From 1468773dcd7f2a6eb0ffa85978a7ad959a152995 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 16:39:40 +0800 Subject: [PATCH 01/11] fix(goal): simplify blockers into one durable phase --- ...rsisted-same-session-goal-domain.i18n.yaml | 4 +- ...7-19-persisted-same-session-goal-domain.md | 12 +- ...9-persisted-same-session-goal-domain.zh.md | 12 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 32 +----- docs/core-data-structures/goal.md | 26 +++-- docs/event-producer-consumer.md | 2 +- docs/glossary.md | 2 +- .../cordis/tool-cordis/src/api-catalog.ts | 28 ++--- packages/goal/goal/README.md | 8 +- packages/goal/goal/src/fold.ts | 61 +++++----- packages/goal/goal/src/index.ts | 96 ++++++++-------- packages/goal/goal/src/types.ts | 21 ++-- packages/goal/goal/tests/goal.spec.ts | 104 +++++++++++------- scripts/gen-cordis-catalog.ts | 2 +- scripts/type-equiv.manifest.json | 2 +- website/zh-CN/api/harness/events.md | 2 +- website/zh-CN/api/harness/goals.md | 89 +++------------ 18 files changed, 219 insertions(+), 286 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.i18n.yaml index d398150b73..b960f69e71 100644 --- a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.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 -2026-07-19-persisted-same-session-goal-domain.md: 1484a919851c18ce978c93c068f6096bbf3b733f -2026-07-19-persisted-same-session-goal-domain.zh.md: 8bcedc6cab6b9219a33a655e8fcbc53762b7413f +2026-07-19-persisted-same-session-goal-domain.md: 75355aa8d94789e0cc227d393c50139708a73f6a +2026-07-19-persisted-same-session-goal-domain.zh.md: fd7e31f4b6a5acec1d2b44fb3088e301b36abd5c diff --git a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md index 1484a91985..75355aa8d9 100644 --- a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md +++ b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md @@ -12,13 +12,13 @@ Durable lifecycle and permission to continue are different facts. A session may ## Decision -`@deepseek-ai/dsh-goal` in `packages/goal/goal/` owns one current same-session goal through `ctx.goals`. A goal has a branded id, objective, durable phase, compare-and-set revision, and `maxGoalRounds`. `defaultMaxGoalRounds` is a validated deployment setting with default `256`; `resolveCreate()` materializes it before mutation. +`@deepseek-ai/dsh-goal` in `packages/goal/goal/` owns one current same-session goal through `ctx.goals`. A goal has a branded id, objective, durable phase, compare-and-set revision, and `maxGoalRounds`. `defaultMaxGoalRounds` is a validated deployment setting with default `256`; `create()` materializes it internally before mutation rather than exposing resolution as another service verb. -The durable phases are `active`, `paused`, `blocked`, `usage-limited`, `budget-limited`, and `complete`. A separate live activation is `armed` or `disarmed`. Creation and explicit resume arm activation; pause, completion, blocking, limit transitions, and clear disarm it. Edits preserve activation. Activation is never part of the persisted snapshot. +The durable phases are `active`, `paused`, `blocked`, and `complete`. A blocked snapshot includes a policy-owned lower-kebab-case code and a normalized free-form message, so usage limits, round caps, execution failures, and human-input dependencies share one lifecycle state without losing their cause. A separate live activation is `armed` or `disarmed`. Creation and explicit resume arm activation; pause, completion, blocking, and clear disarm it. Edits preserve activation and any blocker reason; resume and completion clear that reason. Activation is never part of the persisted snapshot. ### Durable record and replay -Every non-clear mutation uses `Agent.inject()` to append a raw, model-visible `context/message` containing a versioned full snapshot. Clear appends a revisioned tombstone. The context source is `{ kind: 'goal', goalId, revision, round: 0 }`; metadata and rendered `...` content must agree exactly. The session log is the only durable source of truth, so persistence and fork inherit goal records without another database or header field. +Every non-clear mutation uses `Agent.inject()` to append a raw, model-visible `context/message` containing a versioned full snapshot. Clear appends a revisioned tombstone. The context source is `{ kind: 'goal', goalId, revision, round: 0 }`; metadata and rendered `...` content must agree exactly. This descriptive delimiter follows the repository's existing `` convention and [Anthropic's published guidance to structure mixed prompt content with consistent descriptive XML tags](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#structure-prompts-with-xml-tags). That is public model-experience prior art, not evidence about any provider's proprietary training corpus. The session log is the only durable source of truth, so persistence and fork inherit goal records without another database or header field. The replay fold validates JSON shape, source attribution, rendered content, fresh ids, revision continuity, lifecycle transitions, counters, and monotonic per-goal timestamps. Goal rounds are positive sequential `user/message` source numbers for the current active revision and cannot exceed `maxGoalRounds`; ordinary session turns do not affect the counter. A malformed current-format record fails replay rather than being ignored or repaired. @@ -26,7 +26,7 @@ When `Agent.inject()` defers a mutation inside an active tool batch, the service ### Lifecycle and live activation -At most one goal is current. Create requires no current non-complete goal and always generates a revision-one id not used earlier in the session; a completed goal may be replaced. Every other mutation carries the expected `GoalRef`, and stale ids or revisions reject. Resume accepts a stopped phase or a disarmed active goal only when the round cap has remaining capacity; budget limiting requires the admitted count to have reached the cap. +At most one goal is current. Create requires no current non-complete goal and always generates a revision-one id not used earlier in the session; a completed goal may be replaced. Every other mutation carries the expected `GoalRef`, and stale ids or revisions reject. Resume accepts a paused or blocked phase, or a disarmed active goal, only when the round cap has remaining capacity. The domain validates blocker reason shape but deliberately leaves reason codes and the decision to block to policy consumers. A cache built from any seed starts disarmed, and every `agent/session-start` edge disarms it again. Resume and fork therefore preserve the durable objective and history but never initiate work on their own. A later human prompt can be interpreted by the model, whose policy surface may explicitly call resume and arm the goal. @@ -36,7 +36,7 @@ The service accepts only the exact live `Agent` object registered under its id. ## Testing -Unit coverage pins creation defaults, exact-live-agent checks, compare-and-set rejection, every lifecycle transition, cap enforcement, clear/replacement, seeded replay and `SessionStore.fork()` inheritance, session-start disarming and active-goal rearming, FIFO deferred mutation reconciliation, reentrant append observation, rejected-injection rollback, stable corrupt-event replay, service/listener disposal, listener containment, backward-clock clamping, strict record decoding, lifecycle continuity, source/content agreement, and sequential round attribution. A keyless Loader/stdio process test mounts the service and a lifecycle consumer through test-only `cordis.yml`, then reads the persisted JSONL externally to verify the model-visible snapshot and absence of an unrequested goal round. The package source is held to the repository's per-file 100% coverage gate. +Unit coverage pins creation defaults, exact-live-agent checks, compare-and-set rejection, every lifecycle transition, blocker reason validation and retention, cap enforcement on resume, clear/replacement, seeded replay and `SessionStore.fork()` inheritance, session-start disarming and active-goal rearming, FIFO deferred mutation reconciliation, reentrant append observation, rejected-injection rollback, stable corrupt-event replay, service/listener disposal, listener containment, backward-clock clamping, strict record decoding, lifecycle continuity, source/content agreement, and sequential round attribution. A keyless Loader/stdio process test mounts the service and a lifecycle