From 644bf00b86b054d9eb1689d2db86a6d42a6369ad Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Mon, 27 Jul 2026 19:49:22 +0800 Subject: [PATCH] fix(subagent): cancel pending live delivery --- ...continuable-background-subagents.i18n.yaml | 4 +- ...-07-21-continuable-background-subagents.md | 4 +- ...-21-continuable-background-subagents.zh.md | 4 +- docs/cordis-catalog/services.md | 4 +- docs/core-data-structures/subagent.i18n.yaml | 6 +- docs/core-data-structures/subagent.md | 2 +- docs/core-data-structures/subagent.zh.md | 122 +++++++++++++++--- .../cordis/tool-cordis/src/api-catalog.ts | 4 +- packages/subagent/subagent/README.i18n.yaml | 4 +- packages/subagent/subagent/README.md | 2 +- packages/subagent/subagent/README.zh.md | 52 ++++---- .../subagent/subagent/src/continuation.ts | 40 +++++- packages/subagent/subagent/src/index.ts | 5 +- .../subagent/tests/continuation.spec.ts | 28 +++- .../tool-subagent-control/README.i18n.yaml | 6 + .../subagent/tool-subagent-control/README.md | 4 +- .../tool-subagent-control/README.zh.md | 42 ++++++ .../tool-subagent-control/src/index.ts | 1 + .../tests/tool-subagent-control.spec.ts | 51 +++++++- 19 files changed, 320 insertions(+), 65 deletions(-) create mode 100644 packages/subagent/tool-subagent-control/README.i18n.yaml create mode 100644 packages/subagent/tool-subagent-control/README.zh.md diff --git a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.i18n.yaml b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.i18n.yaml index 20ec58ca97..20623c2641 100644 --- a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.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 .agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md -2026-07-21-continuable-background-subagents.md: 5bbc5fb0b605771b0e7c292412d13ec6e56571ba -2026-07-21-continuable-background-subagents.zh.md: 1864f6d47fe95d9771bb73da72caee6bb415ce0f +2026-07-21-continuable-background-subagents.md: 4c2cc4ce2538a3d1cf6756168fe4dc1a6448d22a +2026-07-21-continuable-background-subagents.zh.md: 019b623d447781bf254cb241c1b8f1c64fd49c4a diff --git a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md index 5bbc5fb0b6..4c2cc4ce25 100644 --- a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md +++ b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md @@ -39,7 +39,7 @@ Opening a child session in a human-facing adapter reads its persisted transcript `TaskService.start()` rejects producers when no Task control surface is attached. A human-facing adapter that accepts child input must therefore attach a Task control surface, or run in a deployment that loads `@deepseek-ai/dsh-tool-tasks`; loading the Task service alone is insufficient. SDK-generated spawn and fork compositions mount `@deepseek-ai/dsh-tasks` and `@deepseek-ai/dsh-tool-tasks` with the subagent control pair. This dependency is the cost of using the same Task result, cancellation, and notification path for parent- and human-started activations. -Cancellation always targets the whole current activation. If human and parent messages have joined one turn, either caller's cancellation aborts that turn, disposes its run, and settles its Task as `killed`; the messages do not have independent results or cancellation rights. Independent cancellation requires a later message to start a separate turn instead of steering the current one. +Cancellation always targets the whole current activation. If human and parent messages have joined one turn, either caller's cancellation aborts that turn, disposes its run, and settles its Task as `killed`; the messages do not have independent results or cancellation rights. `sendMessage()` requires the caller's signal, and abort while live steering awaits request admission aborts the activation-owned controller so the provider discards the pending message and the call settles only after the child reaches quiescence. Independent cancellation requires a later message to start a separate turn instead of steering the current one. A cold-resume Task creates its activation-owned `AbortController` before descriptor lookup or any provider await; the lookup, direct-parent authorization, and descriptor fold run inside the Task producer, so the same signal covers them and their failures settle that Task as `failed`. A persistence call that has no signal need not stop its underlying I/O, but the control service rechecks cancellation after every such await and cannot begin or publish child work afterward. Before Agent publication, abort makes the provider reject only after its creation transaction has rolled back and reached quiescence. After publication, the provider closes the creation-signal handoff race, attaches the same signal to the live run before returning it, and cancellation stops the child turn. `task_kill` and exact-owner disposal use this path even when provider resume has not returned a `SubagentRun`; Task settlement waits for rollback or run disposal and records `killed` only after the activation is quiescent. @@ -57,7 +57,7 @@ The control service does not serialize two callers that race a stopped child thr ### Model-facing `send_message` -The model receives one `send_message(subagent_id, message)` tool backed by `SubagentControlService.sendMessage()`. The control operation owns steer-or-resume orchestration and is distinct from the run's `SubagentRun.steer?()`, which only delivers to an already active run. The tool performs no lifecycle routing of its own. It attributes the follow-up as `{ kind: 'coordinator', senderSessionId: parent.id }`; the control service requires a caller-supplied `MessageSource` and carries it through both live steering and cold resume. The child model still receives ordinary user-role content, while the durable source prevents model-generated follow-ups from being classified as direct human input. A human adapter instead supplies `{ kind: 'user' }`. The tool lives in the separately loaded `@deepseek-ai/dsh-tool-subagent-control` package so provider-bound `@deepseek-ai/dsh-tool-subagent` instances can continue registering distinct delegation tools for spawn, fork, or ACP without registering duplicate global control tools. +The model receives one `send_message(subagent_id, message)` tool backed by `SubagentControlService.sendMessage()`. The control operation owns steer-or-resume orchestration and is distinct from the run's `SubagentRun.steer?