` mirror emit](2026-07-04-remove-agent-steering-mirror.md). +- `agent/stream-chunk` — the live token stream. Out of scope for THIS decision (a mirror of the durable `assistant/chunk`, not a boundary), it was removed by its own follow-up: [Stop mirroring the token stream as an agent event](2026-07-02-remove-stream-chunk-mirror.md). +- `agent/created`, `agent/disposed`, `agent/status`, `agent/error`, `agent/queued` — lifecycle/control events that are not transcript data. `agent/queued` in particular is an inbox acknowledgement that fires before any durable event exists (cancelled queued work may never enter the log), so it is deliberately live-only. ## Alternatives considered -- **Remove `agent/steering` in the same change** — rejected because it was a control-record mirror rather than a boundary mirror. -- **Keep turn mirrors for the stdio UI** — rejected because the UI can render `session/event` and recover the agent label from its id map. +- **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` 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/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..20ba40c196 --- /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 + +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 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) 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 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. 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. + +## 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 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. + +## 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/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/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 bf4e85e020..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 @@ -4,7 +4,7 @@ Status: proposed ## Problem -Add isolated subagent providers for Claude Code and Codex. The existing [named-provider seam](../../implemented/feature/2026-06-21-subagent-capability-seam.md) and [ACP backend](../../implemented/feature/2026-06-22-acp-subagent-backend.md) establish the process-boundary shape. A harness turn should be able to delegate a self-contained task to either product and receive its final answer without exposing parent secrets or inheriting host configuration from `~/.claude` or `~/.codex`. +The subagent seam ([the seam RFC](../../implemented/feature/2026-06-21-subagent-capability-seam.md)) hosts multiple named providers on `ctx.subagents`, and the ACP backend ([the ACP backend RFC](../../implemented/feature/2026-06-22-acp-subagent-backend.md)) proved the seam generalizes across a process boundary; its Future-providers section explicitly named the Codex app-server and the Claude Code Agent SDK as mechanically similar siblings. Those two are the engines actually worth delegating to today: a harness turn should be able to hand a self-contained task to a real Claude Code or a real Codex — a separate product with its own model, tools, and sandbox — and get back one final answer, without the parent deployment leaking its secrets into the child or the child's behavior silently depending on whatever `~/.claude` / `~/.codex` state exists on the host machine. ## Proposal @@ -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 follow the ACP backend contract: a fresh child per `start`, one prompt round-trip, no inherited parent context or advertised optional capabilities, ignored `request.parent` and `request.agentOptions`, and a random branded agent id. `result` never rejects; child failures map to stop reasons while the original error reaches the logger. Each mounts `dsh-tool-subagent` under a distinct tool name. The tool result is the only new model-visible artifact, so no new session event is required; workspace mutations remain ambient side effects outside transcript replay. +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) @@ -31,11 +31,11 @@ Both integration surfaces were verified against pinned implementations before th ## Isolation and credentials -Authentication is API-key-only. Each run uses a fresh config directory (`CLAUDE_CONFIG_DIR` with `settingSources: []`, or `CODEX_HOME`) that is removed best-effort on dispose; config may instead select a persistent directory. The shared child-env helper forwards ordinary values such as `PATH`, `HOME`, `TMPDIR`, locale, and proxy settings, removes credential-shaped names, and overlays explicit `config.env`. Claude Code receives its API key through that overlay, while Codex receives it through `account/login/start` rather than a hand-written auth file. +Deployments authenticate with API keys only, and the child must not see the host user's Claude Code / Codex configuration: behavior has to be a function of `cordis.yml` alone. Each run gets a fresh `mkdtemp` config dir — `CLAUDE_CONFIG_DIR` for Claude Code (paired with an explicit `settingSources: []`), `CODEX_HOME` for Codex — removed best-effort on dispose; a config field can pin a persistent dir instead. The child env reuses the ACP backend's `buildChildEnv` semantics verbatim via the extraction: the ambient env is forwarded MINUS credential-shaped vars (`/KEY|SECRET|TOKEN/i`), with `config.env` layered on top — so `PATH`, `HOME`, `TMPDIR`, locale, and proxy vars survive and the CLIs run normally, while only credential-shaped ambient vars are scrubbed (`ANTHROPIC_API_KEY` enters explicitly through `config.env` for Claude Code), and the Codex key travels via the `account/login/start` RPC into the isolated `CODEX_HOME` rather than a hand-written `auth.json`. ## Permission and approval policy -Each backend exposes its engine's native policy vocabulary. Claude Code defaults to `permissionMode: default` with `permission: reject`; Codex defaults to `sandboxMode: read-only`, `approvalPolicy: never`, and the same rejected fallback. Examples opt into `acceptEdits` or `workspace-write`. Known approval, user-input, and elicitation requests receive the configured answer; unknown methods receive method-not-found and unknown notifications are consumed. No prompt reaches a human, and no child can wait indefinitely for unavailable input. +Instead of collapsing to ACP's single `permission: allow|reject` knob, each backend exposes its engine's native vocabulary as config, with conservative defaults: Claude Code gets `permissionMode` (default `default`) plus `permission: allow|reject` (default `reject`) as the `canUseTool` auto-answer for whatever falls through; Codex gets `sandboxMode` (default `read-only`) and `approvalPolicy` (default `never`) plus the same `permission` fallback for approval requests that still arrive. Defaults are deliberately do-no-harm (the out-of-box child cannot write files); examples demonstrate opening up (`acceptEdits` / `workspace-write`). The mechanical rule: EVERY server-initiated request is settled programmatically and promptly — the enumerated approval/user-input/elicitation requests by the configured policy, an unknown request method with a JSON-RPC method-not-found error response (never left pending), unknown notifications consumed — so no child request can wedge a turn waiting on an answer that will never come. Prompts never reach a human in this cut, matching ACP. ## StopReason mapping @@ -45,11 +45,11 @@ Liveness posture, stated explicitly: teardown timing is config, turn duration is ## Testing -Coverage is required at each applicable tier: +Named at every tier per the root AGENTS.md rule, and de-risked up front: -- **Keyless unit/integration:** drive a fake Claude CLI through the real SDK and a scripted Codex app-server through the real wire client. At per-file 100% coverage, exercise round trips, every stop mapping, both cancellation paths and pre-abort, permission policies, unknown messages, spawn failure, reload cleanup, export shape, scrubbed environments, temporary-directory removal, and Codex auth precheck failure. -- **With-key e2e:** each real engine performs file work under `acceptEdits` or `workspace-write`; skips name the missing binary or key and assert no child process remains. -- **Snapshot:** deferred as `TODO(claude-code-subagent-replay)` and `TODO(codex-subagent-replay)` pending the process-specific replay shape described by the [subagent replay RFC](../../implemented/testing/2026-06-22-subagent-snapshot-replay.md). +- **Keyless unit/integration**, mirroring the ACP spec list per backend (round-trip and output accumulation, every stop mapping, both cancel paths, already-aborted, permission auto-answer under both policies, unknown-message tolerance, bad-command spawn failure, HMR provider cleanup, export shape, isolation assertions on child env and temp-dir removal; Codex adds the auth-precheck failure path). Claude Code's harness is a scripted fake `claude` executable behind `pathToClaudeCodeExecutable` driven by the REAL SDK — a spike already passed end-to-end keyless in 24ms (the fake CLI answers one `control_request/initialize` and speaks plain stream-json, ~40 lines). Codex's harness is a scripted mock app-server subprocess speaking the verified wire protocol, the `mock-acp-server.ts` shape. +- **With-key e2e** per backend: the real engine does real file work verified on disk, under a pinned opened-up config so acceptance and the do-no-harm defaults don't collide — `permissionMode: 'acceptEdits'` for Claude Code, `sandboxMode: 'workspace-write'` + `approvalPolicy: 'never'` for Codex; self-skips report exactly what is missing (binary vs key). CI has no secrets, so these run locally per the with-key policy. +- **Snapshot**: deferred as `TODO(claude-code-subagent-replay)` / `TODO(codex-subagent-replay)` — the same distinct replay shape the ACP backend deferred ([the per-session replay RFC](../../implemented/testing/2026-06-22-subagent-snapshot-replay.md)); the keyless suites carry deterministic coverage meanwhile. ## Alternatives considered 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 d94ce11f5c..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,40 +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 and 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. They diverge for config-created agents, resumed sessions, and in-process children, but no production path reattaches one live agent to several sessions or drives one session through several agent ids. Stdio keeps `labelBySession` only to recover an agent label from session events, and hooks expose both values for authors to reconcile. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no identity-specific reservation state: create and resume use one `AgentCreationTransaction`, and both registry entries use the same final-entry collision rule. Separate ids do not duplicate liveness, rollback, or quiescence machinery. Unification deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle; it also makes the live-agent registry enforce the session identity used by background-task ownership. - -`Session` separately exposes `Session.id` and `Session.header.id` even though construction requires them to match. The durable boundary must validate the duplicate, and consumers must choose between two homes for one fact. - -## Proposal - -Use one id for the agent registry entry and `session.header.id`. `CreateAgentOptions` accepts one identity for both final entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; and `Session` keeps one identity home. Preserve the current transaction, final-entry collision checks, exact-entry detach, rollback, and quiescence; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path must first settle its resume-or-create policy. Today it uses a stable agent label and a fresh UUID-suffixed session id to avoid colliding with an existing durable log on the next run. Under unification it must deliberately resume a fixed id, mint a fresh combined id, or expose that policy; implementation must not choose silently. - -`agent/created` and `agent/disposed` remain outside this proposal. They are publication lifecycle events rather than identity aliases; removing them requires a separate production-consumer audit and decision. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured agent label paired with a fresh conversation is a real use of the distinction. If that display or routing identity is required, reject this proposal and enforce session-id uniqueness explicitly instead of hiding the translation in another map. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence guarantees without 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` and `agent/disposed` change only after a separate production-consumer audit. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -Unification forecloses a stable actor identity spanning several session logs, including a future handoff or fork that preserves the actor while changing the session. Reintroducing that design would require a new explicit actor identity. It also makes a persisted, possibly client-chosen session id the registry handle and changes every create/resume call site and fixture. - -The config restart policy is the blocking design decision: a fixed combined id may collide with its existing log, while a per-run id gives up the stable configured label. If either independent actor identity or the stable-label/fresh-session pairing is required, reject this proposal and retain the separate ids with an explicit uniqueness guard. diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index b6b55048e4..a49f771a7f 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -8,7 +8,8 @@ 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' @@ -87,7 +88,7 @@ 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -136,7 +137,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p await writeFile(join(workdir, 'pkg/deep/task.txt'), 'Touch this file to discover the nested instructions.\n') ctx = await workspaceCodeModeHarness() const handle = await ctx.agents.create({ - agentId: AgentId('e2e-code-mode-workspace'), sessionId: SessionId('e2e-code-mode-workspace-session'), meta: { cwd: workdir }, agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, diff --git a/examples/coding-agent/tests/coding-task.e2e.ts b/examples/coding-agent/tests/coding-task.e2e.ts index d53688835e..a5f525e5c3 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-task'), { provider: 'deepseek', 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 6ba2908ad3..d992fc9efa 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' /** * Key-gated smoke for mid-session compaction. It verifies the compact event @@ -46,7 +46,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa }, persistenceRoot: join(workdir, '.sessions'), }) - const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', 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 7314b7ab21..db2eec63fc 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { provider: 'deepseek', 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 c9081c659f..65c7d13b78 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: { provider: 'deepseek', 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: { provider: 'deepseek', 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 a16f15528d..daf5c018b1 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek', 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 68fe88038b..f12f85b6ca 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { provider: 'deepseek', 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -113,7 +113,7 @@ 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { provider: 'deepseek', 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 1f9055c67a..5cd314240f 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -5,7 +5,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import TaskService from '@deepseek-ai/dsh-tasks' @@ -100,7 +99,6 @@ describe('bash tool through the agent loop', () => { ]) const ctx = await harness(adapter, root, dshHome) const handle = await ctx.agents.create({ - agentId: AgentId('session-env'), sessionId: SessionId('session-env-id'), agentOptions: { provider: 'mock', model: 'mock' }, }) @@ -125,7 +123,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-fg'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) @@ -157,7 +155,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-exit'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) @@ -177,7 +175,7 @@ describe('bash tool through the agent loop', () => { textResponse('Background task finished.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-bg'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-bg'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run echo bg-ok in the background' }]) await waitForIdle(ctx, agent) diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index c19846ab13..af0cdcaa1c 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -10,7 +10,7 @@ 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 SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import TaskService from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' @@ -50,18 +50,17 @@ async function setupWithTasks() { } /** - * Build a fake {@link Agent} whose session token is `sessionId`, give it a + * Build a fake {@link Agent} with the shared agent/session identity, give it a * dedicated lifecycle fiber for `Agent.ctx`, and register it in `ctx.agents`. - * The agent id is deliberately different from the session token so a - * wrong-field ownership match fails the test. */ function registerFakeAgent(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 ctx.agents.register(agent) return agent @@ -183,11 +182,13 @@ async function setupSandboxed(withApproval = false) { function sandboxAgent(mode?: 'read-only' | 'workspace-write' | 'danger-full-access', ctx?: Context): Agent { const events: Array<{ type: string; data?: Record }> = [{ type: 'turn/start' }] if (mode !== undefined) events.push({ type: 'bash/sandbox-mode', data: { mode } }) + const id = SessionId('sandbox-session') return { - id: 'sandbox-agent', + id, ...ctx === undefined ? {} : { ctx: ctx.plugin(() => {}).ctx }, session: { - header: { version: 0, id: 'sandbox-session', createdAt: 0 }, + id, + header: { version: 0, id, createdAt: 0 }, events, append: (type: string, data: Record) => { const event = { type, data } 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 d163d84804..757bc107db 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -4,13 +4,12 @@ import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-a import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import TokenMeterService from '@deepseek-ai/dsh-token-meter' -import type { SurfaceEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type SurfaceEvent } from '@deepseek-ai/dsh-session' /** * CBR-001 regression through the real loop. A replacement checkpoint has a high @@ -98,7 +97,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('repro'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'do a long multi-step task' }]) await waitForIdle(ctx, agent) diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 2796e8230c..f2c6afe586 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -4,7 +4,7 @@ import Loader from '@cordisjs/plugin-loader' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { defineTool } from '@deepseek-ai/dsh-tools' import AgentLoop from '@deepseek-ai/dsh-agent-loop' @@ -38,7 +38,7 @@ async function mount(config: Config = {}) { function sessionAgent(session: Session, id = 'agent'): Agent { return { - id: AgentId(id), + id: SessionId(id), options: {}, session, status: 'running', @@ -370,7 +370,7 @@ describe('real agent-loop request history', () => { if (mode === 'throws') throw new Error('later pre-step failure') subject.cancel('later pre-step cancellation') }) - const agent = ctx.agentLoop.create(AgentId(`late-${mode}`), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId(`late-${mode}`), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'start' }]) await agent.whenIdle() @@ -396,7 +396,7 @@ describe('real agent-loop request history', () => { return [{ type: 'text' as const, text: 'advanced' }] }, })) - const agent = ctx.agentLoop.create(AgentId('loop'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('loop'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'start' }]) await agent.whenIdle() diff --git a/packages/context/workspace-context/tests/workspace-context.e2e.ts b/packages/context/workspace-context/tests/workspace-context.e2e.ts index eab9603fa5..0c11da8ed4 100644 --- a/packages/context/workspace-context/tests/workspace-context.e2e.ts +++ b/packages/context/workspace-context/tests/workspace-context.e2e.ts @@ -7,7 +7,7 @@ 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 type { Agent } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -46,7 +46,6 @@ async function harness(): Promise<{ ctx: Context; agent: Agent }> { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: [{ id: 'deepseek-v4-flash' }] }) const handle = await ctx.agents.create({ - agentId: AgentId('workspace-context-e2e'), sessionId: SessionId('workspace-context-e2e-session'), meta: { cwd: workdir }, agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, diff --git a/packages/context/workspace-context/tests/workspace-context.spec.ts b/packages/context/workspace-context/tests/workspace-context.spec.ts index 2894937c9c..2ff2067cf5 100644 --- a/packages/context/workspace-context/tests/workspace-context.spec.ts +++ b/packages/context/workspace-context/tests/workspace-context.spec.ts @@ -7,7 +7,7 @@ import Loader from '@cordisjs/plugin-loader' import * as workspaceContext from '@deepseek-ai/dsh-workspace-context' import LlmService, { CallId, type Message, type StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, SESSION_FORMAT_VERSION, type SessionEvent } from '@deepseek-ai/dsh-session' -import AgentRegistry, { AgentId, type Agent, type HookContext } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type HookContext } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { FileSystem, FsTargetKey, FsVersion } from '@deepseek-ai/dsh-fs' import type { @@ -163,7 +163,7 @@ function stubAgent(cwd?: string, seed: SessionEvent[] = []): Agent { const session = new Session(id, seed, cwd === undefined ? undefined : { version: SESSION_FORMAT_VERSION, id, createdAt: 0, cwd }) return { ctx: new Context(), - id: AgentId('a1'), + id: SessionId('a1'), options: {}, session, status: 'idle', @@ -1591,7 +1591,7 @@ describe('dynamic nested workspace context injection', () => { await ctx.plugin(workspaceContext, { dshHome: home, maxBytes: 65536 }) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('workspace-context-abort'), { provider: 'mock', model: 'mock' }, { cwd: root }) + const agent = ctx.agentLoop.create(SessionId('workspace-context-abort'), { provider: 'mock', model: 'mock' }, { cwd: root }) ctx.tools.register(defineTool({ name: 'abort_step', description: 'Abort the current test step.', diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 96fe378def..70ecd95cba 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', ], @@ -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: AgentId): Agent | undefined', + 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { @@ -293,6 +294,12 @@ 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', @@ -533,7 +540,7 @@ 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?: InjectOptions): 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?: InjectOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', }, { name: 'AgentFactory', @@ -543,10 +550,6 @@ 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 provider?: string;\n model?: string;\n}', @@ -701,7 +704,7 @@ 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', @@ -853,7 +856,7 @@ 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', @@ -1025,7 +1028,7 @@ 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 9823e119b5..d00f75a0d2 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as ToolCordis from '../src/index.ts' @@ -44,7 +44,7 @@ describe('cordis tools through the agent loop', () => { textResponse('Done.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-cordis'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-cordis'), { provider: 'mock', 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-loop/README.md b/packages/core/agent-loop/README.md index cdbf2e49a2..2ad0274fa4 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -1,6 +1,6 @@ # dsh-agent-loop -Concrete `ReactLoopAgent` implementation and loop driver. +THE concrete agent plugin: `ReactLoopAgent` and the loop driver. Implements the `Agent` interface and drives the session/turn/step lifecycle. This is the only package in the harness that contains concrete loop logic. Everything else is an abstract service or a plugin against extension seams — new behavior goes into plugins, not here. @@ -8,16 +8,18 @@ This is the only package in the harness that contains concrete loop logic. Every ### Public API -Creation and resume use one caller-owned transaction: compose while unpublished, enter both registries, announce lifecycle edges, then start the driver. Failure rolls back private resources; caller, handle, and provider teardown share one quiescence boundary. The interface contract and ownership order live in [`dsh-agent`](../agent/README.md) and the [agent-scope runtime RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md). +Creation and resume are one rollback-covered transaction: construct a private session, concrete agent, and scoped context; await optional setup; enter both registries; announce `session/created` then `agent/created`; emit `agent/session-start`; and only then start the driver. Setup receives the full scoped `Context` as trusted same-process composition code and must not drive the unpublished agent. Ordinary typed identity and option inputs are borrowed under their readonly contract, while seed events and session metadata are validated and snapshotted because they cross the durable session boundary. An optional `AbortSignal` cancels only load/setup/publication and is detached before the returned handle becomes visible. -Caller-chosen ids arbitrate only at final registry entry, so concurrent contenders may prepare but every loser rolls back. Entry-bound detach capabilities cannot remove a later same-id replacement. Teardown stops and drains—including idle-injection flushes—before detaching agent, session, and scope; ids become reusable at detach. +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. -- `ctx.agentLoop.create(id, options?, meta?)