refactor(core): fold initiator scope into agents

This commit is contained in:
Tianyi Cui
2026-07-19 13:30:45 +08:00
parent 536cb6f985
commit c23214be56
79 changed files with 1883 additions and 1003 deletions

View File

@@ -16,8 +16,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service
| `ctx.sessions` | `dsh-session` | in-memory event-sourced sessions |
| `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables |
| `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) |
| `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events |
| `ctx.agentExecution` | `dsh-agent-execution` | process-local ambient Agent identity for asynchronous driver work |
| `ctx.agents` | `dsh-agent` | live agents, creation delegation, `agent/*` events, and process-local initiating Agent scope |
| `ctx.agentLoop` | `dsh-agent-loop` | concrete `Agent` driver |
### Capability Services
@@ -119,9 +118,9 @@ Every session event is turn-enclosed. Reloading preserves an interrupted tail an
Every live agent owns a scoped `agent.ctx`. Its registrations shadow globals, receive only that agent's dispatches, and unwind with it; async effects such as background-task cleanup are awaited. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. Typed resolvers derive carrier checks from merged `Events` signatures and `scopeTarget` ([semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md)). See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md) and [subagent composition controls](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md).
### Agent Execution Context
### Initiating Agent Scope
`AgentLoop` establishes process-local `ctx.agentExecution` around each driver; the [decision](rfc/implemented/architecture/2026-07-15-agent-execution-context.md) owns boundary and explicit-identity rules.
`AgentLoop` runs each process-local driver inside `ctx.agents.withInitiator()`; the [decision](rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns boundary and explicit-identity rules.
## State

View File

@@ -48,9 +48,7 @@ flowchart LR
pkg_skill["skill"]
svc_skills["ctx.skills<br/>Skill provider registry"]
pkg_skill_local["skill-local"]
svc_agents["ctx.agents<br/>Agent registry"]
pkg_agent_execution["agent-execution"]
svc_agentExecution["ctx.agentExecution<br/>Agent execution context"]
svc_agents["ctx.agents<br/>Agent service"]
svc_agentLoop["ctx.agentLoop<br/>Concrete loop driver"]
pkg_agent_spine_demo["agent-spine-demo"]
pkg_bash["bash"]
@@ -99,7 +97,6 @@ flowchart LR
pkg_acp --> svc_approval
pkg_acp --> svc_userInteraction
pkg_agent --> svc_agents
pkg_agent_execution --> svc_agentExecution
pkg_agent_loop --> svc_agentLoop
pkg_approval --> svc_approval
pkg_bash --> svc_bash
@@ -145,7 +142,6 @@ flowchart LR
pkg_web_search_perplexity --> svc_web
pkg_workflow --> svc_workflows
pkg_workflow_workerthread --> svc_workflows
svc_agentExecution --> pkg_agent_loop
svc_agentLoop --> pkg_agent_spine_demo
svc_agents --> pkg_acp
svc_agents --> pkg_agent_loop
@@ -216,8 +212,7 @@ flowchart LR
| `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. |
| `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. |
| `ctx.skills` | `seam` | [`skill`](../packages/skill/skill) | [`skill-local`](../packages/skill/skill-local) | [`tool-skill`](../packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. |
| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. |
| `ctx.agentExecution` | `core` | [`agent-execution`](../packages/core/agent-execution) | - | [`agent-loop`](../packages/core/agent-loop) | - | Carries the exact initiating Agent across one process-local asynchronous driver chain; explicit identities remain authoritative at external boundaries. |
| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles, the create/resume factory seam, and process-local initiator propagation. |
| `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. |
| `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. |
| `ctx.bashEnv` | `core` | [`tool-bash`](../packages/bash/tool-bash) | - | - | - | Plugins declare effect-scoped DSH_* facts; tool-bash collects one trusted snapshot per execution and the executor rebuilds the namespace. |