()`, which only delivers to an already active run. The tool performs no lifecycle routing of its own. It attributes the follow-up as `{ kind: 'coordinator', senderSessionId: parent.id }` and forwards its execution signal; the control service requires both the caller-supplied `MessageSource` and cancellation signal. The source crosses both live steering and cold resume, while cancellation owns only a pending live-delivery wait because a cold-resume Task returns immediately and owns its later cancellation. The child model still receives ordinary user-role content, while the durable source prevents model-generated follow-ups from being classified as direct human input. A human adapter instead supplies `{ kind: 'user' }` and its interaction signal. The tool lives in the separately loaded `@deepseek-ai/dsh-tool-subagent-control` package so provider-bound `@deepseek-ai/dsh-tool-subagent` instances can continue registering distinct delegation tools for spawn, fork, or ACP without registering duplicate global control tools. - If the child has a running Task and live-steering capability, the service calls `run.steer(message, source)` and returns the existing Task id; it creates no Task of its own. - If the child has no running Task, `send_message` creates a fresh Task, cold-resumes the durable session with the message, and returns the new Task id. diff --git a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.zh.md b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.zh.md index 1864f6d47f..019b623d44 100644 --- a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.zh.md +++ b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.zh.md @@ -39,7 +39,7 @@ durable child Session 如果没有附加 Task 控制面,`TaskService.start()` 会拒绝 producer。因此,接受 child 输入的用户界面适配器必须附加 Task 控制面,或运行于加载了 `@deepseek-ai/dsh-tool-tasks` 的部署中;仅加载 Task 服务并不足够。SDK 生成的 spawn 与 fork 组合在挂载 subagent 控制插件对的同时,也会挂载 `@deepseek-ai/dsh-tasks` 与 `@deepseek-ai/dsh-tool-tasks`。这项依赖是 parent 和用户启动的激活共用 Task 结果、取消和通知路径所付出的代价。 -取消始终作用于当前完整激活。如果用户消息和 parent 消息已经加入同一个轮次,任一调用方发起取消都会中止该轮次、dispose 其 run,并将对应 Task 结算为 `killed`;这些消息没有独立的结果或取消权。若需要独立取消,后续消息必须另起轮次,而不能加入当前轮次。 +取消始终作用于当前完整激活。如果用户消息和 parent 消息已经加入同一个轮次,任一调用方发起取消都会中止该轮次、dispose 其 run,并将对应 Task 结算为 `killed`;这些消息没有独立的结果或取消权。`sendMessage()` 要求调用方提供信号;若在线 steering 正在等待请求准入时该信号被中止,激活自有的 controller 会被中止,以便提供方丢弃待处理消息,并且该调用仅在子 agent 完全停稳后结算。若需要独立取消,后续消息必须另起轮次,而不能加入当前轮次。 从持久化存储恢复的 Task 会在查找描述符或等待任何提供方操作之前,创建由本次激活持有的 `AbortController`;描述符查找、直接 parent 鉴权和描述符归并都在该 Task producer 内部执行,因此同一信号覆盖它们,其失败会将该 Task 结算为 `failed`。对于不接受信号的持久化调用,可以让底层 I/O 执行完毕;但控制服务必须在每次这类 await 返回后重新检查取消状态,如已取消,之后不得开始或发布任何 child 工作。在 Agent 发布前收到中止信号时,提供方必须先回滚其创建事务并达到完全停稳状态,然后才让恢复调用以拒绝结束。Agent 发布后,提供方必须消除创建期间移交取消信号时的竞态,在返回前将同一信号附加到存活 run;之后取消会停止 child 轮次。即使提供方的恢复调用尚未返回 `SubagentRun`,`task_kill` 与对确切 owner 实例的 dispose 仍通过这条路径生效。Task 结算会等待回滚或 run dispose 完成,只有在激活完全停稳后才记录 `killed`。 @@ -57,7 +57,7 @@ durable child Session ### 面向模型的 `send_message` -模型获得一个由 `SubagentControlService.sendMessage()` 支撑的 `send_message(subagent_id, message)` 工具。控制操作负责在 steering 与恢复之间编排;它不同于 run 的 `SubagentRun.steer?()`,后者只能向已活跃的 run 发送消息。工具本身不执行生命周期路由。该工具将后续消息的来源标记为 `{ kind: 'coordinator', senderSessionId: parent.id }`;控制服务要求调用方提供 `MessageSource`,并在在线 steering 与 cold resume 两条路径中传递该来源。child 模型收到的仍是普通的 user role 内容,而持久化的来源信息可防止模型生成的后续消息被归类为直接用户输入。用户适配器则提供 `{ kind: 'user' }`。该工具位于单独加载的 `@deepseek-ai/dsh-tool-subagent-control` 包中,因此按提供方绑定的 `@deepseek-ai/dsh-tool-subagent` 实例可以继续为 spawn、fork 或 ACP 注册不同的委派工具,而不会重复注册全局控制工具。 +模型获得一个由 `SubagentControlService.sendMessage()` 支撑的 `send_message(subagent_id, message)` 工具。控制操作负责在 steering 与恢复之间编排;它不同于 run 的 `SubagentRun.steer?()`,后者只能向已活跃的 run 发送消息。工具本身不执行生命周期路由。该工具将后续消息的来源标记为 `{ kind: 'coordinator', senderSessionId: parent.id }`,并转发其执行信号;控制服务要求调用方同时提供 `MessageSource` 和取消信号。来源会贯穿在线 steering 和 cold resume 两条路径,而取消只控制尚未完成的在线投递等待,因为 cold resume Task 会立即返回,并自行负责后续取消。child 模型收到的仍是普通的 user role 内容,而持久化的来源信息可防止模型生成的后续消息被归类为直接用户输入。用户适配器则提供 `{ kind: 'user' }` 及其交互信号。该工具位于单独加载的 `@deepseek-ai/dsh-tool-subagent-control` 包中,因此按提供方绑定的 `@deepseek-ai/dsh-tool-subagent` 实例可以继续为 spawn、fork 或 ACP 注册不同的委派工具,而不会重复注册全局控制工具。 - 如果 child 存在运行中的 Task 并支持在线消息,服务会调用 `run.steer(message, source)` 并返回现有 task id;它不会创建新 Task。 - 如果 child 没有运行中的 Task,`send_message` 会创建新 Task,使用该消息从持久化存储恢复会话,并返回新的 task id。 diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 9cb67d757d..89a4dd5dfa 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -1978,9 +1978,11 @@ startContinuable(spec: ContinuableStartSpec): ContinuableStart * @param childId - durable child session id. * @param message - user-role content to deliver. * @param source - durable caller attribution. + * @param signal - caller cancellation; while live delivery awaits admission, + * abort cancels the shared activation so the wait reaches quiescence. * @returns the existing steered Task or newly started Task. */ -sendMessage( parent: Agent, childId: SessionId, message: ContentBlock[], source: MessageSource, ): Promise +sendMessage( parent: Agent, childId: SessionId, message: ContentBlock[], source: MessageSource, signal: AbortSignal, ): Promise /** * Register a provider under its name. Registration is effect-scoped and HMR diff --git a/docs/core-data-structures/subagent.i18n.yaml b/docs/core-data-structures/subagent.i18n.yaml index af4b1decda..aaa02e1587 100644 --- a/docs/core-data-structures/subagent.i18n.yaml +++ b/docs/core-data-structures/subagent.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -subagent.md: 2497dbab9cfc8304eb7aaeba7109404ac614bbff -subagent.zh.md: 2d96e9bc635951746e72ed58a7c3638dc2598cc2 +# pnpm run verify-translation-pairing --write docs/core-data-structures/subagent.md +subagent.md: 1321429ac9e6280878016601646dd08981ab2b40 +subagent.zh.md: 072b2d2c1635d7c2c59b5a24d2bafc6ee32f8422 diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 9864df25bd..1321429ac9 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -105,7 +105,7 @@ interface SubagentStartRequest { ## Continuable children: `SubagentContinuation` and `SubagentResumeRequest` -A **continuable background subagent** is a durable child session with a series of Task-backed activations. `SubagentService.startContinuable()` allocates the stable child id, snapshots the versioned `subagent/descriptor` payload, and passes both through the resolved start request; the provider publishes exactly that id and appends the descriptor inside the child's first turn. `SubagentService.sendMessage()` loads and authorizes a stopped child before dispatching a fully resolved resume request through the raw `resume()` operation, or steers its live activation. An internal manager owns descriptor lookup and Task association only while `ctx.tasks` and `ctx.agents` exist; persistence is required per continuation operation, not to load the provider registry. `startContinuable()` returns both identities, while `sendMessage()` reports whether the message `steered` the existing Task or `started` a fresh one. Every sender supplies a `MessageSource`; the optional model-facing tool uses `CoordinatorMessageSource`, while a human adapter uses `{ kind: 'user' }`. +A **continuable background subagent** is a durable child session with a series of Task-backed activations. `SubagentService.startContinuable()` allocates the stable child id, snapshots the versioned `subagent/descriptor` payload, and passes both through the resolved start request; the provider publishes exactly that id and appends the descriptor before the initial prompt is admitted. `SubagentService.sendMessage()` loads and authorizes a stopped child before dispatching a fully resolved resume request through the raw `resume()` operation, or steers its live activation. An internal manager owns descriptor lookup and Task association only while `ctx.tasks` and `ctx.agents` exist; persistence is required per continuation operation, not to load the provider registry. `startContinuable()` returns both identities, while `sendMessage()` reports whether the message `steered` the existing Task or `started` a fresh one. Every sender supplies a `MessageSource` and cancellation signal; abort while live delivery awaits admission cancels the shared activation and rejects after quiescence. The optional model-facing tool uses `CoordinatorMessageSource` and its tool-execution signal, while a human adapter uses `{ kind: 'user' }` and its interaction signal. ```ts type-equiv /** Attribution for a model coordinator's follow-up to one of its children. */ diff --git a/docs/core-data-structures/subagent.zh.md b/docs/core-data-structures/subagent.zh.md index 2d96e9bc63..072b2d2c16 100644 --- a/docs/core-data-structures/subagent.zh.md +++ b/docs/core-data-structures/subagent.zh.md @@ -4,13 +4,13 @@ subagent seam:一个 agent(智能体)将工作委派给子 agent。与 [bash](bash.md) 一样,它是**一项可选能力**,不属于 agent loop(智能体循环)主干,因此其词汇定义在此而非 [core.md](core.md) 中。但它在一个维度上与其他所有 seam 不同:**同一上下文中可共存多个提供方实现**,按名称注册(`ctx.subagents`),而 bash 只允许一个执行器。注册表的形状参照 [LLM(大语言模型)适配器注册表](llm-streaming.md),而非单服务的 bash 执行器。 -接口:[dsh-subagent](../../packages/subagent/subagent)(`ctx.subagents` + 下文词汇)。实现为三个兄弟包(package):`dsh-subagent-spawn`、`-fork`、`-acp`;面向模型的消费方是 [dsh-tool-subagent](../../packages/subagent/tool-subagent)。提案与设计理由见 [subagent Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md)。 +接口:[dsh-subagent](../../packages/subagent/subagent)(`ctx.subagents` + 下文词汇)。实现为三个兄弟包(package):`dsh-subagent-spawn`、`-fork`、`-acp`;面向模型的消费方包括 [dsh-tool-subagent](../../packages/subagent/tool-subagent)(按提供方委派)和 [dsh-tool-subagent-control](../../packages/subagent/tool-subagent-control)(可选的全局 `send_message`)。同一个 `ctx.subagents` 服务通过由 Task 支撑的内部管理器负责可继续子 agent 编排。设计理由见 [subagent Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md)、[可继续后台 subagent Agent Note](../../.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md)和[服务合并 Agent Note](../../.agents/notes/implemented/simplification/2026-07-26-merge-subagent-control-service.md)。 -源码:[`packages/subagent/subagent/src/types.ts`](../../packages/subagent/subagent/src/types.ts) +源码:[`packages/subagent/subagent/src/types.ts`](../../packages/subagent/subagent/src/types.ts)、[`packages/subagent/subagent/src/index.ts`](../../packages/subagent/subagent/src/index.ts)和 [`packages/subagent/subagent/src/continuation.ts`](../../packages/subagent/subagent/src/continuation.ts) ## 两类能力,两种发现方式 -提供方通过一个静态描述符公布其**启动时**特性,服务在 run 存在之前即行检查;如果请求依赖提供方不具备的特性,会被大声拒绝(`SubagentError('UNSUPPORTED_CAPABILITY')`),绝不会被接受后静默忽略。**运行时**特性(steering(中途引导)、恢复)则是 [`SubagentRun`](#a-live-run-subagentrun) 上的可选方法——方法的存在即为能力,TypeScript 的类型收窄即为发现机制。 +提供方通过一个静态描述符公布其**启动时**特性,服务在 run 存在之前即行检查;如果请求依赖提供方不具备的特性,会被大声拒绝(`SubagentError('UNSUPPORTED_CAPABILITY')`),绝不会被接受后静默忽略。**运行时**特性则是可选方法;方法存在即为能力,TypeScript 的类型收窄即为发现机制:提供确认语义的在线 steering(中途引导)是 [`SubagentRun.steer`](#a-live-run-subagentrun),从持久化存储恢复是 [`SubagentProvider.resume`](#the-provider-seam-subagentprovider)。 ```ts type-equiv /** @@ -18,9 +18,10 @@ subagent seam:一个 agent(智能体)将工作委派给子 agent。与 [ba * {@link SubagentProvider.start}: a request that needs a capability the chosen provider lacks * is rejected with a typed error rather than accepted-then-ignored (the "fail loud, no silent * degradation" rule). These static flags cover features needed before a run exists; runtime - * capabilities such as steering and resume are optional {@link SubagentRun} methods whose presence - * is the capability. Each flag corresponds one-to-one to a {@link SubagentStartRequest} option: - * `depthLimit` to `maxDepth`; the other names match. + * capabilities are optional methods whose presence is the capability — confirmed live steering + * is {@link SubagentRun.steer} and persisted cold resume is {@link SubagentProvider.resume}. Each + * flag corresponds one-to-one to a {@link SubagentStartRequest} option: `depthLimit` to + * `maxDepth`; the other names match. */ interface SubagentCapabilities { readonly outputSchema: boolean @@ -88,11 +89,82 @@ interface SubagentStartRequest { * persona (strict `{{…}}` interpolation against the registered variables). */ readonly persona?: string + /** + * Continuable-child intent, resolved by `ctx.subagents` before start. + * The provider MUST publish exactly `sessionId` as the child identity + * instead of allocating one internally, and MUST append the snapshotted + * `descriptor` as the child's turn-enclosed `subagent/descriptor` event + * before its first request. Requires {@link SubagentProvider.resume} (the + * continuation capability); the service rejects the request otherwise. + */ + readonly continuation?: SubagentContinuation } ``` `signal` 是就绪前后唯一的取消通道。[subagent 组合控制 Agent Note](../../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)规定 persona、live 全局工具过滤、绝对深度以及「可见性而非权限」的设计理由。 +## 可继续子 agent:`SubagentContinuation` 与 `SubagentResumeRequest` + +**可继续后台 subagent** 是一份持久化子 agent 会话,由一系列由 Task 支撑的激活组成。`SubagentService.startContinuable()` 会分配稳定的子 agent id、对版本化的 `subagent/descriptor` payload 建立快照,并通过已解析的启动请求传入二者;提供方会准确发布该 id,并在初始 prompt 获准前追加描述符。`SubagentService.sendMessage()` 会先加载并授权已停止的子 agent,再通过底层 `resume()` 操作分发完全解析的恢复请求,或引导其实时激活。只有 `ctx.tasks` 和 `ctx.agents` 存在时,内部管理器才会负责描述符查找与 Task 关联;每项继续执行操作都要求持久化,而加载提供方注册表不要求持久化。`startContinuable()` 返回两个标识,`sendMessage()` 则报告消息是对现有 Task 执行了 `steered`,还是 `started` 一个新 Task。每个发送方都会提供 `MessageSource` 和取消信号;若在在线投递等待准入期间中止该信号,则会取消共享激活,并在其完全停稳后拒绝调用。可选的面向模型工具使用 `CoordinatorMessageSource` 及其工具执行信号,人工适配器则使用 `{ kind: 'user' }` 及其交互信号。 + +```ts type-equiv +/** Attribution for a model coordinator's follow-up to one of its children. */ +interface CoordinatorMessageSource { + readonly kind: 'coordinator' + /** Session id of the agent whose tool call produced the follow-up. */ + readonly senderSessionId: SessionId +} +``` + +```ts type-equiv +/** + * The resolved continuable-child identity and durable composition record a + * continuation caller attaches to a start request. + */ +interface SubagentContinuation { + /** Service-allocated stable child session id, published verbatim. */ + readonly sessionId: SessionId + /** Snapshotted descriptor persisted in the child log for cold resume. */ + readonly descriptor: SubagentDescriptorData +} +``` + +```ts type-equiv +/** + * What a caller asks for when resuming a persisted continuable child. The + * continuation manager loads the child log, folds and authorizes its descriptor, + * and passes this fully resolved request to + * {@link SubagentService.resume}, which dispatches to + * {@link SubagentProvider.resume}. The provider reconstructs the declared + * composition under the live parent's scope and drives one turn with `prompt`. + */ +interface SubagentResumeRequest { + /** The persisted child session id to resume. */ + readonly sessionId: SessionId + /** The follow-up message that starts the resumed activation's turn. */ + readonly prompt: ContentBlock[] + /** Attribution retained when the follow-up becomes the resumed turn's user-role message. */ + readonly source: MessageSource + /** + * The live parent agent — the direct parent recorded in the persisted child + * header. In-process backends reconstruct the child under this agent's + * currently loaded scope. + */ + readonly parent: Agent + /** + * Activation-owned cancellation signal, created before descriptor lookup. + * Same pre/post-publication contract as {@link SubagentStartRequest.signal}: + * an abort before publication rejects after rollback quiescence, and an + * abort afterward cancels the published child turn. + */ + readonly signal: AbortSignal + /** The folded durable descriptor whose composition the provider reconstructs. */ + readonly descriptor: SubagentDescriptorData +} +``` + +描述符([descriptor.ts](../../packages/subagent/subagent/src/descriptor.ts) 中的 `SubagentDescriptorData`)会对显式字段建立快照,包括提供方名称、已解析的子 agent `agentOptions.provider`/`model`,以及可选的 `persona`/`toolFilter`;它绝不会对可通过合并扩展的 `AgentOptions` 对象建立快照,因此无关的扩展值不会破坏继续执行,后续新增组合配置输入则必须明确更改版本。描述符省略 `subagentDepth`(从持久化存储恢复时,以持久化 header 中的 `delegationDepth` 为单调下界)和 `outputSchema`(单次激活的结果契约,而非持久化组合配置)。`subagent/descriptor` 事件只进入日志:不含 `surfaceOp`,绝不进入模型历史,并由仅追加日志跨压缩保留。 + ## 终态结果:`SubagentResult` 一次 run 的最终产出,由 `SubagentRun.result` resolve。`structured` 仅在请求了 `outputSchema` 且成功满足时才存在;请求 schema 不保证一定能得到它,当子 agent 失败或结束时未产出有效 capture 时,提供方可能返回 `stopReason: 'error'`。非 `completed` 的 `stopReason` 意味着 `output` 可能不完整——消费方将其映射为 `isError` 的工具结果,而非将部分输出报告为成功。 @@ -144,7 +216,7 @@ interface SubagentStopReasonMap { ## 活跃 run:`SubagentRun` -`SubagentRun` 是消费方持有的、指向一个就绪子 agent 的句柄。消费方 await `result` 并始终 dispose(资源释放)该 run,直至其完全停稳。子 agent 失败时以非 completed 的 stop reason resolve;只有不可表示的基础设施故障才会 reject。可选的 `sendMessage` 和 `resume` 方法通过自身的存在来公布运行时能力。 +`SubagentRun` 是消费方持有的、指向一个就绪子 agent 的句柄;它表示一次可 dispose(资源释放)的激活,绝不是持久化子 agent handle。消费方 await `result` 并始终 dispose 该 run,直至其完全停稳。子 agent 失败时以非 completed 的 stop reason resolve;只有不可表示的基础设施故障才会 reject。可继续结果为 completed 还表示提供方已确认本次激活的最终状态具备持久性;必需检查点失败则会 reject。可选且提供确认语义的 `steer` 方法通过自身的存在公布在线投递功能,并且只有在请求快照准入该消息后才会兑现。从持久化存储恢复属于提供方级操作:`SubagentProvider.resume` 会根据子 agent 的持久化会话重建一个新 run,因为进程内 run 在 dispose 或进程重启后就不再存在。 ```ts type-equiv /** @@ -169,8 +241,10 @@ interface SubagentRun { * Resolves with the child's terminal {@link SubagentResult} when the run * settles. Does NOT reject on a child-level failure — a model/transport * failure resolves with `stopReason: 'error'` so the consumer maps it to an - * `isError` tool result. Rejects only on an infrastructure fault the seam - * cannot represent as a stop reason. + * `isError` tool result. For a continuable activation, a completed result + * also means the provider confirmed the activation's final state durable. + * Rejects on an infrastructure fault the seam cannot represent as a stop + * reason, including a failed required durability checkpoint. */ readonly result: Promise /** @@ -179,15 +253,16 @@ interface SubagentRun { */ dispose(): Promise /** - * OPTIONAL (steering capability): send additional content to the running - * child between steps. Present only on providers that support live steering. + * OPTIONAL (confirmed live-steering capability): submit additional content + * to the active child and fulfill only after a committed request snapshot + * admits it. Rejects when terminal policy, cancellation, disposal, or a lost + * settlement race prevents admission; it never falls through to a queued + * untracked turn or cold resume. A run represents one disposable activation, + * so resuming a settled child goes through {@link SubagentProvider.resume}. + * `source` is retained on the admitted steering message without changing its + * user role in model history. */ - sendMessage?(content: ContentBlock[]): void - /** - * OPTIONAL (resume capability): send a follow-up task to a settled child, - * continuing its session, and return a fresh run for the continuation. - */ - resume?(content: ContentBlock[]): Promise + steer?(content: ContentBlock[], source: MessageSource): Promise } ``` @@ -223,10 +298,21 @@ interface SubagentProvider { * promise rejects. Ownership transfers to the caller only on fulfillment. */ start(request: SubagentStartRequest): Promise + /** + * OPTIONAL (continuation capability): reconstruct a persisted continuable + * child from its own transcript and declared descriptor, drive one + * follow-up turn, and return a fresh run. Method presence is the capability + * — the service rejects `resume` dispatch and continuable starts on + * providers without it. Same publication contract as {@link start}: if + * reconstruction fails or `request.signal` aborts before fulfillment, the + * provider rolls its creation transaction back to quiescence before + * rejecting; after fulfillment the same signal cancels the published run. + */ + resume?(request: SubagentResumeRequest): Promise } ``` -`start()` 仅在 run 就绪时 fulfill。服务铸造唯一 `runId`,从提供方的确切 `localAgent` 快照 `local`,观察结果,emit `subagent/start`,并返回同一个 run;rejection 意味着提供方已清理,且不会 emit 生命周期事件对。配对的 `subagent/end` 携带相同标识与最终输出或基础设施失败。两个事件都仅用于观察,每个 listener 异常都会被独立隔离。 +`start()` 仅在 run 就绪时 fulfill;`resume()` 采用相同的发布与生命周期观察契约。服务铸造唯一 `runId`,从提供方的确切 `localAgent` 快照 `local`,观察结果,emit `subagent/start`,并返回同一个 run;rejection 意味着提供方已清理,且不会 emit 生命周期事件对。配对的 `subagent/end` 携带相同标识与最终输出或基础设施失败。两个事件都仅用于观察,每个 listener 异常都会被独立隔离。 ## 进程内后端:深度与种子 diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 80fb096b4f..624e7aab14 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -893,8 +893,8 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ jsDoc: '/**\n * Start one durable continuable child through a Task-backed initial\n * activation.\n * @param spec - provider, Task label, and delegation request.\n * @returns the stable child id and initial activation Task id.\n */', }, { - signature: 'sendMessage( parent: Agent, childId: SessionId, message: ContentBlock[], source: MessageSource, ): Promise', - jsDoc: '/**\n * Deliver a message to a continuable child by steering its live activation\n * or cold-resuming a fresh Task-backed activation.\n * @param parent - live direct parent authorizing the operation.\n * @param childId - durable child session id.\n * @param message - user-role content to deliver.\n * @param source - durable caller attribution.\n * @returns the existing steered Task or newly started Task.\n */', + signature: 'sendMessage( parent: Agent, childId: SessionId, message: ContentBlock[], source: MessageSource, signal: AbortSignal, ): Promise', + jsDoc: '/**\n * Deliver a message to a continuable child by steering its live activation\n * or cold-resuming a fresh Task-backed activation.\n * @param parent - live direct parent authorizing the operation.\n * @param childId - durable child session id.\n * @param message - user-role content to deliver.\n * @param source - durable caller attribution.\n * @param signal - caller cancellation; while live delivery awaits admission,\n * abort cancels the shared activation so the wait reaches quiescence.\n * @returns the existing steered Task or newly started Task.\n */', }, { signature: 'registerProvider(provider: SubagentProvider): () => void', diff --git a/packages/subagent/subagent/README.i18n.yaml b/packages/subagent/subagent/README.i18n.yaml index e2e1b999ab..7ae82932d2 100644 --- a/packages/subagent/subagent/README.i18n.yaml +++ b/packages/subagent/subagent/README.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 packages/subagent/subagent/README.md -README.md: 3d5d5e7498b1700c07486cc6e894e72fed681bec -README.zh.md: eb26c79665d387a1e779050dad476d8672f67642 +README.md: c0811eb3bd76543b4a07e7242772e38bd51db67e +README.zh.md: 6d346ee423af8e242c58486164cdef85d241b53d diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index af8a2f7b71..c0811eb3bd 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -31,7 +31,7 @@ Multiple providers may coexist under different names. This lets a deployment exp | `start(name, request)` | Validate requested capabilities and semantic values, then await the provider until a real child is ready. Fulfillment returns a holder-owned `SubagentRun`; rejection means the provider has already cleaned every partial startup resource. | | `resume(name, request)` | Capability-checked raw dispatch to `provider.resume?()` with the same run lifecycle observation as `start`; the caller owns descriptor lookup, authorization, and collection. | | `startContinuable(spec)` | Allocate a durable child id and register its initial Task-backed activation. Requires `ctx.tasks`, `ctx.agents`, session persistence, and a resumable provider. | -| `sendMessage(parent, childId, message, source)` | Steer the current activation or start a new Task that cold-resumes the durable child. Requires `ctx.tasks` and `ctx.agents`; cold resume also requires session persistence. | +| `sendMessage(parent, childId, message, source, signal)` | Steer the current activation or start a new Task that cold-resumes the durable child. Aborting `signal` while live delivery awaits admission cancels the shared activation and rejects after it reaches quiescence. Requires `ctx.tasks` and `ctx.agents`; cold resume also requires session persistence. | `SubagentStartRequest.signal` is required and is the canonical cancellation channel. An abort before publication makes `start()` reject after rollback; an abort after publication cancels the live child. The request may also select a model, require structured output, cap delegation depth, restrict child tools, set a child persona, or carry a resolved `continuation` (the control-allocated stable child id plus its durable descriptor), which requires the provider's `resume` capability. diff --git a/packages/subagent/subagent/README.zh.md b/packages/subagent/subagent/README.zh.md index e202718f81..6d346ee423 100644 --- a/packages/subagent/subagent/README.zh.md +++ b/packages/subagent/subagent/README.zh.md @@ -2,34 +2,38 @@ [English](README.md) | 中文 -subagent seam 允许一个 agent(智能体)通过具名提供方把工作委派给子 agent。调用方使用统一的服务 API(`ctx.subagents`);提供方决定子 agent 在当前进程中、另一进程中,还是通过未来的传输机制运行。 +subagent seam 允许一个 agent(智能体)通过具名提供方把工作委派给子 agent。调用方使用统一的服务 API(`ctx.subagents`);提供方决定子 agent 在当前进程、另一进程还是未来的传输之上运行。 -## 包(package)的角色 +## 包角色 -该系列包把稳定接口与实现、面向模型的工具分开: +该能力族把稳定接口与实现、面向模型的工具分开: | 包 | 角色 | |---|---| -| `@deepseek-ai/dsh-subagent` | 提供方注册表、请求/结果类型和生命周期事件。 | -| `@deepseek-ai/dsh-subagent-spawn` | 全新的进程内子 agent。 | -| `@deepseek-ai/dsh-subagent-fork` | 以父 agent 已完成轮次作为初始内容的进程内子 agent。 | -| `@deepseek-ai/dsh-subagent-acp` | 全新的进程外 ACP(Agent Client Protocol)子 agent。 | -| `@deepseek-ai/dsh-tool-subagent` | 基于一个已配置提供方、面向模型的工具。 | +| `@deepseek-ai/dsh-subagent` | 提供方注册表、请求/结果/描述符类型、生命周期事件和可继续子 agent 编排。 | +| `@deepseek-ai/dsh-subagent-spawn` | 支持从持久化存储恢复的全新进程内子 agent。 | +| `@deepseek-ai/dsh-subagent-fork` | 以父 agent 已完成轮次作为初始内容,并支持从持久化存储恢复的进程内子 agent。 | +| `@deepseek-ai/dsh-subagent-acp` | 全新的进程外 ACP(Agent Client Protocol)子 agent(一次性)。 | +| `@deepseek-ai/dsh-tool-subagent` | 基于一个已配置提供方、面向模型的委派工具。 | +| `@deepseek-ai/dsh-tool-subagent-control` | 全局具名 `send_message` 后续操作工具。 | 多个提供方可以使用不同名称共存。因此,部署可以同时公开低成本的进程内子 agent 和隔离的 ACP 子 agent,而无需改变服务契约。 ## 服务 API -`SubagentService` 有四个主要操作: +`SubagentService` 有七个主要操作: | 成员 | 含义 | |---|---| -| `registerProvider(provider)` | 按名称注册一个可信的同进程实现。注册受 effect 作用域约束;移除注册会阻止新的启动,但不会撤销已返回给调用方的运行。重复名称会明确报错。 | +| `registerProvider(provider)` | 按名称注册一个可信的同进程实现。注册受 effect 作用域约束;移除注册会阻止新的启动,但不会撤销已返回给调用方的运行。重复名称会立即失败。 | | `getProvider(name)` | 返回提供方;不存在时返回 `undefined`。 | | `list()` | 按插入顺序返回提供方名称。 | -| `start(name, request)` | 校验请求的能力和语义值,然后等待提供方,直到真实子 agent 就绪。兑现时返回由持有方拥有的 `SubagentRun`;拒绝表示提供方已清理启动过程中取得的全部资源。 | +| `start(name, request)` | 校验请求的能力和语义值,然后等待提供方,直到真实子 agent 就绪。兑现时返回由持有方拥有的 `SubagentRun`;拒绝表示提供方已清理所有局部启动资源。 | +| `resume(name, request)` | 在功能检查后将底层请求分发给 `provider.resume?()`,并沿用与 `start` 相同的运行生命周期观察;描述符查找、授权与收集由调用方负责。 | +| `startContinuable(spec)` | 分配持久化子 agent id,并注册其初始的由 Task 支撑的激活。要求 `ctx.tasks`、`ctx.agents`、会话持久化及可恢复的提供方。 | +| `sendMessage(parent, childId, message, source, signal)` | 引导当前激活,或启动新 Task 从持久化存储恢复子 agent。