` synchronously creates a caller-fiber-owned agent with a fresh generated session id and optional cwd. Each call starts a new session rather than applying resume-or-create policy. +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 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): -- `ctx.agents.create({ agentId, sessionId, meta?, seed?, agentOptions?, setup?, signal? })` validates and snapshots durable seed and metadata, awaits optional composition while unpublished, creates on the supplied session id, and returns an owned [`AgentHandle`](../agent/README.md). Its signal applies only until publication. -- `ctx.agents.resume({ agentId, resumeSessionId, agentOptions?, setup?, signal? })` loads through optional [session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md), continues stored history and turn numbering under the resumed session id, and follows the same unpublished setup and creation-only cancellation boundary. It rejects when no persistence backend is mounted. +- `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. @@ -50,7 +52,7 @@ Configured agents start automatically. A model call requires both `provider` and ### Loop lifecycle (`loop.ts`) -The driver owns one agent for its lifetime. It records turn, step, request, stream, and tool boundaries in the session log; live extension events coordinate policy around those durable facts. The [architecture turn flow](../../../docs/architecture.md#turn-flow) and generated [event catalog](../../../docs/cordis-catalog/events.md) are the authoritative sequence and signatures. +The internal loop driver runs one agent for its whole lifetime: Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history. @@ -85,6 +87,6 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p ## Known Limitations and Deferred Work - **Classification is unary** — calls whose safety depends on comparing siblings or resources must remain exclusive ([rationale](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)). -- **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. diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index c8784453b9..d93832b361 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, HookContext, InjectOptions, SendOptions } from '@deepseek-ai/dsh-agent' +import type { AgentOptions, AgentStatus, HookContext, InjectOptions, 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' @@ -58,7 +58,11 @@ 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, maxParallelToolCalls: number, + ctx: Context, + id: SessionId, + options: AgentOptions, + session: Session, + maxParallelToolCalls: number, ): PreparedReactLoopAgent { if (claimedDriverSessions.has(session)) { throw new Error(`session "${session.id}" already has a concrete agent driver`) @@ -159,7 +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, maxParallelToolCalls: number, diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 5f5b9a9eb6..a816127fa3 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, @@ -43,10 +42,21 @@ 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 + private readonly inactive = Promise.withResolvers() private transactions = new Set() + private startupTasks = new Set>() constructor(private readonly fiber: Context['fiber']) {} @@ -59,17 +69,31 @@ 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) + } + + /** 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)), - ) + await Promise.all([ + ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), + ...this.startupTasks, + ]) } } /** 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 }) } @@ -115,7 +139,7 @@ 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() @@ -237,7 +261,7 @@ 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() @@ -326,6 +350,18 @@ 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. 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 + */ + 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void + } } export { DEFAULT_MAX_PARALLEL_TOOL_CALLS } @@ -339,8 +375,10 @@ export interface Config { maxParallelToolCalls?: number /** 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 stable identity; remounts resume its materialized history, while first use creates it fresh. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -348,6 +386,24 @@ 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 "${exactIdentity}"`) + } + exactIdentities.set(exactIdentity, id) + } +} + /** Concrete ReactLoopAgent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] @@ -357,6 +413,7 @@ export class AgentLoop extends Service implements AgentFactory { maxParallelToolCalls: z.number().step(1).min(1).default(DEFAULT_MAX_PARALLEL_TOOL_CALLS), agents: z.array(z.object({ id: z.string().required(), + sessionId: z.string().min(1), provider: z.string(), model: z.string(), cwd: z.string(), @@ -372,6 +429,7 @@ export class AgentLoop extends Service implements AgentFactory { constructor(ctx: Context, public config: Config) { super(ctx, 'agentLoop') + validateConfiguredAgents(config.agents) this.maxParallelToolCalls = resolveMaxParallelToolCalls(config.maxParallelToolCalls) this.ownership = new FactoryOwnership(ctx.fiber) this.runtime = { ctx } @@ -381,19 +439,28 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('model', context => context.agent?.options.model) ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) - for (const { id, cwd, resumeSessionId, ...options } of config.agents) { + for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { + const meta = cwd === undefined ? {} : { cwd } if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(id, options, cwd === undefined ? {} : { cwd }) + const configuredId = sessionId ?? SessionId(`${id}-session-${randomUUID()}`) + const persistence = sessionId === undefined ? undefined : ctx.get('sessionPersistence') + if (persistence === undefined) { + this.create(configuredId, options, meta) + } else { + const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + this.reportConfiguredStartupFailure(id, 'restore', configuredId, error) + }) + this.ownership.trackStartup(startup) + } continue } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { - agentId: id, resumeSessionId, agentOptions: options, }).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven resume of "${resumeSessionId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'resume', resumeSessionId, error) }) }) return fiber.dispose @@ -401,20 +468,83 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Report a contained declarative-start failure to identity-bound consumers. */ + private reportConfiguredStartupFailure( + configId: string, + action: 'restore' | 'resume', + sessionId: SessionId, + error: unknown, + ): void { + if (!this.ownership.isActive()) return + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) + const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] + for (const callback of this.ctx.events.dispatch('emit', args)) { + try { + const returned: unknown = callback(...args) + void Promise.resolve(returned).catch((listenerError: unknown) => { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${renderThrown(listenerError)}`) + }) + } catch (listenerError: unknown) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${renderThrown(listenerError)}`) + } + } + } + + /** 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 { + 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) { + await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) + return + } + 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', checkReleased) + const disposeSessionListener = ownerCtx.on('session/disposed', checkReleased) + try { + checkReleased() + await this.ownership.waitWhileActive(released.promise) + } finally { + disposeAgentListener() + disposeSessionListener() + } + } + /** - * 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, this.maxParallelToolCalls) transaction.publish('startup') return agent @@ -438,7 +568,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.sessionId, options.signal, ) try { @@ -483,7 +613,7 @@ 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 8c2a550b12..e5a6f3750a 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' @@ -54,12 +53,12 @@ describe('ReactLoopAgent', () => { await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) const prepared = prepareReactLoopAgent( - ctx, AgentId('first-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ctx, SessionId('first-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, ) expect(() => prepared.agent.ctx).toThrow('context is not bound') expect(() => prepareReactLoopAgent( - ctx, AgentId('second-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ctx, SessionId('second-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, )) .toThrow('already has a concrete agent driver') @@ -70,11 +69,11 @@ describe('ReactLoopAgent', () => { it('borrows caller options and binds its scoped context exactly once', async () => { const ctx = await harness(new MockAdapter([textResponse('unused')])) const options = { provider: 'mock', 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() @@ -85,7 +84,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -100,7 +99,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -115,7 +114,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -128,7 +127,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 @@ -154,7 +153,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // inject() is synchronous and fires a fire-and-forget flush; a rejecting // flush must be contained (logged), never thrown into the caller. @@ -167,7 +166,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) @@ -185,7 +184,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) // Session contains a throwing post-commit turn/end observer. The accepted @@ -208,7 +207,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 })) @@ -227,7 +226,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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. @@ -242,7 +241,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // steer while idle delegates to send agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } }) @@ -259,7 +258,7 @@ describe('ReactLoopAgent', () => { await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) const prepared = prepareReactLoopAgent( - ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ctx, SessionId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, ) const { agent } = prepared @@ -279,7 +278,7 @@ describe('ReactLoopAgent', () => { await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('pre-start-dispose')) const prepared = prepareReactLoopAgent( - ctx, AgentId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ctx, SessionId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, ) await prepared.dispose() @@ -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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' }) // Drive `agent` into `running`, then await whenIdle() — it subscribes to // agent/status and resolves on the first transition out of running. @@ -378,7 +377,7 @@ describe('ReactLoopAgent', () => { ctx.llm.registerAdapter(['mock'], adapter) const session = ctx.sessions.create(SessionId('bare')) const prepared = prepareReactLoopAgent( - ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ctx, SessionId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, ) const { agent } = prepared prepared.markPublished() @@ -401,7 +400,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -420,7 +419,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -441,7 +440,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'running') throw new Error('bad running listener') }) @@ -459,7 +458,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 fc6055a00c..f84dcbc688 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -13,7 +13,8 @@ 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' @@ -54,7 +55,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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. @@ -71,7 +72,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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. @@ -90,7 +91,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // This waiter cannot rely on a running→idle transition because cancellation // drops the turn before it runs; the skip path must settle it directly. @@ -109,7 +110,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -126,7 +127,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -142,7 +143,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // First turn hangs; cancel it mid-step. send(agent, 'first') @@ -164,7 +165,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 @@ -198,7 +199,6 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -227,7 +227,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // The interrupted first composition must not cache its degraded empty value; // the next prompt recomposes and logs/sends the fresh prefix. @@ -257,7 +257,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // A turn/start listener fires before a step controller exists, so the // turn-scoped marker—not step abort—must drop the pending step. @@ -284,7 +284,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 @@ -323,7 +323,6 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -355,7 +354,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 const reasons: TurnEndReason[] = [] @@ -387,7 +386,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // `agent/status` is synchronous, so cancellation can land after the first // pre-step check; the second check must drop the now-empty turn. @@ -411,7 +410,7 @@ describe('Agent.cancel()', () => { // Cancellation must not settle idle while replacement work remains queued. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let replaced = false const dispose = ctx.on('agent/status', (subject, status) => { @@ -438,7 +437,7 @@ describe('Agent.cancel()', () => { // prompt B is queued before the loop resumes from the idle wait. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -457,7 +456,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 86db33a8ca..8713630820 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' @@ -23,7 +24,281 @@ 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('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, { + 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('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) + 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('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('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) + const ctx = await makeCoreContext() + 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 }) + }) + 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(failures).toEqual([{ sessionId: SessionId('stdio-exact-failure'), error: failure }]) + 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() + }) + + 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.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) + + 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() await ctx.plugin(LlmService) @@ -32,7 +307,7 @@ describe('config-driven session id', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) const loopFiber = await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }], + agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }], }) const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)') @@ -53,11 +328,13 @@ 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'), provider: 'mock', model: 'mock' }] }) + await ctx1.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', 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 +347,11 @@ 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'), provider: 'mock', model: 'mock' }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', 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 +374,7 @@ 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() @@ -109,7 +387,7 @@ 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'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -117,11 +395,12 @@ 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') @@ -137,16 +416,16 @@ 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'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) + await ctx.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', 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/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 12460039b1..fc839c934d 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -4,7 +4,7 @@ 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, type PostToolDecision } 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, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -55,7 +55,7 @@ describe('session log records what agent/step-result actually produced', () => { return [{ type: 'text', text: 'ran' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // Plugin rewrites the message: replaces the text AND adds a tool call. let rewritten = false @@ -97,7 +97,7 @@ describe('session log records what agent/step-result actually produced', () => { response[response.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState } const adapter = new MockAdapter([response]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('replay-state'), { provider: 'mock', model: 'next-model' }) + const agent = ctx.agentLoop.create(SessionId('replay-state'), { provider: 'mock', model: 'next-model' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -121,7 +121,7 @@ describe('session log records what agent/step-result actually produced', () => { if (block?.type === 'text') block.text = 'mutated' return message }) - const agent = ctx.agentLoop.create(AgentId('mutated-replay-state'), { provider: 'mock', model: 'next-model' }) + const agent = ctx.agentLoop.create(SessionId('mutated-replay-state'), { provider: 'mock', model: 'next-model' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -141,7 +141,7 @@ describe('successful provider completion survives agent/step-result failure', () const adapter = new MockAdapter([response]) const ctx = await harness(adapter) await ctx.plugin(Invariants) - const agent = ctx.agentLoop.create(AgentId(id), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId(id), { provider: 'mock', model: 'mock' }) const failure = new Error(`${id} result processing failed`) const reported: Error[] = [] @@ -214,7 +214,7 @@ describe('abort during tool execution ends the turn', () => { ]) const ctx = await harness(adapter) const executed: string[] = [] - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -253,7 +253,7 @@ describe('abort during tool execution ends the turn', () => { it('records context accepted before a tool-step abort in the same turn', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'aborter', {})]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-abort-injection'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-abort-injection'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -299,7 +299,7 @@ describe('abort during tool execution ends the turn', () => { { type: 'finish', reason: { kind: 'tool-calls' } }, ] satisfies StreamChunk[]]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-later-abort-context'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-later-abort-context'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'first', description: '', @@ -347,7 +347,7 @@ describe('abort during tool execution ends the turn', () => { const started = Promise.withResolvers() let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-injection'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-injection'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) ctx.tools.register(defineTool({ name: 'waiter', @@ -400,7 +400,7 @@ describe('abort during tool execution ends the turn', () => { textResponse('later turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-historical-tool-pair'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-historical-tool-pair'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -442,7 +442,7 @@ describe('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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let steeredOnce = false ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => { @@ -468,7 +468,7 @@ describe('steering from late extension points is never stranded', () => { textResponse('after goal reminder'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let steeredOnce = false ctx.on('session/event', (subject, event) => { @@ -496,7 +496,7 @@ describe('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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const turns: number[] = [] let steeredOnce = false @@ -522,7 +522,7 @@ describe('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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -545,7 +545,7 @@ describe('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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('agent/turn-continuation', async (): Promise => { @@ -573,7 +573,7 @@ describe('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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let rejectedOnce = false ctx.on('session/flush', async () => { @@ -603,7 +603,7 @@ describe('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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const statuses: string[] = [] @@ -626,7 +626,7 @@ describe('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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) ctx.on('agent/status', (_agent, status) => { @@ -639,7 +639,7 @@ describe('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 }) }) @@ -658,7 +658,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { 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)) @@ -673,7 +673,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { 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, provider: 'mock', model: 'mock' } @@ -688,7 +688,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'noop', description: '', @@ -716,7 +716,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-send'), { provider: 'mock', model: 'mock' }) const content = [{ type: 'text' as const, text: 'accepted-send' }] const source = { kind: 'plugin' as const, plugin: 'accepted-source' } let notifiedContent: ContentBlock[] | undefined @@ -752,7 +752,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-steer'), { provider: 'mock', model: 'mock' }) const entered = Promise.withResolvers() const release = Promise.withResolvers() ctx.tools.register(defineTool({ @@ -806,7 +806,7 @@ describe('turn numbering continues across seeded 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -823,7 +823,7 @@ describe('turn numbering continues across seeded sessions', () => { const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] }) const prepared = prepareReactLoopAgent( - ctx2, AgentId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ctx2, SessionId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded, DEFAULT_MAX_PARALLEL_TOOL_CALLS, ) const forked = prepared.agent prepared.markPublished() @@ -868,7 +868,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', () ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -893,7 +893,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', () ] const adapter = new MockAdapter([abortedStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-aborted'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -911,7 +911,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', () ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error-nocode'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -927,7 +927,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-step-order'), { provider: 'mock', model: 'mock' }) // Append commits before observers run. const observed: { turn: number; step: number; lastEventType: string | undefined; sawStepStart: boolean }[] = [] @@ -982,7 +982,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart'), { provider: 'mock', model: 'mock' }) // Session owns post-commit containment. The loop sees a successful append, // runs the request, and balances the ordinary step and turn boundaries. @@ -1011,7 +1011,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -1042,7 +1042,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnend-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -1076,7 +1076,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -1108,7 +1108,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-errorlistener'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } }) @@ -1141,7 +1141,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1168,7 +1168,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) let threw = false @@ -1199,7 +1199,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-preturn'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_session, event) => { @@ -1230,7 +1230,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-throw'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1269,7 +1269,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stependthrow'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1299,7 +1299,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnendappend'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1345,7 +1345,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-callid'), { provider: 'mock', model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -1376,7 +1376,7 @@ describe('surface: assistant/message records exact empty provenance when no chun const adapter = new MockAdapter([[]]) const ctx = await harness(adapter) await ctx.plugin(Invariants) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({ role: 'assistant' as const, @@ -1423,7 +1423,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1473,7 +1473,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1527,7 +1527,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1578,7 +1578,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1628,7 +1628,7 @@ 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index ddbac2716d..2453b3125b 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -240,7 +241,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 9932d9ca25..b3218f0f46 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 additionalContexts injects separate context/message events into the turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const meta = { kind: 'prompt-context', version: 1 } ctx.on('agent/prompt-submit', async (): Promise => @@ -129,7 +125,7 @@ describe('agent/prompt-submit', () => { // compaction listener measures the current surface before the single derive. const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -159,7 +155,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'block', reason: 'blocked by policy' })) @@ -195,7 +191,7 @@ describe('agent/prompt-submit', () => { // the allowed prompt keeps the turn from ending rejected. const adapter = new MockAdapter([textResponse('ran once')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise => { const text = content.map(b => (b.type === 'text' ? b.text : '')).join('') @@ -231,7 +227,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('agent/prompt-submit', async () => { @@ -264,7 +260,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // fires synchronously at create, before any turn expect(sources).toEqual(['startup']) expect(events(agent).some(e => e.type === 'turn/start')).toBe(false) @@ -283,7 +279,7 @@ describe('agent/session-start', () => { agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } }) }) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -301,8 +297,8 @@ 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'), { provider: 'mock', model: 'mock' }) - expect(agent.id).toBe(AgentId('a1')) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + expect(agent.id).toBe(SessionId('a1')) // and the agent still runs send(agent, 'go') @@ -315,8 +311,8 @@ 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'), { provider: 'mock', model: 'mock' }) - const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { provider: 'mock', model: 'mock' }) + const agentA = ctx.agentLoop.create(SessionId('prefix-a'), { provider: 'mock', model: 'mock' }) + const agentB = ctx.agentLoop.create(SessionId('prefix-b'), { provider: 'mock', model: 'mock' }) const seen: string[] = [] ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => { seen.push(`global:${agent.id}`) @@ -353,7 +349,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'catalog' }] } let composed = 0 @@ -386,7 +382,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] } const order: string[] = [] @@ -413,7 +409,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // Both listeners use the canonical `[mine, ...await next()]` prepend: the // waterfall unwinds innermost-first (the second listener's array is built @@ -435,7 +431,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // A listener that delegates without contributing — the canonical no-op. ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next()) @@ -451,7 +447,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let mutationError: unknown ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise => { @@ -480,7 +476,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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]) @@ -501,7 +497,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/turn-continuation', async (): Promise => ({ action: 'stop' })) @@ -563,7 +559,7 @@ describe('tool additionalContexts buffering across a step', () => { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // Each call attaches one context naming itself. ctx.on('tools/post-execute', async (exec, _result): Promise => @@ -611,7 +607,7 @@ describe('tool additionalContexts buffering across a step', () => { return [{ type: 'text', text: 'outer result' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -638,7 +634,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('tools/pre-execute', async (exec, next): Promise => { if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' } @@ -700,7 +696,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'please echo hi') await waitForIdle(ctx, agent) @@ -723,7 +719,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -742,7 +738,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a3'), { provider: 'mock', 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 6f4f15ba0c..87cb8cd9b1 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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: { provider: 'mock', model: 'mock' }, @@ -188,7 +188,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -230,7 +230,7 @@ describe('agent loop', () => { ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, provider: 'mock', 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) @@ -256,7 +256,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-meta-agent'), { provider: 'mock', model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -285,7 +285,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-no-system'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -297,7 +297,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -321,7 +321,7 @@ describe('agent loop', () => { ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'slow', description: '', @@ -353,7 +353,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.steer([{ type: 'text', text: 'hello' }]) await waitForIdle(ctx, agent) @@ -363,7 +363,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 @@ -387,7 +387,7 @@ describe('agent loop', () => { it('inject() can persist raw structured context without the generic context envelope', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('raw-context'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('raw-context'), { provider: 'mock', model: 'mock' }) const text = 'Additional instructions from: pkg/AGENTS.md' const meta = { kind: 'workspace-instructions', @@ -416,7 +416,7 @@ describe('agent loop', () => { textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let visibleDuringTool = false const meta = { kind: 'deferred-test', version: 1 } ctx.tools.register(defineTool({ @@ -482,7 +482,7 @@ describe('agent loop', () => { textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('invalid-context'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('invalid-context'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'invalid-injector', description: 'attempts an invalid context injection', @@ -512,7 +512,7 @@ describe('agent loop', () => { textResponse('step 3'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -538,7 +538,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const) @@ -553,7 +553,7 @@ describe('agent loop', () => { it('agent/request waterfall switches models by returning a replacement config; the switch is logged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 @@ -586,7 +586,7 @@ describe('agent loop', () => { name: 'echo', description: 'echo', parameters: {}, async execute() { return [{ type: 'text', text: 'echoed' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { @@ -610,7 +610,7 @@ describe('agent loop', () => { // same step's request must include it. const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let injected = false ctx.on('agent/pre-step', (subject) => { @@ -644,7 +644,7 @@ describe('agent loop', () => { // closing, the turn records error, and the loop remains available. const adapter = new MockAdapter([textResponse('second turn ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let throwOnce = true ctx.on('agent/pre-step', () => { @@ -678,7 +678,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -698,7 +698,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -721,7 +721,7 @@ describe('agent loop', () => { textResponse('second half'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -752,7 +752,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -785,7 +785,7 @@ describe('agent loop', () => { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -822,7 +822,7 @@ describe('agent loop', () => { parameters: { text: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -847,7 +847,7 @@ describe('agent loop', () => { // a durable successful-call boundary for replay consumers. const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -884,7 +884,7 @@ describe('agent loop', () => { expect(message.content).toEqual([{ type: 'text', text: 'partial text' }]) return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -911,7 +911,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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. @@ -930,7 +930,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const turns: number[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) }) @@ -955,7 +955,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let flushed = 0 let flushedBeforeIdle = false @@ -975,7 +975,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const errors: Error[] = [] const reasons: TurnEndReason[] = [] @@ -1000,10 +1000,10 @@ describe('agent loop', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', 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') @@ -1012,7 +1012,7 @@ 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') }) @@ -1025,13 +1025,14 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), provider: 'mock', model: 'mock' }], + agents: [{ id: SessionId('config-agent'), provider: 'mock', 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 @@ -1048,10 +1049,10 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), provider: 'mock', model: 'mock', cwd: '/work/project' }], + agents: [{ id: SessionId('config-agent'), provider: 'mock', 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') }) @@ -1069,7 +1070,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 6e502187a6..b61c4d7fd5 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -1,7 +1,12 @@ /** - * Deterministic property tests for inbox scheduling: every sent message logs - * once, turn numbers increase, and status follows idle→running→idle/disposed. - * Schedules advance on status events rather than wall-clock sleeps. + * Property-based tests for the agent loop's inbox/turn scheduling (the + * property-testing RFC). Deterministic by construction: schedules are driven + * through the `agent/status` settle signal (no wall-clock sleeps), so a flake + * is a finding, not timing noise. + * + * Invariants: every sent message appears exactly once in the log (none lost); + * turn numbers strictly increase; status transitions follow the legal machine + * idle→running→idle (and →disposed at teardown). */ import { describe, expect, it } from 'vitest' @@ -9,10 +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' @@ -90,7 +96,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', 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. @@ -115,7 +121,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' }) for (const text of texts) { const idle = nextIdle(ctx, agent) agent.send([{ type: 'text', text }]) @@ -140,7 +146,7 @@ describe('agent loop scheduling properties', () => { async (steps) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' }) // Capture before each send; the last waiter covers the final turn, and // awaiting an already-settled earlier waiter is harmless. let lastIdle: Promise | undefined diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 72c2c577ab..9fc832fd0a 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' @@ -69,7 +70,7 @@ 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { provider: 'deepseek', 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 ab2c18c99d..e9f89d4715 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -12,7 +12,8 @@ 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' @@ -71,7 +72,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -92,7 +93,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -106,7 +107,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -139,7 +140,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -163,7 +164,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let injected = false ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { @@ -191,7 +192,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -212,7 +213,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('gen1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -221,7 +222,6 @@ 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: { provider: 'mock', model: 'mock' }, @@ -241,7 +241,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { const config = await next() @@ -275,7 +275,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 aa131009c6..6777852f1f 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: { provider: 'mock', 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: { provider: 'mock', 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: { provider: 'mock', 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: { provider: 'mock', 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: { provider: 'mock', 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: { provider: 'mock', model: 'mock' } }) + resuming = inner.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', 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: { provider: 'mock', model: 'mock' } })) + const retry = await promptly(ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', 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: { provider: 'mock', model: 'mock' } }) + const resuming = ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', 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) @@ -464,7 +455,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // clean disposal follows, so disk presence proves its own checkpoint ran. 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' } }) @@ -487,7 +478,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // survive persistence and resume. 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' } }) @@ -505,7 +496,7 @@ 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() @@ -515,7 +506,7 @@ 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] @@ -535,7 +526,7 @@ 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) @@ -563,7 +554,7 @@ 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/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 472cb8cd8a..2325da5717 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 +131,45 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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('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({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } }) const { agent } = handle agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' }) agent.ctx.tools.register({ @@ -179,8 +194,8 @@ 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'), { provider: 'mock', model: 'mock' }) - const b = ctx.agentLoop.create(AgentId('b'), { provider: 'mock', model: 'mock' }) + const a = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' }) + const b = ctx.agentLoop.create(SessionId('b'), { provider: 'mock', model: 'mock' }) const heard: string[] = [] a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`)) @@ -210,7 +225,6 @@ describe('agent scope lifecycle', () => { }) const handle = await ctx.agents.create({ - agentId: AgentId('child'), sessionId: SessionId('child-s'), agentOptions: { provider: 'mock', model: 'mock' }, setup: async (agentCtx) => { @@ -224,14 +238,14 @@ 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 +253,10 @@ describe('agent scope lifecycle', () => { const acceptedOptions = { provider: 'mock', 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') @@ -253,8 +266,8 @@ describe('agent scope lifecycle', () => { }, }) await setupStarted.promise - expect(ctx.agents.get(AgentId('atomic'))).toBeUndefined() - expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() + expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() + expect(ctx.sessions.get(SessionId('atomic'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) const handle = await creating @@ -281,16 +294,14 @@ 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: { provider: 'mock', model: 'mock' }, setup, }) const second = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-b'), + sessionId, agentOptions: { provider: 'mock', model: 'mock' }, setup, }) @@ -304,7 +315,7 @@ 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 +329,6 @@ 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: { provider: 'mock', model: 'mock' }, signal: pendingController.signal, @@ -330,12 +340,11 @@ 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: { provider: 'mock', model: 'mock' }, signal: liveController.signal, @@ -358,7 +367,6 @@ 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: { provider: 'mock', model: 'mock' }, setup: async () => { @@ -372,7 +380,7 @@ 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 +394,6 @@ 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: { provider: 'mock', model: 'mock' }, setup: async () => { @@ -400,7 +407,7 @@ 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 +420,6 @@ 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: { provider: 'mock', model: 'mock' }, setup: async () => { @@ -426,7 +432,7 @@ 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 +450,6 @@ describe('agent scope lifecycle', () => { }) const creating = ctx.agents.create({ - agentId: AgentId('factory-scope-race'), sessionId: SessionId('factory-scope-race-s'), agentOptions: { provider: 'mock', model: 'mock' }, setup: () => { setupCalls += 1 }, @@ -452,7 +457,7 @@ 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 +484,6 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -495,7 +499,7 @@ 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 +515,17 @@ describe('agent scope lifecycle', () => { void loopFiber.dispose() }) - expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { provider: 'mock', model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-scope-race'), { provider: 'mock', 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, { provider: 'mock', model: 'mock' }, { cwd: 'relative' })) .toThrow(/absolute path/) @@ -542,12 +546,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('factory-scope-throw'), sessionId: SessionId('factory-scope-throw-s'), agentOptions: { provider: 'mock', 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 +559,21 @@ 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'), agentOptions: { provider: 'mock', 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 +584,6 @@ 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: { provider: 'mock', model: 'mock' }, setup: (agentCtx) => { @@ -623,7 +623,7 @@ 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 +638,6 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -652,7 +651,7 @@ 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 +665,19 @@ 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 +686,6 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -703,7 +701,7 @@ 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 +713,12 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -730,7 +727,7 @@ 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 +741,15 @@ 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 +759,6 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -775,7 +771,7 @@ 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 +783,6 @@ 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: { provider: 'mock', model: 'mock' }, setup: async () => { @@ -798,13 +793,13 @@ 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: { provider: 'mock', model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', 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 +812,15 @@ describe('agent scope lifecycle', () => { }] as unknown as SessionEvent[] await expect(ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { provider: 'mock', 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: { provider: 'mock', model: 'mock' }, }) @@ -843,13 +836,13 @@ 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: { provider: 'mock', model: 'mock' }, + sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', 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: { provider: 'mock', model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } }) expect(scopeOf(retry.agent.ctx)).toBe(retry.agent) await retry.dispose() }) @@ -866,18 +859,17 @@ 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: { provider: 'mock', 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 +884,23 @@ describe('agent scope lifecycle', () => { } }) - expect(() => ctx.agentLoop.create(AgentId('config-bad'), { provider: 'mock', model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-bad'), { provider: 'mock', 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: { provider: 'mock', model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' }) const heard: string[] = [] agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`)) @@ -921,7 +913,7 @@ 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: { provider: 'mock', model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('o1-s'), agentOptions: { provider: 'mock', model: 'mock' } }) }, { inject: ['agents'] })) const { agent } = handle @@ -930,7 +922,7 @@ 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=${ctx.sessions.get(SessionId('o1-s')) !== undefined}`) }) @@ -953,7 +945,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { provider: 'mock', model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('h1-s'), agentOptions: { provider: 'mock', model: 'mock' } }) }, { inject: ['agents'] })) const teardownDone: string[] = [] @@ -965,23 +957,22 @@ describe('agent scope lifecycle', () => { // actually finished (the raw wrapper returns undefined on a repeat call). await handle.dispose() expect(teardownDone).toContain('unregistered') - expect(ctx.agents.get(AgentId('h1'))).toBeUndefined() + expect(ctx.agents.get(SessionId('h1-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('h1-s'))).toBeUndefined() await unload }) it('successful handle disposal retires its caller ownership effect', async () => { const ctx = await harness() - const agentId = AgentId('retired-owner-effect') + const sessionId = SessionId('retired-owner-effect') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('retired-owner-effect-s'), + sessionId, agentOptions: { provider: 'mock', model: 'mock' }, }) - expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${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() }) @@ -992,7 +983,6 @@ 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: { provider: 'mock', model: 'mock' }, setup(agentCtx) { @@ -1012,7 +1002,7 @@ 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() }) @@ -1022,13 +1012,11 @@ 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: { provider: 'mock', model: 'mock' }, setup(agentCtx) { @@ -1041,10 +1029,10 @@ 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: { provider: 'mock', model: 'mock' } }) - expect(ctx.agents.get(agentId)).toBe(replacement.agent) + const replacement = await ctx.agents.create({ sessionId, agentOptions: { provider: 'mock', model: 'mock' } }) + expect(ctx.agents.get(sessionId)).toBe(replacement.agent) expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session) gate.resolve(undefined) @@ -1056,7 +1044,6 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -1075,12 +1062,12 @@ 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-calls.spec.ts b/packages/core/agent-loop/tests/tool-calls.spec.ts index 8feb20bd96..373a9a2301 100644 --- a/packages/core/agent-loop/tests/tool-calls.spec.ts +++ b/packages/core/agent-loop/tests/tool-calls.spec.ts @@ -6,11 +6,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' -import SessionStore, { SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import LlmService from '@deepseek-ai/dsh-llm' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } 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' @@ -103,7 +103,7 @@ describe('tool-call scheduler: grouping and barriers', () => { const ctx = await harness(adapter) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 3) @@ -132,7 +132,7 @@ describe('tool-call scheduler: grouping and barriers', () => { name: 'w', description: 'write', parameters: { id: { type: 'string', required: true } }, async execute(args) { order.push(`w-${args.id}`); return [{ type: 'text', text: 'w' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -167,7 +167,7 @@ describe('tool-call scheduler: grouping and barriers', () => { return [{ type: 'text', text: 'replaced' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => replacement.started.length === 1) @@ -198,7 +198,7 @@ describe('tool-call scheduler: grouping and barriers', () => { disposeInitial() ctx.tools.register(replacement.tool) }) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => initial.started.length === 2) @@ -224,7 +224,7 @@ describe('tool-call scheduler: model-order results despite out-of-order settleme const ctx = await harness(adapter) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) @@ -247,7 +247,7 @@ describe('tool-call scheduler: model-order results despite out-of-order settleme const ctx = await harness(adapter) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) gated.release('2'); gated.release('1') @@ -292,7 +292,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => const ctx = await harness(adapter, 2) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) @@ -322,7 +322,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => const ctx = await harness(adapter, 1) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 1) await new Promise(r => setTimeout(r, 5)) @@ -348,7 +348,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => ctx.llm.registerAdapter(['mock'], adapter) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 1) await new Promise(r => setTimeout(r, 5)) @@ -374,7 +374,7 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () = const post: string[] = [] ctx.on('tools/pre-execute', async (exec, next): Promise => { pre.push(String(exec.callId)); return next() }) ctx.on('tools/post-execute', async (exec, _result, next): Promise => { post.push(String(exec.callId)); return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 3) @@ -395,7 +395,7 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () = ctx.tools.register(gated.tool) ctx.on('tools/post-execute', async (exec, _result): Promise => ({ kind: 'accept', additionalContexts: [{ content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) @@ -433,7 +433,7 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () = post.push(String(exec.callId)) return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 1) @@ -458,7 +458,7 @@ describe('tool-call scheduler: abort handling', () => { const ctx = await harness(adapter) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('session/event', (session, event) => { if (session === agent.session && event.type === 'assistant/message') { ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('already aborted') @@ -481,7 +481,7 @@ describe('tool-call scheduler: abort handling', () => { const ctx = await harness(adapter) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('tools/pre-execute', async (exec, next): Promise => { if (exec.callId === CallId('c1')) { ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('pre cancelled') @@ -514,7 +514,7 @@ describe('tool-call scheduler: abort handling', () => { ...await next(), additionalContexts: [{ content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }], })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) @@ -555,7 +555,7 @@ describe('tool-call scheduler: abort handling', () => { parameters: { id: { type: 'string', required: true } }, async execute(args) { exclusive.push(args.id); return [{ type: 'text', text: 'x' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index 940b7fdabe..6f327f1600 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -9,11 +9,12 @@ 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' @@ -56,7 +57,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { ctx, agent, adapter } @@ -98,7 +99,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 5e979988d7..7e7b37b58b 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-steering'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-steering'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-send'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) - const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { provider: 'mock', model: 'mock' }) + const stopped = ctx.agentLoop.create(SessionId('stopped'), { provider: 'mock', model: 'mock' }) + const ordinary = ctx.agentLoop.create(SessionId('ordinary'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-listener'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-policy'), { provider: 'mock', 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 1255731484..ce6b344f1d 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -8,28 +8,29 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i ### Public API -`Agent.ctx` owns registrations visible only to that agent. `agentEvents()` couples event subjects to their scope carrier, and `assembleContextFor()` couples the agent and prompt scope. Creation and resume may compose this context through `setup`; the agent remains unpublished and must not be driven until creation