consumer through test-only `cordis.yml`, then reads the persisted JSONL externally to verify the model-visible snapshot and absence of an unrequested goal round. The package source is held to the repository's per-file 100% coverage gate. ## Alternatives considered @@ -52,7 +52,7 @@ Unit coverage pins creation defaults, exact-live-agent checks, compare-and-set r - Resume and fork expose the same durable phase while remaining operationally inert until an explicit resume mutation arms activation. - Full snapshots simplify inspection and strict replay but repeat the objective and state fields in model history until compaction shadows them. - Revision and lifecycle validation reject tampered, partially written, or producer-inconsistent goal records early. -- Round caps bound continuation count only; token, currency, time, and provider limits remain separate policy concerns. +- Round caps bound continuation count only; policy consumers map round, token, currency, time, and provider limits to blocked reasons when they stop work. ## Known limitations and deferred work diff --git a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.zh.md b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.zh.md index 8bcedc6cab..fd7e31f4b6 100644 --- a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.zh.md @@ -12,13 +12,13 @@ Status: implemented ## 决策 -位于 `packages/goal/goal/` 的 `@deepseek-ai/dsh-goal` 通过 `ctx.goals` 管理一个当前的同会话目标。目标包含品牌化 id、目标描述、持久阶段、比较并交换修订号和 `maxGoalRounds`。`defaultMaxGoalRounds` 是经过校验的部署配置，默认值为 `256`；`resolveCreate()` 在变更前将其解析为完整值。 +位于 `packages/goal/goal/` 的 `@deepseek-ai/dsh-goal` 通过 `ctx.goals` 管理一个当前的同会话目标。目标包含品牌化 id、目标描述、持久阶段、比较并交换修订号和 `maxGoalRounds`。`defaultMaxGoalRounds` 是经过校验的部署配置，默认值为 `256`；`create()` 在变更前于内部将其解析为完整值，而不会把解析过程暴露为额外的服务动词。 -持久阶段包括 `active`、`paused`、`blocked`、`usage-limited`、`budget-limited` 和 `complete`。独立的实时激活态为 `armed` 或 `disarmed`。创建与显式恢复会激活目标；暂停、完成、阻塞、达到限制和清除都会解除激活。编辑保留激活态。持久快照绝不包含激活态。 +持久阶段包括 `active`、`paused`、`blocked` 和 `complete`。阻塞快照包含由策略提供的 kebab-case 小写代码和规范化自由文本消息，因此用量限制、回合上限、执行失败和等待人工输入可以共享一个生命周期状态而不丢失原因。独立的实时激活态为 `armed` 或 `disarmed`。创建与显式恢复会激活目标；暂停、完成、阻塞和清除都会解除激活。编辑保留激活态及阻塞原因；恢复和完成会清除该原因。持久快照绝不包含激活态。 ### 持久记录与回放 -每次非清除变更都通过 `Agent.inject()` 追加一条原始且模型可见的 `context/message`，其中包含带版本的完整快照。清除操作追加带修订号的墓碑。上下文来源为 `{ kind: 'goal', goalId, revision, round: 0 }`；元数据必须与渲染后的 `...` 内容完全一致。会话日志是唯一的持久事实来源，因此持久化和 fork 会继承目标记录，而无需另设数据库或头字段。 +每次非清除变更都通过 `Agent.inject()` 追加一条原始且模型可见的 `context/message`，其中包含带版本的完整快照。清除操作追加带修订号的墓碑。上下文来源为 `{ kind: 'goal', goalId, revision, round: 0 }`；元数据必须与渲染后的 `...` 内容完全一致。这个描述性分隔符沿用了仓库已有的 `` 约定，也符合 [Anthropic 关于用一致且描述明确的 XML 标签组织混合提示词内容的公开指南](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#structure-prompts-with-xml-tags)。这是公开的模型体验先例，并非对任何提供方专有训练语料的推断。会话日志是唯一的持久事实来源，因此持久化和 fork 会继承目标记录，而无需另设数据库或头字段。 回放折叠会校验 JSON 形状、来源归属、渲染内容、新 id、修订连续性、生命周期转换、计数器以及单个目标内单调递增的时间戳。目标回合是当前活跃修订上带正数且连续编号的 `user/message` 来源，且不能超过 `maxGoalRounds`；普通会话轮次不会影响该计数器。当前格式的畸形记录会使回放失败，而不会被忽略或修复。 @@ -26,7 +26,7 @@ Status: implemented ### 生命周期与实时激活态 -最多只有一个当前目标。创建要求不存在未完成的当前目标，并始终生成该会话此前未使用过、修订号为一的 id；已完成目标可以被替换。其他每次变更都携带预期的 `GoalRef`，陈旧的 id 或修订号会被拒绝。仅当回合上限仍有余量时，停止阶段或已解除激活的活跃目标才能恢复；只有已接纳回合数达到上限后，才能标记预算受限。 +最多只有一个当前目标。创建要求不存在未完成的当前目标，并始终生成该会话此前未使用过、修订号为一的 id；已完成目标可以被替换。其他每次变更都携带预期的 `GoalRef`，陈旧的 id 或修订号会被拒绝。仅当回合上限仍有余量时，暂停或阻塞阶段以及已解除激活的活跃目标才能恢复。领域层校验阻塞原因的形状，但会把原因代码和是否阻塞的决策留给策略消费者。 从任何种子构建的缓存都以未激活状态开始，每次 `agent/session-start` 边沿也会再次解除激活。因此，恢复和 fork 会保留持久目标与历史，但绝不会自行启动工作。后续人类提示词可由模型解释，其策略表面可以显式调用恢复操作并激活目标。 @@ -36,7 +36,7 @@ Status: implemented ## 测试 -单元测试固定创建默认值、精确实时 agent 校验、比较并交换拒绝、所有生命周期转换、上限执行、清除与替换、种子回放和 `SessionStore.fork()` 继承、会话启动时解除激活与活跃目标重新激活、FIFO 延迟变更协调、重入追加观察、注入拒绝回滚、损坏事件的稳定回放、服务与监听器销毁、监听器隔离、挂钟后退钳制、严格记录解码、生命周期连续性、来源与内容一致性，以及连续目标回合归属。无密钥 Loader/stdio 进程测试通过测试专用 `cordis.yml` 挂载服务与生命周期消费者，再从外部读取持久 JSONL，以验证模型可见快照以及不存在未经请求的目标回合。包源码受仓库逐文件 100% 覆盖率门禁约束。 +单元测试固定创建默认值、精确实时 agent 校验、比较并交换拒绝、所有生命周期转换、阻塞原因校验与保留、恢复时的上限执行、清除与替换、种子回放和 `SessionStore.fork()` 继承、会话启动时解除激活与活跃目标重新激活、FIFO 延迟变更协调、重入追加观察、注入拒绝回滚、损坏事件的稳定回放、服务与监听器销毁、监听器隔离、挂钟后退钳制、严格记录解码、生命周期连续性、来源与内容一致性，以及连续目标回合归属。无密钥 Loader/stdio 进程测试通过测试专用 `cordis.yml` 挂载服务与生命周期消费者，再从外部读取持久 JSONL，以验证模型可见快照以及不存在未经请求的目标回合。包源码受仓库逐文件 100% 覆盖率门禁约束。 ## 考虑过的替代方案 @@ -52,7 +52,7 @@ Status: implemented - 恢复与 fork 会暴露同一持久阶段，但在显式恢复变更激活目标前不会执行任何操作。 - 完整快照便于检查和严格回放，但在压缩隐藏它们之前，会在模型历史中重复目标描述与状态字段。 - 修订号与生命周期校验会尽早拒绝遭篡改、部分写入或生产者不一致的目标记录。 -- 回合上限只约束继续执行次数；token、费用、时间和提供方限制仍属于独立策略。 +- 回合上限只约束继续执行次数；当回合、token、费用、时间或提供方限制停止工作时，策略消费者会把它们映射为不同的阻塞原因。 ## 已知限制与延期工作 diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index c90eacde5e..92f3b16240 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -471,7 +471,7 @@ Goal mutation accepted by one live agent. The matching context event is already Types: [Agent](../core-data-structures/core.md) · [GoalChanged](../core-data-structures/goal.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/goal/goal/src/types.ts:166`](../../packages/goal/goal/src/types.ts) +Source: [`packages/goal/goal/src/types.ts:167`](../../packages/goal/goal/src/types.ts) ## `llm/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 7d33e49c13..bf639bed08 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -484,13 +484,6 @@ Source: [`packages/fs/fs/src/index.ts:80`](../../packages/fs/fs/src/index.ts) Goal service (`ctx.goals`) backed exclusively by the owning session log. ```ts cordis-catalog -/** - * Materialize deployment defaults and validate one create request. - * @param request - objective plus optional caller-selected round cap. - * @returns detached, fully resolved create specification. - */ -resolveCreate(request: CreateGoalRequest): CreateGoalSpec - /** * Read the current goal for one exact live agent. * @param agent - owning live agent. @@ -546,25 +539,10 @@ complete(agent: Agent, ref: GoalRef): GoalView * Mark an active goal blocked and disarm it. * @param agent - owning live agent. * @param ref - expected current revision. - * @returns the blocked view. + * @param reason - policy-owned stable code and human-readable explanation. + * @returns the blocked view with its durable reason. */ -block(agent: Agent, ref: GoalRef): GoalView - -/** - * Mark an active goal stopped by an external usage limit. - * @param agent - owning live agent. - * @param ref - expected current revision. - * @returns the usage-limited view. - */ -markUsageLimited(agent: Agent, ref: GoalRef): GoalView - -/** - * Mark an active goal stopped at its configured round cap. - * @param agent - owning live agent. - * @param ref - expected current revision. - * @returns the budget-limited view. - */ -markBudgetLimited(agent: Agent, ref: GoalRef): GoalView +block(agent: Agent, ref: GoalRef, reason: GoalBlockReason): GoalView /** * Clear the current goal while retaining a durable tombstone and history. @@ -575,9 +553,9 @@ markBudgetLimited(agent: Agent, ref: GoalRef): GoalView clear(agent: Agent, ref: GoalRef): GoalRef ``` -Types: [Agent](../core-data-structures/core.md) · [CreateGoalRequest](../core-data-structures/goal.md) · [CreateGoalSpec](../core-data-structures/goal.md) · [EditGoalRequest](../core-data-structures/goal.md) · [GoalRef](../core-data-structures/goal.md) · [GoalView](../core-data-structures/goal.md) +Types: [Agent](../core-data-structures/core.md) · [CreateGoalRequest](../core-data-structures/goal.md) · [EditGoalRequest](../core-data-structures/goal.md) · [GoalBlockReason](../core-data-structures/goal.md) · [GoalRef](../core-data-structures/goal.md) · [GoalView](../core-data-structures/goal.md) -Source: [`packages/goal/goal/src/index.ts:104`](../../packages/goal/goal/src/index.ts) +Source: [`packages/goal/goal/src/index.ts:131`](../../packages/goal/goal/src/index.ts) ## `ctx.llm` — `LlmService` diff --git a/docs/core-data-structures/goal.md b/docs/core-data-structures/goal.md index d7b8b25fb4..6c4ac165f7 100644 --- a/docs/core-data-structures/goal.md +++ b/docs/core-data-structures/goal.md @@ -24,11 +24,21 @@ type GoalPhase = | 'active' | 'paused' | 'blocked' - | 'usage-limited' - | 'budget-limited' | 'complete' ``` +Blocking is the single durable stopped-by-a-problem state. Its policy-owned reason carries a stable lower-kebab-case code for routing and a free-form explanation for humans and models. + +```ts type-equiv +/** Machine-routable and human-readable explanation for a blocked goal. */ +interface GoalBlockReason { + /** Stable lower-kebab-case classification chosen by the blocking policy. */ + readonly code: string + /** Non-empty explanation