若在在线投递等待准入期间中止 `signal`,则会取消共享激活,并在其完全停稳后拒绝该调用。要求 `ctx.tasks` 和 `ctx.agents`;从持久化存储恢复还要求会话持久化。 | -`SubagentStartRequest.signal` 是必填项,也是规范取消通道。发布前中止会使 `start()` 在回滚后拒绝;发布后中止会取消正在运行的子 agent。请求还可以选择模型、要求结构化输出、限制委派深度、约束子 agent 工具或设置子 agent persona。 +`SubagentStartRequest.signal` 是必填项,也是规范取消通道。发布前中止会使 `start()` 在回滚后拒绝;发布后中止会取消实时子 agent。请求还可以选择模型、要求结构化输出、限制委派深度、约束子 agent 工具、设置子 agent persona,或携带已解析的 `continuation`(由控制层分配的稳定子 agent id 及其持久化描述符);后者要求提供方具备 `resume` 功能。 同进程请求、描述符、结果和事件 payload 都是以不可变方式借用的可信类型值。服务不会克隆或冻结它们;序列化和不可信输入校验属于真实的进程、worker、持久化和模型边界。 @@ -42,7 +46,11 @@ subagent seam 允许一个 agent(智能体)通过具名提供方把工作委 - `toolFilter`:应用请求的子 agent 工具限制; - `persona`:应用每个子 agent 独立的 persona。 -运行时功能通过可选方法是否存在来检查能力:`SubagentRun.steer?` 只有在活跃子 agent 的请求 snapshot 接纳消息后才会兑现,并会拒绝而非排队一个未跟踪轮次;`SubagentProvider.resume?` 则重建已持久化且可继续的子 agent。一次运行表示一个可 dispose(资源释放)的 activation,因此刻意不提供冷恢复操作;已释放的运行无法在重启后重建。 +运行时功能以可选方法表示,方法是否存在就是功能检查:`SubagentRun.steer?` 只有在活跃子 agent 的请求快照准入消息后才会兑现;无法准入时会拒绝,而不会把消息排入未受跟踪的轮次。`SubagentProvider.resume?` 则会重建持久化的可继续子 agent。run 表示一次可 dispose 的激活,因此有意不提供从持久化存储恢复操作;进程重启后无法重建已 dispose 的 run。 + +## 持久化描述符 + +该 seam 拥有版本化的 `subagent/descriptor` 会话事件词汇(`src/descriptor.ts`):`snapshotSubagentDescriptor()` 会在任何 Task 存在之前校验并分离声明的组合配置,`foldSubagentDescriptor()` 则会在从已加载子 agent 日志中恢复描述符之前,校验当前版本的完整 payload。格式错误的当前版本 payload 会在提供方分发前失败;不受支持的版本会使子 agent 无法恢复。payload 记录提供方名称、已解析的子 agent `agentOptions.provider`/`model`,以及可选的 `persona`/`toolFilter`;这些是显式字段,绝不是可通过合并扩展的 `AgentOptions` 对象,因此无关的扩展值不会破坏继续执行。它省略 `subagentDepth`(持久化 header 的 `delegationDepth` 是单调下界)和 `outputSchema`(单次激活的结果契约)。该事件只进入日志:不含 `surfaceOp`,不进入模型历史,并由仅追加日志跨压缩保留。 ## 委派深度 @@ -52,13 +60,13 @@ subagent seam 允许一个 agent(智能体)通过具名提供方把工作委 ## 所有权与生命周期 -`provider.start(request): Promise` 是所有权转移边界。兑现前,提供方拥有设置过程,并且每次失败时都必须取消、回滚并使启动过程中已取得的资源完全停稳。兑现后,调用方拥有该运行,并且必须在每条路径上调用 `dispose()`。 +`provider.start(request): Promise` 是所有权转移边界。兑现前,提供方拥有设置过程,并且每次失败时都必须取消、回滚并使局部资源完全停稳。兑现后,调用方拥有该运行,并且必须在每条路径上调用 `dispose()`。`provider.resume?(request)` 对恢复后的激活采用相同契约。 -`SubagentRun.result` 兑现为 `{ output, structured?, stopReason }`。子 agent 级失败会以非 `completed` 原因兑现;只有 seam 无法表示的基础设施故障才可以拒绝。`dispose()` 是幂等的,会取消剩余工作,并等待子 agent 资源完全停稳。 +`SubagentRun.result` 兑现为 `{ output, structured?, stopReason }`。子 agent 级失败会以非 `completed` 原因兑现;只有 seam 无法表示的基础设施故障才可以拒绝。对于可继续激活,完成的结果还会确认提供方已使其最终状态具备持久性;必需检查点失败会作为基础设施故障拒绝,而不会发布未经确认的输出。`dispose()` 是幂等的,会取消剩余工作,并等待子 agent 资源完全停稳。 -本地运行会在 `start()` 兑现前发布普通的子 agent/会话,把该共享会话 id 作为 `SubagentRun.id` 返回,以 `SubagentRun.localAgent` 公开该子 agent 本身,并把 `request.parent.session.id` 记录到子 agent 的 `parentSession` header。远程提供方则生成父级作用域的生命周期 id,并返回 `localAgent: undefined`。 +本地运行会在 `start()` 兑现前发布普通的子 agent/会话,把该共享会话 id 作为 `SubagentRun.id` 返回,以 `SubagentRun.localAgent` 公开准确的子 agent,并把 `request.parent.session.id` 记录到子 agent 的 `parentSession` header。可继续启动会准确发布由服务分配的 `continuation.sessionId`。远程提供方则生成父级作用域的生命周期 id,并返回 `localAgent: undefined`。 -服务只会发出 `subagent/start`,而且是在 `start()` 兑现后。它在同步通知前附加结果观察器,因此即使子 agent 已经结算,也仍会先产生 `subagent/start`,再产生 `subagent/end`。这对事件共享服务生成的 `runId`;其 `local` 标志取自提供方准确 `localAgent` 的快照,因此观察器绝不会从可复用的提供方/会话名称推断运行身份或本地性。 +服务只会在 `start()` 或 `resume()` 兑现后发出 `subagent/start`。它在同步通知前附加结果观察器,因此即使子 agent 已经结算,也仍会先产生 `subagent/start`,再产生 `subagent/end`。这对事件共享服务生成的 `runId`;其 `local` 标志取自提供方准确 `localAgent` 的快照,因此观察器绝不会从可复用的提供方/会话名称推断运行身份或本地性。 运行事件受执行委派的父级作用域约束。每个监听器都独立隔离:同步抛出或返回的 promise 被拒绝时,只会记录日志,不会阻塞同级监听器或改变运行。 @@ -66,17 +74,17 @@ subagent seam 允许一个 agent(智能体)通过具名提供方把工作委 ## 收集模型 -面向模型的工具默认同步收集:先等待子 agent 结果,再对运行执行 dispose(资源释放),然后才返回。后台委派不会改变该 seam;消费方把启动过程和最终运行注册到通用 `ctx.tasks` 运行时,随后使用共享任务工具进行收集和取消。完整契约见[后台 subagent 任务 Agent Note(agent 决策记录)](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md)、[能力 seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md)和 `src/types.ts`。 +面向模型的工具默认同步收集:先等待子 agent 结果,再 dispose 运行,然后才返回。一次性后台委派会在工具中注册普通 Task。可继续后台委派会调用 `ctx.subagents.startContinuable()`;只有 `ctx.tasks` 和 `ctx.agents` 可用时,其内部管理器才会存在,而会话持久化按每项继续执行操作解析。收集和取消使用共享 Task 工具。完整契约见[后台 subagent 任务 Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md)、[可继续后台 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md)、[服务合并 Agent Note](../../../.agents/notes/implemented/simplification/2026-07-26-merge-subagent-control-service.md)、[能力 seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md)和 `src/types.ts`。 ## 模型体验 -通过 `dsh-tool-subagent` 间接产生影响;它渲染提供方特定的 schema,以及前台或通用后台结果,同时子 agent 工作上下文只留在子 agent 中。 +通过 `dsh-tool-subagent` 和 `dsh-tool-subagent-control` 间接产生影响;它们渲染提供方特定的 schema,以及前台、后台或后续操作结果,同时子 agent 工作上下文只留在子 agent 中。 #### KV Cache 影响 -不会直接使缓存失效;具名消费方负责请求前缀的任何变化。 +不会直接使缓存失效;具名消费方共同负责请求前缀的任何变化。 -## 已知限制与暂缓事项 +## 已知限制与延期工作 -- **运行时 steering 和延续只是 seam 能力**:当前工具中没有消费 `sendMessage` 和 `resume` 的面向模型消费方。 +- **ACP 子 agent 仍为一次性**:`AcpProvider.resume` 需要在提供方专用描述符数据中持久化远端会话 id,并按子 agent 声明继续执行功能,因为 ACP 的 `loadSession` 支持按子 agent 协商,而不是通过提供方方法是否存在来确定。 - **生命周期事件只供观察**:影响运行的 `subagent/end` 延续或决策接口仍需等待具体消费方。 diff --git a/packages/subagent/subagent/src/continuation.ts b/packages/subagent/subagent/src/continuation.ts index 15bb14bbe4..cd3f7f1f76 100644 --- a/packages/subagent/subagent/src/continuation.ts +++ b/packages/subagent/subagent/src/continuation.ts @@ -248,6 +248,8 @@ export class SubagentContinuationManager { * @param childId - the stable child session id. * @param message - the user-role content to deliver. * @param source - caller-supplied attribution retained across either route. + * @param signal - caller cancellation. During live delivery, abort cancels + * the shared activation and rejects only after it reaches quiescence. * @returns whether the message `steered` the existing Task or `started` a new one. */ async sendMessage( @@ -255,13 +257,14 @@ export class SubagentContinuationManager { childId: SessionId, message: ContentBlock[], source: MessageSource, + signal: AbortSignal, ): Promise { this.assertOwnership(childId) const activation = this.activations.get(childId) if (activation !