View File

@@ -75,7 +75,7 @@ Source: [`packages/examples/acp-demo/src/index.ts:33`](../packages/examples/acp-
## `@deepseek-ai/dsh-agent-loop`
Requires: `agents` · `agentExecution` · `sessions` · `llm` · `tools` · `systemPrompt`
Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt`
```ts config-catalog
/** Agent-loop plugin configuration. */
@@ -101,7 +101,7 @@ export interface Config {
Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:370`](../packages/core/agent-loop/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:369`](../packages/core/agent-loop/src/index.ts)
## `@deepseek-ai/dsh-agent-spine-demo`
@@ -157,7 +157,7 @@ export interface SkillConfig {
Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts)
Source: [`packages/examples/agent-spine-demo/src/index.ts:58`](../packages/examples/agent-spine-demo/src/index.ts)
Source: [`packages/examples/agent-spine-demo/src/index.ts:57`](../packages/examples/agent-spine-demo/src/index.ts)
## `@deepseek-ai/dsh-bash-local`
@@ -1415,7 +1415,6 @@ Source: [`packages/context/workspace-context/src/config.ts:16`](../packages/cont
These load from a `cordis.yml` entry with no `config:` block; they declare no config surface.
- `@deepseek-ai/dsh-agent` ([`packages/core/agent/src/index.ts`](../packages/core/agent/src/index.ts))
- `@deepseek-ai/dsh-agent-execution` ([`packages/core/agent-execution/src/index.ts`](../packages/core/agent-execution/src/index.ts))
- `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts))
- `@deepseek-ai/dsh-invariants` — requires `sessions` ([`packages/support/invariants/src/index.ts`](../packages/support/invariants/src/index.ts))
- `@deepseek-ai/dsh-llm` ([`packages/llm/llm/src/index.ts`](../packages/llm/llm/src/index.ts))

View File

@@ -3,9 +3,9 @@
# Cordis Events Catalog
Every cordis event a plugin can listen to: exact signature, dispatch mode, and the declaration's JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.<key>` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around.
Every cordis event a plugin can listen to: exact signature, dispatch mode, and original declaration JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.<key>` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around.
This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence (skipped by doc-typecheck, since a bare signature is not standalone-compilable). Type names in a signature link to the page that documents them.
This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence and include the original source JSDoc immediately before each event or service method. doc-typecheck skips these bare declaration fragments; type names in a signature link to the page that documents them.
The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary this repo owns, grouped by scope. The **inherited tier** at the end is the cordis-core + loader/hmr/timer event surface a plugin also sees — pinned vendor source, summarized tersely.
@@ -18,6 +18,16 @@ Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `n
A fully configured agent and live session were published. Setup is composition-only; `agent/session-start` is the first startup-driving seam. Synchronous listener failure vetoes publication, while returned-promise rejection is reported. Detach requested during dispatch waits until every creation listener has observed the stable entry.
```ts cordis-catalog
/**
* A fully configured agent and live session were published. Setup is
* composition-only; `agent/session-start` is the first startup-driving seam.
* Synchronous listener failure vetoes publication, while returned-promise
* rejection is reported. Detach requested during dispatch waits until every
* creation listener has observed the stable entry.
* @param 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.
* @mode emit
*/
'agent/created'(this: Scoped<Agent>, agent: Agent): void
```
@@ -30,6 +40,14 @@ Source: [`packages/core/agent/src/types.ts:141`](../../packages/core/agent/src/t
An agent left the registry; AgentLoop emits this after driver quiescence but before session detachment and scoped-registration unwind. Custom registry users own their driver-ordering contract.
```ts cordis-catalog
/**
* An agent left the registry; AgentLoop emits this after driver quiescence
* but before session detachment and scoped-registration unwind. Custom
* registry users own their driver-ordering contract.
* @param agent - the exact agent removed from the registry.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode emit
*/
'agent/disposed'(this: Scoped<Agent>, agent: Agent): void
```
@@ -42,6 +60,16 @@ Source: [`packages/core/agent/src/types.ts:150`](../../packages/core/agent/src/t
A step or turn errored. The loop reports a failure here (plus the logger) even when the error has no in-turn position for a session `error` event.
```ts cordis-catalog
/**
* A step or turn errored. The loop reports a failure here (plus the logger)
* even when the error has no in-turn position for a session `error` event.
* @param agent - the agent whose turn errored.
* @param turn - the turn in which the failure surfaced.
* @param step - the step at which the failure surfaced.
* @param error - the failure, verbatim.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode emit
*/
'agent/error'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, error: Error): void
```
@@ -54,6 +82,22 @@ Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/t
Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step. The loop derives history once afterward, so compaction records and replacements are included without rewriting an assembled request. The prompt and prefix are the exact pressure inputs for that request, and `signal` cancels listener work. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
```ts cordis-catalog
/**
* Awaited serial checkpoint for session-surface mutation after prompt
* assembly and before `step/start`; appends land outside the pending step.
* The loop derives history once afterward, so compaction records and
* replacements are included without rewriting an assembled request. The
* prompt and prefix are the exact pressure inputs for that request, and
* `signal` cancels listener work.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @param agent - the agent opening the step.
* @param turn - the open turn number.
* @param step - the pending step number.
* @param fullSystemPrompt - the assembled prompt.
* @param sessionPrefix - the frozen request prefix.
* @param signal - the turn abort signal.
* @mode serial
*/
'agent/pre-step'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise<void> | void
```
@@ -66,6 +110,15 @@ Source: [`packages/core/agent/src/types.ts:204`](../../packages/core/agent/src/t
Allow, rewrite, or block one drained prompt before it becomes a user message. Call `next()` for the unchanged default.
```ts cordis-catalog
/**
* Allow, rewrite, or block one drained prompt before it becomes a user
* message. Call `next()` for the unchanged default.
* @param agent - the agent draining its inbox.
* @param content - the drained message's blocks, as queued.
* @param source - the message's resolved source.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
'agent/prompt-submit'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise<PromptDecision>): Promise<PromptDecision>
```
@@ -78,6 +131,15 @@ Source: [`packages/core/agent/src/types.ts:214`](../../packages/core/agent/src/t
Detached, frozen content entered the agent's inbox. Source defaults have already been applied, so these are the exact values retained for the log.
```ts cordis-catalog
/**
* Detached, frozen content entered the agent's inbox. Source defaults have
* already been applied, so these are the exact values retained for the log.
* @param agent - the agent whose inbox received the message.
* @param content - the accepted content blocks retained by the inbox.
* @param info - the accepted source plus whether it entered as steering.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode emit
*/
'agent/queued'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void
```
@@ -90,6 +152,17 @@ Source: [`packages/core/agent/src/types.ts:169`](../../packages/core/agent/src/t
Replace the frozen call configuration. Model-visible content must use logged channels; this seam cannot mutate messages. Injection here joins the next request because the current step boundary is already fixed.
```ts cordis-catalog
/**
* Replace the frozen call configuration. Model-visible content must use
* logged channels; this seam cannot mutate messages. Injection here joins
* the next request because the current step boundary is already fixed.
* @param agent - the agent making the model call.
* @param turn - the open turn number.
* @param step - the step whose request this is.
* @param 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.
* @mode waterfall
*/
'agent/request'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise<LlmCallConfig>): Promise<LlmCallConfig>
```
@@ -102,6 +175,20 @@ Source: [`packages/core/agent/src/types.ts:226`](../../packages/core/agent/src/t
Compose request-only messages placed before derived history. The frozen result is computed once per loop instance, logged on its anchoring request header, and reused so the provider prefix remains stable. Interrupted composition is discarded. Composition precedes the first `agent/pre-step` and request boundary, so listener appends join the current request and pressure accounting sees the composed prefix. Changing context belongs in history; contributors should prepend to `await next()` to preserve registration order. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
```ts cordis-catalog
/**
* Compose request-only messages placed before derived history. The frozen
* result is computed once per loop instance, logged on its anchoring request
* header, and reused so the provider prefix remains stable. Interrupted
* composition is discarded. Composition precedes the first `agent/pre-step`
* and request boundary, so listener appends join the current request and
* pressure accounting sees the composed prefix. Changing context belongs in
* history; contributors should prepend to `await next()` to preserve registration order.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @param agent - the agent whose session prefix is being composed.
* @param prefix - the frozen seed; return an extended replacement.
* @param signal - aborts composition when the step is torn down.
* @mode waterfall
*/
'agent/session-prefix'(this: Scoped<Agent>, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise<Message[]>): Promise<Message[]>
```
@@ -114,6 +201,16 @@ Source: [`packages/core/agent/src/types.ts:241`](../../packages/core/agent/src/t
The session lifecycle began, once before the first turn. Use `agent.inject()` to seed model-facing context. This is a notification, not a veto; disposal requested by a lifecycle owner is rechecked before the driver starts.
```ts cordis-catalog
/**
* The session lifecycle began, once before the first turn. Use
* `agent.inject()` to seed model-facing context. This is a notification, not
* a veto; disposal requested by a lifecycle owner is rechecked before the
* driver starts.
* @param agent - the agent whose session lifecycle began.