shown to humans and models. */ + readonly message: string +} +``` + ```ts type-equiv /** Full durable state written by every non-clear goal mutation. */ interface GoalSnapshot extends GoalRef { @@ -36,6 +46,8 @@ interface GoalSnapshot extends GoalRef { readonly objective: string /** Durable lifecycle phase. */ readonly phase: GoalPhase + /** Present exactly while `phase` is `blocked`. */ + readonly blockedReason?: GoalBlockReason /** Total admitted goal-round cap. */ readonly maxGoalRounds: number } @@ -98,7 +110,7 @@ interface GoalMessageSource { ## Requests and notifications -Creation separates caller omission from the resolved deployment choice. An edit is a partial replacement whose runtime validator requires at least one field. Every mutation notification carries the accepted operation and exact revision; clear omits `goal`. +Creation separates caller omission from the deployment choice, which `create()` resolves internally. An edit is a partial replacement whose runtime validator requires at least one field. Every mutation notification carries the accepted operation and exact revision; clear omits `goal`. ```ts type-equiv /** Input whose omitted round cap is resolved by the service configuration. */ @@ -108,14 +120,6 @@ interface CreateGoalRequest { } ``` -```ts type-equiv -/** Validated create input with every deployment default materialized. */ -interface CreateGoalSpec { - readonly objective: string - readonly maxGoalRounds: number -} -``` - ```ts type-equiv /** Fields changed by an edit; at least one must be present. */ interface EditGoalRequest { diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 8f1fd333fe..e0d5914f6c 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -27,7 +27,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:61`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:70`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:53`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | -| `goal/changed` | `emit` | [`packages/goal/goal/src/types.ts:166`](../packages/goal/goal/src/types.ts) | [`goal`](../packages/goal/goal) (`emit`) | - | +| `goal/changed` | `emit` | [`packages/goal/goal/src/types.ts:167`](../packages/goal/goal/src/types.ts) | [`goal`](../packages/goal/goal) (`emit`) | - | | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:43`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | diff --git a/docs/glossary.md b/docs/glossary.md index 0166f01f63..13b800d9a8 100644 --- a/docs/glossary.md +++ b/docs/glossary.md @@ -18,7 +18,7 @@ FIXME(glossary-completeness): Expand this glossary before the first release so i ## goal -- **goal** — one durable completion objective attached to an existing session, with a revisioned lifecycle phase and a goal-round cap. A goal is state, not a scheduler or a separate conversation; the session log remains its source of truth. +- **goal** — one durable completion objective attached to an existing session, with a revisioned `active` / `paused` / `blocked` / `complete` phase and a goal-round cap; `blocked` retains a policy code and explanation. A goal is state, not a scheduler or a separate conversation; the session log remains its source of truth. - **goal round** — one continuation cycle admitted for the current goal. The same-session driver materializes a goal round as one goal-sourced [turn](#turn), which can contain multiple steps; unrelated human turns in the same session do not consume the goal-round cap. - **goal activation** — process-local permission for a continuation consumer to admit another goal round. Activation is either `armed` or `disarmed`; it is deliberately absent from durable replay, so resume and fork require a later explicit resume mutation before automatic work. diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 38242445df..ba53f5c0ec 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -254,10 +254,6 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'goals', summary: 'Goal service (`ctx.goals`) backed exclusively by the owning session log.', methods: [ - { - signature: 'resolveCreate(request: CreateGoalRequest): CreateGoalSpec', - jsDoc: '/**\n * Materialize deployment defaults and validate one create request.\n * @param request - objective plus optional caller-selected round cap.\n * @returns detached, fully resolved create specification.\n */', - }, { signature: 'get(agent: Agent): GoalView | undefined', jsDoc: '/**\n * Read the current goal for one exact live agent.\n * @param agent - owning live agent.\n * @returns a fresh view or `undefined` when no goal is current.\n * @throws {@link GoalError} when the agent is not the registry\'s live instance.\n */', @@ -283,16 +279,8 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ jsDoc: '/**\n * Mark a current non-complete goal complete and disarm it.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @returns the completed view.\n */', }, { - signature: 'block(agent: Agent, ref: GoalRef): GoalView', - jsDoc: '/**\n * Mark an active goal blocked and disarm it.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @returns the blocked view.\n */', - }, - { - signature: 'markUsageLimited(agent: Agent, ref: GoalRef): GoalView', - jsDoc: '/**\n * Mark an active goal stopped by an external usage limit.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @returns the usage-limited view.\n */', - }, - { - signature: 'markBudgetLimited(agent: Agent, ref: GoalRef): GoalView', - jsDoc: '/**\n * Mark an active goal stopped at its configured round cap.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @returns the budget-limited view.\n */', + signature: 'block(agent: Agent, ref: GoalRef, reason: GoalBlockReason): GoalView', + jsDoc: '/**\n * Mark an active goal blocked and disarm it.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @param reason - policy-owned stable code and human-readable explanation.\n * @returns the blocked view with its durable reason.\n */', }, { signature: 'clear(agent: Agent, ref: GoalRef): GoalRef', @@ -1137,10 +1125,6 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'CreateGoalRequest', declaration: 'export interface CreateGoalRequest {\n readonly objective: string;\n readonly maxGoalRounds?: number;\n}', }, - { - name: 'CreateGoalSpec', - declaration: 'export interface CreateGoalSpec {\n readonly objective: string;\n readonly maxGoalRounds: number;\n}', - }, { name: 'CreateSessionOptions', declaration: 'export interface CreateSessionOptions {\n readonly seed?: readonly SessionEvent[];\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly createdAt?: number;\n readonly seedLength?: number;\n };\n}', @@ -1241,13 +1225,17 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'GoalActivation', declaration: 'export type GoalActivation = \'armed\' | \'disarmed\';', }, + { + name: 'GoalBlockReason', + declaration: 'export interface GoalBlockReason {\n readonly code: string;\n readonly message: string;\n}', + }, { name: 'GoalId', declaration: 'export type GoalId = Branded<\'GoalId\'>;', }, { name: 'GoalPhase', - declaration: 'export type GoalPhase = \'active\' | \'paused\' | \'blocked\' | \'usage-limited\' | \'budget-limited\' | \'complete\';', + declaration: 'export type GoalPhase = \'active\' | \'paused\' | \'blocked\' | \'complete\';', }, { name: 'GoalRef', @@ -1255,7 +1243,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'GoalSnapshot', - declaration: 'export interface GoalSnapshot extends GoalRef {\n readonly objective: string;\n readonly phase: GoalPhase;\n readonly maxGoalRounds: number;\n}', + declaration: 'export interface GoalSnapshot extends GoalRef {\n readonly objective: string;\n readonly phase: GoalPhase;\n readonly blockedReason?: GoalBlockReason;\n readonly maxGoalRounds: number;\n}', }, { name: 'GoalView', diff --git a/packages/goal/goal/README.md b/packages/goal/goal/README.md index 0e0807f684..175d0d0d79 100644 --- a/packages/goal/goal/README.md +++ b/packages/goal/goal/README.md @@ -11,13 +11,13 @@ Event-sourced same-session goal state. The service retains one current completio defaultMaxGoalRounds: 256 ``` -`defaultMaxGoalRounds` must be a positive safe integer. `resolveCreate()` materializes this deployment default before `create()` commits a goal; a request-level value overrides it. +`defaultMaxGoalRounds` must be a positive safe integer. `create()` materializes this deployment default internally before committing a goal; a request-level value overrides it. ## Service contract -`ctx.goals` accepts only the exact live `Agent` instance registered under its id. `get()` returns a detached `GoalView`; mutations use a `GoalRef { id, revision }` compare-and-set fence and reject stale refs. The service exposes create, edit, pause, resume, complete, block, usage-limit, budget-limit, and clear verbs through the generated [service catalog](../../../docs/cordis-catalog/services.md). +`ctx.goals` accepts only the exact live `Agent` instance registered under its id. `get()` returns a detached `GoalView`; mutations use a `GoalRef { id, revision }` compare-and-set fence and reject stale refs. The service exposes create, edit, pause, resume, complete, block, and clear verbs through the generated [service catalog](../../../docs/cordis-catalog/services.md). Creation default resolution is an internal implementation step, not an additional public verb. -At most one goal is current. Creation produces an active revision-one goal and arms it. A non-complete goal must be edited, transitioned, or cleared; a completed goal may be replaced by a globally fresh id. Edits retain phase and activation. Pause, completion, blocking, limit transitions, and clear disarm activation. Resume accepts a stopped phase or a disarmed active goal only while the configured round cap has remaining capacity; an active armed goal rejects the redundant operation. +At most one goal is current. Creation produces an active revision-one goal and arms it. A non-complete goal must be edited, transitioned, or cleared; a completed goal may be replaced by a globally fresh id. Edits retain phase, blocker reason, and activation. Pause, completion, blocking, and clear disarm activation. A block records a policy-owned lower-kebab-case code plus a normalized free-form explanation; provider limits, configured budgets, execution errors, and requests for human input all use this one durable phase rather than multiplying lifecycle states. Resume accepts a stopped phase or a disarmed active goal only while the configured round cap has remaining capacity; it clears any former blocker reason. An active armed goal rejects the redundant operation. Every non-clear mutation appends a complete versioned snapshot through `agent.inject()`; clear appends a revisioned tombstone. The raw `context/message`, its `{ kind: 'goal' }` source, and its metadata must agree exactly. Replay rejects malformed shapes, source/content drift, discontinuous revisions, illegal lifecycle transitions, non-monotonic per-goal timestamps, and non-sequential goal rounds. Mutation timestamps clamp against the preceding goal update when wall time moves backward. @@ -35,7 +35,7 @@ Policy plugins call the service verbs and react to the scoped `goal/changed` eve #### What the model sees -Each mutation is one raw user-role context block. A snapshot is rendered as `{"goal":...,"roundsStarted":...,"createdAt":...,"updatedAt":...}`; a clear renders the tombstone id/revision and `clearedAt`. There is no hidden state summary outside the log. +Each mutation is one raw user-role context block. A snapshot is rendered as `{"goal":...,"roundsStarted":...,"createdAt":...,"updatedAt":...}`; a clear renders the tombstone id/revision and `clearedAt`. There is no hidden state summary outside the log. The descriptive XML delimiter follows this repository's existing `` convention and [Anthropic's published XML-tag prompting guidance](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#structure-prompts-with-xml-tags); it is public model-experience prior art, not a claim about any provider's proprietary training corpus. #### Token effect diff --git a/packages/goal/goal/src/fold.ts b/packages/goal/goal/src/fold.ts index d7256a38db..5f80e7fd4c 100644 --- a/packages/goal/goal/src/fold.ts +++ b/packages/goal/goal/src/fold.ts @@ -6,6 +6,7 @@ import { renderGoalChange } from './render.ts' import { GOAL_CHANGE_VERSION, GoalId } from './runtime.ts' import type { FoldedGoal, + GoalBlockReason, GoalChangeMeta, GoalClearChangeMeta, GoalMessageSource, @@ -25,17 +26,8 @@ const SNAPSHOT_OPERATIONS: ReadonlySet> = new Se 'resume', 'complete', 'block', - 'mark-usage-limited', - 'mark-budget-limited', -]) -const PHASES: ReadonlySet = new Set([ - 'active', - 'paused', - 'blocked', - 'usage-limited', - 'budget-limited', - 'complete', ]) +const PHASES: ReadonlySet = new Set(['active', 'paused', 'blocked', 'complete']) /** Mutable accumulator kept private to the pure fold. */ export interface GoalFoldState { @@ -83,13 +75,24 @@ function nonNegativeInteger(value: unknown, field: string): number { return value } +/** Decode one canonical blocker explanation. */ +function decodeBlockReason(value: unknown): GoalBlockReason { + if (!isRecord(value) || Object.keys(value).sort().join(',') !== 'code,message') { + throw new Error('goal change goal.blockedReason has an invalid shape') + } + if (typeof value['code'] !== 'string' || !/^[a-z][a-z0-9]*(?:-[a-z0-9]+)*$/.test(value['code'])) { + throw new Error('goal change goal.blockedReason.code must be lower-kebab-case') + } + if (typeof value['message'] !== 'string' || value['message'].trim().length === 0 + || value['message'] !== value['message'].trim()) { + throw new Error('goal change goal.blockedReason.message must be non-empty and normalized') + } + return { code: value['code'], message: value['message'] } +} + /** Decode and validate one snapshot. */ function decodeSnapshot(value: unknown): GoalSnapshot { if (!isRecord(value)) throw new Error('goal change goal must be a record') - const keys = Object.keys(value).sort() - if (keys.join(',') !== 'id,maxGoalRounds,objective,phase,revision') { - throw new Error('goal change goal has an invalid shape') - } if (typeof value['id'] !== 'string' || value['id'].length === 0) { throw new Error('goal change goal.id must be a non-empty string') } @@ -100,12 +103,20 @@ function decodeSnapshot(value: unknown): GoalSnapshot { if (typeof value['phase'] !== 'string' || !PHASES.has(value['phase'] as GoalPhase)) { throw new Error('goal change goal.phase is invalid') } + const phase = value['phase'] as GoalPhase + const expectedKeys = phase === 'blocked' + ? 'blockedReason,id,maxGoalRounds,objective,phase,revision' + : 'id,maxGoalRounds,objective,phase,revision' + if (Object.keys(value).sort().join(',') !== expectedKeys) { + throw new Error('goal change goal has an invalid shape') + } return { id: GoalId(value['id']), revision: positiveInteger(value['revision'], 'goal.revision'), objective: value['objective'], - phase: value['phase'] as GoalPhase, + phase, maxGoalRounds: positiveInteger(value['maxGoalRounds'], 'goal.maxGoalRounds'), + ...phase === 'blocked' ? { blockedReason: decodeBlockReason(value['blockedReason']) } : {}, } } @@ -208,7 +219,10 @@ function validateSnapshotTransition( } switch (change.operation) { case 'edit': - if (next.phase !== current.phase) throw new Error('goal edit cannot change phase') + if (next.phase !== current.phase + || JSON.stringify(next.blockedReason) !== JSON.stringify(current.blockedReason)) { + throw new Error('goal edit cannot change phase or blocked reason') + } break case 'pause': requireSameDefinition(current, next, change.operation) @@ -220,8 +234,6 @@ function validateSnapshotTransition( 'active', 'paused', 'blocked', - 'usage-limited', - 'budget-limited', ]) if (!resumable.has(current.phase) || next.phase !== 'active' || state.roundsStarted >= next.maxGoalRounds) { throw new Error('goal resume has an invalid phase transition or exhausted round budget') @@ -236,19 +248,6 @@ function validateSnapshotTransition( requireSameDefinition(current, next, change.operation) if (current.phase !== 'active' || next.phase !== 'blocked') throw new Error('goal block has an invalid phase transition') break - case 'mark-usage-limited': - requireSameDefinition(current, next, change.operation) - if (current.phase !== 'active' || next.phase !== 'usage-limited') { - throw new Error('goal mark-usage-limited has an invalid phase transition') - } - break - case 'mark-budget-limited': - requireSameDefinition(current, next, change.operation) - if (current.phase !== 'active' || next.phase !