== undefined) { return { route: 'steered', - taskId: await this.steerActivation(activation, parent, childId, message, source), + taskId: await this.steerActivation(activation, parent, childId, message, source, signal), } } return { route: 'started', taskId: this.resumeActivation(parent, childId, message, source) } @@ -298,6 +301,7 @@ export class SubagentContinuationManager { childId: SessionId, message: ContentBlock[], source: MessageSource, + signal: AbortSignal, ): Promise { const taskId = activation.taskId /* v8 ignore next 3 -- the install and Task registration share one synchronous frame, so an observed activation carries its Task id. */ @@ -323,9 +327,23 @@ export class SubagentContinuationManager { 'NOT_DELIVERED', ) } + const cancelActivation = (): void => { + activation.controller.abort(signal.reason) + } + signal.addEventListener('abort', cancelActivation, { once: true }) + if (signal.aborted) { + cancelActivation() + signal.removeEventListener('abort', cancelActivation) + return await this.cancelledLiveDelivery(activation, childId) + } try { await run.steer(message, source) } catch (error: unknown) { + try { + signal.throwIfAborted() + } catch { + return await this.cancelledLiveDelivery(activation, childId, error) + } // Confirmed steering lost the race with request admission. Deliberately no // cold-resume fallback here: that would attach the message to a turn the // caller did not observe. @@ -334,10 +352,30 @@ export class SubagentContinuationManager { 'NOT_DELIVERED', { cause: error }, ) + } finally { + signal.removeEventListener('abort', cancelActivation) } return taskId } + /** Reject a cancelled live delivery only after its shared activation is quiescent. */ + private async cancelledLiveDelivery( + activation: ActiveActivation, + childId: SessionId, + cause?: unknown, + ): Promise { + /* v8 ignore if -- a published run implies the producer assigned `done` before its provider await resolved. */ + if (activation.done === undefined) { + throw new Error('published subagent activation has no settlement promise') + } + await activation.done + throw new SubagentError( + `subagent "${childId}" live delivery was cancelled; the message was not delivered`, + 'CANCELLED', + cause === undefined ? undefined : { cause }, + ) + } + /** * Cold-resume a persisted child into a fresh Task-backed activation. The * Task owns its `AbortController` before descriptor lookup: the load, diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 8809e6d4ea..902f9bcaea 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -228,6 +228,8 @@ export class SubagentService extends Service { * @param childId - durable child session id. * @param message - user-role content to deliver. * @param source - durable caller attribution. + * @param signal - caller cancellation; while live delivery awaits admission, + * abort cancels the shared activation so the wait reaches quiescence. * @returns the existing steered Task or newly started Task. */ sendMessage( @@ -235,8 +237,9 @@ export class SubagentService extends Service { childId: SessionId, message: ContentBlock[], source: MessageSource, + signal: AbortSignal, ): Promise { - return this.requireContinuations().sendMessage(parent, childId, message, source) + return this.requireContinuations().sendMessage(parent, childId, message, source, signal) } /** diff --git a/packages/subagent/subagent/tests/continuation.spec.ts b/packages/subagent/subagent/tests/continuation.spec.ts index 1ef761881d..7cf2ca91b8 100644 --- a/packages/subagent/subagent/tests/continuation.spec.ts +++ b/packages/subagent/subagent/tests/continuation.spec.ts @@ -119,14 +119,16 @@ const coordinatorSource = { kind: 'coordinator', senderSessionId: SessionId('parent'), } as const +const testSendSignal = new AbortController().signal function sendMessage( ctx: Context, parent: Agent, childId: SessionId, content: ReturnType, + signal: AbortSignal = testSendSignal, ) { - return ctx.subagents.sendMessage(parent, childId, content, { kind: 'user' }) + return ctx.subagents.sendMessage(parent, childId, content, { kind: 'user' }, signal) } describe('SubagentService.startContinuable', () => { @@ -422,6 +424,7 @@ describe('SubagentService.sendMessage', () => { started.childId, message('also consider Y'), coordinatorSource, + testSendSignal, ) releaseFirst() const delivered = await delivery @@ -440,6 +443,27 @@ describe('SubagentService.sendMessage', () => { expect(steering?.data.message.source).toEqual(coordinatorSource) }) + it('cancels the active Task without enqueueing when live delivery is already aborted', async () => { + const { ctx, parent, adapter } = await setup(['hang']) + const started = ctx.subagents.startContinuable(startSpec(parent)) + await vi.waitFor(() => { expect(adapter.requests).toHaveLength(1) }) + const controller = new AbortController() + controller.abort('caller already cancelled') + + await expect(sendMessage( + ctx, + parent, + started.childId, + message('must not enqueue'), + controller.signal, + )).rejects.toMatchObject({ code: 'CANCELLED' }) + expect(ctx.agents.get(started.childId)).toBeUndefined() + const snapshot = await waitTerminal(ctx, started.taskId, parent) + expect(snapshot.status).toBe('killed') + const loaded = await ctx.sessionPersistence.load(started.childId) + expect(loaded.events.some(event => event.type === 'steering/message')).toBe(false) + }) + it('rejects before acknowledgement when terminal policy prevents steering admission', async () => { const { ctx, parent, adapter } = await setup([ toolCallResponse('c1', 'structured_output', { answer: 7 }), @@ -473,6 +497,7 @@ describe('SubagentService.sendMessage', () => { started.childId, message('follow-up that terminal policy rejects'), coordinatorSource, + testSendSignal, ) releaseTool.resolve(undefined) await expect(delivery).rejects.toThrow(/message was not delivered/) @@ -495,6 +520,7 @@ describe('SubagentService.sendMessage', () => { started.childId, message('and then?'), coordinatorSource, + testSendSignal, ) expect(followUp.route).toBe('started') expect(followUp.taskId).not.toBe(started.taskId) diff --git a/packages/subagent/tool-subagent-control/README.i18n.yaml b/packages/subagent/tool-subagent-control/README.i18n.yaml new file mode 100644 index 0000000000..cf3afead31 --- /dev/null +++ b/packages/subagent/tool-subagent-control/README.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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 packages/subagent/tool-subagent-control/README.md +README.md: 0f1eb7a966689d1540c47f41e2f3fa89d2011d2b +README.zh.md: bd140f93f7338a6b1f0e89a285b273080cc5d3cb diff --git a/packages/subagent/tool-subagent-control/README.md b/packages/subagent/tool-subagent-control/README.md index c308e11d99..0f1eb7a966 100644 --- a/packages/subagent/tool-subagent-control/README.md +++ b/packages/subagent/tool-subagent-control/README.md @@ -1,8 +1,10 @@ # @deepseek-ai/dsh-tool-subagent-control +English | [中文](README.zh.md) + The optional, globally named `send_message` tool: a thin adapter over `ctx.subagents.sendMessage()`. Provider-bound `@deepseek-ai/dsh-tool-subagent` instances register distinct delegation tools per transport; this separately loaded package registers one shared follow-up tool, so multiple delegation tools never register duplicate global controls. Its presence does not determine whether