resolves. +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 factory lifecycle: `enter(agent)` publishes without announcing and returns an entry-bound detach; `announce(agent)` emits creation once. Detach during creation dispatch is deferred. Ordinary plugins use `register()`. -- `ctx.agents.get(id: AgentId): Agent | undefined` +- 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. #### Factory seam (creation) -The loop plugin registers `AgentFactory`, keeping consumers independent of its concrete package. Each call is traced through the caller's context so the caller owns the resulting transaction and handle. +Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-agent-loop`), registered via `setFactory`. This keeps creation on the `dsh-agent` interface so consumers (UI, the ACP bridge) program against `ctx.agents` without depending on the concrete loop package. The registry canonicalizes an already traced Service to its concrete target and re-traces each call through the caller's context; this avoids nested Cordis shadows while passing an explicit caller-bound `ownerCtx` to plain factories. - `ctx.agents.setFactory(factory: AgentFactory): () => void` — register the creation factory (the loop calls this on construction). Throws on a second factory; the slot clears on dispose. -- `ctx.agents.create(options)` creates and composes an unpublished session and agent, then atomically enters the registries and starts the loop. A creation-only signal cancels before publication; same-ID contenders arbitrate at entry and losers roll back. -- `ctx.agents.resume(options)` loads a persisted session and follows the same composition and publication boundary. It requires [session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md). +- `ctx.agents.create(options: CreateAgentOptions): Promise` — create a session and agent, await optional setup while unpublished, then publish through final `SessionStore.enter()` and `AgentRegistry.enter()` checks. Concurrent same-ID creation is unsupported: more than one operation may prepare, but only one can enter; every loser rolls its private scope/session/driver back. An optional creation-only `signal` cancels unpublished setup and is detached before the handle is returned; later cancellation uses `handle.dispose()` or `agent.cancel()`. Publication is rollback-covered and every delivered creation edge is paired during rollback. Rejects if no factory is registered. +- `ctx.agents.resume(options: ResumeAgentOptions): Promise` — load a persisted session ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), mint a fresh unpublished agent scope, await optional setup, and use the same final-entry publication sequence. Its optional `signal` is likewise creation-only. Rejects if no factory is registered or session persistence is unconfigured. -`AgentHandle = { agent, dispose }` is the consumer teardown capability; registry observers receive only the bare agent. Disposal stops and drains the loop and idle-injection flushes before unregistering the agent, detaching its session, and unwinding its scope. Caller and factory unload share that memoized boundary. +`AgentHandle = { agent: Agent; dispose(): Promise }`. The disposer is a **consumer capability** — no observer holding the bare registry entry can tear the agent down. The caller fiber and the registered factory provider are structural co-owners: caller unload enforces structured ownership, while factory unload must stop old instances because their scoped dependency surface belongs to that provider. `dispose()` from any owner reaches one memoized quiescence boundary: it stops the loop, `await`s its exit plus every outstanding idle-injection flush (not just the `disposed` status flip), unregisters the agent, removes its session from the store, and finally unwinds its scoped world. This order captures every agent-started `session/flush` before the session is detached and keeps scoped listeners alive through those checkpoints. `ctx.agents.get(id)` still returns a bare `Agent`; the ACP bridge and in-process subagent backends hold consumer handles, while config-created agents are already owned by the loop fiber. ### Live events `dsh-agent` declares the live `agent/*` coordination vocabulary so plugins do not depend on the concrete loop. Exact signatures, dispatch modes, scope-filtering rules, and payload contracts live in the generated [Cordis event catalog](../../../docs/cordis-catalog/events.md); the [architecture turn flow](../../../docs/architecture.md#turn-flow) shows their order relative to durable session events. -`agent/created` runs after setup and both registry entries; the following `agent/session-start` is the first supported startup injection point. `agent/disposed` means the exact entry left the registry. The loop quiesces its driver first; directly registered custom agents own any stronger ordering. +The lifecycle edges have two important local caveats. `agent/created` runs after scoped setup and after both session and agent registry entries exist. Setup is trusted composition-only code; the immediately following non-vetoing `agent/session-start` notification is the first supported startup injection point. `agent/disposed` always means the exact agent has left the registry. AgentLoop emits it after its driver is quiescent, while ordered teardown may still be detaching the session and unwinding the scope; custom agents registered directly own any stronger driver-ordering contract themselves. Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` is a serial surface-mutation checkpoint, while `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way). @@ -75,3 +76,4 @@ The handle every plugin programs against: - **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface RFC](../../../docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md)). - **`HookContext` carries exactly one `MessageSource`** — contributions from several plugins merged onto one tool call collapse under one source; mixed provenance is unrepresentable. - **`SessionStartSource` reserves `'clear'`/`'compact'` with no emitter yet** — only `'startup'`/`'resume'` occur until the driving subsystems land (`TODO(compaction)`). +- **`agent/pre-step`'s `fullSystemPrompt`/`sessionPrefix` parameters are a flagged smell** — compaction is their only consumer; a lazy prompt provider or a compaction-specific pressure seam is the marked revisit. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 6f6f3717fc..abafa38e45 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' @@ -31,23 +31,57 @@ declare module 'cordis' { } } -/** Options for creating an agent and its caller-named session. */ +/** + * Options for programmatically creating an agent through the registry factory + * ({@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 - /** Durable session metadata, validated and detached before setup. */ + /** + * Session creation metadata: validated absolute `cwd`, `parentSession` + * fork lineage, and the `seedLength` seed boundary. Mirrors the + * `cwd`/`parentSession`/`seedLength` fields of + * {@link CreateSessionOptions.meta} in dsh-session (the internal-only + * `createdAt`, used when reconstructing a persisted session, is deliberately + * excluded — a factory caller never sets it). This is durable session data, + * so the session boundary validates and snapshots it before asynchronous + * setup begins. + */ readonly meta?: { readonly cwd?: string; readonly parentSession?: SessionId; readonly seedLength?: number } - /** Balanced contiguous event prefix for a forked session. */ + /** + * Seed events to reconstruct the child session's log from (the fork lineage + * primitive). When present, the factory creates the session with this event + * prefix so `deriveMessages()`/`lastTurnNumber` continue from it — used by the + * in-process FORK subagent backend to seed a child with a balanced + * completed-turn prefix of the parent's log. The prefix MUST be contiguous + * from seq 0, carry only lossless-JSON data, and be balanced (no open + * turn/step, no dangling tool-call), or the session constructor (and the + * dev-mode invariants replay) reject it. The factory passes the raw seed to + * the session's durable validator/snapshot boundary. Absent for a fresh + * (spawn) child. + */ readonly seed?: readonly SessionEvent[] /** Per-agent options (model, …). */ readonly agentOptions?: AgentOptions /** Optional creation-only cancellation signal; detached before the returned handle becomes visible. */ readonly signal?: AbortSignal /** - * Compose the unpublished scoped context before lifecycle announcements. - * Failure rolls back without publishing either id; setup must not drive the agent. + * Creation-time composition of the agent's scoped world. The factory awaits + * setup after minting `agentCtx` but BEFORE inserting or announcing either + * the session or agent, so observers can never see a partially configured + * world. Everything registered through `agentCtx` (scoped tools, prompt + * sections/variables, `restrict()`, listeners, awaited child plugins) exists + * before `session/created`, `agent/created`, `agent/session-start`, and the + * first prompt assembly. A throw/rejection or owner disposal rolls the scope + * back without publishing either id. + * + * **Setup composes, it never drives**: the callback is trusted same-process + * code and receives the full scoped context, so this is a contract rather + * than a runtime restriction. Drive the agent only after creation resolves. */ readonly setup?: (agentCtx: Context) => Promise | void } @@ -57,23 +91,41 @@ 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 /** Optional creation-only cancellation signal for persistence load/setup; detached before return. */ readonly signal?: AbortSignal - /** Compose after persistence load under the same unpublished rollback contract as create. */ + /** + * Resume-time composition of the agent's fresh scoped world. Persistence is + * loaded first; the factory then mints `agentCtx` and awaits setup while the + * reconstructed session and agent remain unpublished. The callback has the + * same trusted composition-only contract as + * {@link CreateAgentOptions.setup}: all registrations exist before either + * creation announcement, and rejection or owner disposal rolls the + * transaction back without publishing either id. + */ readonly setup?: (agentCtx: Context) => Promise | void } /** - * Holder-owned agent capability. Disposal stops and drains the loop and idle - * flushes before unregistering the agent, detaching its session, and unwinding - * its scoped context. Provider unload reaches the same quiescence boundary; - * registry observers receive only the bare {@link Agent}. + * An owned agent plus its disposer, returned by {@link AgentRegistry.create} / + * {@link AgentRegistry.resume}. The disposer is a CAPABILITY: among consumers, + * only the holder can tear this agent down. The registered factory provider is + * also a structural owner because the scoped agent depends on that provider's + * service surface; provider unload stops and drains every live handle it made. + * `dispose()` stops the loop, awaits its exit and every outstanding + * idle-injection flush (quiescence — NOT just the `disposed` + * status flip), unregisters the agent, removes its session from the store, and + * finally unwinds its scoped world. This order captures every agent-started + * `session/flush` before the session is detached and keeps scoped listeners + * alive through those checkpoints. + * + * `ctx.agents.get(id)` still returns a bare {@link Agent} — the handle is + * exposed only to the consumer owner that created it; the structural provider + * reaches the same teardown internally. Config-created agents (the loop's own + * startup) are owned by the loop fiber and never need a handle. */ export interface AgentHandle { agent: Agent @@ -88,16 +140,30 @@ export interface AgentHandle { */ export interface AgentFactory { /** - * Create and compose under caller ownership, publish and announce session then - * agent, emit session-start, and start the driver. Rollback pairs any creation - * announcement that began. + * Create a new agent on a caller-supplied session id. Async because creation + * awaits unpublished setup, inserts both session and agent, emits their + * creation notifications in order, emits `agent/session-start`, and only + * then starts the loop. The sequence is + * rollback-covered, but notifications delivered before a later listener + * failure remain observable; every agent or session creation announcement + * that began is paired by `agent/disposed` or `session/disposed` during + * rollback. The owner disposes the resolved handle to stop/drain, + * unregister, remove the session, and unwind the scope. + * The registry passes a context carrying the `create()` caller's fiber and + * scope as `ownerCtx`. The implementation attaches the unpublished + * transaction and resulting lifecycle to that owner; it must not infer + * ownership from the factory object's registration context. * @param ownerCtx - caller-bound context that owns the transaction and live handle. * @param options - agent/session identity, configuration, and optional setup. * @returns the owned handle after setup, both announcements, and loop start complete. */ createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise /** - * Load, compose, publish, announce, and resume an agent under caller ownership. + * Load a persisted session and resume an agent on it. Async because it awaits + * both `ctx.sessionPersistence.load` and the optional unpublished setup + * transaction; must be called after that service exists (consumers inject + * `sessionPersistence`). Publication follows the same ordered boundary as + * {@link createAgent}. * @param ownerCtx - caller-bound context that owns load, setup, and the live handle. * @param options - persisted identity, configuration, and optional setup. * @returns the owned handle after setup, both announcements, and loop start complete. @@ -110,8 +176,10 @@ 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 + /** Runtime creator-agent ownership; independent of durable session lineage. */ + readonly owner: Agent | undefined readonly carrier: Scoped announced: boolean announcing: boolean @@ -131,30 +199,46 @@ interface FactorySlot { * {@link setFactory}. */ export class AgentRegistry extends Service { - private store = new Map() + private store = new Map() private factory: FactorySlot | undefined constructor(ctx: Context) { super(ctx, 'agents') - // Agent contexts shadow this plain-context default with an own property. + // The `ctx.agent` DX accessor: default `undefined` on every context, so a + // plain plugin context reads cleanly instead of hitting the Cordis + // unknown-property throw. Each Agent.ctx shadows it with an own property + // (own properties resolve before the context proxy is consulted), so the + // accessor body never needs to resolve a scope itself. Effect-scoped: + // unwinds with this service's fiber. ctx.accessor('agent', { get: () => undefined }) } /** - * Register the effect-scoped creation factory, rejecting a duplicate. Service - * factories are retraced through each create/resume caller for ownership. + * Register the agent-creation factory (the loop calls this on construction, + * effect-scoped). A traced Cordis service is canonicalized to its concrete + * target; each create/resume call is then traced through that caller's + * context so ownership follows the caller without stacking proxy layers. + * Throws if a factory is already registered. Returns the disposer; on + * dispose the factory slot is cleared. * @param factory - the loop-owned factory {@link create}/{@link resume} delegate to. - * @returns the exact Cordis effect disposer. + * @returns the disposer that clears the factory slot. The exact + * Cordis effect disposer (single-shot): composite (generator) effects may + * yield it directly — exact identity nests the teardown in order. */ setFactory(factory: AgentFactory): () => void { const dispose = this.ctx.effect(() => { if (this.factory !== undefined) throw new Error('an agent factory is already registered') - // Store the concrete service; calls are retraced through their owner. + // Avoid stacking two Cordis shadow layers when a caller passes a Service + // already read through a context. Calls are re-traced through their + // actual owner context below. const target = (factory as AgentFactory & { [symbols.original]?: AgentFactory })[symbols.original] ?? factory this.factory = { target } return () => { this.factory = undefined } }, 'agents.setFactory()') - // Return the exact disposer so composite effects preserve teardown order. + // The exact cordis effect disposer (the agents.register() convention): a + // caller's composite effect can yield it for in-order teardown; the + // loop's constructor effect returns it directly, identity-nesting the + // registration under that effect. // eslint-disable-next-line @typescript-eslint/no-misused-promises -- synchronous cleanup; direct return preserves disposer identity return dispose } @@ -166,14 +250,20 @@ export class AgentRegistry extends Service { } /** - * Create and publish an owned agent and session through the active factory. - * Rejects if no factory is registered or creation, setup, or publication fails. - * @param options - agent id, session id/seed/metadata, and agent options. + * Create and publish a new agent through the registered factory. + * Distinct from {@link register} (which records an already-constructed + * 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 - 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 { const ownerCtx = this.ctx - // Bind service effects to this caller while preserving factory dependencies. + // Re-trace a Service-backed factory through the accessing context + // explicitly. This preserves AgentLoop's dependency origin while binding + // its effects to ownerCtx; plain factories receive ownerCtx as an explicit + // capability and need no Cordis tracker magic. const { target } = this.requireFactory() const receiver = getTraceable(ownerCtx, target) // eslint-disable-next-line @typescript-eslint/unbound-method -- Reflect.apply intentionally supplies the caller-traced receiver @@ -196,14 +286,26 @@ export class AgentRegistry extends Service { } /** - * Register a live agent in the calling effect scope, with scope-filtered - * creation and disposal events. Duplicate ids throw. + * Register a live agent. Throws if an agent with the same id is already + * registered. Emits `agent/created` on registration and `agent/disposed` + * when the calling fiber is disposed — both with the agent's scope carrier + * (`scopeTarget(agent, agent)`): the subject is the agent in hand, so the + * emits are scope-filtered regardless of which context invoked `register` + * (calling through `agent.ctx` scopes EFFECTS; dispatch scoping always + * requires passing the carrier). Returns the disposer. * @param agent - the already-constructed agent to record in the store. - * @returns the exact Cordis effect disposer for nested teardown ordering. + * @returns the EXACT Cordis effect disposer (single-shot; a repeat call + * returns undefined without awaiting an in-flight teardown). Exact + * identity is load-bearing: a composite (generator) effect that owns a + * teardown ORDER — the agent factory's lifecycle chain — must yield THIS + * function so Cordis nests the unregistration at that yield position; + * yielding a wrapper would leave it disposing as a concurrent sibling on + * owner unload, unregistering the agent (and emitting `agent/disposed`) + * while its final turn is still draining. */ 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 @@ -211,13 +313,25 @@ export class AgentRegistry extends Service { } /** - * Insert an unpublished agent for an ordered factory transaction. + * Insert an already-constructed agent without announcing it. This is the + * advanced ordered-lifecycle primitive used by the async agent factory: it + * first completes setup while the agent is unpublished, then assigns the + * returned detach closure into its pre-installed composite teardown before + * calling {@link announce}. Ordinary callers use {@link register}. * @param agent - the prepared, unpublished agent. - * @returns an idempotent closure that removes this exact entry and emits the - * paired disposal edge; detachment during creation dispatch is deferred. + * @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 + 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. @@ -225,6 +339,7 @@ export class AgentRegistry extends Service { const entry: AgentEntry = { id, agent, + owner, carrier, announced: false, announcing: false, @@ -235,7 +350,11 @@ export class AgentRegistry extends Service { const detach = (): void => { if (!entered) return entered = false - // Creation listeners observe one stable entry before paired disposal. + // Every callback reached by this creation dispatch must observe the same + // live entry, and disposal must follow creation. A listener may own + // the advanced detach capability, so make that ordering structural: + // visibility and the paired disposal are deferred until announce()'s + // synchronous dispatch has unwound. if (entry.announcing) { entry.detachRequested = true return @@ -314,10 +433,10 @@ 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 } @@ -328,6 +447,18 @@ 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/src/types.ts b/packages/core/agent/src/types.ts index 5c709c828b..7ce42d7024 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -5,25 +5,11 @@ * @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 { ContextEnvelope, JsonValue, 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 { ContextEnvelope, JsonValue, Session } from '@deepseek-ai/dsh-session' - declare module '@deepseek-ai/dsh-system-prompt' { interface AssembleContext { /** Agent for this assembly; absent on diagnostics. When present, `scope` must identify the same agent. */ @@ -96,7 +82,8 @@ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' /** Public agent handle; the concrete driver belongs to `@deepseek-ai/dsh-agent-loop`. */ 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..d2866cacb3 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -2,15 +2,16 @@ 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: {}, - session: new Session(SessionId(`${id}-session`)), + session: new Session(id), status: 'idle', ctx: new Context(), send() {}, @@ -41,6 +42,7 @@ describe('AgentRegistry', () => { const dispose = ctx.agents.register(agent) expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.agents.list()).toEqual([agent]) + expect(ctx.agents.roots()).toEqual([agent]) expect(() => ctx.agents.register(stubAgent('a1'))).toThrow(/already registered/) dispose() @@ -48,6 +50,33 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('rejects an agent whose registry and session identities differ', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const agent = { ...stubAgent('agent-id'), session: new Session(SessionId('session-id')) } + + expect(() => ctx.agents.enter(agent, undefined)) + .toThrow('agent id "agent-id" does not match session id "session-id"') + expect(ctx.agents.list()).toEqual([]) + }) + + it('tracks runtime creator ownership separately from registry order', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const root = stubAgent('root') + const child = stubAgent('child') + const detachRoot = ctx.agents.enter(root, undefined) + ctx.agents.announce(root) + const detachChild = ctx.agents.enter(child, root) + ctx.agents.announce(child) + + expect(ctx.agents.list()).toEqual([root, child]) + expect(ctx.agents.roots()).toEqual([root]) + + detachChild() + detachRoot() + }) + it('rolls an entry back and pairs a partially delivered creation when a listener throws', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -57,7 +86,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${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']) }) @@ -93,7 +122,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) const first = stubAgent('split') - const detachFirst = ctx.agents.enter(first) + const detachFirst = ctx.agents.enter(first, undefined) expect(lifecycle).toEqual([]) ctx.agents.announce(first) expect(() => { ctx.agents.announce(first) }).toThrow(/already announced/) @@ -101,7 +130,7 @@ describe('AgentRegistry', () => { detachFirst() const replacement = stubAgent('split') - const detachReplacement = ctx.agents.enter(replacement) + const detachReplacement = ctx.agents.enter(replacement, undefined) detachFirst() expect(ctx.agents.get(replacement.id)).toBe(replacement) expect(() => { ctx.agents.announce(first) }).toThrow(/not live/) @@ -121,7 +150,7 @@ describe('AgentRegistry', () => { }) ctx.on('agent/created', () => void order.push(`second:${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() @@ -158,11 +187,11 @@ 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 +200,15 @@ 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 +221,9 @@ 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 +243,18 @@ 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 985d475101..ef84a6bfbc 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -279,7 +279,12 @@ 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 d4660f7ed7..bbc19d5d75 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 d4851cdbd7..49ffc0bac9 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/examples/agent-spine-demo/tests/agent-core.spec.ts b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts index fdf17286ee..5d5b336ff9 100644 --- a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts +++ b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts @@ -6,7 +6,7 @@ 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 { SessionId } from '@deepseek-ai/dsh-session' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' import { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.