* @param source - why the session started (fresh startup, resume, …).
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode emit
*/
'agent/session-start'(this: Scoped<Agent>, agent: Agent, source: SessionStartSource): void
```
@@ -126,6 +223,14 @@ Source: [`packages/core/agent/src/types.ts:182`](../../packages/core/agent/src/t
Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does not enter `running` synchronously; drive lifecycle from this event.
```ts cordis-catalog
/**
* Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does
* not enter `running` synchronously; drive lifecycle from this event.
* @param agent - the agent whose status flipped.
* @param status - the status just entered (the transition's destination).
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode emit
*/
'agent/status'(this: Scoped<Agent>, agent: Agent, status: AgentStatus): void
```
@@ -138,6 +243,16 @@ Source: [`packages/core/agent/src/types.ts:159`](../../packages/core/agent/src/t
Waterfall: post-process the assembled assistant Message before tool dispatch (validation, content rewriting, …).
```ts cordis-catalog
/**
* Waterfall: post-process the assembled assistant {@link Message} before
* tool dispatch (validation, content rewriting, …).
* @param agent - the agent that received the step's response.
* @param turn - the open turn number.
* @param step - the step that produced the message.
* @param message - the assistant message as assembled from the stream.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
'agent/step-result'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, message: Message, next: () => Promise<Message>): Promise<Message>
```
@@ -150,6 +265,15 @@ Source: [`packages/core/agent/src/types.ts:252`](../../packages/core/agent/src/t
Override whether the turn continues. The default continues after tool calls or steering and stops otherwise; a continue reason becomes steering.
```ts cordis-catalog
/**
* Override whether the turn continues. The default continues after tool
* calls or steering and stops otherwise; a continue reason becomes steering.
* @param agent - the agent deciding whether to run another step.
* @param turn - the turn being continued or stopped.
* @param defaultDecision - what the loop would do absent an override.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
'agent/turn-continuation'(this: Scoped<Agent>, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise<ContinuationDecision>): Promise<ContinuationDecision>
```
@@ -162,6 +286,15 @@ Source: [`packages/core/agent/src/types.ts:262`](../../packages/core/agent/src/t
Monotonic terminal-stop checkpoint after continuation and steering are folded; a stop remains authoritative through turn close and flush: steering queued in that window is discarded, while ordinary sends survive.
```ts cordis-catalog
/**
* Monotonic terminal-stop checkpoint after continuation and steering are
* folded; a stop remains authoritative through turn close and flush:
* steering queued in that window is discarded, while ordinary sends survive.
* @param agent - the agent whose composed continuation outcome may be stopped.
* @param turn - the turn at its terminal-stop checkpoint.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode serial
*/
'agent/turn-stop'(this: Scoped<Agent>, agent: Agent, turn: number): ContinuationStop | undefined
```
@@ -176,10 +309,19 @@ Source: [`packages/core/agent/src/types.ts:272`](../../packages/core/agent/src/t
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
/**
* 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
```
Source: [`packages/core/agent-loop/src/index.ts:363`](../../packages/core/agent-loop/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:362`](../../packages/core/agent-loop/src/index.ts)
## `approval/*`
@@ -188,6 +330,13 @@ Source: [`packages/core/agent-loop/src/index.ts:363`](../../packages/core/agent-
Ask composed answerers for one decision. Return an outcome to claim the request or call `next()`; failure yields the fail-closed default. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
```ts cordis-catalog
/**
* Ask composed answerers for one decision. Return an outcome to claim the
* request or call `next()`; failure yields the fail-closed default.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @param req - the pending decision (agent, tool identity, reason, signal).
* @mode waterfall
*/
'approval/request'(this: Scoped<ApprovalService>, req: ApprovalRequest, next: () => Promise<ApprovalOutcome>): Promise<ApprovalOutcome>
```
@@ -202,6 +351,13 @@ Source: [`packages/ui/user-approval/src/index.ts:31`](../../packages/ui/user-app
Single-slot decision for the next FileSystem.editText. Calling `next()` yields an unconditional edit; the first returned guard wins.
```ts cordis-catalog
/**
* Single-slot decision for the next {@link FileSystem.editText}. Calling
* `next()` yields an unconditional edit; the first returned guard wins.
* @param target - the resolved target about to be edited.
* @param actor - the opaque tool-execution context the decider keys off.
* @mode waterfall
*/
'fs/edit-intent'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined>
```
@@ -214,6 +370,14 @@ Source: [`packages/fs/fs/src/index.ts:61`](../../packages/fs/fs/src/index.ts)
Record a successful observation. Listeners must be synchronous recorders: throws fail the tool call and returned promises are not awaited.
```ts cordis-catalog
/**
* Record a successful observation. Listeners must be synchronous recorders:
* throws fail the tool call and returned promises are not awaited.
* @param target - the target that was read/written/edited.
* @param version - the version the actor now holds as its observation.
* @param actor - the observing tool-execution context; undefined records nothing useful.
* @mode emit
*/
'fs/observed'(target: FsTarget, version: FsVersion, actor: object | undefined): void
```
@@ -226,6 +390,14 @@ Source: [`packages/fs/fs/src/index.ts:70`](../../packages/fs/fs/src/index.ts)
Single-slot decision for the next FileSystem.writeText. Calling `next()` yields the bare provider's unconditional write; the first listener that returns an intent owns the decision rather than composing with peers.
```ts cordis-catalog
/**
* Single-slot decision for the next {@link FileSystem.writeText}. Calling
* `next()` yields the bare provider's unconditional write; the first listener
* that returns an intent owns the decision rather than composing with peers.
* @param target - the resolved target about to be written.
* @param actor - the opaque tool-execution context the decider keys off.
* @mode waterfall
*/
'fs/write-intent'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise<FsWriteIntent | undefined>): Promise<FsWriteIntent | undefined>
```
@@ -240,6 +412,17 @@ Source: [`packages/fs/fs/src/index.ts:53`](../../packages/fs/fs/src/index.ts)
Waterfall around every streaming model call (retry, replay, routing). Bound to the LlmService; call `next()` to reach the resolved adapter's stream, or yield your own chunks to short-circuit.
```ts cordis-catalog
/**
* Waterfall around every streaming model call (retry, replay, routing).
* Bound to the {@link LlmService}; call `next()` to reach the resolved
* adapter's stream, or yield your own chunks to short-circuit.
* @param options - the full request. A LOOP-built request arrives
* deep-frozen (mutation throws): its content is a pure function of the
* session log (the reconstructability RFC), so listeners read it, never
* rewrite it. A hand-built one-shot (compaction summarize) is the
* caller's own object and stays mutable here.
* @mode waterfall
*/
'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable<StreamChunk>): AsyncIterable<StreamChunk>
```
@@ -254,6 +437,17 @@ Source: [`packages/llm/llm/src/index.ts:40`](../../packages/llm/llm/src/index.ts
Creation announcement during session publication. A synchronous throw vetoes and rolls back with a paired disposal; detach requested during dispatch is deferred. A returned-promise rejection is logged but cannot retroactively veto this synchronous boundary. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only sessions entered through that agent's context.
```ts cordis-catalog
/**
* Creation announcement during session publication. A synchronous throw vetoes and rolls
* back with a paired disposal; detach requested during dispatch is deferred.
* A returned-promise rejection is logged but cannot retroactively veto this
* synchronous boundary.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners
* receive only sessions entered through that agent's context.
* @param session - the session just entered and announced.
* @dshScopeScan unsupported
* @mode emit
*/
'session/created'(this: Scoped<Session>, session: Session): void
```
@@ -264,6 +458,15 @@ Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/sr
Emitted once when an announced session leaves the store, including publication rollback, but never for an entry whose creation announcement did not begin. Listener failures are logged and contained. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope.
```ts cordis-catalog
/**
* Emitted once when an announced session leaves the store, including
* publication rollback, but never for an entry whose creation announcement
* did not begin. Listener failures are logged and contained.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope.
* @param session - the session that is no longer live in the store.
* @dshScopeScan unsupported
* @mode emit
*/
'session/disposed'(this: Scoped<Session>, session: Session): void
```
@@ -274,6 +477,17 @@ Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/sr
Post-commit, fire-and-forget append feed. The listener snapshot resolves before the log push, but callbacks run after it; observer failures are logged and contained without making the committed append fail. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only events from sessions entered through that agent's context.
```ts cordis-catalog
/**
* Post-commit, fire-and-forget append feed. The listener snapshot resolves
* before the log push, but callbacks run after it; observer failures are
* logged and contained without making the committed append fail.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners
* receive only events from sessions entered through that agent's context.
* @param session - the session whose log grew.
* @param event - the appended event, exactly as recorded.
* @dshScopeScan unsupported
* @mode emit
*/
'session/event'(this: Scoped<Session>, session: Session, event: SessionEvent): void
```
@@ -286,6 +500,15 @@ Source: [`packages/core/session/src/index.ts:69`](../../packages/core/session/sr
Awaited parallel durability checkpoint: every listener runs and the caller awaits all of them, with no waterfall veto. Dispatch through SessionStore.flush. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the session's owner scope.
```ts cordis-catalog
/**
* Awaited parallel durability checkpoint: every listener runs and the
* caller awaits all of them, with no waterfall veto. Dispatch through
* {@link SessionStore.flush}. Scope-filtered dispatch
* (`@deepseek-ai/dsh-scope`) reuses the session's owner scope.
* @param session - the session whose buffered events must reach durable storage.
* @dshScopeScan unsupported