a delegation tool starts continuable work. -The tool performs no lifecycle routing. It attributes every follow-up as `{ kind: 'coordinator', senderSessionId: parent.id }`; the subagent service preserves that source while deciding between live delivery to the running activation's existing Task and a fresh Task that cold-resumes the durable child. The tool renders which route was taken and the relevant Task id. A delivery failure becomes an errored tool result stating the message was not delivered. +The tool performs no lifecycle routing. It attributes every follow-up as `{ kind: 'coordinator', senderSessionId: parent.id }`; the subagent service preserves that source while deciding between live delivery to the running activation's existing Task and a fresh Task that cold-resumes the durable child. The tool forwards its execution signal, so cancellation while live delivery awaits admission cancels the shared activation and settles only after the child reaches quiescence. The tool renders which route was taken and the relevant Task id. A delivery failure becomes an errored tool result stating the message was not delivered. ## Model Experience diff --git a/packages/subagent/tool-subagent-control/README.zh.md b/packages/subagent/tool-subagent-control/README.zh.md new file mode 100644 index 0000000000..bd140f93f7 --- /dev/null +++ b/packages/subagent/tool-subagent-control/README.zh.md @@ -0,0 +1,42 @@ +# @deepseek-ai/dsh-tool-subagent-control + +[English](README.md) | 中文 + +可选的全局具名 `send_message` 工具:`ctx.subagents.sendMessage()` 之上的轻量适配器。绑定提供方的 `@deepseek-ai/dsh-tool-subagent` 实例会为每种传输注册不同的委派工具;这个单独加载的包(package)只注册一个共享后续操作工具,因此多个委派工具绝不会重复注册全局控制工具。是否加载本工具不会决定委派工具是否启动可继续工作。 + +本工具不执行生命周期路由。它将每条后续消息的来源标记为 `{ kind: 'coordinator', senderSessionId: parent.id }`;subagent 服务会保留该来源,并在向运行中激活的现有 Task 在线投递消息与创建新 Task、从持久化存储恢复子 agent 之间做出选择。本工具会转发其执行信号,因此,若在在线投递等待准入期间取消,则会取消共享激活,并仅在子 agent 完全停稳后结算。本工具会渲染实际采用的路由及相关 Task id。投递失败会变为出错的工具结果,并明确说明消息未送达。 + +## 模型体验 + +### 工具 schema + +#### 模型看到的内容 + +已生成的 [`send_message` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent-control):包含 `subagent_id` 和 `message`,说明投递或继续执行的语义,以及通过 `task_output` 收集结果的路径。 + +#### Token 影响 + +每个父级请求支付固定的 schema 成本。 + +#### KV Cache 影响 + +前缀保持稳定;schema 不会在运行时改变。 + +### 投递结果 + +#### 模型看到的内容 + +消息加入运行中的激活时返回 `message delivered to running task `;消息启动一次从持久化存储恢复的激活时返回 `message started task continuing subagent `。同步路由失败,包括所有权冲突、steering(中途引导)竞态失败和缺少在线投递功能,都会成为出错的结果,其消息说明该消息未送达。不存在激活时始终报告 `started`:查找在该 Task 内运行,因此未知、属于其他 parent 或缺少描述符的子 agent 会表现为已启动的 Task 结算为 `failed`(通过 `task_output` 读取),而不是出错的 `send_message` 结果。 + +#### Token 影响 + +每次调用产生一条简短确认消息;子 agent 的响应只会在通过 `task_output` 收集时进入父级历史(完成通知是状态行,绝不是响应)。 + +#### KV Cache 影响 + +仅追加;新增可见内容位于可复用请求前缀之后,不会使现有 KV-cache 条目失效。 + +## 已知限制与延期工作 + +- **已投递的消息没有独立结果**:其效果体现在当前 Task 的最终结果中;只有已启动的后续操作才拥有新的 Task 结果。 +- **投递可能在时序竞态中失败**:消息与 Task 结算、取消或清理发生竞态时会明确失败,不会改用从持久化存储恢复;模型会在 Task 结算后重试。 diff --git a/packages/subagent/tool-subagent-control/src/index.ts b/packages/subagent/tool-subagent-control/src/index.ts index d95ecb77a9..3e3bc8eff9 100644 --- a/packages/subagent/tool-subagent-control/src/index.ts +++ b/packages/subagent/tool-subagent-control/src/index.ts @@ -72,6 +72,7 @@ export function apply(ctx: Context): void { SessionId(args.subagent_id), message, { kind: 'coordinator', senderSessionId: parent.id }, + exec.signal, ) return Promise.resolve(result) }, diff --git a/packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts b/packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts index 02c7e6c1a3..c91c657bac 100644 --- a/packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts +++ b/packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts @@ -1,4 +1,4 @@ -import { afterEach, describe, expect, it } from 'vitest' +import { afterEach, describe, expect, it, vi } from 'vitest' import { mkdtempSync, rmSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' @@ -34,9 +34,10 @@ async function setup(script: ConstructorParameters[0]) { await ctx.plugin(LocalTaskService) await ctx.plugin(ToolTasks, {}) await ctx.plugin(tool) - ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) + const adapter = new MockAdapter(script) + ctx.llm.registerAdapter(['mock'], adapter) const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' }) - return { ctx, parent } + return { ctx, parent, adapter } } function text(result: { content: { type: string; text?: string }[] }): string { @@ -44,9 +45,15 @@ function text(result: { content: { type: string; text?: string }[] }): string { } let calls = 0 -function callTool(ctx: Context, name: string, args: unknown, agent?: unknown) { +function callTool( + ctx: Context, + name: string, + args: unknown, + agent?: unknown, + signal: AbortSignal = testToolSignal, +) { return ctx.tools.execute({ - signal: testToolSignal, + signal, callId: CallId(`call-${++calls}`), name, arguments: args, @@ -114,6 +121,40 @@ describe('dsh-tool-subagent-control', () => { expect(text(result)).toBe('message delivered to running task subagent-9') }) + it('cancels a pending live-delivery wait when the tool signal aborts', async () => { + const { ctx, parent, adapter } = await setup(['hang']) + const started = ctx.subagents.startContinuable({ + provider: 'spawn', + label: 'hung work', + request: { prompt: [{ type: 'text', text: 'wait' }], parent }, + }) + await vi.waitFor(() => { expect(adapter.requests).toHaveLength(1) }) + const deliveryStarted: PromiseWithResolvers = Promise.withResolvers() + const sendMessage = ctx.subagents.sendMessage.bind(ctx.subagents) + ctx.subagents.sendMessage = (agent, childId, message, source, signal) => { + const delivery = sendMessage(agent, childId, message, source, signal) + deliveryStarted.resolve() + return delivery + } + + const controller = new AbortController() + const execution = callTool(ctx, 'send_message', { + subagent_id: started.childId, + message: 'follow up', + }, parent, controller.signal) + await deliveryStarted.promise + controller.abort('parent tool cancelled') + + const result = await execution + expect(result.isError).toBe(true) + expect(result.error?.info?.code).toBe('CANCELLED') + expect(ctx.agents.get(started.childId)).toBeUndefined() + const snapshot = await ctx.tasks.wait(started.taskId, 5_000, parent) + expect(snapshot.status).toBe('killed') + const loaded = await ctx.sessionPersistence.load(started.childId) + expect(loaded.events.some(event => event.type === 'steering/message')).toBe(false) + }) + it('reports a delivery failure as an errored, not-delivered result', async () => { const { ctx, parent } = await setup([]) const result = await callTool(ctx, 'send_message', {