== 'budget-limited' - || state.roundsStarted < next.maxGoalRounds) { - throw new Error('goal mark-budget-limited has an invalid phase transition or remaining round budget') - } - break /* v8 ignore start -- the caller excludes create and GoalOperation is closed; these arms retain fail-loud exhaustiveness */ case 'create': throw new Error('goal create cannot be validated as a current-goal transition') diff --git a/packages/goal/goal/src/index.ts b/packages/goal/goal/src/index.ts index c8583894ef..dc485bcc8a 100644 --- a/packages/goal/goal/src/index.ts +++ b/packages/goal/goal/src/index.ts @@ -27,9 +27,9 @@ import { } from './runtime.ts' import type { CreateGoalRequest, - CreateGoalSpec, EditGoalRequest, GoalActivation, + GoalBlockReason, GoalChangeMeta, GoalChanged, GoalClearChangeMeta, @@ -79,6 +79,12 @@ interface GoalCache { readonly pending: PendingGoalChange[] } +/** Validated create input with every deployment default materialized. */ +interface ResolvedCreateGoal { + readonly objective: string + readonly maxGoalRounds: number +} + /** Validate a caller-visible positive safe-integer round cap. */ function resolveMaxGoalRounds(value: number): number { if (!Number.isSafeInteger(value) || value < 1) { @@ -95,6 +101,31 @@ function resolveObjective(value: string): string { return value.trim() } +/** Materialize deployment defaults and validate one create request. */ +function resolveCreateGoal(request: CreateGoalRequest, defaultMaxGoalRounds: number): ResolvedCreateGoal { + return { + objective: resolveObjective(request.objective), + maxGoalRounds: resolveMaxGoalRounds(request.maxGoalRounds ?? defaultMaxGoalRounds), + } +} + +/** Validate and detach one policy-owned blocker explanation. */ +function resolveBlockReason(reason: unknown): GoalBlockReason { + const record = typeof reason === 'object' && reason !== null && !Array.isArray(reason) + ? reason as Record + : undefined + const code = record?.['code'] + const message = record?.['message'] + if (typeof code !== 'string' || !/^[a-z][a-z0-9]*(?:-[a-z0-9]+)*$/.test(code) + || typeof message !== 'string' || message.trim().length === 0) { + throw new GoalError( + 'goal block reason requires a lower-kebab-case code and a non-empty message', + 'GOAL_INVALID_BLOCK_REASON', + ) + } + return { code, message: message.trim() } +} + /** Compare the complete canonical payloads used for deferred reconciliation. */ function sameChange(left: GoalChangeMeta, right: GoalChangeMeta): boolean { return JSON.stringify(left) === JSON.stringify(right) @@ -121,18 +152,6 @@ export class GoalService extends Service { }) } - /** - * Materialize deployment defaults and validate one create request. - * @param request - objective plus optional caller-selected round cap. - * @returns detached, fully resolved create specification. - */ - resolveCreate(request: CreateGoalRequest): CreateGoalSpec { - return { - objective: resolveObjective(request.objective), - maxGoalRounds: resolveMaxGoalRounds(request.maxGoalRounds ?? this.resolved.defaultMaxGoalRounds), - } - } - /** * Read the current goal for one exact live agent. * @param agent - owning live agent. @@ -154,7 +173,7 @@ export class GoalService extends Service { * @returns the created live view. */ create(agent: Agent, request: CreateGoalRequest): GoalView { - const spec = this.resolveCreate(request) + const spec = resolveCreateGoal(request, this.resolved.defaultMaxGoalRounds) const cache = this.prepareMutation(agent) const current = cache.state.goal if (current !== undefined && current.phase !== 'complete') { @@ -213,7 +232,7 @@ export class GoalService extends Service { resume(agent: Agent, ref: GoalRef): GoalView { const cache = this.prepareMutation(agent) const current = this.expectCurrent(cache, ref) - const resumable: readonly GoalPhase[] = ['active', 'paused', 'blocked', 'usage-limited', 'budget-limited'] + const resumable: readonly GoalPhase[] = ['active', 'paused', 'blocked'] if (!resumable.includes(current.phase)) { throw this.transitionError(current, 'resume', resumable) } @@ -240,7 +259,7 @@ export class GoalService extends Service { agent, ref, 'complete', - ['active', 'paused', 'blocked', 'usage-limited', 'budget-limited'], + ['active', 'paused', 'blocked'], 'complete', 'disarmed', ) @@ -250,45 +269,20 @@ export class GoalService extends Service { * Mark an active goal blocked and disarm it. * @param agent - owning live agent. * @param ref - expected current revision. - * @returns the blocked view. + * @param reason - policy-owned stable code and human-readable explanation. + * @returns the blocked view with its durable reason. */ - block(agent: Agent, ref: GoalRef): GoalView { - return this.transition(agent, ref, 'block', ['active'], 'blocked', 'disarmed') - } - - /** - * Mark an active goal stopped by an external usage limit. - * @param agent - owning live agent. - * @param ref - expected current revision. - * @returns the usage-limited view. - */ - markUsageLimited(agent: Agent, ref: GoalRef): GoalView { - return this.transition(agent, ref, 'mark-usage-limited', ['active'], 'usage-limited', 'disarmed') - } - - /** - * Mark an active goal stopped at its configured round cap. - * @param agent - owning live agent. - * @param ref - expected current revision. - * @returns the budget-limited view. - */ - markBudgetLimited(agent: Agent, ref: GoalRef): GoalView { + block(agent: Agent, ref: GoalRef, reason: GoalBlockReason): GoalView { const cache = this.prepareMutation(agent) const current = this.expectCurrent(cache, ref) if (current.phase !== 'active') { - throw this.transitionError(current, 'mark-budget-limited', ['active']) - } - if (cache.state.roundsStarted < current.maxGoalRounds) { - throw new GoalError( - `goal "${current.id}" has started ${cache.state.roundsStarted}/${current.maxGoalRounds} rounds`, - 'GOAL_INVALID_TRANSITION', - ) + throw this.transitionError(current, 'block', ['active']) } return this.commitCurrent( agent, cache, - 'mark-budget-limited', - this.withPhase(current, 'budget-limited'), + 'block', + { ...this.withPhase(current, 'blocked'), blockedReason: resolveBlockReason(reason) }, 'disarmed', ) } @@ -384,7 +378,13 @@ export class GoalService extends Service { /** Build a new revision with one replacement phase. */ private withPhase(current: GoalSnapshot, phase: GoalPhase): GoalSnapshot { - return { ...current, revision: current.revision + 1, phase } + return { + id: current.id, + revision: current.revision + 1, + objective: current.objective, + phase, + maxGoalRounds: current.maxGoalRounds, + } } /** Shared validated phase transition. */ diff --git a/packages/goal/goal/src/types.ts b/packages/goal/goal/src/types.ts index ef40e997ef..2c6798718d 100644 --- a/packages/goal/goal/src/types.ts +++ b/packages/goal/goal/src/types.ts @@ -22,16 +22,24 @@ export type GoalPhase = | 'active' | 'paused' | 'blocked' - | 'usage-limited' - | 'budget-limited' | 'complete' +/** Machine-routable and human-readable explanation for a blocked goal. */ +export interface GoalBlockReason { + /** Stable lower-kebab-case classification chosen by the blocking policy. */ + readonly code: string + /** Non-empty explanation shown to humans and models. */ + readonly message: string +} + /** Full durable state written by every non-clear goal mutation. */ export interface GoalSnapshot extends GoalRef { /** Human-requested completion objective. */ readonly objective: string /** Durable lifecycle phase. */ readonly phase: GoalPhase + /** Present exactly while `phase` is `blocked`. */ + readonly blockedReason?: GoalBlockReason /** Total admitted goal-round cap. */ readonly maxGoalRounds: number } @@ -59,8 +67,6 @@ export type GoalOperation = | 'resume' | 'complete' | 'block' - | 'mark-usage-limited' - | 'mark-budget-limited' | 'clear' /** Full-snapshot goal mutation retained in a model-visible context event. */ @@ -121,12 +127,6 @@ export interface CreateGoalRequest { readonly maxGoalRounds?: number } -/** Validated create input with every deployment default materialized. */ -export interface CreateGoalSpec { - readonly objective: string - readonly maxGoalRounds: number -} - /** Fields changed by an edit; at least one must be present. */ export interface EditGoalRequest { readonly objective?: string @@ -149,6 +149,7 @@ export type GoalErrorCode = | 'GOAL_STALE_REVISION' | 'GOAL_INVALID_OBJECTIVE' | 'GOAL_INVALID_MAX_ROUNDS' + | 'GOAL_INVALID_BLOCK_REASON' | 'GOAL_INVALID_EDIT' | 'GOAL_INVALID_TRANSITION' diff --git a/packages/goal/goal/tests/goal.spec.ts b/packages/goal/goal/tests/goal.spec.ts index 4dcae8938a..eac96e0374 100644 --- a/packages/goal/goal/tests/goal.spec.ts +++ b/packages/goal/goal/tests/goal.spec.ts @@ -111,17 +111,13 @@ function appendRound(session: Session, ref: GoalRef, round: number): void { } describe('GoalService creation and