* @mode parallel
*/
'session/flush'(this: Scoped<Session>, session: Session): Promise<void> | void
```
@@ -298,6 +521,14 @@ Source: [`packages/core/session/src/index.ts:79`](../../packages/core/session/sr
A ready child settled. Scope-filtered dispatch uses the same delegating parent carrier as `subagent/start`, so the lifecycle pair reaches the same scoped audience.
```ts cordis-catalog
/**
* A ready child settled. Scope-filtered dispatch uses the same delegating
* parent carrier as `subagent/start`, so the lifecycle pair reaches the
* same scoped audience.
* @param info - the run identity and terminal outcome.
* @dshScopeScan unsupported
* @mode emit
*/
'subagent/end'(this: Scoped<SubagentService>, info: SubagentRunEndInfo): void
```
@@ -308,6 +539,11 @@ Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/
A provider became resolvable in the registry.
```ts cordis-catalog
/**
* A provider became resolvable in the registry.
* @param provider - the registered provider.
* @mode emit
*/
'subagent/provider-added'(provider: SubagentProvider): void
```
@@ -318,6 +554,11 @@ Source: [`packages/subagent/subagent/src/index.ts:86`](../../packages/subagent/s
A provider left the registry. Accepted runs remain holder-owned.
```ts cordis-catalog
/**
* A provider left the registry. Accepted runs remain holder-owned.
* @param name - the provider name that no longer resolves.
* @mode emit
*/
'subagent/provider-removed'(name: string): void
```
@@ -328,6 +569,16 @@ Source: [`packages/subagent/subagent/src/index.ts:92`](../../packages/subagent/s
A provider established a ready child. For in-process providers, `ctx.agents.get(info.id)` resolves during this notification. Scope-filtered dispatch keys the carrier by the delegating parent, so a parent-scoped listener observes only its own delegations. Paired with `subagent/end`.
```ts cordis-catalog
/**
* A provider established a ready child. For in-process providers,
* `ctx.agents.get(info.id)` resolves during this notification.
* Scope-filtered dispatch keys the carrier by the delegating parent, so a
* parent-scoped listener observes only its own delegations. Paired with
* `subagent/end`.
* @param info - the provider and ready child identity.
* @dshScopeScan unsupported
* @mode emit
*/
'subagent/start'(this: Scoped<SubagentService>, info: SubagentRunInfo): void
```
@@ -340,6 +591,14 @@ Source: [`packages/subagent/subagent/src/index.ts:103`](../../packages/subagent/
Expert waterfall over the assembled sections, tools, and variables. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners receive only that scope's assemblies. The returned value is authoritative.
```ts cordis-catalog
/**
* Expert waterfall over the assembled sections, tools, and variables.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners
* receive only that scope's assemblies. The returned value is authoritative.
* @param assembly - the mutable assembly built from registered providers.
* @param context - the caller's per-assembly context.
* @mode waterfall
*/
'system-prompt/assemble'(this: Scoped<SystemPrompt>, assembly: PromptAssembly, context: AssembleContext, next: () => Promise<PromptAssembly>): Promise<PromptAssembly>
```
@@ -350,6 +609,11 @@ Source: [`packages/core/system-prompt/src/index.ts:27`](../../packages/core/syst
Emitted when any prompt provider changes. This registry notification is unfiltered because a global change affects every scope.
```ts cordis-catalog
/**
* Emitted when any prompt provider changes. This registry notification is
* unfiltered because a global change affects every scope.
* @mode emit
*/
'system-prompt/change'(): void
```
@@ -362,6 +626,15 @@ Source: [`packages/core/system-prompt/src/index.ts:33`](../../packages/core/syst
A tool was registered or unregistered, or a scoped restriction changed (the available tool set changed — possibly for one scope only). An UNFILTERED registry-subject notification, deliberately not scope-filtered dispatch: a global change concerns every agent's next assembly, so a scoped listener subscribing here sees every change, not just its own scope's.
```ts cordis-catalog
/**
* A tool was registered or unregistered, or a scoped restriction changed
* (the available tool set changed — possibly for one scope only). An
* UNFILTERED registry-subject notification, deliberately not scope-filtered
* dispatch: a global change concerns every agent's next assembly, so a
* scoped listener subscribing here sees every change, not just its own
* scope's.
* @mode emit
*/
'tools/change'(): void
```
@@ -372,6 +645,14 @@ Source: [`packages/core/tools/src/index.ts:116`](../../packages/core/tools/src/i
Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns a normalized result; wrappers may change only `exec.signal`, while call identity remains immutable. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
```ts cordis-catalog
/**
* Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns
* a normalized result; wrappers may change only `exec.signal`, while call
* identity remains immutable.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
* @param exec - the allowed call about to dispatch (name, parsed arguments, caller agent, signal).
* @mode waterfall
*/
'tools/execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
```
@@ -384,6 +665,14 @@ Source: [`packages/core/tools/src/index.ts:89`](../../packages/core/tools/src/in
Accept, replace, enrich, or block a normalized dispatch result. `next()` accepts it unchanged; thrown tools still reach this seam as errors. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
```ts cordis-catalog
/**
* Accept, replace, enrich, or block a normalized dispatch result. `next()`
* accepts it unchanged; thrown tools still reach this seam as errors.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
* @param exec - the call that just ran (name, parsed arguments, caller agent).
* @param result - the dispatch outcome a listener may accept, replace, or block.
* @mode waterfall
*/
'tools/post-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, result: Readonly<ToolExecutionResult>, next: () => Promise<PostToolDecision>): Promise<PostToolDecision>
```
@@ -396,6 +685,13 @@ Source: [`packages/core/tools/src/index.ts:98`](../../packages/core/tools/src/in
Allow, deny, or ask before dispatch. `next()` delegates to allow; missing approval support turns `ask` into denial. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
```ts cordis-catalog
/**
* Allow, deny, or ask before dispatch. `next()` delegates to allow; missing
* approval support turns `ask` into denial.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
* @param exec - the pending call (name, parsed arguments, caller agent).
* @mode waterfall
*/
'tools/pre-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>
```
@@ -408,6 +704,13 @@ Source: [`packages/core/tools/src/index.ts:80`](../../packages/core/tools/src/in
Observe the frozen, lossless-JSON final outcome. Listener failures are contained. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`.
```ts cordis-catalog
/**
* Observe the frozen, lossless-JSON final outcome. Listener failures are contained.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`.
* @param exec - the execution object that traversed the pipeline.
* @param result - a deep-frozen snapshot of the final returned result.
* @mode emit
*/
'tools/result'(this: Scoped<ToolRegistry>, exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): undefined
```
@@ -422,6 +725,16 @@ Source: [`packages/core/tools/src/index.ts:106`](../../packages/core/tools/src/i
One `agent()` call settled (clean result, child failure, or run cancellation). Paired with Events['workflow/agent-start'] by `agent.seq`, exactly once per started call on every stop path — on an engine termination path (a worker killed past its grace) the end is engine-synthesized with outcome `'cancelled'`.
```ts cordis-catalog
/**
* One `agent()` call settled (clean result, child failure, or run
* cancellation). Paired with {@link Events['workflow/agent-start']} by
* `agent.seq`, exactly once per started call on every stop path — on an
* engine termination path (a worker killed past its grace) the end is
* engine-synthesized with outcome `'cancelled'`.
* @param info - the run's identity snapshot.
* @param agent - the call identity plus its outcome.
* @mode emit
*/
'workflow/agent-end'(info: WorkflowRunInfo, agent: WorkflowAgentEndInfo): void
```
@@ -432,6 +745,15 @@ Source: [`packages/workflow/workflow/src/index.ts:81`](../../packages/workflow/w
One `agent()` call established a ready child run. Paired with Events['workflow/agent-end'] by `agent.seq`. A call that never receives a ready run from the provider emits neither event in this pair.
```ts cordis-catalog
/**
* One `agent()` call established a ready child run. Paired with
* {@link Events['workflow/agent-end']} by `agent.seq`. A call that never
* receives a ready run from the provider emits neither
* event in this pair.
* @param info - the run's identity snapshot.
* @param agent - the call's sequence number, label, phase, and child id.
* @mode emit
*/
'workflow/agent-start'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): void
```
@@ -442,6 +764,15 @@ Source: [`packages/workflow/workflow/src/index.ts:70`](../../packages/workflow/w
A workflow run settled (any stop reason). Fired when WorkflowRun.result resolves. Paired with Events['workflow/start'].
```ts cordis-catalog
/**
* A workflow run settled (any stop reason). Fired when
* {@link WorkflowRun.result} resolves. Paired with
* {@link Events['workflow/start']}.
* @param info - the run's identity snapshot.
* @param result - the outcome data (stop reason, error, agent count) —
* deliberately WITHOUT the result value (see {@link WorkflowResultInfo}).
* @mode emit
*/
'workflow/end'(info: WorkflowRunInfo, result: WorkflowResultInfo): void
```
@@ -452,6 +783,12 @@ Source: [`packages/workflow/workflow/src/index.ts:91`](../../packages/workflow/w
The script emitted a narration line (a `log(message)` call).
```ts cordis-catalog
/**
* The script emitted a narration line (a `log(message)` call).
* @param info - the run's identity snapshot.
* @param message - the logged message, verbatim.
* @mode emit
*/
'workflow/log'(info: WorkflowRunInfo, message: string): void
```
@@ -462,6 +799,13 @@ Source: [`packages/workflow/workflow/src/index.ts:60`](../../packages/workflow/w
The script entered a phase (a `phase(title)` call) — progress grouping for observers; no execution semantics.
```ts cordis-catalog
/**
* The script entered a phase (a `phase(title)` call) — progress grouping
* for observers; no execution semantics.
* @param info - the run's identity snapshot.
* @param title - the phase title, verbatim.
* @mode emit
*/
'workflow/phase'(info: WorkflowRunInfo, title: string): void
```
@@ -472,6 +816,12 @@ Source: [`packages/workflow/workflow/src/index.ts:53`](../../packages/workflow/w
A workflow run started — the script's meta block validated, the body about to execute. Paired with Events['workflow/end'].
```ts cordis-catalog
/**
* A workflow run started — the script's meta block validated, the body
* about to execute. Paired with {@link Events['workflow/end']}.
* @param info - the run's identity snapshot (id + meta).
* @mode emit
*/
'workflow/start'(info: WorkflowRunInfo): void
```