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() } @@ -129,17 +129,19 @@ describe('dsh-agent-spine-demo bundle', () => { it('defaults the agents list to empty (no pre-created agents)', async () => { const ctx = await mount({ workspaceContext: false }) - 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'), provider: 'mock', model: 'mock' }], + agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock' }], persona: 'You are main.', workspaceContext: false, }) - 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() @@ -147,7 +149,7 @@ describe('dsh-agent-spine-demo bundle', () => { it('forwards the global maxParallelToolCalls config to agent-loop', async () => { const ctx = await mount({ - agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock' }], + agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock' }], maxParallelToolCalls: 3, workspaceContext: false, }) @@ -178,7 +180,6 @@ describe('dsh-agent-spine-demo bundle', () => { await ctx.plugin(LocalFileSystem, { cwd: '/' }) ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('main'), sessionId: SessionId('main-session'), meta: { cwd: root }, agentOptions: { provider: 'mock', model: 'mock' }, @@ -186,7 +187,7 @@ 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') @@ -209,14 +210,13 @@ describe('dsh-agent-spine-demo bundle', () => { const ctx = await mount({ workspaceContext: { maxBytes: 0 } }) ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('main'), sessionId: SessionId('main-disabled-session'), meta: { cwd: root }, agentOptions: { provider: 'mock', model: 'mock' }, }) 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() @@ -299,14 +299,13 @@ describe('dsh-agent-spine-demo bundle', () => { content: 'body', }) const handle = await ctx.agents.create({ - agentId: AgentId('main'), sessionId: SessionId('prefix-order-session'), meta: { cwd: root }, agentOptions: { provider: 'mock', model: 'mock' }, }) 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') diff --git a/packages/examples/stdio-demo/README.md b/packages/examples/stdio-demo/README.md index 5eb6ea766c..b783ca0078 100644 --- a/packages/examples/stdio-demo/README.md +++ b/packages/examples/stdio-demo/README.md @@ -15,7 +15,7 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | `@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 | -| `@deepseek-ai/dsh-stdio` | the readline UI, bound to the `main` agent | +| `@deepseek-ai/dsh-stdio` | the readline UI, bound to the exact app-owned agent/session identity 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`. @@ -39,7 +39,7 @@ 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`, so project-scoped features such as skill discovery and default bash workdir follow the directory where `dsh-stdio-demo` 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 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/examples/stdio-demo/package.json b/packages/examples/stdio-demo/package.json index a523f61213..992b63e1af 100644 --- a/packages/examples/stdio-demo/package.json +++ b/packages/examples/stdio-demo/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-spine-demo": "^0.0.1", "@deepseek-ai/dsh-workspace-context": "^0.0.1", @@ -53,6 +54,7 @@ "@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-spine-demo": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index 91c377e9f7..71196ed647 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -2,7 +2,8 @@ * The stdio chat app: the default agent spine ({@link @deepseek-ai/dsh-agent-spine-demo}) plus the * coupled front-door cluster a terminal chat needs — a console logger, the independently * packaged readline UI, JSONL session persistence, the user-interaction seam with its - * `ask_user_question` tool, and a pre-created `main` agent the UI drives. + * `ask_user_question` tool, and one pre-created agent whose exact shared + * agent/session identity the UI drives under its `main` display label. * Swappable adapters, executors, optional tools, and HMR stay in the leaf. This * Loader plugin intentionally exposes named exports only; a default export * would hide its `Config` schema (see docs/postmortem/0001). @@ -10,9 +11,9 @@ */ import type { Context } from 'cordis' +import { randomUUID } from 'node:crypto' 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-spine-demo' @@ -60,7 +61,7 @@ export interface Config { /** Generic background-task control-tool config forwarded through agent-core. */ toolTasks?: NonNullable /** - * 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`). */ @@ -92,26 +93,32 @@ export const Config: z = z.object({ }) /** - * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-spine-demo 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 - * 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, { ...agentCore.pickSpineConfig(config), agents: [{ - id: AgentId('main'), + id: SessionId('main'), provider: config.provider, model: config.model, cwd: process.cwd(), - ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, + ...resumeSessionId === undefined ? { sessionId } : { resumeSessionId: sessionId }, }], }) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) - ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', agent: 'main' }) } diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index 4c81eb93e4..ddfc0ec95d 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/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' @@ -73,13 +74,33 @@ describe('dsh-stdio-demo 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. + 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) + expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) await ctx.fiber.dispose() }) + it('normalizes an empty resume id to a fresh exact app identity', async () => { + const ctx = await mount({ + provider: 'mock', + model: 'mock', + resumeSessionId: '', + persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', + skills: await isolatedSkillsConfig(), + workspaceContext: false, + }) + 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) + 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 @@ -88,9 +109,9 @@ describe('dsh-stdio-demo app', () => { const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. stdioAgent.apply(ctx, { provider: 'mock', model: 'mock', skills: await isolatedSkillsConfig(), workspaceContext: false }) - await new Promise(resolve => setTimeout(resolve, 80)) + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + expect(ctx.get('agents')?.list()[0]?.id).toMatch(/^main-session-/) await ctx.fiber.dispose() }) @@ -102,7 +123,8 @@ describe('dsh-stdio-demo app', () => { persistenceRoot: '/tmp/dsh-stdio-demo-spec-workspace-context', workspaceContext: false, }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) + expect(ctx.get('agents')?.list()[0]?.id).toMatch(/^main-session-/) await ctx.fiber.dispose() }) @@ -119,7 +141,7 @@ describe('dsh-stdio-demo 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({ provider: 'mock', @@ -130,7 +152,7 @@ describe('dsh-stdio-demo app', () => { skills: await isolatedSkillsConfig(), workspaceContext: false, }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.list()).toEqual([]) await ctx.fiber.dispose() }) diff --git a/packages/fs/tool-fs/tests/fs-tools.e2e.ts b/packages/fs/tool-fs/tests/fs-tools.e2e.ts index ca93bad63d..472b32f47a 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('fs-e2e'), { provider: 'deepseek', 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: { provider: 'deepseek', model: 'deepseek-v4-flash' }, diff --git a/packages/guard/repeat-tool-guard/README.md b/packages/guard/repeat-tool-guard/README.md index 5a9fed247f..2927e3f20a 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 9df8dd399f..2279f53ade 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -1,15 +1,14 @@ /** - * Advisory repeat-call loop breaker. It never registers, blocks, or rewrites a tool; configured - * consecutive canonical calls add source-attributed context after downstream post-policy. The - * loop logs that model-visible reminder as reconstructable context. Counters are per agent and - * in-memory, so one agent cannot trip another and resumed sessions start fresh. Named exports - * preserve loader metadata. See the package README for chain semantics and thresholds. + * 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 */ 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' @@ -169,9 +168,7 @@ 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 { @@ -194,9 +191,9 @@ 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 @@ -226,12 +223,7 @@ 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 3c5c9051bf..6dd4e45a71 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 @@ -1,9 +1,8 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' -import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' @@ -53,7 +52,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -74,7 +73,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -96,7 +95,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -120,7 +119,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -138,7 +137,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -159,7 +158,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -175,7 +174,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -191,7 +190,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -211,8 +210,8 @@ describe('chain semantics', () => { toolCallResponse('b3', 'probe', { q: 1 }), textResponse('done'), ])) - const agentA = ctx.agentLoop.create(AgentId('a'), { provider: 'mock-a', model: 'model-a' }) - const agentB = ctx.agentLoop.create(AgentId('b'), { provider: 'mock-b', model: 'model-b' }) + const agentA = ctx.agentLoop.create(SessionId('a'), { provider: 'mock-a', model: 'model-a' }) + const agentB = ctx.agentLoop.create(SessionId('b'), { provider: 'mock-b', model: 'model-b' }) agentA.send([{ type: 'text', text: 'go' }]) agentB.send([{ type: 'text', text: 'go' }]) await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)]) @@ -231,7 +230,7 @@ describe('chain semantics', () => { textResponse('turn two done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) agent.send([{ type: 'text', text: 'again' }]) @@ -252,14 +251,14 @@ 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'), { provider: 'mock', model: 'mock' }) + first = inner.agentLoop.create(SessionId('reused'), { provider: 'mock', 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'), { provider: 'mock', model: 'mock' }) + const second = ctx.agentLoop.create(SessionId('reused'), { provider: 'mock', model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, second) @@ -275,7 +274,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -291,7 +290,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -313,7 +312,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -344,7 +343,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 672a89188a..136ee893c6 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -4,9 +4,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context, type Fiber } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' @@ -14,8 +13,11 @@ import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' /** - * Full-loop Claude bridge tests with a mock model, the real loop and bash - * executor, and shell hooks from a temporary config. + * Full-loop bridge tests: a scripted mock MODEL drives the REAL agent loop + REAL + * bash executor, and the REAL `dsh-hooks-claude` bridge runs REAL shell hook + * scripts written to a temp dir — only the model is mocked (the "prefer the real + * implementation" rule). Each test writes a `hooks.json` + executable scripts, + * loads the bridge pointed at them, and asserts the hook's effect on the loop. */ const dirs: string[] = [] @@ -87,7 +89,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'do something' }]) await waitForIdle(ctx, agent) @@ -110,7 +112,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -135,7 +137,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'use danger' }]) await waitForIdle(ctx, agent) @@ -158,7 +160,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'use safe' }]) await waitForIdle(ctx, agent) @@ -180,11 +182,12 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') + // PostToolUse blocks AFTER the tool ran: the result is rewritten to isError + feedback. expect(result?.type === 'tool/result' && result.data.isError).toBe(true) expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('output rejected, retry'))).toBe(true) }) @@ -200,7 +203,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -224,7 +227,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -248,7 +251,7 @@ describe('hooks-claude bridge — SessionStart', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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. @@ -284,17 +287,21 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const { ctx, hooks } = await harnessWithFiber(dir, adapter) // 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 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' }] }) + // child lookup yields undefined and it simply runs the hook. + 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. await waitFor(() => existsSync(startMarker) && existsSync(stopMarker)) expect(existsSync(startMarker)).toBe(true) expect(existsSync(stopMarker)).toBe(true) - // A marker proves only that the process ran. Disposal drains its detached continuation so the - // no-context branch completes before the per-file coverage snapshot instead of racing CI. + // The markers prove the hook PROCESSES ran, not that the detached `.then` + // continuations did (`touch` lands before the process exits). Dispose drains + // them, so the no-context arm of the SubagentStart continuation — covered + // only here — executes before this file's coverage snapshot instead of + // racing it (the arm went uncovered on a loaded CI runner and failed the + // per-file 100% branch gate). await hooks.dispose() }) @@ -304,8 +311,10 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const pidFile = join(dir, 'pid') const marker = join(dir, 'started') const slowHook = join(dir, 'slow.sh') - // Record the PID and marker before sleeping past the suite timeout. Disposal must abort and - // kill the process rather than await its exit or the default ten-minute hook timeout. + // Record the hook shell's PID and touch the marker FIRST so the test can + // tell "the hook is genuinely mid-run", then sleep far past the suite + // timeout. Dispose must KILL the process (the tracker's abort signal), not + // await its exit or its 10-minute default hook timeout. writeFileSync(slowHook, `#!/usr/bin/env bash\necho $$ > "${pidFile}"\ntouch "${marker}"\nsleep 30\n`) chmodSync(slowHook, 0o755) writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { @@ -315,15 +324,18 @@ 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() - // Disposal reaches quiescence: it returns only after the aborted run settles and the process - // is reaped, so `kill(pid, 0)` must report ESRCH. Untracked fire-and-forget work would remain. + // Quiescence, not just promptness: the drain resolves only after the run + // settled, and the run settles only after the killed process was reaped — + // so by the time dispose returns, the PID must be GONE (kill(pid, 0) + // throws ESRCH). An untracked fire-and-forget regression would leave the + // process alive (or unreaped) and fail this deterministically. expect(() => process.kill(pid, 0)).toThrow() - // runHook resolves an aborted run as a non-blocking error, so draining must - // not log a rejected continuation. + // The aborted run resolves as a non-blocking error (runHook never rejects), + // so the drained continuation must NOT have logged a failure. expect(warn).not.toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) }) }) @@ -337,7 +349,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The turn ran normally — no hooks, no crash. @@ -345,8 +357,11 @@ describe('hooks-claude bridge — load resilience', () => { }) it('disposing the bridge fiber removes its listeners (HMR safety)', async () => { - // This is the only bridge mount, and its blocking hook would veto the prompt and log an event - // if its listener leaked after disposal. A no-op hook would not expose that leak. + // A BLOCKING UserPromptSubmit hook: if the listener leaked past dispose it + // would veto the prompt (0 model requests) and log a hook/invoked. Build the + // ctx WITHOUT the harness's own bridge mount so this is the ONLY mount, then + // dispose it — a leaked listener fails the test (a no-op `true` hook would + // pass even leaked, so it proved nothing). const dir = writeConfig({ UserPromptSubmit: [{ hooks: [{ type: 'command', command: 'exit 2' }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = new Context() @@ -356,7 +371,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone @@ -364,8 +379,10 @@ describe('hooks-claude bridge — load resilience', () => { }) it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/apply', () => { - // A default export would make `unwrapExports` collapse the namespace and drop `inject`, causing - // load to fail. Guard the shape from postmortem 0001 directly. + // Postmortem 0001 guard: this plugin HAS `inject = ['bash']`, so a stray + // `export default apply` would collapse the module via `unwrapExports` + // (`exports.default ?? exports`), DROP `inject`, and crash at load with + // "cannot get property … without inject". Guard the shape directly. expect('default' in HooksClaude).toBe(false) expect(HooksClaude.name).toBe('hooks-claude') expect(HooksClaude.inject).toEqual(['bash']) diff --git a/packages/hooks/hooks-claude/tests/coverage-cases.ts b/packages/hooks/hooks-claude/tests/coverage-cases.ts index 774e2a8451..9d4004c1ff 100644 --- a/packages/hooks/hooks-claude/tests/coverage-cases.ts +++ b/packages/hooks/hooks-claude/tests/coverage-cases.ts @@ -3,10 +3,9 @@ import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' -import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' @@ -65,7 +64,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('transcript'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('transcript'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { @@ -95,7 +94,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) // substituted command ran @@ -111,7 +110,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // updatedInput is NOT honored — the tool ran with the ORIGINAL args. @@ -127,7 +126,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The prompt proceeded unchanged; no context/message injected. @@ -157,7 +156,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -182,7 +181,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -198,7 +197,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) @@ -214,7 +213,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // A second model request ran → the empty-reason block forced continuation. @@ -230,9 +229,9 @@ export function defineCoverageCases(group: CoverageGroup): void { 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: { id: SessionId('child-x'), 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') }) @@ -246,9 +245,9 @@ export function defineCoverageCases(group: CoverageGroup): void { 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: { id: SessionId('child-y'), 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')) }) @@ -262,7 +261,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -276,7 +275,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -292,7 +291,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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) }) @@ -305,7 +304,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') @@ -320,7 +319,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // ask (no reason) → degrades to deny with the registry's generic message. @@ -335,7 +334,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -360,7 +359,7 @@ export function defineCoverageCases(group: CoverageGroup): void { // 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) @@ -375,7 +374,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) @@ -390,7 +389,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -409,7 +408,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -426,7 +425,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -446,7 +445,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran @@ -464,7 +463,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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: { provider: 'mock', model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { provider: 'mock', 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' @@ -481,9 +480,8 @@ export function defineCoverageCases(group: CoverageGroup): void { 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') ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // the downstream block won: the model was never called, no user/message was @@ -512,7 +510,7 @@ export function defineCoverageCases(group: CoverageGroup): void { meta: { owner: 'policy' }, }], })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) @@ -541,7 +539,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -565,7 +563,7 @@ export function defineCoverageCases(group: CoverageGroup): void { meta: { owner: 'policy' }, }], })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -589,7 +587,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -613,7 +611,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -629,7 +627,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // Make inject throw, forcing the SessionStart .catch path. const original = agent.inject.bind(agent) let threw = false @@ -663,7 +661,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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: { provider: 'mock', model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) @@ -692,7 +690,7 @@ export function defineCoverageCases(group: CoverageGroup): void { // 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: { provider: 'mock', model: 'mock' } }) + const childHandle = await ctx.agents.create({ sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { provider: 'mock', model: 'mock' } }) ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) @@ -713,7 +711,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) @@ -731,7 +729,7 @@ export function defineCoverageCases(group: CoverageGroup): void { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 e686b565f2..904ca0111b 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -4,9 +4,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' @@ -76,7 +75,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run ls' }]) await waitForIdle(ctx, agent) @@ -97,7 +96,7 @@ describe('hooks-codex bridge', () => { 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -112,7 +111,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) @@ -122,7 +121,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) @@ -142,7 +141,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone @@ -165,7 +164,7 @@ 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'), { provider: 'mock', model: 'mock' }) // fires agent/session-start + ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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-cases.ts b/packages/hooks/hooks-codex/tests/coverage-cases.ts index d11c74951d..b131d74369 100644 --- a/packages/hooks/hooks-codex/tests/coverage-cases.ts +++ b/packages/hooks/hooks-codex/tests/coverage-cases.ts @@ -3,10 +3,9 @@ import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' -import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' @@ -62,7 +61,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('transcript'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('transcript'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { @@ -81,7 +80,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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') @@ -93,7 +92,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') }) @@ -106,7 +105,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -129,7 +128,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro meta: { owner: 'policy' }, }], })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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') @@ -153,7 +152,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -175,7 +174,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro meta: { owner: 'policy' }, }], })) - const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const contexts = events(agent).filter(event => event.type === 'context/message') @@ -194,7 +193,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -207,7 +206,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -220,7 +219,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -233,7 +232,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) }) @@ -247,7 +246,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' }) @@ -258,7 +257,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -271,7 +270,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -294,7 +293,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) + '…') @@ -317,7 +316,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro // 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) @@ -330,7 +329,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -344,7 +343,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -356,7 +355,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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')) @@ -371,7 +370,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -384,7 +383,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -400,7 +399,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 @@ -413,7 +412,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -425,7 +424,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -442,7 +441,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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('') @@ -478,7 +477,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -494,7 +493,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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') @@ -507,7 +506,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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') }) @@ -521,7 +520,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -535,7 +534,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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') @@ -546,7 +545,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -560,7 +559,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') }) @@ -575,7 +574,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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') @@ -591,7 +590,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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) @@ -603,7 +602,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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') @@ -626,7 +625,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro 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: { provider: 'mock', model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', 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/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..a79818908c 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 +15,35 @@ export async function main(boot: SdkBootContext) { if (resume !== undefined && (typeof resume !