replay', () => { - it('resolves the configured default and writes one balanced raw context snapshot', async () => { + it('applies the configured default and writes one balanced raw context snapshot', async () => { vi.useFakeTimers() vi.setSystemTime(1_700_000_000_000) const { ctx, agent, session } = await harness({ defaultMaxGoalRounds: 17 }) const seen: string[] = [] ctx.on('goal/changed', (_subject, change) => { seen.push(change.operation) }) - expect(ctx.goals.resolveCreate({ objective: ' finish the feature ' })).toEqual({ - objective: 'finish the feature', - maxGoalRounds: 17, - }) const goal = ctx.goals.create(agent, { objective: ' finish the feature ' }) expect(goal).toMatchObject({ @@ -151,18 +147,19 @@ describe('GoalService creation and replay', () => { vi.useRealTimers() }) - it('uses 256 rounds by default and validates create input at the owning resolver', async () => { + it('uses 256 rounds by default and validates create input inside create', async () => { const { ctx, agent } = await harness() - expect(ctx.goals.resolveCreate({ objective: 'x' })).toEqual({ objective: 'x', maxGoalRounds: 256 }) - expect(() => ctx.goals.resolveCreate({ objective: ' ' })).toThrow(expect.objectContaining({ + expect(() => ctx.goals.create(agent, { objective: ' ' })).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_OBJECTIVE', })) - expect(() => ctx.goals.resolveCreate({ objective: 'x', maxGoalRounds: 0 })).toThrow(expect.objectContaining({ + expect(() => ctx.goals.create(agent, { objective: 'x', maxGoalRounds: 0 })).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_MAX_ROUNDS', })) - expect(() => ctx.goals.resolveCreate({ objective: 'x', maxGoalRounds: 1.5 })).toThrow(GoalError) - expect(() => ctx.goals.resolveCreate({ objective: 'x', maxGoalRounds: 1.5 })).toThrow(HarnessError) - expect(() => ctx.goals.resolveCreate({ objective: 'x', maxGoalRounds: Number.MAX_SAFE_INTEGER + 1 })).toThrow(GoalError) + expect(() => ctx.goals.create(agent, { objective: 'x', maxGoalRounds: 1.5 })).toThrow(GoalError) + expect(() => ctx.goals.create(agent, { objective: 'x', maxGoalRounds: 1.5 })).toThrow(HarnessError) + expect(() => ctx.goals.create(agent, { + objective: 'x', maxGoalRounds: Number.MAX_SAFE_INTEGER + 1, + })).toThrow(GoalError) expect(ctx.goals.create(agent, { objective: 'x' }).maxGoalRounds).toBe(256) }) @@ -170,9 +167,10 @@ describe('GoalService creation and replay', () => { const ctx = new Context() await ctx.plugin(AgentRegistry) const goals = new GoalService(ctx) - expect(goals.resolveCreate({ objective: 'direct' })).toEqual({ - objective: 'direct', - maxGoalRounds: 256, + const stub = stubAgent('goal-direct-construction') + ctx.agents.register(stub.agent) + expect(goals.create(stub.agent, { objective: 'direct' })).toMatchObject({ + objective: 'direct', maxGoalRounds: 256, }) }) @@ -287,18 +285,19 @@ describe('GoalService mutations', () => { })) }) - it('supports pause, resume, block, usage-limit, and completion transitions', async () => { + it('supports pause, resume, block, and completion transitions', async () => { const { ctx, agent } = await harness() let goal = ctx.goals.create(agent, { objective: 'lifecycle' }) goal = ctx.goals.pause(agent, goal) expect(goal).toMatchObject({ phase: 'paused', activation: 'disarmed', revision: 2 }) goal = ctx.goals.resume(agent, goal) expect(goal).toMatchObject({ phase: 'active', activation: 'armed', revision: 3 }) - goal = ctx.goals.block(agent, goal) - expect(goal).toMatchObject({ phase: 'blocked', activation: 'disarmed' }) - goal = ctx.goals.resume(agent, goal) - goal = ctx.goals.markUsageLimited(agent, goal) - expect(goal.phase).toBe('usage-limited') + goal = ctx.goals.block(agent, goal, { code: 'needs-input', message: 'A choice is required.' }) + expect(goal).toMatchObject({ + phase: 'blocked', + blockedReason: { code: 'needs-input', message: 'A choice is required.' }, + activation: 'disarmed', + }) goal = ctx.goals.resume(agent, goal) goal = ctx.goals.pause(agent, goal) goal = ctx.goals.complete(agent, goal) @@ -307,15 +306,13 @@ describe('GoalService mutations', () => { }) it('allows completion from every stopped phase and replacement only after completion', async () => { - const phases = ['paused', 'blocked', 'usage-limited'] as const + const phases = ['paused', 'blocked'] as const for (const phase of phases) { const { ctx, agent } = await harness() let goal = ctx.goals.create(agent, { objective: phase }) goal = phase === 'paused' ? ctx.goals.pause(agent, goal) - : phase === 'blocked' - ? ctx.goals.block(agent, goal) - : ctx.goals.markUsageLimited(agent, goal) + : ctx.goals.block(agent, goal, { code: 'test-blocker', message: 'Blocked for the test.' }) const complete = ctx.goals.complete(agent, goal) const replacement = ctx.goals.create(agent, { objective: `after ${phase}` }) expect(complete.phase).toBe('complete') @@ -333,32 +330,45 @@ describe('GoalService mutations', () => { expect(() => ctx.goals.resume(agent, goal)).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_TRANSITION' })) const paused = ctx.goals.pause(agent, goal) expect(() => ctx.goals.pause(agent, paused)).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_TRANSITION' })) - expect(() => ctx.goals.block(agent, paused)).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_TRANSITION' })) - expect(() => ctx.goals.markUsageLimited(agent, paused)).toThrow(expect.objectContaining({ - code: 'GOAL_INVALID_TRANSITION', - })) - expect(() => ctx.goals.markBudgetLimited(agent, paused)).toThrow(expect.objectContaining({ + expect(() => ctx.goals.block(agent, paused, { + code: 'test-blocker', message: 'Blocked for the test.', + })).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_TRANSITION', })) }) - it('enforces the goal-round cap before budget limiting and resuming', async () => { + it('records canonical blocker reasons and enforces the round cap on resume', async () => { const { ctx, agent, session } = await harness() let goal = ctx.goals.create(agent, { objective: 'bounded', maxGoalRounds: 2 }) + for (const reason of [null, [], { code: 1, message: 'invalid code' }, { code: 'round-limit', message: 1 }]) { + expect(() => ctx.goals.block(agent, goal, reason as never)).toThrow(expect.objectContaining({ + code: 'GOAL_INVALID_BLOCK_REASON', + })) + } + expect(() => ctx.goals.block(agent, goal, { + code: 'Not Canonical', message: 'invalid code', + })).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_BLOCK_REASON' })) + expect(() => ctx.goals.block(agent, goal, { + code: 'round-limit', message: ' ', + })).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_BLOCK_REASON' })) appendRound(session, goal, 1) expect(ctx.goals.get(agent)?.roundsStarted).toBe(1) - expect(() => ctx.goals.markBudgetLimited(agent, goal)).toThrow(expect.objectContaining({ - code: 'GOAL_INVALID_TRANSITION', - })) appendRound(session, goal, 2) - goal = ctx.goals.markBudgetLimited(agent, goal) - expect(goal).toMatchObject({ phase: 'budget-limited', roundsStarted: 2, activation: 'disarmed' }) + goal = ctx.goals.block(agent, goal, { code: 'round-limit', message: ' Goal round limit reached. ' }) + expect(goal).toMatchObject({ + phase: 'blocked', + blockedReason: { code: 'round-limit', message: 'Goal round limit reached.' }, + roundsStarted: 2, + activation: 'disarmed', + }) expect(() => ctx.goals.resume(agent, goal)).