File diff suppressed because it is too large Load Diff

View File

@@ -403,49 +403,9 @@ interface Agent {
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.
## Agent execution context
## Initiating Agent
`AgentExecution` is the process-local ambient frame established around a concrete driver's lifetime. It holds the exact Agent object rather than duplicating Session or step state; ambient presence is neither liveness proof nor authorization.
Source: [`packages/core/agent-execution/src/types.ts`](../../packages/core/agent-execution/src/types.ts)
```ts type-equiv
interface AgentExecution {
readonly agent: Agent
}
```
The mandatory service reads, requires, establishes, or explicitly clears that frame. `run()` preserves the operation's exact synchronous value or Promise.
Source: [`packages/core/agent-execution/src/index.ts`](../../packages/core/agent-execution/src/index.ts)
```ts type-equiv
interface AgentExecutionService {
/**
* Read the active execution without requiring one.
* @returns the inherited execution, or `undefined` outside/inside a cleared boundary.
* @throws when this service instance has been disposed.
*/
current(): AgentExecution | undefined
/**
* Read the active execution and fail when no boundary is active.
* @returns the inherited execution.
* @throws when no execution is active or this service instance has been disposed.
*/
require(): AgentExecution
/**
* Run an operation inside an execution boundary. Passing `undefined` clears
* an inherited execution; the exact synchronous value or Promise is returned.
* @param execution - execution to inherit, or `undefined` for a clearing boundary.
* @param operation - synchronous or asynchronous operation to invoke.
* @returns the exact value returned by `operation`.
* @throws when this service is closing/disposed, or when `operation` throws.
*/
run<T>(execution: AgentExecution | undefined, operation: () => T): T
}
```
The process-local initiator carried by `ctx.agents` is the exact `Agent` above, not a separate frame or copied identity. Ambient presence is neither liveness proof nor authorization; the [initiator-scope decision](../rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns its lifetime and boundary rules.
## Interception decisions

View File

@@ -22,7 +22,6 @@ flowchart TD
end
subgraph group_core["packages/core"]
pkg_agent["agent"]
pkg_agent_execution["agent-execution"]
pkg_agent_loop["agent-loop"]
pkg_scope["scope"]
pkg_session["session"]
@@ -194,7 +193,6 @@ flowchart TD
pkg_llm_replay --> pkg_session
pkg_sandbox_local --> pkg_llm
pkg_sandbox_local --> pkg_sandbox
pkg_agent_execution --> pkg_agent
pkg_bash_local --> pkg_bash
pkg_bash_local --> pkg_timeout
pkg_compact_basic --> pkg_agent
@@ -248,7 +246,6 @@ flowchart TD
pkg_permission --> pkg_session
pkg_permission --> pkg_user_approval
pkg_agent_loop --> pkg_agent
pkg_agent_loop --> pkg_agent_execution
pkg_agent_loop --> pkg_llm
pkg_agent_loop --> pkg_scope
pkg_agent_loop --> pkg_session
@@ -311,7 +308,6 @@ flowchart TD
pkg_hooks_codex --> pkg_session_persistence
pkg_hooks_codex --> pkg_tools
pkg_agent_loop_testkit --> pkg_agent
pkg_agent_loop_testkit --> pkg_agent_execution
pkg_agent_loop_testkit --> pkg_llm
pkg_agent_loop_testkit --> pkg_session
pkg_agent_loop_testkit --> pkg_system_prompt
@@ -390,7 +386,6 @@ flowchart TD
pkg_tui --> pkg_tools
pkg_tui --> pkg_user_interaction
pkg_agent_spine_demo --> pkg_agent
pkg_agent_spine_demo --> pkg_agent_execution
pkg_agent_spine_demo --> pkg_agent_loop
pkg_agent_spine_demo --> pkg_home
pkg_agent_spine_demo --> pkg_invariants
@@ -481,7 +476,6 @@ flowchart TD
| [`session-persistence`](../packages/session-persistence/session-persistence) | `session-persistence` | [`session`](../packages/core/session) |
| [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
| [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) |
| [`agent-execution`](../packages/core/agent-execution) | `core` | [`agent`](../packages/core/agent) |
| [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) |
| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) |
| [`spill-local`](../packages/spill/spill-local) | `spill` | [`spill`](../packages/spill/spill) |
@@ -498,7 +492,7 @@ flowchart TD
| [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) |
| [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) |
| [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) |
| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`agent-execution`](../packages/core/agent-execution), [`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) |
| [`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) |
@@ -510,7 +504,7 @@ flowchart TD
| [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
| [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) |
| [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools) |
| [`agent-loop-testkit`](../packages/support/agent-loop-testkit) | `support` | [`agent`](../packages/core/agent), [`agent-execution`](../packages/core/agent-execution), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
| [`agent-loop-testkit`](../packages/support/agent-loop-testkit) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) |
| [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
| [`workspace-context`](../packages/context/workspace-context) | `context` | [`agent`](../packages/core/agent), [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |

View File

@@ -163,7 +163,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
| [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 |
| [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 |
| [Provider-routed LLM adapters and a generic pi-ai backend](implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) | 2026-07-14 |
| [Agent execution context over AsyncLocalStorage](implemented/architecture/2026-07-15-agent-execution-context.md) | 2026-07-15 |
| [Initiating Agent scope over AsyncLocalStorage](implemented/architecture/2026-07-15-agent-initiator-scope.md) | 2026-07-15 |
| [Advisory LLM catalogs and per-session ACP model selection](implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) | 2026-07-15 |
| [Replay token meter service](implemented/architecture/2026-07-15-replay-token-meter-service.md) | 2026-07-15 |