== 'string' || resume.length === 0)) { throw new Error('stdio startup requires --resume=') } - if (resume === undefined) { - await ctx.agents.create({ - agentId: AgentId('main'), - sessionId: SessionId(`main-session-${randomUUID()}`), - meta: { cwd: boot.cwd }, - agentOptions: { model }, - }) - } else { - await ctx.agents.resume({ - agentId: AgentId('main'), - resumeSessionId: SessionId(resume), - agentOptions: { model }, - }) + const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`) + process.env.DSH_SDK_SESSION_ID = sessionId +{{/if}} + const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) +{{#if isStdio}} + try { + if (resume === undefined) { + await ctx.agents.create({ + sessionId, + meta: { cwd: boot.cwd }, + agentOptions: { model }, + }) + } else { + await ctx.agents.resume({ + resumeSessionId: sessionId, + agentOptions: { model }, + }) + } + } catch (error) { + try { + await ctx.fiber.dispose() + } catch (disposeError) { + throw new AggregateError([error, disposeError], 'stdio startup and cleanup failed') + } + throw error } {{else}} {{#if isEmbed}} await ctx.agents.create({ - agentId: AgentId('main'), sessionId: SessionId(`main-session-${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..655b308911 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -167,6 +167,12 @@ 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(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', @@ -175,7 +181,11 @@ 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 +296,10 @@ 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) @@ -862,6 +875,12 @@ 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([ diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index 69a5f14181..a620051506 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/package.json b/packages/subagent/subagent-acp/package.json index ec55845f91..fa16edcf60 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.7" @@ -36,6 +37,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-loader-smoke": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-subagent-subprocess": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.5", diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 9416d58865..b7b10ecb97 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,8 +23,8 @@ 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' @@ -149,9 +149,11 @@ 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()) - 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()) // Keep diagnostics on parent stderr; only ACP output contributes to the result. const child = spawn(spec.command, spec.args, { @@ -241,7 +243,9 @@ 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 }), @@ -253,13 +257,18 @@ 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 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 const result: Promise = (async (): Promise => { try { // Race the remote turn against local cancellation. 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: remoteSessionId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index 1496f882aa..2bbf457c18 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -1,9 +1,45 @@ /** - * Minimal no-network ACP child process for keyless backend tests. Environment variables script its - * text and stop reason, a cancel-cooperative or cancel-ignoring hang, permission requests, and a - * readiness marker. Disposal fixtures can delay an EOF flush, ignore EOF but exit and mark - * SIGTERM, or trap SIGTERM to require SIGKILL. The specs run this protocol-only fixture directly - * with Node's type stripping; it imports no harness code or workspace paths. + * A minimal mock ACP AGENT, run as a subprocess, for the keyless + * `dsh-subagent-acp` tests. It speaks the agent side of ACP over stdio and is + * fully scripted by environment variables — no model, no network: + * + * - `MOCK_TEXT` — the assistant text it streams as one `agent_message_chunk`. + * - `MOCK_STOP` — the ACP `StopReason` it returns from `prompt` + * (`end_turn` default, or `max_tokens`/`refusal`/…). + * - `MOCK_HANG` — if `1`, `prompt` never resolves on its own (it waits for + * a `session/cancel`), to exercise the client's cancel path. + * - `MOCK_IGNORE_CANCEL` — if `1` (with MOCK_HANG), the agent receives + * `session/cancel` but NEVER resolves the pending prompt + * and never exits — a non-cooperative child. The backend's + * `result` must still settle `aborted` on its own and + * `dispose()` must still kill the process. + * - `MOCK_PERMISSION` — if `1`, the agent calls `session/request_permission` + * before answering, to exercise the client's auto-answer. + * - `MOCK_READY_FILE` — if set, the path the agent touches once its `prompt` + * 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 + * path and exits ON ITS OWN — no signal. Stands in for a + * child whose durable flush completes only if dispose + * gives EOF a real window before escalating to SIGTERM. + * - `MOCK_IGNORE_EOF` — if `1`, keep the event loop alive past stdin EOF (a bare + * timer) but install a SIGTERM handler that exits (and, if + * MOCK_SIGTERM_FILE is set, touches it as an observable + * proof the SIGTERM rung fired). The child ignores the + * graceful EOF window yet dies cooperatively on SIGTERM — + * exercising dispose's middle tier (exit during the SIGTERM + * grace, before the SIGKILL escalation). Touches + * MOCK_READY_FILE once armed. + * + * It is not a test spec: the specs launch this protocol-only fixture through + * the mode-aware example resolver (tsx in source mode, Node type stripping in + * built mode). It imports no harness code or workspace paths. + * * @module @deepseek-ai/dsh-subagent-acp/tests/mock-acp-server */ @@ -64,7 +100,8 @@ 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() } + if (process.env.MOCK_MISSING_SESSION_ID === '1') return {} as NewSessionResponse + return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { // No auth methods advertised; nothing to do. @@ -124,8 +161,11 @@ function makeAgent(conn: AgentSideConnection): Agent { process.exit(1) } if (IGNORE_CANCEL) { - // A non-cooperative child receives cancellation but neither resolves nor exits. The - // backend must still settle `aborted`, and disposal must kill the process. + // A NON-COOPERATIVE child: receive session/cancel but never resolve the + // pending prompt and never exit. The backend's `result` must still settle + // `aborted` on its own (the cancel-settle race), and `dispose()` must + // still kill the process — proving cancellation does not depend on the + // child cooperating. return Promise.resolve() } resolveCancel?.('cancelled') @@ -142,9 +182,12 @@ new AgentSideConnection( ), ) -// Under MOCK_TRAP_SIGTERM, ignore SIGTERM and keep stdin open so the process neither quiesces -// on EOF nor dies on the graceful signal — exercising the backend dispose path's SIGKILL -// escalation. READY_FILE proves the trap was armed before the test disposes the run. +// Under MOCK_TRAP_SIGTERM, ignore SIGTERM and keep stdin open so the process +// neither quiesces on EOF nor dies on the graceful signal — exercising the +// backend dispose path's SIGKILL escalation. Without this the process exits +// normally on SIGTERM / stdin end. Touch READY_FILE once the trap is armed, so +// a test waits for that CONDITION before disposing (the trap must be in place, +// not merely the process spawned — otherwise SIGTERM hits the default handler). if (process.env.MOCK_TRAP_SIGTERM === '1') { process.on('SIGTERM', () => { /* trapped: refuse to exit on the graceful signal */ }) // Keep the event loop alive (a bare timer) so nothing else lets it exit. @@ -152,10 +195,13 @@ if (process.env.MOCK_TRAP_SIGTERM === '1') { if (READY_FILE !== undefined) writeFileSync(READY_FILE, 'trap-armed') } -// Under MOCK_FLUSH_ON_EOF, model the real acp-agent's EOF-driven quiesce: on stdin 'end' (the -// dispose path's `child.stdin.end()`), take an ASYNC beat to "flush", then touch the marker and -// exit on its own. A signal sent before MOCK_FLUSH_DELAY_MS would suppress the marker, so it proves -// the EOF grace window was long enough for durable flush. +// Under MOCK_FLUSH_ON_EOF, model the real acp-agent's EOF-driven quiesce: on +// stdin 'end' (the dispose path's `child.stdin.end()`), take an ASYNC beat to +// "flush", then touch the marker and exit ON OUR OWN — no signal involved. The +// beat is MOCK_FLUSH_DELAY_MS (default 150). A dispose that sends SIGTERM before +// the beat completes (no graceful window, or an EOF grace shorter than the +// flush) default-terminates this process and the marker is missing; a dispose +// that gives the EOF quiesce enough window first lets the flush land. if (FLUSH_ON_EOF !== undefined) { const flushDelayMs = Number(process.env.MOCK_FLUSH_DELAY_MS ?? '150') process.stdin.on('end', () => { @@ -166,9 +212,14 @@ if (FLUSH_ON_EOF !== undefined) { }) } -// Ignore EOF but exit on SIGTERM to exercise the middle disposal tier before SIGKILL. The signal -// marker distinguishes that catchable rung from an immediate, uncatchable SIGKILL; READY_FILE -// proves the handler was armed before disposal. +// Under MOCK_IGNORE_EOF, keep the loop alive past stdin EOF (so the graceful EOF +// window times out) but INSTALL A SIGTERM HANDLER that records it and exits — the +// child ignores the graceful EOF window yet dies cooperatively on SIGTERM, +// exercising dispose's MIDDLE tier (exit during the SIGTERM grace, before the +// SIGKILL escalation). When MOCK_SIGTERM_FILE is set the handler touches it, an +// OBSERVABLE proof that the SIGTERM rung fired: if dispose skipped the middle +// rung and jumped EOF→SIGKILL, SIGKILL is uncatchable so the handler never runs +// and the marker is missing. Touch READY_FILE once armed (a test waits on it). if (process.env.MOCK_IGNORE_EOF === '1') { const sigtermFile = process.env.MOCK_SIGTERM_FILE process.on('SIGTERM', () => { diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index bfc8476bae..2f242e3fab 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -58,7 +58,7 @@ function text(blocks: { type: string; text?: string }[]): string { /** * Poll until `file` exists (the mock touches it once its prompt is in flight), * so a cancel test waits on a CONDITION rather than an arbitrary timeout — the - * subprocess cold-start under tsx is variable, and a fixed sleep both flakes and + * subprocess cold-start is variable, and a fixed sleep both flakes and * slows the suite. Fails loud if the child never signals readiness. */ async function waitForFile(file: string, timeoutMs = 5000): Promise { @@ -117,15 +117,22 @@ 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' }) + 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).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 () => { @@ -184,6 +191,31 @@ 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: [mockServer], + cwd: process.cwd(), + permission: 'reject', + env: { + MOCK_MISSING_SESSION_ID: '1', + MOCK_FLUSH_ON_EOF: flushed, + MOCK_FLUSH_DELAY_MS: '20', + }, + 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 diff --git a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts index 4a2c6b9133..df3b74d346 100644 --- a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts +++ b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -30,7 +30,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', 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 f1ca8f0b75..668f5ad9bc 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -1,7 +1,8 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -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 { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -36,7 +37,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 8ec8a6aac2..018f93051f 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 parentProvider = parent.options.provider @@ -129,8 +129,7 @@ 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 4222dde760..e50457bcb4 100644 --- a/packages/subagent/subagent-inprocess/tests/structured.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/structured.spec.ts @@ -1,8 +1,8 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { CallId, type ContentBlock, type GenerateOptions } from '@deepseek-ai/dsh-llm' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContinuationDecision } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -61,7 +61,7 @@ async function setup(script: Script, options: SetupOptions = {}) { start: (request: SubagentStartRequest) => startInProcessRun(request, {}), }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter, disposeProvider } } @@ -322,7 +322,7 @@ 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 eeab453e40..f503ecd1db 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -1,6 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -17,7 +18,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', 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 1b278c9748..89efb2b815 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'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) + const parent = ctx.agentLoop.create(SessionId('e2e-parent'), { provider: 'deepseek', 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 147b83dd9a..414c071d14 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -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 { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' @@ -29,7 +29,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter } } @@ -225,7 +225,6 @@ 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: { provider: 'mock', model: 'mock' }, @@ -242,7 +241,6 @@ 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: {}, }) @@ -302,7 +300,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' }) const controller = new AbortController() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'q' }], @@ -329,7 +327,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' }) const parentEffects = parent.ctx.fiber.getEffects().length const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) @@ -422,7 +420,6 @@ 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: { provider: 'mock', model: 'mock' }, }) @@ -445,7 +442,6 @@ 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: { provider: 'mock', model: 'mock' }, }) diff --git a/packages/subagent/subagent/package.json b/packages/subagent/subagent/package.json index 0b09033fd3..84d2c963d5 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.7" }, @@ -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.7" } diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 0d156ae725..00762cc413 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -34,7 +34,8 @@ 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, @@ -114,7 +115,7 @@ 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. */ @@ -122,7 +123,7 @@ 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 05bb40d575..f29eeda54e 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' /** @@ -132,8 +133,8 @@ export interface SubagentResult { * capability discovery; narrow their presence 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). */ - readonly id: AgentId + /** 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 * 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 90f84bfceb..7ba2a1508a 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -4,7 +4,7 @@ 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 AgentRegistry from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import TaskService from '@deepseek-ai/dsh-tasks' @@ -12,6 +12,7 @@ import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' import * as mock from '@deepseek-ai/dsh-subagent-mock' import * as tool from '../src/index.ts' import { runOutcome, settleRun } from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * Drives the REAL plugin body: mounts `dsh-tool-subagent` on a real @@ -24,7 +25,7 @@ import { runOutcome, settleRun } 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 = {}) { @@ -85,7 +86,7 @@ describe('dsh-tool-subagent', () => { // Schema omission is advertising, not enforcement: the arg validator // allows undeclared keys, so the opt-out must also hold in execute(). const ctx = await setup({ provider: 'mock', enableRunInBackground: false }) - const parent = { id: AgentId('agent-sess-off'), inject: () => {}, session: { header: { version: 0, id: 'sess-off', createdAt: 0 } } } as unknown as Agent + const parent = { id: SessionId('sess-off'), inject: () => {}, session: { header: { version: 0, id: 'sess-off', createdAt: 0 } } } as unknown as Agent const forced = await callSubagent(ctx, { description: 'd', prompt: 'p', run_in_background: true }, { agent: parent }) expect(forced.isError).toBe(true) @@ -156,7 +157,7 @@ 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 () => {}, }), @@ -183,7 +184,7 @@ 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 () => {}, } @@ -212,7 +213,7 @@ 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 () => {}, } @@ -339,7 +340,7 @@ 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(), }), @@ -361,7 +362,7 @@ 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(), }), @@ -392,7 +393,7 @@ describe('dsh-tool-subagent', () => { resolveResult({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('spy-child'), + id: SessionId('spy-child'), result, dispose: async () => {}, } @@ -484,7 +485,7 @@ 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 () => {}, } @@ -541,7 +542,7 @@ 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 () => {}, } @@ -570,7 +571,7 @@ 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 () => {}, } @@ -602,11 +603,12 @@ describe('dsh-tool-subagent background mode', () => { /** A live parent with a dedicated scope fiber for structural task cleanup. */ function ownerAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void = () => {}): Agent { const scopeFiber = ctx.plugin(() => {}) + const id = SessionId(sessionId) const agent = { - id: AgentId(`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 ctx.agents.register(agent) return agent @@ -736,7 +738,7 @@ describe('dsh-tool-subagent background mode', () => { inheritsParentContext: false, start: async (request) => { let settle!: (value: { output: { type: 'text'; text: string }[]; stopReason: 'aborted' }) => void - const id = AgentId(`hang-${++starts}`) + const id = SessionId(`hang-${++starts}`) const result = new Promise<{ output: { type: 'text'; text: string }[]; stopReason: 'aborted' }>((res) => { settle = res }) request.signal.addEventListener('abort', () => { cancels.push(typeof request.signal.reason === 'string' ? request.signal.reason : undefined) @@ -782,7 +784,7 @@ describe('dsh-tool-subagent background mode', () => { it('settleRun disposes the run before reporting, on both result paths', async () => { const order: string[] = [] const completed = await settleRun({ - id: AgentId('child-1'), + id: SessionId('child-1'), result: Promise.resolve({ output: [{ type: 'text' as const, text: 'ok' }], stopReason: 'completed' as const }), dispose() { order.push('dispose'); return Promise.resolve() }, }) @@ -793,7 +795,7 @@ describe('dsh-tool-subagent background mode', () => { // An infrastructure rejection still disposes and reports failed. let disposed = false const failed = await settleRun({ - id: AgentId('child-2'), + id: SessionId('child-2'), result: Promise.reject(new Error('transport gone')), dispose() { disposed = true; return Promise.resolve() }, }) @@ -801,14 +803,14 @@ describe('dsh-tool-subagent background mode', () => { expect(disposed).toBe(true) const disposeFailed = await settleRun({ - id: AgentId('child-3'), + id: SessionId('child-3'), result: Promise.resolve({ output: [], stopReason: 'completed' }), dispose: () => Promise.reject(new Error('reap failed')), }) expect(disposeFailed).toEqual({ status: 'failed', detail: 'dispose failed: Error: reap failed' }) const bothFailed = await settleRun({ - id: AgentId('child-4'), + id: SessionId('child-4'), result: Promise.reject(new Error('result failed')), dispose: () => Promise.reject(new Error('reap failed')), }) @@ -826,11 +828,12 @@ describe('background preflight failure (no orphaned child, by construction)', () await ctx.plugin(AgentRegistry) await ctx.plugin(TaskService) const scopeFiber = ctx.plugin(() => {}) + const id = SessionId('sess-p') const parent = { - id: AgentId('agent-sess-p'), + id, ctx: scopeFiber.ctx, inject: () => {}, - session: { header: { version: 0, id: 'sess-p', createdAt: 0 } }, + session: { id, header: { version: 0, id, createdAt: 0 } }, } as unknown as Agent ctx.agents.register(parent) @@ -842,7 +845,7 @@ describe('background preflight failure (no orphaned child, by construction)', () start: async () => { starts += 1 return { - id: AgentId('probe-child'), + id: SessionId('probe-child'), result: Promise.resolve({ output: [], stopReason: 'completed' as const }), dispose: () => Promise.resolve(), } diff --git a/packages/support/subagent-mock/package.json b/packages/support/subagent-mock/package.json index a4ed0a0c6e..c9d0982f55 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.7" }, @@ -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.5", "cordis": "^4.0.0-rc.7" diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts index 5032c92529..c2e94c521f 100644 --- a/packages/support/subagent-mock/src/index.ts +++ b/packages/support/subagent-mock/src/index.ts @@ -7,8 +7,8 @@ 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, @@ -54,7 +54,7 @@ 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 c9700a14b1..aec0fd7db1 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/tasks/tasks/src/index.ts b/packages/tasks/tasks/src/index.ts index e9c896c3a1..457f5473a3 100644 --- a/packages/tasks/tasks/src/index.ts +++ b/packages/tasks/tasks/src/index.ts @@ -151,9 +151,9 @@ export class TaskService extends Service { * @returns fresh snapshots. */ list(caller?: Agent): TaskSnapshot[] { - const session = caller?.session.header.id + const session = caller?.id return [...this.store.values()] - .filter(task => task.owner === undefined || task.owner.session.header.id === session) + .filter(task => task.owner === undefined || task.owner.id === session) .map(task => this.snapshot(task)) } @@ -317,14 +317,14 @@ export class TaskService extends Service { * open, and a no-agent caller can never match an owned one). */ private assertAccess(task: TrackedTask, caller?: Agent): void { - if (task.owner !== undefined && task.owner.session.header.id !== caller?.session.header.id) { + if (task.owner !== undefined && task.owner.id !== caller?.id) { throw new Error(`task ${task.id} belongs to another session`) } } /** Project a fresh read-only snapshot from the mutable record. */ private snapshot(task: TrackedTask): TaskSnapshot { - const ownerSession = task.owner?.session.header.id + const ownerSession = task.owner?.id return { id: task.id, kind: task.kind, diff --git a/packages/tasks/tasks/tests/tasks.spec.ts b/packages/tasks/tasks/tests/tasks.spec.ts index f21eb9c433..0d3eae8338 100644 --- a/packages/tasks/tasks/tests/tasks.spec.ts +++ b/packages/tasks/tasks/tests/tasks.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, expectTypeOf, it, vi } from 'vitest' import { Context } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import TaskService, { TaskId } from '@deepseek-ai/dsh-tasks' import type { TaskHooks, TaskKind, TaskOutcome, TaskSnapshot, TaskStart } from '@deepseek-ai/dsh-tasks' @@ -14,13 +14,13 @@ declare module '@deepseek-ai/dsh-tasks' { const agentScopeDisposers = new WeakMap Promise>() -function stubAgent(ctx: Context, rawId: string, rawSessionId = `${rawId}-session`): Agent { - const id = AgentId(rawId) +function stubAgent(ctx: Context, rawId: string): Agent { + const id = SessionId(rawId) const scopeFiber = ctx.plugin(() => {}) const agent = { id, options: {}, - session: new Session(SessionId(rawSessionId)), + session: new Session(id), status: 'idle' as const, ctx: scopeFiber.ctx, send() {}, @@ -453,11 +453,11 @@ describe('TaskService owner isolation', () => { it('rejects a stale owner instance after another agent reuses its id', async () => { const ctx = await harness() - const staleOwner = stubAgent(ctx, 'owner', 'stale-session') + const staleOwner = stubAgent(ctx, 'owner') const unregisterStale = ctx.agents.register(staleOwner) unregisterStale() - const currentOwner = stubAgent(ctx, 'owner', 'current-session') + const currentOwner = stubAgent(ctx, 'owner') ctx.agents.register(currentOwner) const current = producer({ owner: currentOwner }) ctx.tasks.start(current.spec) // Attach the current owner's cleanup first. @@ -467,7 +467,10 @@ describe('TaskService owner isolation', () => { expect(() => ctx.tasks.start({ ...stale.spec, run: staleRun })) .toThrow('is not the registered agent instance') expect(staleRun).not.toHaveBeenCalled() - expect(ctx.tasks.list(staleOwner)).toEqual([]) + // Access is keyed by the unified session id, so a reconnect carrying the + // same identity can observe the current task even though stale ownership + // registration is rejected by exact-instance validation. + expect(ctx.tasks.list(staleOwner)).toHaveLength(1) expect(ctx.tasks.list(currentOwner)).toHaveLength(1) current.settle({ status: 'completed' }) @@ -524,7 +527,7 @@ describe('TaskService owner cleanup', () => { it('does not let an old scope cleanup cancel a same-id/session replacement task', async () => { const ctx = await harness() - const oldOwner = stubAgent(ctx, 'owner', 'shared-session') + const oldOwner = stubAgent(ctx, 'owner') const detachOld = ctx.agents.register(oldOwner) const cancels: string[] = [] @@ -543,7 +546,7 @@ describe('TaskService owner cleanup', () => { start(oldOwner, 'old task') detachOld() - const replacement = stubAgent(ctx, 'owner', 'shared-session') + const replacement = stubAgent(ctx, 'owner') ctx.agents.register(replacement) const replacementId = start(replacement, 'replacement task') 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) diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 97c24a822e..e2be92f6cc 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -1,7 +1,6 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import type { SessionEvent } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' @@ -57,7 +56,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Plan recorded.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'plan a two-step task' }]) await waitForIdle(ctx, agent) @@ -85,7 +84,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo-2'), { provider: 'mock', 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 c2843cbcfe..2059bf13e8 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 e8fb326d9b..f08d5ae3f5 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -45,7 +45,6 @@ import { import type { ContentBlock, LlmCallConfig, LlmModelInfo, LlmProviderInfo } 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' // Side-effect type import: resolves `ctx.get('permission')` to the service. import type {} from '@deepseek-ai/dsh-permission' @@ -677,7 +676,6 @@ export function apply(ctx: Context, config: AcpConfig): void { const directory = modelDirectory(await readModelCatalog(), target.current) assertOpen() const handle = await agents.create({ - agentId: AgentId(sessionId), sessionId, meta: { cwd: params.cwd }, agentOptions: agentOptions(config), @@ -753,7 +751,6 @@ export function apply(ctx: Context, config: AcpConfig): void { assertOpen() const target: LlmTargetRef = { current: configuredTarget(), assembled: undefined } const handle = await agents.resume({ - agentId: AgentId(sessionId), resumeSessionId: sessionId, agentOptions: agentOptions(config), setup: (agentCtx) => { installTarget(agentCtx, target) }, 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 30faf9aafe..5cbdb6859b 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', () => { @@ -17,25 +16,29 @@ 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' }] }) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') - // Teardown must abort and await the loop: once it resolves the agent is settled, and the - // hanging prompt itself completes as cancelled rather than remaining pending. + // Dispose the whole context. The bridge's teardown must abort the agent and + // AWAIT whenIdle() — so right after dispose resolves, the agent is settled + // (not still running). Proves disposal waited, not just requested. await harness.ctx.fiber.dispose() expect(agent.status).not.toBe('running') + // The in-flight prompt settled (cancelled) rather than hanging forever. const res = await promptDone expect(res.stopReason).toBe('cancelled') }) it('after an ACP-only HMR dispose, a late session/new creates no orphan agent (closed guard)', async () => { - // Unload only the bridge while transport and shared services remain live. Its closed guard must - // reject late creation before an orphan agent can enter the registry. + // Dispose JUST the bridge's fiber (an HMR reload) while agents/agent-loop + // stay up and the transport is still live. A late session/new must hit the + // `closed` guard and reject — NOT create an agent the disposed bridge can no + // longer stream or settle. Verify the world: no agent appeared. const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const before = harness.ctx.agents.list().length @@ -47,21 +50,29 @@ describe('acp bridge — disposal & HMR safety', () => { }) it('an agent created through the bridge is unregistered when ONLY the bridge fiber is disposed', async () => { - // The traced service proxy binds loop registration to the caller (bridge) fiber. ACP-only - // disposal must therefore reclaim the agent even while agent-loop itself remains mounted. + // The factory (`ctx.agents.create`) is reached through the bridge's + // traceable service proxy, so `AgentLoop.start`'s `this.ctx.effect(...)