View File

@@ -1,61 +0,0 @@
# RFC: Agent execution context over AsyncLocalStorage
Status: implemented
English | [中文](2026-07-15-agent-execution-context.zh.md)
## Problem
The harness has two useful but different notions of context. A Cordis `Context` selects services, registration ownership, and lifetime; `agent.ctx` is the flat registration scope owned by one live Agent. Agent and Session identity instead describe the subject of an asynchronous operation. Changing a root `ctx.agent` to mean “whichever Agent is running” would conflate those meanings and fail when one process drives Agents concurrently.
Deep process-local infrastructure sometimes needs a trusted initiating Agent below explicit loop, tool, and request parameters—for example, a host-aware transport, tracing helper, logger, or gateway client. Requiring every private helper to forward `agent` adds repetition, while a process-global mutable slot is incorrect across `await`. Model-visible arguments are unsuitable because a model must not choose a trusted Session or routing header. The carrier is mandatory control infrastructure rather than optional model-visible context.
## Decision
`@deepseek-ai/dsh-agent-execution` provides the mandatory `ctx.agentExecution` service using Node `AsyncLocalStorage`. The named `AgentExecution` frame contains only the exact Agent object; the [core-data catalog](../../../core-data-structures/core.md#agent-execution-context) owns the literal frame and service types.
`current()` reads optionally, `require()` throws `no agent execution context is active`, and `run()` preserves the operation's exact synchronous value or Promise. `run(undefined, operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `execution.agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners.
`AgentLoop` injects the service and wraps each concrete driver's complete `runLoop` lifetime in `agentExecution.run({ agent }, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child.
Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local.
The provider uses an ordered composite effect. Teardown first rejects new boundaries, then removes the service and awaits injected dependents such as AgentLoop, then waits for active returned-Promise boundaries before calling `AsyncLocalStorage.disable()`. `current()` and `require()` remain usable through a retained in-flight service reference while that drain runs; after disposal, retained calls throw `agent execution service is disposed`. Root Context disposal may start sibling fiber teardown concurrently, so active-boundary counting is required in addition to Cordis dependency ordering.
`run()` does not own detached work: provider drain tracks only the Promise returned by `operation`. Asynchronous resources created inside the boundary inherit its store until they settle or ALS is disabled, so their owning seam must stop unreturned work explicitly. Agent-owned foreground work returns its lifetime and keeps its cancellation contract. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)`; queue, worker, process, and wire boundaries serialize identity rather than expecting ALS propagation.
A host-aware transport may derive a deployment-owned header such as `X-Harness-Session-Id` from `ctx.agentExecution.require().agent.session.id`; the header is absent from model-visible schema and arguments. No production MCP or Web transport adopts such a header in this decision. A test-double transport proves the trusted boundary without assigning host routing policy to an existing provider-neutral seam.
This decision extends the [Agent registration-scope contract](2026-07-08-agent-scope-contexts.md) and its [runtime design](2026-07-12-agent-scope-runtime-design.md); it does not change their static `agent.ctx` meaning.
## Verification
Service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, overlapping, nested, and cleared boundaries, restoration after throws or rejection, drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, missing-provider activation, service restart, and provider/root teardown. Composition, module-graph, build, and runtime-closure checks keep the provider wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses.
Only a test-double host-aware transport consumes ambient identity; it derives `X-Harness-Session-Id` internally and verifies that tool schema and logged arguments contain no identity field. The service deliberately does not drain async work omitted from the Promise returned by `operation`; that work remains subject to its owner's explicit stop contract.
## Alternatives considered
**Pass Agent through every function.** Public, worker, process, persistence, and wire boundaries continue to do this, but requiring every process-local private helper to carry Agent adds repetitive forwarding without improving trust. ALS is confined to the asynchronous chain inside those explicit boundaries.
**Make `ctx.agent` dynamic.** `ctx.agent` already means the static Agent associated with an Agent-scoped Cordis context. Changing the root meaning would mix registration and execution scopes and make concurrent behavior surprising.
**Store a complete mutable runtime frame.** Agent, Session, inbox, cancellation, turn, step, tool execution, and persistence already have authoritative owners. Duplicating them would create stale snapshots and another lifecycle. A named frame makes the execution-context boundary explicit without duplicating owner state.
**Include a step `AbortSignal`, `cwd`, sandbox, or authorization.** Their lifetimes and authority do not match the driver boundary, and their existing seams already pass them explicitly. Adding a control capability requires a separate decision and nested lifecycle contract.
**Use a process-global `currentAgent`.** Concurrent Agents and subagents overwrite one another across awaited continuations, so a mutable global is correct only under a serialization guarantee the harness does not make.
**Derive identity from model-visible arguments.** Model or user input cannot be trusted to select Session, tenant, or sandbox routing.
**Add routing identity to every capability seam.** That spreads hosting concerns through provider-neutral APIs. A host-aware implementation owns its transport header while public boundaries remain explicit.
## Consequences
Deep infrastructure gains one trusted process-local initiating Agent without widening existing tool and capability requests. Concurrent and nested drivers isolate automatically, AgentLoop stays inactive when the provider is absent, and HMR/root disposal reaches quiescence before ALS is disabled.
The dependency is implicit in function signatures and carries a capability-bearing Agent object. Consumers must restrict it to cross-cutting infrastructure, treat ambient presence as neither liveness nor authorization, and retain explicit cancellation and ownership checks. ALS also has an always-on propagation cost and does not cross worker, process, HTTP, or durable queue boundaries.
The teardown design deliberately accepts Node's [Stability 1 (Experimental)](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) `AsyncLocalStorage.disable()` dependency. Node requires `disable()` before an ALS instance can be garbage-collected, which matters when HMR replaces provider-owned instances; the service state guard prevents a later `run()` from re-entering the instance after disposal.
The frame deliberately omits turn, step, `signal`, `cwd`, sandbox, and authorization. A real consumer that cannot use existing explicit fields must justify any refinement separately; a stale copied field may at most mislabel telemetry, never grant control.

View File

@@ -1,61 +0,0 @@
# RFC: 基于 AsyncLocalStorage 的 Agent 执行上下文
Status: implemented
[English](2026-07-15-agent-execution-context.md) | 中文
## 问题
Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负责选择服务、注册归属和生命周期;`agent.ctx` 是一个存活 Agent 所拥有的扁平注册作用域。Agent 与会话身份描述的则是异步操作主体。若把根 `ctx.agent` 改成「当前正在运行的 Agent」就会混淆这两种含义并在单进程并发驱动多个 Agent 时失效。
进程内深层基础设施有时需要在显式传递的循环、工具及请求参数之下获取可信的发起 Agent例如宿主感知传输层、追踪辅助函数、日志器或网关客户端。要求每个私有辅助函数都转发 `agent` 会造成重复,而进程级可变槽会在跨 `await` 时发生并发错误。模型可见参数也不适用,因为模型不得选择可信的会话或路由请求头。该载体属于必需的控制基础设施,而非模型可见的可选上下文。
## 决策
`@deepseek-ai/dsh-agent-execution` 使用 Node `AsyncLocalStorage` 提供必需的 `ctx.agentExecution` 服务。命名的 `AgentExecution` 帧仅包含同一个 Agent 对象;[核心数据目录](../../../core-data-structures/core.md#agent-execution-context)是帧与服务字面类型定义的真源。
`current()` 用于可选读取,`require()` 抛出 `no agent execution context is active``run()` 保留操作返回的同步值或 Promise 本身。`run(undefined, operation)` 会建立清空边界,供不得继承 Agent 的工作使用。会话仍通过 `execution.agent.session` 推导;轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。
`AgentLoop` 注入该服务,并用 `agentExecution.run({ agent }, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此,并发驱动使用彼此独立的存储,子驱动会遮蔽父驱动,子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外:由父 Agent 发起的创建使用父身份,而 `agentCtx.agent` 显式标识子 Agent。
隐式身份不会取代显式契约。`ToolExecution.agent``AssembleContext.agent``GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent``agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求,因为 ALS 只在进程内有效。
提供方使用有序复合 effect。teardown 会先拒绝新边界,再移除服务并等待 AgentLoop 等注入方排空,随后等待活动的返回 Promise 边界,最后调用 `AsyncLocalStorage.disable()`。排空期间,进行中代码可通过保留的服务引用继续调用 `current()``require()`dispose 后,保留引用会抛出 `agent execution service is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown因此除 Cordis 依赖顺序外还必须统计活动边界。
`run()` 不负责管理脱离返回链的工作:提供方排空只跟踪 `operation` 返回的 Promise。边界内创建的异步资源会继承其存储直到自身结束或 ALS 被禁用;所属 seam 必须显式停止未纳入返回 Promise 的工作。Agent 所有前台工作会把完整生命周期纳入返回值,并保留显式取消契约。无关的定时器、队列和部署基础设施在 `run(undefined, operation)` 下启动队列、worker、进程和协议边界必须序列化身份不能期待 ALS 传播。
宿主感知的传输层可以从 `ctx.agentExecution.require().agent.session.id` 推导由部署方拥有的 `X-Harness-Session-Id` 等请求头;模型可见 schema 和参数中不包含该请求头。本决策不让现有生产 MCP 或 Web 传输层采用此请求头。测试替身传输层用于证明可信边界,而不会把宿主路由策略分配给现有的提供方无关 seam。
本决策扩展 [Agent 注册作用域契约](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md),不会改变其中 `agent.ctx` 的静态含义。
## 验证
服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、缺少提供方时的激活行为、服务重启,以及提供方或根 Context 的销毁流程。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 都装载提供方。
只有测试替身形式的宿主感知传输层消费隐式身份;它在内部推导 `X-Harness-Session-Id`,并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空 `operation` 返回的 Promise 之外的异步工作;这类工作仍由所属方的显式停止契约管理。
## 考虑过的替代方案
**在每个函数中传递 Agent。** 公开、worker、进程、持久化和协议边界继续显式传递但要求每个进程内私有辅助函数都携带 Agent 只会造成重复转发不会提高可信度。ALS 仅限于这些显式边界内部的异步调用链。
**让 `ctx.agent` 变成动态值。** `ctx.agent` 已经表示与 Agent 作用域 Cordis 上下文静态关联的 Agent。改变根上下文的含义会混合注册作用域与执行作用域并让并发行为变得意外。
**保存完整的可变运行时帧。** Agent、会话、inbox、取消、轮次、步骤、工具执行和持久化已经有各自的真源。重复保存会产生陈旧快照和另一套生命周期。命名帧能够明确标识执行上下文边界而不重复保存归属方状态。
**包含步骤级 `AbortSignal`、`cwd`、沙箱或授权。** 它们的生命周期及权限范围与驱动边界不一致,而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期契约。
**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步延续执行之间相互覆盖,因此可变全局值只在 Harness 不具备的串行保证下才正确。
**从模型可见参数推导身份。** 不能信任模型或用户输入来选择会话、租户或沙箱路由。
**给每个能力 seam 增加路由身份。** 这会把宿主关注点扩散到提供方无关 API。宿主感知实现拥有其传输请求头而公开边界继续显式传递身份。
## 后果
深层基础设施可以获得一个可信的进程内发起 Agent而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离缺少提供方时 AgentLoop 保持未激活HMR 或根 Context dispose 会在禁用 ALS 前完成排空。
该依赖不会出现在函数签名中,并且携带一个具有控制能力的 Agent 对象。消费方必须将其限制在横切基础设施中把隐式存在视为既不证明存活、也不授予权限并保留显式取消和归属检查。ALS 还有常驻传播成本,也无法跨越 worker、进程、HTTP 或持久化队列边界。
该销毁设计有意依赖 Node 的 [Stability 1实验性](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) API `AsyncLocalStorage.disable()`。Node 要求在 ALS 实例可被垃圾回收前调用 `disable()`,这对 HMR 替换提供方所拥有的实例尤为重要;服务状态守卫会阻止 dispose 后通过后续 `run()` 重新进入该实例。
该帧有意省略轮次、步骤、`signal``cwd`、沙箱和授权。若真实消费方无法使用现有显式字段,必须另行论证扩展;陈旧字段最多只能误标遥测数据,绝不能授予控制权。

View File

@@ -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
2026-07-15-agent-execution-context.md: 2ea88cddf7a686713157c77ce1d7520082a9da28
2026-07-15-agent-execution-context.zh.md: 1c4e0ba9c3fa787dfa816eff4c5d04cff5c2f7b1
2026-07-15-agent-initiator-scope.md: 480bb56f811567406e964ca94fca04fd3d4ace62
2026-07-15-agent-initiator-scope.zh.md: 29ea3a47f42d607a4584b888ace232de124e7598

View File

@@ -0,0 +1,63 @@
# RFC: Initiating Agent scope over AsyncLocalStorage
Status: implemented
English | [中文](2026-07-15-agent-initiator-scope.zh.md)
## Problem
The harness has two useful but different notions of context. A Cordis `Context` selects services, registration ownership, and lifetime; `agent.ctx` is the flat registration scope owned by one live Agent. Agent and Session identity instead describe the subject of an asynchronous operation. Changing a root `ctx.agent` to mean “whichever Agent is running” would conflate those meanings and fail when one process drives Agents concurrently.
Deep process-local infrastructure sometimes needs a trusted initiating Agent below explicit loop, tool, and request parameters—for example, a host-aware transport, tracing helper, logger, or gateway client. Requiring every private helper to forward `agent` adds repetition, while a process-global mutable slot is incorrect across `await`. Model-visible arguments are unsuitable because a model must not choose a trusted Session or routing header. The carrier belongs to the Agent service rather than optional model-visible context.
## Decision
The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the initiating Agent. It stores the exact `Agent` directly rather than introducing a one-field frame; the [core-data catalog](../../../core-data-structures/core.md#initiating-agent) identifies the carried type.
`currentInitiator()` reads optionally, `requireInitiator()` throws `no initiating agent is active`, and `withInitiator(agent, operation)` preserves the operation's exact synchronous value or Promise. `withoutInitiator(operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners.
`AgentLoop` already injects `ctx.agents` and wraps each concrete driver's complete `runLoop` lifetime in `agents.withInitiator(agent, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child.
Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local.
`AgentRegistry` owns an ordered initiator lifecycle. Teardown first rejects new boundaries; removing `ctx.agents` then drains injected dependents such as AgentLoop, and the registry waits for active returned-Promise boundaries before calling `AsyncLocalStorage.disable()`. `currentInitiator()` and `requireInitiator()` remain usable through a retained in-flight service reference while that drain runs; after disposal, initiator methods throw `agent initiator scope is disposed`. Root Context disposal may start sibling fiber teardown concurrently, so active-boundary counting remains necessary in addition to Cordis dependency ordering.
Initiator scope does not own detached work: registry drain tracks only the Promise returned by `withInitiator()` or `withoutInitiator()`. Asynchronous resources created inside a boundary inherit its store until they settle or ALS is disabled, so their owning seam must stop unreturned work explicitly. Agent-owned foreground work returns its lifetime and keeps its cancellation contract. Unrelated timers, queues, and deployment infrastructure start under `withoutInitiator(operation)`; queue, worker, process, and wire boundaries serialize identity rather than expecting ALS propagation.
A host-aware transport may derive a deployment-owned header such as `X-Harness-Session-Id` from `ctx.agents.requireInitiator().session.id`; the header is absent from model-visible schema and arguments. No production MCP or Web transport adopts such a header in this decision. A test-double transport proves the trusted boundary without assigning host routing policy to an existing provider-neutral seam.
This decision extends the [Agent registration-scope contract](2026-07-08-agent-scope-contexts.md) and its [runtime design](2026-07-12-agent-scope-runtime-design.md); it does not change their static `agent.ctx` meaning.
## Verification
Agent service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, overlapping, nested, and cleared boundaries, restoration after throws or rejection, drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, AgentRegistry restart, and root teardown. Composition, module-graph, build, and runtime-closure checks keep `ctx.agents` wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses without another provider.
Only a test-double host-aware transport consumes ambient identity; it derives `X-Harness-Session-Id` internally and verifies that tool schema and logged arguments contain no identity field. The service deliberately does not drain async work omitted from the Promise returned by the boundary operation; that work remains subject to its owner's explicit stop contract.
## Alternatives considered
**Pass Agent through every function.** Public, worker, process, persistence, and wire boundaries continue to do this, but requiring every process-local private helper to carry Agent adds repetitive forwarding without improving trust. ALS is confined to the asynchronous chain inside those explicit boundaries.
**Make `ctx.agent` dynamic.** `ctx.agent` already means the static Agent associated with an Agent-scoped Cordis context. Changing the root meaning would mix registration and execution scopes and make concurrent behavior surprising.
**Add a separate `ctx.agentExecution` service.** The carrier has no independent backend, configuration, or identity type: it stores the same `Agent` that `ctx.agents` already owns, and AgentLoop already depends on that service. A second mandatory provider would add package, composition, lifecycle, generated-catalog, and test-harness wiring without separating a real capability.
**Store a named or complete runtime frame.** A one-field `{ agent }` frame only wraps the value, while Agent, Session, inbox, cancellation, turn, step, tool execution, and persistence already have authoritative owners. Adding more fields would create stale snapshots and another lifecycle; carrying `Agent` directly keeps the boundary named by its methods without duplicating state.
**Include a step `AbortSignal`, `cwd`, sandbox, or authorization.** Their lifetimes and authority do not match the driver boundary, and their existing seams already pass them explicitly. Adding a control capability requires a separate decision and nested lifecycle contract.
**Use a process-global `currentAgent`.** Concurrent Agents and subagents overwrite one another across awaited continuations, so a mutable global is correct only under a serialization guarantee the harness does not make.
**Derive identity from model-visible arguments.** Model or user input cannot be trusted to select Session, tenant, or sandbox routing.
**Add routing identity to every capability seam.** That spreads hosting concerns through provider-neutral APIs. A host-aware implementation owns its transport header while public boundaries remain explicit.
## Consequences
Deep infrastructure gains one trusted process-local initiating Agent without widening existing tool and capability requests. Concurrent and nested drivers isolate automatically, AgentLoop gains no additional mandatory service, and HMR/root disposal reaches quiescence before ALS is disabled.
The dependency is implicit in function signatures and carries a capability-bearing Agent object. Consumers must restrict it to cross-cutting infrastructure, treat ambient presence as neither liveness nor authorization, and retain explicit cancellation and ownership checks. ALS also has an always-on propagation cost and does not cross worker, process, HTTP, or durable queue boundaries.
The teardown design deliberately accepts Node's [Stability 1 (Experimental)](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) `AsyncLocalStorage.disable()` dependency. Node requires `disable()` before an ALS instance can be garbage-collected, which matters when HMR replaces AgentRegistry-owned instances; the service state guard prevents a later boundary from re-entering the instance after disposal.
The scope deliberately carries only the Agent, omitting turn, step, `signal`, `cwd`, sandbox, and authorization. A real consumer that cannot use existing explicit fields must justify any refinement separately; a stale copied field may at most mislabel telemetry, never grant control.