` + // registration binds to the CALLER context — the bridge fiber — not the + // AgentLoop fiber. Disposing JUST the bridge fiber (an ACP-only HMR reload) + // must therefore reclaim the agent's registry entry, even though agents/ + // agent-loop stay up. This pins the fiber-ownership the bridge's teardown + // doc comment relies on; if a refactor rebinds the registration to the + // AgentLoop fiber, the agent would survive bridge dispose and this fails. 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() }) it('no agent is created by a session/new after the bridge has closed (closed guard)', async () => { - // Disconnect sets the closed guard and severs the RPC, so registry state—not the rejection - // shape—proves a late request did not create an undriveable agent. + // After teardown (here a client disconnect sets `closed`), a late + // `session/new` must NOT create an orphan agent the bridge can no longer + // drive/settle. The transport is gone so the RPC rejects; assert the world: + // no new agent appeared in the registry. const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const before = harness.ctx.agents.list().length @@ -73,43 +84,59 @@ describe('acp bridge — disposal & HMR safety', () => { }) it('a client disconnect mid-prompt disposes the session (no registered agent left)', async () => { - // Disconnect mid-stream must dispose, not merely idle, the owned agent; otherwise updates would - // be swallowed while a registered session survived without a client. + // The ACP transport closes (editor quits) while a turn runs. The bridge must + // settle the in-flight prompt cancelled and DISPOSE the agent (the session's + // per-agent AgentHandle teardown) rather than leaving an orphaned running — + // or even idled-but-still-registered — agent whose updates are swallowed. 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))! - // The transport will close before this hanging RPC settles. + 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(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') + // Sever the transport — the bridge's conn.closed teardown runs and drives the + // agent's AgentHandle dispose to quiescence on its OWN (before any dispose()). await harness.closeClientTransport() await agent.whenIdle() + // The agent's loop has stopped: status `disposed`. expect(agent.status).toBe('disposed') - // Await the same memoized bridge teardown without removing root services. It must finish the - // AgentHandle teardown and remove both registry records, not just stop the loop. + // Await the bridge teardown to completion WITHOUT tearing down the root + // agents/sessions services (so we can still query them). acpFiber.dispose() + // invokes the SAME memoized quiesce() the disconnect started and awaits its + // promise — which resolves only after every rec.dispose() (loop exit + + // session removal) has finished, closing the whenIdle()/owned.dispose() + // microtask race. The AgentHandle dispose has run: the agent is unregistered + // 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() }) it('a client disconnect racing fiber dispose both reach quiescence (shared teardown)', async () => { - // Transport close and fiber disposal can race. Both must await one memoized teardown; a guard - // based only on record removal could let the second caller return while the first still drains. + // conn.closed teardown and ctx.fiber.dispose() can fire near-simultaneously. + // They must share one teardown promise: dispose() must NOT return before the + // disconnect teardown's whenIdle() has settled (a `record === undefined`-only + // guard would let the second caller return early mid-teardown). 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') + // Fire both teardown paths without awaiting the first, then await both. const close = harness.closeClientTransport() const dispose = harness.ctx.fiber.dispose() await Promise.all([close, dispose]) + // After BOTH settle, the agent has fully drained (not still running). expect(agent.status).not.toBe('running') }) @@ -117,7 +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 @@ -129,18 +156,27 @@ describe('acp bridge — disposal & HMR safety', () => { }) it('the final turn closing events are persisted across an AgentHandle dispose (durability)', async () => { - // AgentHandle teardown stops and awaits the loop, flushes through still-attached store hooks, - // then detaches the session. Reloading verifies that order from durable state. + // The teardown-ORDER guarantee: a per-agent dispose must stop the loop, + // AWAIT its exit (so the loop's final `turn/end` + `session/flush` fire + // through the still-attached store observer → `session/event`), and only + // THEN remove its publication hooks and session entry. If the order were inverted + // (detach first), the closing events would never reach persistence. Drive a + // CLEAN turn to completion, dispose JUST the bridge, then re-load the + // persisted log from disk and assert the closing turn/end is on disk — the + // world, not the agent's self-report. const harness = await makeBridgeHarness({ storageDir, script: [textResponse('done')] }) 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. const reloaded = await harness.ctx.sessionPersistence.load(SessionId(sessionId)) expect(reloaded.events.length).toBe(liveEvents) const last = reloaded.events.at(-1)! @@ -149,20 +185,35 @@ describe('acp bridge — disposal & HMR safety', () => { }) it('a turn aborted BY the dispose still flushes its closing turn/end to disk (durability, mid-turn)', async () => { - // Here disposal itself makes the loop append `turn/end {disposed}` and flush. Reload must find - // that real closer, not crash recovery's synthetic `interrupted`, proving detach ran last. + // The teardown-order contract only earns its keep when the closing events are + // produced BY the dispose itself. Here the model stream HANGS, so the turn is + // still open when teardown runs: the composite agent effect stops the loop, + // the loop unwinds and appends `turn/end {disposed}` + runs its final + // `session/flush` — all while the store-owned publication hooks are still attached (the session + // detach is the LAST disposer in the same effect's LIFO chain) — and only + // THEN is the session detached. If the order were inverted (or the session + // were a racing SIBLING effect), the abort-produced `turn/end` would never + // reach disk and a re-load would instead show crash-recovery's synthetic + // `interrupted` closer. Re-load from disk and assert the REAL `disposed` + // reason landed — proving the loop's own closing event was captured, not a + // recovered substitute. 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') + // The turn is OPEN in the log (turn/start appended, no turn/end yet). const openTurnEnds = agent.session.events.filter(e => e.type === 'turn/end').length + // 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. const reloaded = await harness.ctx.sessionPersistence.load(SessionId(sessionId)) const persistedTurnEnds = reloaded.events.filter(e => e.type === 'turn/end') expect(persistedTurnEnds.length).toBe(openTurnEnds + 1) @@ -171,55 +222,71 @@ describe('acp bridge — disposal & HMR safety', () => { }) it('per-session AgentHandle dispose leaves sibling agents untouched', async () => { - // A per-session handle owns exactly one agent and session. Dispose A and assert B remains fully - // published, which guards against context-wide teardown. + // The factory returns a per-agent AgentHandle whose dispose() tears down + // EXACTLY that agent + its session — RFC 011 isolation. Create two agents + // directly through the registry factory (the same path the ACP bridge uses), + // dispose one handle, and assert the other survives, registered and + // 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: { provider: 'mock', model: 'mock' }, + sessionId: SessionId('sib-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) const handleB = await harness.ctx.agents.create({ - agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { provider: 'mock', model: 'mock' }, + sessionId: SessionId('sib-b'), agentOptions: { provider: 'mock', 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() - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBeUndefined() + // A is gone — unregistered AND its session removed from the store. + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('sib-a'))).toBeUndefined() expect(handleA.agent.status).toBe('disposed') - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + // B is wholly unaffected. + 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() }) it('a throwing agent/disposed listener does not prevent session removal (composite-effect containment)', async () => { - // Composite disposers run in sequence. A throwing `agent/disposed` listener must be contained or - // it would skip later session detach, leaking publication hooks and creating a durability hole. + // The AgentHandle teardown folds session-detach, register, and loop-stop + // into ONE composite effect whose disposers run as a `.then()` chain. The + // register disposer emits `agent/disposed`; if a listener throws and the + // emit is UNCONTAINED, the rejected chain skips the LATER session-detach + // disposer — stranding the session in the store with its publication hooks attached (a + // leak AND a durability hole, since the new design relies on detach + // running). The emit must be contained. Register a throwing listener, drive + // a clean turn, dispose, and assert the session was STILL removed. 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: { provider: 'mock', model: 'mock' }, + sessionId: SessionId('guard-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) handle.agent.send([{ type: 'text', text: 'go' }]) await handle.agent.whenIdle() expect(harness.ctx.sessions.get(SessionId('guard-a'))).toBeDefined() + // 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() }) it('concurrent AgentHandle dispose() calls all await the SAME teardown (memoized)', async () => { - // The Cordis effect disposer is single-shot and would let a second call return after its epoch - // clears. AgentHandle must memoize the whole async teardown so every caller awaits quiescence. + // The handle's dispose() must memoize: the underlying cordis effect disposer + // is single-shot, so a second dispose() while the first is mid-teardown would + // otherwise resolve IMMEDIATELY (effect epoch already cleared) — before the + // first call's await agent.done + final flush finished. Every caller must + // 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: { provider: 'mock', model: 'mock' }, + sessionId: SessionId('conc-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) - // A hanging turn makes disposal produce a final flush; gate it so the second call arrives while - // teardown is observably in flight. + // 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 + // teardown observably in-flight. handle.agent.send([{ type: 'text', text: 'go' }]) await new Promise(r => setTimeout(r, 30)) expect(handle.agent.status).toBe('running') @@ -227,21 +294,25 @@ describe('acp bridge — disposal & HMR safety', () => { const flushGate = new Promise((resolve) => { releaseFlush = resolve }) harness.ctx.on('session/flush', () => flushGate) + // First dispose enters teardown (aborts the hanging step) and blocks in the + // gated final flush. const first = handle.dispose() let firstSettled = false void first.then(() => { firstSettled = true }) await new Promise(r => setTimeout(r, 20)) expect(firstSettled).toBe(false) + // Second dispose MUST await the same in-flight teardown, not resolve early. const second = handle.dispose() let secondSettled = false void second.then(() => { secondSettled = true }) await new Promise(r => setTimeout(r, 20)) expect(secondSettled).toBe(false) // memoized: still pending with the first + // 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 de3a7a6f03..35dd54a634 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: { provider: 'mock', model: 'mock' } }) + const { agent: foreign } = await harness.ctx.agents.create({ sessionId: SessionId('foreign-session'), agentOptions: { provider: 'mock', 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 f57767fb38..b8de5b8557 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. */ @@ -185,7 +184,7 @@ 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 () => { @@ -205,11 +204,11 @@ 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 () => { @@ -243,7 +242,7 @@ 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 78591ffa76..15c2415449 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 { @@ -274,7 +274,7 @@ 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. @@ -328,7 +328,7 @@ 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() const turnStarts = agent.session.events.filter(e => e.type === 'turn/start').length expect(turnStarts).toBeLessThanOrEqual(1) diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 2b3646c731..31acae532f 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -11,7 +11,6 @@ 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' @@ -246,7 +245,6 @@ 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: { provider: this.provider, model: this.model }, diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 22f01178ec..47269d2a72 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-spine-demo' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' @@ -136,7 +137,6 @@ 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: { provider: 'deepseek', model: 'dsagent-model' }, @@ -171,8 +171,8 @@ 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 }, @@ -264,20 +264,18 @@ 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: { provider: 'deepseek', model: 'deepseek' }, }) const handle = await ctx.agents.create({ - agentId: AgentId('child-agent'), sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { provider: 'deepseek', 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' }], }) @@ -286,7 +284,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'spawn', - agentId: 'child-agent', + agentId: 'child-session', parentSessionId: 'main', childSessionId: 'child-session', status: 'ok', @@ -312,19 +310,16 @@ 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: { provider: 'deepseek', 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: { provider: 'deepseek', model: 'deepseek' }, }) failedHandle = await ctx.agents.create({ - agentId: AgentId('failed-child-agent'), sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { provider: 'deepseek', model: 'deepseek' }, @@ -334,18 +329,18 @@ 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', }) @@ -353,7 +348,7 @@ 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', @@ -365,7 +360,7 @@ 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/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 3b00dc6625..e1bffdf171 100644 --- a/packages/ui/stdio/package.json +++ b/packages/ui/stdio/package.json @@ -23,10 +23,16 @@ "license": "BSD-3-Clause", "peerDependencies": { "@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-session": "^0.0.1", "@deepseek-ai/dsh-user-interaction": "^0.0.1", - "cordis": "^4.0.0-rc.6" + "cordis": "^4.0.0-rc.7" + }, + "peerDependenciesMeta": { + "@deepseek-ai/dsh-agent-loop": { + "optional": true + } }, "dependencies": { "schemastery": "^3.18.0" @@ -34,9 +40,10 @@ "devDependencies": { "@cordisjs/plugin-loader": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-user-interaction": "workspace:^", - "cordis": "^4.0.0-rc.6" + "cordis": "^4.0.0-rc.7" } } diff --git a/packages/ui/stdio/src/index.ts b/packages/ui/stdio/src/index.ts index 1e665381ce..6f73d948bf 100644 --- a/packages/ui/stdio/src/index.ts +++ b/packages/ui/stdio/src/index.ts @@ -1,7 +1,8 @@ /** * The stdio app's readline UI: reads lines from stdin into `agent.send()` or - * `steer()`, renders the durable event stream to stdout, and exits piped input - * only after submitted work reaches idle. + * `steer()`, renders the durable event stream to stdout, buffers startup input + * for one exact agent/session identity, and exits piped input only after + * submitted work reaches idle. * * This package is the independently composable stdio front door. It establishes * the terminal channel and drives an agent created or resumed by app or @@ -13,7 +14,9 @@ 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 type {} from '@deepseek-ai/dsh-agent-loop' +import { SessionId } from '@deepseek-ai/dsh-session' import { UserInteractionError, type AskUserQuestionAnswer, @@ -30,13 +33,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - /** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */ - agent?: string + /** Exact shared agent/session identity stdin drives. Defaults to `'main'`. */ + sessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - agent: z.string().default('main'), + sessionId: z.string().default('main'), }) /** @@ -59,6 +62,15 @@ 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 @@ -74,10 +86,15 @@ type OptionSelection = | { kind: 'invalid' } /** - * Register stdio chat against an injectable I/O runtime. - * @param ctx - agent and event context. - * @param config - plugin config, defaulted for direct callers. - * @param runtime - line source, render sink, and exit hook. + * The plugin body, parameterized over its I/O runtime. `apply` is the thin + * production wrapper that binds the real `process` streams; tests call this + * directly with fakes. Returns nothing — all registration is via `ctx.on`/ + * `ctx.effect`, so fiber disposal tears every listener and the readline + * interface down. + * @param ctx - the context supplying the `agents` service and the event feeds. + * @param config - the plugin config; defaults are re-applied here for direct + * callers that bypass Loader validation. + * @param runtime - the process-I/O seam (line source, render sink, exit hook). */ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRuntime): void { // Default here too (not just via schemastery's `.default()`): this helper is @@ -85,18 +102,22 @@ 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 sessionId = SessionId(config.sessionId ?? 'main') const { input, output, exit } = runtime - // Session ids need not equal agent ids. Seed existing agents before listening - // so a pre-created or HMR-surviving agent still gets its short render label. - 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) }) + // 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 === sessionId && ctx.agents.roots().includes(agent) + let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === sessionId) - // Render the canonical append order from session/event so reasoning state is - // deterministic across chunks and boundaries; there are no agent/* mirrors. + // Transcript rendering off the durable `session/event` feed — the assistant + // token stream, turn/step boundaries, tool activity, and todos all come from + // the one canonical stream (no agent/* mirrors). A single listener over the + // append order keeps `inReasoning` transitions deterministic across chunk and + // boundary events. let inReasoning = false ctx.on('session/event', (session, event) => { if (event.type === 'assistant/chunk') { @@ -112,7 +133,7 @@ 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') @@ -138,10 +159,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt }) ctx.effect(() => { - const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) - // On piped EOF, exit immediately if no work was submitted. Otherwise wait - // for a real running state followed by idle: sends do not synchronously mark - // running, and several queued lines may share one turn. + // 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 + // for. (Gating on an observed 'running' here would hang forever.) + // - If work WAS submitted, exit the next time the agent settles to idle + // AFTER having run. Two subtleties this handles: the loop batches + // several queued messages into ONE turn (one idle), so we don't count + // sends; and agent.send() does NOT synchronously flip status to + // 'running', so requiring an observed 'running' first (`sawRunning`) + // avoids exiting in the gap before the turn starts and dropping work. let stdinClosed = false let disposed = false let submittedWork = false @@ -149,6 +176,38 @@ 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 + let failedStartup: { error: unknown } | undefined + + 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 + failedStartup = undefined + }) + 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 @@ -156,19 +215,33 @@ 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 final output flush; track the timer so re-entry coalesces and HMR - // disposal can cancel it before it exits the replacement process. + // Let any final output flush, then exit. The handle is tracked so the + // disposer can cancel it — a dispose within the flush window must not let + // the process exit out from under HMR. Re-entrant `maybeExit` calls (e.g. + // repeated idle signals) coalesce onto the one pending timer. if (exitTimer !== undefined) { return // exit already scheduled — coalesce re-entrant calls } exitTimer = setTimeout(() => { exit(0) }, 200) } + const disposeStartupFailedListener = ctx.on('agent-loop/config-start-failed', (failedSessionId, error) => { + if (failedSessionId !== 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)): ${renderThrown(error)}`) + } + maybeExit() + }) + 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() }) @@ -321,17 +394,25 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return - const agent = ctx.agents.get(agentId) - if (!agent) { - ctx.logger.error('ui-stdio: agent "%s" is not running', agentId) + if (failedStartup !== undefined) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${renderThrown(failedStartup.error)}`) return } - submittedWork = true - if (agent.status === 'running') { - agent.steer([{ type: 'text', text }]) - } else { - agent.send([{ type: 'text', text }]) + const agent = target + 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 } + submit(agent, text) }) reader.on('close', () => { // Fires for BOTH stdin EOF and plugin disposal (reader.close() below); @@ -347,31 +428,25 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposePendingQuestions() disposeUserInteractionProvider() disposeStatusListener() + disposeCreatedListener() + disposeSessionStartListener() + disposeDisposedListener() + disposeStartupFailedListener() reader.close() } }, 'ui-stdio') } /** - * Open the terminal channel once its configured agent exists. Generated stdio - * projects boot the Cordis tree first and create or resume the agent from - * developer code immediately afterward, so stdin must remain untouched until - * the matching `agent/created` notification arrives. + * Open the terminal channel for one exact identity. The chat registers before + * that agent necessarily exists so it can buffer startup input and observe a + * config-start failure instead of leaving piped stdin hanging. * @param ctx - the context supplying the agent registry and event stream. * @param config - presentation and target-agent configuration. * @param runtime - process-I/O seam. */ export function mountStdio(ctx: Context, config: Config, runtime: StdioRuntime): void { - const agentId = AgentId(config.agent ?? 'main') - if (ctx.agents.get(agentId) !== undefined) { - createStdioChat(ctx, config, runtime) - return - } - const dispose = ctx.on('agent/created', (agent) => { - if (agent.id !== agentId) return - dispose() - createStdioChat(ctx, config, runtime) - }) + createStdioChat(ctx, config, runtime) } /** diff --git a/packages/ui/stdio/tests/readline.spec.ts b/packages/ui/stdio/tests/readline.spec.ts index 638e98bf59..6a97eab06a 100644 --- a/packages/ui/stdio/tests/readline.spec.ts +++ b/packages/ui/stdio/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 label map 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/tests/stdio.spec.ts b/packages/ui/stdio/tests/stdio.spec.ts index 7bb6a6f245..a3069462ff 100644 --- a/packages/ui/stdio/tests/stdio.spec.ts +++ b/packages/ui/stdio/tests/stdio.