View File

@@ -0,0 +1,63 @@
# RFC: 基于 AsyncLocalStorage 的发起 Agent 作用域
Status: implemented
[English](2026-07-15-agent-initiator-scope.md) | 中文
## 问题
Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负责选择服务、注册归属和生命周期;`agent.ctx` 是一个存活 Agent 所拥有的扁平注册作用域。Agent 与会话身份描述的则是异步操作主体。若把根 `ctx.agent` 改成「当前正在运行的 Agent」就会混淆这两种含义并在单进程并发驱动多个 Agent 时失效。
进程内深层基础设施有时需要在显式传递的循环、工具及请求参数之下获取可信的发起 Agent例如宿主感知传输层、追踪辅助函数、日志器或网关客户端。要求每个私有辅助函数都转发 `agent` 会造成重复,而进程级可变槽会在跨 `await` 时发生并发错误。模型可见参数也不适用,因为模型不得选择可信的会话或路由请求头。该载体归 Agent 服务所有,而非模型可见的可选上下文。
## 决策
必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`,不引入只有一个字段的帧;[核心数据目录](../../../core-data-structures/core.md#initiating-agent)标明了所携带的类型。
`currentInitiator()` 用于可选读取,`requireInitiator()` 抛出 `no initiating agent is active``withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界,供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导;轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。
`AgentLoop` 已经注入 `ctx.agents`,并用 `agents.withInitiator(agent, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此,并发驱动使用彼此独立的存储,子驱动会遮蔽父驱动,子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外:由父 Agent 发起的创建使用父身份,而 `agentCtx.agent` 显式标识子 Agent。
隐式身份不会取代显式契约。`ToolExecution.agent``AssembleContext.agent``GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent``agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求,因为 ALS 只在进程内有效。
`AgentRegistry` 管理一个有序的发起方生命周期。teardown 会先拒绝新边界;移除 `ctx.agents`AgentLoop 等注入方开始排空,注册表随后等待活动的返回 Promise 边界,最后调用 `AsyncLocalStorage.disable()`。排空期间,进行中代码可通过保留的服务引用继续调用 `currentInitiator()``requireInitiator()`dispose 后,发起方方法会抛出 `agent initiator scope is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown因此除 Cordis 依赖顺序外仍必须统计活动边界。
发起方作用域不负责管理脱离返回链的工作:注册表排空只跟踪 `withInitiator()``withoutInitiator()` 返回的 Promise。边界内创建的异步资源会继承其存储直到自身结束或 ALS 被禁用;所属 seam 必须显式停止未纳入返回 Promise 的工作。Agent 所有前台工作会把完整生命周期纳入返回值,并保留显式取消契约。无关的定时器、队列和部署基础设施在 `withoutInitiator(operation)` 下启动队列、worker、进程和协议边界必须序列化身份不能期待 ALS 传播。
宿主感知的传输层可以从 `ctx.agents.requireInitiator().session.id` 推导由部署方拥有的 `X-Harness-Session-Id` 等请求头;模型可见 schema 和参数中不包含该请求头。本决策不让现有生产 MCP 或 Web 传输层采用此请求头。测试替身传输层用于证明可信边界,而不会把宿主路由策略分配给现有的提供方无关 seam。
本决策扩展 [Agent 注册作用域契约](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md),不会改变其中 `agent.ctx` 的静态含义。
## 验证
Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、AgentRegistry 重启及根 Context 销毁。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 通过 `ctx.agents` 完成接线,无需其他提供方。
只有测试替身形式的宿主感知传输层消费隐式身份;它在内部推导 `X-Harness-Session-Id`,并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空边界操作所返回 Promise 之外的异步工作;这类工作仍由所属方的显式停止契约管理。
## 考虑过的替代方案
**在每个函数中传递 Agent。** 公开、worker、进程、持久化和协议边界继续显式传递但要求每个进程内私有辅助函数都携带 Agent 只会造成重复转发不会提高可信度。ALS 仅限于这些显式边界内部的异步调用链。
**让 `ctx.agent` 变成动态值。** `ctx.agent` 已经表示与 Agent 作用域 Cordis 上下文静态关联的 Agent。改变根上下文的含义会混合注册作用域与执行作用域并让并发行为变得意外。
**新增独立的 `ctx.agentExecution` 服务。** 该载体没有独立后端、配置或身份类型:它存储的是 `ctx.agents` 已经管理的同一个 `Agent`,而 AgentLoop 本就依赖该服务。第二个必需提供方会增加包、组合、生命周期、生成目录及测试 harness 接线,却没有拆出真实能力。
**保存命名帧或完整运行时帧。** 只有一个字段的 `{ agent }` 帧只是包装该值,而 Agent、会话、inbox、取消、轮次、步骤、工具执行和持久化已经有各自的真源。增加更多字段会产生陈旧快照和另一套生命周期直接携带 `Agent`,由方法名标识边界,无需重复保存状态。
**包含步骤级 `AbortSignal`、`cwd`、沙箱或授权。** 它们的生命周期及权限范围与驱动边界不一致,而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期契约。
**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步延续执行之间相互覆盖,因此可变全局值只在 Harness 不具备的串行保证下才正确。
**从模型可见参数推导身份。** 不能信任模型或用户输入来选择会话、租户或沙箱路由。
**给每个能力 seam 增加路由身份。** 这会把宿主关注点扩散到提供方无关 API。宿主感知实现拥有其传输请求头而公开边界继续显式传递身份。
## 后果
深层基础设施可以获得一个可信的进程内发起 Agent而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离AgentLoop 不增加新的必需服务HMR 或根 Context dispose 会在禁用 ALS 前完成排空。
该依赖不会出现在函数签名中,并且携带一个具有控制能力的 Agent 对象。消费方必须将其限制在横切基础设施中把隐式存在视为既不证明存活、也不授予权限并保留显式取消和归属检查。ALS 还有常驻传播成本,也无法跨越 worker、进程、HTTP 或持久化队列边界。
该销毁设计有意依赖 Node 的 [Stability 1实验性](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) API `AsyncLocalStorage.disable()`。Node 要求在 ALS 实例可被垃圾回收前调用 `disable()`,这对 HMR 替换 AgentRegistry 所拥有的实例尤为重要;服务状态守卫会阻止 dispose 后通过后续边界重新进入该实例。
该作用域有意只携带 Agent省略轮次、步骤、`signal``cwd`、沙箱和授权。若真实消费方无法使用现有显式字段,必须另行论证扩展;陈旧字段最多只能误标遥测数据,绝不能授予控制权。