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, mountStdio, type Config, type StdioRuntime } from '../src/index.ts' @@ -57,17 +57,23 @@ 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 } +/** 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(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 +81,11 @@ 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', 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() @@ -94,7 +104,7 @@ function flushExit(): Promise { } describe('mountStdio readiness', () => { - it('leaves stdin untouched until the configured agent is created', async () => { + it('opens before the configured agent is created so startup input can queue', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) @@ -103,9 +113,9 @@ describe('mountStdio readiness', () => { mountStdio(inner, CONFIG, runtime) }, { inject: ['agents', 'userInteraction'] })) - expect(out.text()).toBe('') + expect(out.text()).toBe('hi there\n> ') ctx.agents.register(makeAgent('other')) - expect(out.text()).toBe('') + expect(out.text()).toBe('hi there\n> ') ctx.agents.register(makeAgent('main')) expect(out.text()).toBe('hi there\n> ') await fiber.dispose() @@ -125,7 +135,7 @@ describe('mountStdio readiness', () => { await fiber.dispose() }) - it('waits for main when no target agent is configured', async () => { + it('opens for the default main identity when no target is configured', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) @@ -134,8 +144,9 @@ describe('mountStdio readiness', () => { mountStdio(inner, { welcome: 'ready' }, runtime) }, { inject: ['agents', 'userInteraction'] })) + expect(out.text()).toBe('ready\n> ') ctx.agents.register(makeAgent('other')) - expect(out.text()).toBe('') + expect(out.text()).toBe('ready\n> ') ctx.agents.register(makeAgent('main')) expect(out.text()).toBe('ready\n> ') await fiber.dispose() @@ -148,12 +159,11 @@ 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 () => { @@ -205,9 +215,8 @@ 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. - ctx.emit('agent/created', agent) - const session = makeSession('main') + 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' } }, } as SessionEvent) @@ -218,35 +227,59 @@ 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 () => { - // 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()` preserves the `[main turn N]` label instead - // of falling back to the raw session id. + 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 preserves the terminal's fixed `[main turn N]` label. const ctx = new Context() 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) => { 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] ') }) + 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([]) + + ctx.emit('agent/session-start', resumed, 'resume') + await new Promise(resolve => setImmediate(resolve)) + + expect(unrelated.sent).toEqual([]) + 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') @@ -257,17 +290,63 @@ 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'), { + 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, { 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('main') + 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' } }, + } as SessionEvent) + expect(out.text()).toContain('[main turn 1] ') + }) + + 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) + 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(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' }]]) + }) + + 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 = registerReady(ctx, 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 () => { @@ -683,7 +762,7 @@ 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' }]]) @@ -693,7 +772,7 @@ 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' }]]) @@ -709,22 +788,57 @@ 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: agent "%s" is not running', 'main') + 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 agent named in config, not a hardcoded id', async () => { - const { ctx, input } = await setup({ welcome: 'w', agent: 'worker' }) + 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 = 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)): ', + ) + }) + + 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') - ctx.agents.register(agent) + registerReady(ctx, agent, 'resume') input.feed('hi') await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) }) + }) describe('createStdioChat EOF exit', () => { @@ -738,7 +852,7 @@ 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() @@ -753,10 +867,50 @@ 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('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'), unrenderableFailure()) + await flushExit() + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', + ) + 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 @@ -774,7 +928,7 @@ 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() @@ -788,7 +942,7 @@ 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') @@ -837,7 +991,7 @@ 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() diff --git a/packages/ui/stdio/tsconfig.json b/packages/ui/stdio/tsconfig.json index 00cb815a75..e0c578ed32 100644 --- a/packages/ui/stdio/tsconfig.json +++ b/packages/ui/stdio/tsconfig.json @@ -17,6 +17,9 @@ { "path": "../../core/agent" }, + { + "path": "../../core/agent-loop" + }, { "path": "../../core/session" }, diff --git a/packages/util/brand/README.md b/packages/util/brand/README.md index 46e6c1ff98..e292f0bd26 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. Comparison, ## Policy: brand ids that cross package boundaries -A package brands the ids it owns — `CallId` in `dsh-llm`, `SessionId` in `dsh-session`, `AgentId` in `dsh-agent`, and `TaskId` in `dsh-tasks`. Brand cross-package ids that could plausibly be confused; not every string needs one. +A package brands the ids it owns — `CallId` in `dsh-llm`, the shared agent/session `SessionId` in `dsh-session`, and `TaskId` in `dsh-tasks`. Brand cross-package ids that could plausibly be confused; not every string needs one. This package owns only the primitive. Keeping it dependency-free lets `dsh-tasks`, for example, brand `TaskId` without importing an unrelated capability package merely to reach `Branded`. diff --git a/packages/util/brand/src/index.ts b/packages/util/brand/src/index.ts index 0c669e2416..c95cfd6445 100644 --- a/packages/util/brand/src/index.ts +++ b/packages/util/brand/src/index.ts @@ -4,13 +4,13 @@ * 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, and + * correlation), the shared agent/session `SessionId` in dsh-session, and * `TaskId` in dsh-tasks. 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 diff --git a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts index 5caffca5ac..08bc8171c3 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 } } @@ -232,7 +232,7 @@ 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 b5dbed1744..d82eae699d 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -13,8 +13,8 @@ */ 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' @@ -295,7 +295,7 @@ 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 25aa76cf48..320a5322c7 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -30,7 +30,7 @@ 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'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter } } @@ -66,7 +66,7 @@ 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 d49633636d..74d42f739b 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: { provider: 'deepseek', 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 dffb5c3f9d..5905161e6a 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -3,7 +3,6 @@ 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' @@ -11,10 +10,11 @@ import type { WorkflowMeta, WorkflowResult, WorkflowResultInfo, WorkflowRunInfo import * as workerEngineModule from '../src/index.ts' import WorkerWorkflowEngine, { type Config } from '../src/index.ts' import { HostToWorkerType, WorkerToHostType } from '../src/protocol.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 } // Allow cold worker startup on contended CI runners. @@ -104,7 +104,7 @@ 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 @@ -361,7 +361,7 @@ 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(), }), @@ -395,7 +395,7 @@ 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(), }) @@ -418,7 +418,7 @@ 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') }, @@ -439,7 +439,7 @@ 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 @@ -766,7 +766,7 @@ 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(), } @@ -1087,7 +1087,7 @@ 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 @@ -1123,7 +1123,7 @@ 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/package.json b/packages/workflow/workflow/package.json index 696955db4f..476866382a 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.7" }, "devDependencies": { diff --git a/packages/workflow/workflow/src/types.ts b/packages/workflow/workflow/src/types.ts index 21d8b4a4fb..faef18aeb0 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'> @@ -141,7 +142,7 @@ 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. */ diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 9810a9a61e..d04c4d04dd 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -762,6 +762,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-loop': + specifier: workspace:^ + version: link:../../core/agent-loop '@deepseek-ai/dsh-agent-spine-demo': specifier: workspace:^ version: link:../agent-spine-demo @@ -1444,6 +1447,9 @@ 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 @@ -1472,6 +1478,9 @@ importers: '@deepseek-ai/dsh-loader-smoke': specifier: workspace:^ version: link:../../support/loader-smoke + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../subagent @@ -1754,6 +1763,9 @@ 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 @@ -2011,6 +2023,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-loop': + specifier: workspace:^ + version: link:../../core/agent-loop '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm @@ -2021,7 +2036,7 @@ importers: specifier: workspace:^ version: link:../user-interaction cordis: - specifier: ^4.0.0-rc.6 + specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@vendor+loader) packages/ui/tool-ask-user: diff --git a/website/zh-CN/api/harness/agent-loop.md b/website/zh-CN/api/harness/agent-loop.md index 413cc4f7c8..11582fb226 100644 --- a/website/zh-CN/api/harness/agent-loop.md +++ b/website/zh-CN/api/harness/agent-loop.md @@ -6,23 +6,23 @@ Concrete ReactLoopAgent factory and driver service. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L352) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L408) ### ctx.agentLoop.create(id, options?, meta?) ```ts website-api -create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent +create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent ``` -Create an agent on a fresh per-run session, owned by the accessing fiber. Constructor-driven config calls use the loop fiber itself. +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. -- `id` — agent registry id. +- `id` — shared agent/session identity. - `options` — concrete loop options. - `meta` — optional fresh-session workspace metadata. **Returns** the published running agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L412) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L543) ### ctx.agentLoop.createAgent(ownerCtx, options) @@ -37,7 +37,7 @@ Create an owned agent on a caller-supplied session id. **Returns** the published handle. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L435) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L565) ### ctx.agentLoop.resume(ownerCtx, options) @@ -52,4 +52,4 @@ Resume an owned agent from the configured persistence service. **Returns** the published handle. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L467) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L597) diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md index ef20c585d7..c6491134ec 100644 --- a/website/zh-CN/api/harness/agents.md +++ b/website/zh-CN/api/harness/agents.md @@ -6,7 +6,7 @@ Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L133) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L201) ### ctx.agents.setFactory(factory) @@ -14,13 +14,13 @@ Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator setFactory(factory: AgentFactory): () => void ``` -Register the effect-scoped creation factory, rejecting a duplicate. Service factories are retraced through each create/resume caller for ownership. +Register the agent-creation factory (the loop calls this on construction, effect-scoped). A traced Cordis service is canonicalized to its concrete target; each create/resume call is then traced through that caller's context so ownership follows the caller without stacking proxy layers. Throws if a factory is already registered. Returns the disposer; on dispose the factory slot is cleared. - `factory` — the loop-owned factory `create`/`resume` delegate to. -**Returns** the exact Cordis effect disposer. +**Returns** the disposer that clears the factory slot. The exact Cordis effect disposer (single-shot): composite (generator) effects may yield it directly — exact identity nests the teardown in order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L149) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L228) ### ctx.agents.create(options) @@ -28,13 +28,13 @@ Register the effect-scoped creation factory, rejecting a duplicate. Service fact async create(options: CreateAgentOptions): Promise ``` -Create and publish an owned agent and session through the active factory. Rejects if no factory is registered or creation, setup, or publication fails. +Create and publish a new agent through the registered factory. Distinct from register (which records an already-constructed agent): this constructs the agent and its session. Rejects if no factory is registered or creation/setup fails. The resolved AgentHandle lets the owner tear down exactly this agent. -- `options` — agent id, session id/seed/metadata, and agent options. +- `options` — shared identity, session seed/metadata, and agent options. **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L174) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L261) ### ctx.agents.resume(options) @@ -48,7 +48,7 @@ Load a persisted session and resume an agent on it through the registered factor **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L190) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L280) ### ctx.agents.register(agent) @@ -56,27 +56,28 @@ Load a persisted session and resume an agent on it through the registered factor register(agent: Agent): () => void ``` -Register a live agent in the calling effect scope, with scope-filtered creation and disposal events. Duplicate ids throw. +Register a live agent. Throws if an agent with the same id is already registered. Emits `agent/created` on registration and `agent/disposed` when the calling fiber is disposed — both with the agent's scope carrier (`scopeTarget(agent, agent)`): the subject is the agent in hand, so the emits are scope-filtered regardless of which context invoked `register` (calling through `agent.ctx` scopes EFFECTS; dispatch scoping always requires passing the carrier). Returns the disposer. - `agent` — the already-constructed agent to record in the store. -**Returns** the exact Cordis effect disposer for nested teardown ordering. +**Returns** the EXACT Cordis effect disposer (single-shot; a repeat call returns undefined without awaiting an in-flight teardown). Exact identity is load-bearing: a composite (generator) effect that owns a teardown ORDER — the agent factory's lifecycle chain — must yield THIS function so Cordis nests the unregistration at that yield position; yielding a wrapper would leave it disposing as a concurrent sibling on owner unload, unregistering the agent (and emitting `agent/disposed`) while its final turn is still draining. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L204) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L306) -### ctx.agents.enter(agent) +### ctx.agents.enter(agent, owner) ```ts website-api -enter(agent: Agent): () => void +enter(agent: Agent, owner: Agent | undefined): () => void ``` -Insert an unpublished agent for an ordered factory transaction. +Insert an already-constructed agent without announcing it. This is the advanced ordered-lifecycle primitive used by the async agent factory: it first completes setup while the agent is unpublished, then assigns the returned detach closure into its pre-installed composite teardown before calling announce. Ordinary callers use register. - `agent` — the prepared, unpublished agent. +- `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 the paired disposal edge; detachment during creation dispatch is deferred. +**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. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L219) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L330) ### ctx.agents.announce(agent) @@ -88,21 +89,21 @@ Announce an agent previously inserted with enter. - `agent` — the live inserted agent to announce. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L286) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L405) ### ctx.agents.get(id) ```ts website-api -get(id: AgentId): Agent | undefined +get(id: SessionId): Agent | undefined ``` Look up a live agent. -- `id` — the agent id to look up. +- `id` — the shared agent/session id to look up. **Returns** the agent, or undefined when no live agent has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L320) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L439) ### ctx.agents.list() @@ -114,4 +115,16 @@ All live agents, in registration order. **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L328) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L447) + +### ctx.agents.roots() + +```ts website-api +roots(): 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. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L457) diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index 5f99cb4f32..d719e023c8 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -2,7 +2,7 @@ # Harness events -Every event the harness packages declare on the cordis event bus (39 total), grouped by scope. The **mode** is the dispatch semantics (`emit` fire-and-forget, `parallel` awaited, `serial` first-bail, `waterfall` veto-chain — a waterfall listener MUST call `next()` to delegate). +Every event the harness packages declare on the cordis event bus (40 total), grouped by scope. The **mode** is the dispatch semantics (`emit` fire-and-forget, `parallel` awaited, `serial` first-bail, `waterfall` veto-chain — a waterfall listener MUST call `next()` to delegate). ## agent/* @@ -18,7 +18,7 @@ A fully configured agent and live session were published. Setup is composition-o - `agent` — the newly registered agent with its live session and completed setup. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L154) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L141) ### agent/disposed @@ -32,7 +32,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef - `agent` — the exact agent removed from the registry. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L163) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L150) ### agent/error @@ -49,7 +49,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w - `step` — the step at which the failure surfaced. - `error` — the failure, verbatim. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L298) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L285) ### agent/pre-step @@ -68,7 +68,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and - `sessionPrefix` — the frozen request prefix. - `signal` — the turn abort signal. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L217) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L204) ### agent/prompt-submit @@ -84,7 +84,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca - `content` — the drained message's blocks, as queued. - `source` — the message's resolved source. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L227) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L214) ### agent/queued @@ -100,7 +100,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already - `content` — the accepted content blocks retained by the inbox. - `info` — the accepted source plus whether it entered as steering. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L182) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L169) ### agent/request @@ -117,7 +117,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha - `step` — the step whose request this is. - `config` — the config the loop would use (frozen); return a replacement to switch. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L239) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L226) ### agent/session-prefix @@ -133,7 +133,7 @@ Compose request-only messages placed before derived history. The frozen result i - `prefix` — the frozen seed; return an extended replacement. - `signal` — aborts composition when the step is torn down. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L254) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L241) ### agent/session-start @@ -148,7 +148,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to - `agent` — the agent whose session lifecycle began. - `source` — why the session started (fresh startup, resume, …). Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L195) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L182) ### agent/status @@ -163,7 +163,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no - `agent` — the agent whose status flipped. - `status` — the status just entered (the transition's destination). Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L172) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L159) ### agent/step-result @@ -180,7 +180,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va - `step` — the step that produced the message. - `message` — the assistant message as assembled from the stream. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L265) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L252) ### agent/turn-continuation @@ -196,7 +196,7 @@ Override whether the turn continues. The default continues after tool calls or s - `turn` — the turn being continued or stopped. - `defaultDecision` — what the loop would do absent an override. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L275) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L262) ### agent/turn-stop @@ -211,7 +211,24 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a - `agent` — the agent whose composed continuation outcome may be stopped. - `turn` — the turn at its terminal-stop checkpoint. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L285) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L272) + +## agent-loop/* + +### agent-loop/config-start-failed + +**Mode:** `emit` + +```ts website-api +'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void +``` + +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. + +- `sessionId` — exact shared agent/session identity that failed startup. +- `error` — persistence, setup, or publication failure. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L363) ## approval/* @@ -366,7 +383,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c - `info` — the run identity and terminal outcome. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L108) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L109) ### subagent/provider-added @@ -380,7 +397,7 @@ A provider became resolvable in the registry. - `provider` — the registered provider. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L82) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L83) ### subagent/provider-removed @@ -394,7 +411,7 @@ A provider left the registry. Accepted runs remain holder-owned. - `name` — the provider name that no longer resolves. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L88) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L89) ### subagent/start @@ -408,7 +425,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( - `info` — the provider and ready child identity. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L99) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L100) ## system-prompt/* diff --git a/website/zh-CN/api/harness/sessions.md b/website/zh-CN/api/harness/sessions.md index e5c8997c49..e39006dd88 100644 --- a/website/zh-CN/api/harness/sessions.md +++ b/website/zh-CN/api/harness/sessions.md @@ -7,7 +7,7 @@ In-memory session store (`ctx.sessions`). Persistence is intentionally not implemented here — persistence plugins subscribe to `session/event` and flush on `session/flush` / dispose. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L580) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L585) ### ctx.sessions.create(id?, options?) @@ -23,7 +23,7 @@ For an agent whose session must be torn down IN ORDER with its loop (so the loop **Returns** the live session, already entered and announced. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L609) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L614) ### ctx.sessions.prepare(id?, options?) @@ -38,7 +38,7 @@ Build a session WITHOUT entering it into the store — validate the id/cwd and c **Returns** the constructed session, NOT yet in the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L638) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L643) ### ctx.sessions.enter(session) @@ -53,7 +53,7 @@ Re-checks the id for a duplicate: `prepare` and `enter` are public cross-package **Returns** the detach disposer (publication hooks + store removal). When called from a synchronous `session/created` listener, removal and disposal wait until that creation dispatch unwinds. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L682) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L687) ### ctx.sessions.announce(session) @@ -65,7 +65,7 @@ Emit `session/created` exactly once for an entered session (with the carrier ent - `session` — the entered session to announce to listeners. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L737) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L742) ### ctx.sessions.flush(session) @@ -79,7 +79,7 @@ Dispatch the awaited `session/flush` durability checkpoint for `session`, with t **Returns** resolves when every flush listener has settled; after all settle, rejects with the first registered listener failure if any listener failed. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L789) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L794) ### ctx.sessions.get(id) @@ -93,7 +93,7 @@ Look up a live session. **Returns** the session, or undefined when no live session has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L821) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L826) ### ctx.sessions.list() @@ -105,7 +105,7 @@ All live sessions, in creation order. **Returns** a fresh array; mutating it does not affect the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L829) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L834) ### ctx.sessions.fork(source, boundary?, childSessionId?) @@ -121,4 +121,4 @@ Create a live child session from a turn-enclosed prefix of a live source. `bound **Returns** The created live child session. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L846) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L851) diff --git a/website/zh-CN/api/harness/subagents.md b/website/zh-CN/api/harness/subagents.md index e1fb492723..54fe5aa76e 100644 --- a/website/zh-CN/api/harness/subagents.md +++ b/website/zh-CN/api/harness/subagents.md @@ -6,7 +6,7 @@ Named provider registry and capability-checked start surface. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L141) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L142) ### ctx.subagents.registerProvider(provider) @@ -20,7 +20,7 @@ Register a provider under its name. Registration is effect-scoped and HMR safe; **Returns** the exact Cordis effect disposer. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L155) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L156) ### ctx.subagents.getProvider(name) @@ -34,7 +34,7 @@ Look up a provider by name. **Returns** the provider, or undefined when absent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L178) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L179) ### ctx.subagents.list() @@ -46,7 +46,7 @@ List registered provider names in insertion order. **Returns** the registered names. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L186) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L187) ### ctx.subagents.start(name, request) @@ -61,4 +61,4 @@ Establish a ready child on the named provider. Capability and semantic checks ru **Returns** the ready holder-owned run. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L199) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L200)