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_TRANSITION' })) goal = ctx.goals.edit(agent, goal, { maxGoalRounds: 3 }) + expect(goal.blockedReason).toEqual({ code: 'round-limit', message: 'Goal round limit reached.' }) goal = ctx.goals.resume(agent, goal) expect(goal).toMatchObject({ phase: 'active', maxGoalRounds: 3, activation: 'armed' }) + expect(goal.blockedReason).toBeUndefined() appendRound(session, goal, 3) - goal = ctx.goals.markBudgetLimited(agent, goal) + goal = ctx.goals.block(agent, goal, { code: 'round-limit', message: 'Goal round limit reached.' }) expect(ctx.goals.complete(agent, goal).phase).toBe('complete') }) @@ -598,7 +608,16 @@ describe('goal replay validation', () => { return { ...current, operation, - goal: { ...current.goal, revision: current.goal.revision + 1, phase }, + goal: { + id: current.goal.id, + revision: current.goal.revision + 1, + objective: current.goal.objective, + phase, + ...phase === 'blocked' + ? { blockedReason: { code: 'test-blocker', message: 'Blocked for replay validation.' } } + : {}, + maxGoalRounds: current.goal.maxGoalRounds, + }, updatedAt: current.updatedAt + 1, ...overrides, } @@ -694,9 +713,6 @@ describe('goal replay validation', () => { mutation(base, 'resume', 'paused'), mutation(base, 'complete', 'active'), mutation(base, 'block', 'active'), - mutation(base, 'mark-usage-limited', 'active'), - mutation(base, 'mark-budget-limited', 'active'), - mutation(base, 'mark-budget-limited', 'budget-limited'), ] for (const change of invalid) expect(() => foldPair(base, change)).toThrow() @@ -782,6 +798,12 @@ describe('goal replay validation', () => { { ...base.goal, objective: ' ' }, { ...base.goal, objective: ' padded ' }, { ...base.goal, phase: 'unknown' }, + { ...base.goal, blockedReason: { code: 'unexpected', message: 'Only blocked goals have reasons.' } }, + { ...base.goal, phase: 'blocked' }, + { ...base.goal, phase: 'blocked', blockedReason: null }, + { ...base.goal, phase: 'blocked', blockedReason: { code: 'test-blocker', message: 'Valid.', extra: true } }, + { ...base.goal, phase: 'blocked', blockedReason: { code: 'NOT_CANONICAL', message: 'Bad code.' } }, + { ...base.goal, phase: 'blocked', blockedReason: { code: 'test-blocker', message: ' padded ' } }, { ...base.goal, revision: 0 }, { ...base.goal, maxGoalRounds: -1 }, ] diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 289a2e9778..ac59617e98 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -69,8 +69,8 @@ export const LINK_MAP: Record = { FsWriteIntent: 'filesystem.md', FsWriteOutcome: 'filesystem.md', CreateGoalRequest: 'goal.md', - CreateGoalSpec: 'goal.md', EditGoalRequest: 'goal.md', + GoalBlockReason: 'goal.md', GoalChanged: 'goal.md', GoalRef: 'goal.md', GoalView: 'goal.md', diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 1092c6c0b0..36b1e3816f 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -29,13 +29,13 @@ { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalRef", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalPhase", "source": "packages/goal/goal/src/types.ts" }, + { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalBlockReason", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalSnapshot", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalView", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalSnapshotChangeMeta", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalClearChangeMeta", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalMessageSource", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "CreateGoalRequest", "source": "packages/goal/goal/src/types.ts" }, - { "doc": "docs/core-data-structures/goal.md", "symbol": "CreateGoalSpec", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "EditGoalRequest", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalChanged", "source": "packages/goal/goal/src/types.ts" }, diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index ebe71dc559..6c7bcb3603 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -543,7 +543,7 @@ Goal mutation accepted by one live agent. The matching context event is already - `agent` — agent whose session owns the goal. - `change` — fresh current projection or clear tombstone. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/types.ts#L166) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/types.ts#L167) ## llm/* diff --git a/website/zh-CN/api/harness/goals.md b/website/zh-CN/api/harness/goals.md index 8789074e36..38c2daaafc 100644 --- a/website/zh-CN/api/harness/goals.md +++ b/website/zh-CN/api/harness/goals.md @@ -6,26 +6,7 @@ Goal service (`ctx.goals`) backed exclusively by the owning session log. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L104) - -### ctx.goals.resolveCreate(request) - -```ts website-api -/** - * Materialize deployment defaults and validate one create request. - * @param request - objective plus optional caller-selected round cap. - * @returns detached, fully resolved create specification. - */ -resolveCreate(request: CreateGoalRequest): CreateGoalSpec -``` - -Materialize deployment defaults and validate one create request. - -- `request` — objective plus optional caller-selected round cap. - -**Returns** detached, fully resolved create specification. - -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L129) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L131) ### ctx.goals.get(agent) @@ -45,7 +26,7 @@ Read the current goal for one exact live agent. **Returns** a fresh view or `undefined` when no goal is current. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L142) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L157) ### ctx.goals.create(agent, request) @@ -67,7 +48,7 @@ Create and arm a goal. A completed goal may be replaced; every other current pha **Returns** the created live view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L156) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L171) ### ctx.goals.edit(agent, ref, request) @@ -90,7 +71,7 @@ Edit objective and/or round cap without changing phase. **Returns** the edited view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L181) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L196) ### ctx.goals.pause(agent, ref) @@ -111,7 +92,7 @@ Pause an active goal and disarm automatic continuation. **Returns** the paused view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L202) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L217) ### ctx.goals.resume(agent, ref) @@ -133,7 +114,7 @@ Resume and arm a stopped goal, or rearm an active goal after a session-start edg **Returns** the active view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L213) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L228) ### ctx.goals.complete(agent, ref) @@ -154,70 +135,30 @@ Mark a current non-complete goal complete and disarm it. **Returns** the completed view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L238) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L253) -### ctx.goals.block(agent, ref) +### ctx.goals.block(agent, ref, reason) ```ts website-api /** * Mark an active goal blocked and disarm it. * @param agent - owning live agent. * @param ref - expected current revision. - * @returns the blocked view. + * @param reason - policy-owned stable code and human-readable explanation. + * @returns the blocked view with its durable reason. */ -block(agent: Agent, ref: GoalRef): GoalView +block(agent: Agent, ref: GoalRef, reason: GoalBlockReason): GoalView ``` Mark an active goal blocked and disarm it. - `agent` — owning live agent. - `ref` — expected current revision. +- `reason` — policy-owned stable code and human-readable explanation. -**Returns** the blocked view. +**Returns** the blocked view with its durable reason. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L255) - -### ctx.goals.markUsageLimited(agent, ref) - -```ts website-api -/** - * Mark an active goal stopped by an external usage limit. - * @param agent - owning live agent. - * @param ref - expected current revision. - * @returns the usage-limited view. - */ -markUsageLimited(agent: Agent, ref: GoalRef): GoalView -``` - -Mark an active goal stopped by an external usage limit. - -- `agent` — owning live agent. -- `ref` — expected current revision. - -**Returns** the usage-limited view. - -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L265) - -### ctx.goals.markBudgetLimited(agent, ref) - -```ts website-api -/** - * Mark an active goal stopped at its configured round cap. - * @param agent - owning live agent. - * @param ref - expected current revision. - * @returns the budget-limited view. - */ -markBudgetLimited(agent: Agent, ref: GoalRef): GoalView -``` - -Mark an active goal stopped at its configured round cap. - -- `agent` — owning live agent. -- `ref` — expected current revision. - -**Returns** the budget-limited view. - -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L275) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L271) ### ctx.goals.clear(agent, ref) @@ -238,4 +179,4 @@ Clear the current goal while retaining a durable tombstone and history. **Returns** the tombstone ref whose revision is one past the cleared snapshot. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L302) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L292) From 63d1f7679cbc6bbbdec710f5660fdade1a625145 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 16:50:29 +0800 Subject: [PATCH 02/11] docs(goal): refresh generated service references --- docs/cordis-catalog/services.md | 2 +- website/zh-CN/api/harness/goals.md | 18 +++++++++--------- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index bf639bed08..67884e71c2 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -555,7 +555,7 @@ clear(agent: Agent, ref: GoalRef): GoalRef Types: [Agent](../core-data-structures/core.md) · [CreateGoalRequest](../core-data-structures/goal.md) · [EditGoalRequest](../core-data-structures/goal.md) · [GoalBlockReason](../core-data-structures/goal.md) · [GoalRef](../core-data-structures/goal.md) · [GoalView](../core-data-structures/goal.md) -Source: [`packages/goal/goal/src/index.ts:131`](../../packages/goal/goal/src/index.ts) +Source: [`packages/goal/goal/src/index.ts:135`](../../packages/goal/goal/src/index.ts) ## `ctx.llm` — `LlmService` diff --git a/website/zh-CN/api/harness/goals.md b/website/zh-CN/api/harness/goals.md index 38c2daaafc..ee86d7be62 100644 --- a/website/zh-CN/api/harness/goals.md +++ b/website/zh-CN/api/harness/goals.md @@ -6,7 +6,7 @@ Goal service (`ctx.goals`) backed exclusively by the owning session log. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L131) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L135) ### ctx.goals.get(agent) @@ -26,7 +26,7 @@ Read the current goal for one exact live agent. **Returns** a fresh view or `undefined` when no goal is current. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L157) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L161) ### ctx.goals.create(agent, request) @@ -48,7 +48,7 @@ Create and arm a goal. A completed goal may be replaced; every other current pha **Returns** the created live view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L171) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L175) ### ctx.goals.edit(agent, ref, request) @@ -71,7 +71,7 @@ Edit objective and/or round cap without changing phase. **Returns** the edited view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L196) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L200) ### ctx.goals.pause(agent, ref) @@ -92,7 +92,7 @@ Pause an active goal and disarm automatic continuation. **Returns** the paused view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L217) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L221) ### ctx.goals.resume(agent, ref) @@ -114,7 +114,7 @@ Resume and arm a stopped goal, or rearm an active goal after a session-start edg **Returns** the active view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L228) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L232) ### ctx.goals.complete(agent, ref) @@ -135,7 +135,7 @@ Mark a current non-complete goal complete and disarm it. **Returns** the completed view. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L253) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L257) ### ctx.goals.block(agent, ref, reason) @@ -158,7 +158,7 @@ Mark an active goal blocked and disarm it. **Returns** the blocked view with its durable reason. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L271) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L275) ### ctx.goals.clear(agent, ref) @@ -179,4 +179,4 @@ Clear the current goal while retaining a durable tombstone and history. **Returns** the tombstone ref whose revision is one past the cleared snapshot. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L292) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L296) From 15640ca697b5bfcee514faad467a1584a6b0cf01 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 16:53:10 +0800 Subject: [PATCH 03/11] fix(goal): require explained model blockers --- ...26-07-19-model-facing-goal-tools.i18n.yaml | 4 +- .../2026-07-19-model-facing-goal-tools.md | 8 +- .../2026-07-19-model-facing-goal-tools.zh.md | 8 +- docs/tool-catalog.md | 8 +- .../tests/fixtures/goal/tool-goal/cordis.yml | 26 ---- .../fixtures/goal/tool-goal/scripted-llm.ts | 88 ------------ .../headless-agent/goal.cordis.snapshot.yml | 13 ++ examples/headless-agent/goal.cordis.yml | 12 ++ .../headless-agent/tests/headless.snapshot.ts | 109 ++++++++++++--- .../tests/snapshots/goal-tools/input.json | 9 ++ .../snapshots/goal-tools/replay.override.json | 33 +++++ .../goal-tools/stream-json.expected.jsonl | 34 +++++ knip.json | 1 - packages/goal/tool-goal/README.md | 8 +- packages/goal/tool-goal/src/index.ts | 34 ++++- .../goal/tool-goal/tests/tool-goal.e2e.ts | 127 ------------------ .../goal/tool-goal/tests/tool-goal.spec.ts | 54 +++++++- 17 files changed, 289 insertions(+), 287 deletions(-) delete mode 100644 examples/echo-agent/tests/fixtures/goal/tool-goal/cordis.yml delete mode 100644 examples/echo-agent/tests/fixtures/goal/tool-goal/scripted-llm.ts create mode 100644 examples/headless-agent/goal.cordis.snapshot.yml create mode 100644 examples/headless-agent/goal.cordis.yml create mode 100644 examples/headless-agent/tests/snapshots/goal-tools/input.json create mode 100644 examples/headless-agent/tests/snapshots/goal-tools/replay.override.json create mode 100644 examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl delete mode 100644 packages/goal/tool-goal/tests/tool-goal.e2e.ts diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml index f857c5360e..fd97351a0e 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.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 -2026-07-19-model-facing-goal-tools.md: e37eaabecfd1984e1198c26a460e78a92375dac1 -2026-07-19-model-facing-goal-tools.zh.md: c0d289271d2a8053193299c16a2bc9477f2f1038 +2026-07-19-model-facing-goal-tools.md: 2ef77b53cd8b95c9cdffd12e20c723fb1cff3a5d +2026-07-19-model-facing-goal-tools.zh.md: 08619600355c71ccd30d608e3c4e5a7fba753d4e diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md index e37eaabecf..2ef77b53cd 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md @@ -16,9 +16,9 @@ The surface also needs to preserve the separation between durable state and live ### Tools and model contract -`get_goal()` returns the current goal or `null`. A non-null result contains the compare-and-set id and revision, objective, durable phase, admitted and maximum goal rounds, plus the process-local activation observation. `create_goal(objective, max_goal_rounds?)` creates one long-running same-session objective. `update_goal(goal_id, revision, action, objective?, max_goal_rounds?)` supports `edit`, `pause`, `resume`, `complete`, and `blocked`; replacement fields are valid only for `edit`. +`get_goal()` returns the current goal or `null`. A non-null result contains the compare-and-set id and revision, objective, durable phase, admitted and maximum goal rounds, any blocker reason, plus the process-local activation observation. `create_goal(objective, max_goal_rounds?)` creates one long-running same-session objective. `update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` supports `edit`, `pause`, `resume`, `complete`, and `blocked`; replacement fields are valid only for `edit`, while a non-empty `blocked_reason` is required only for `blocked` and persists under the stable `model-reported` code. -The prompt tells the model that it may infer goal intent from a direct human request in any wording or language, but should not convert routine single-turn work into a goal. It must read the current goal before updating and copy the exact id and revision. On a restored or forked active-but-disarmed goal, a semantic human request to continue is grounds for `resume`. Completion is reserved for an achieved objective, and difficulty or uncertainty alone is not a blocker. +The prompt tells the model that it may infer goal intent from a direct human request in any wording or language, but should not convert routine single-turn work into a goal. It must read the current goal before updating and copy the exact id and revision. On a restored or forked active-but-disarmed goal, a semantic human request to continue is grounds for `resume`. Completion is reserved for an achieved objective, and difficulty or uncertainty alone is not a blocker; a block report must name the concrete condition. All three tools use exclusive execution so a model-ordered batch observes prior mutations and their new revisions. Results are compact JSON. ACP presentation is a pure function of arguments and uses generic read or mutation cards; activation is reported only as live observation and is never written into replay state. @@ -34,11 +34,11 @@ Complete and blocked accept either direct-human authority or the exact current g ### Blocking threshold -`blockedAfterConsecutiveRounds` is a validated positive safe-integer configuration with default `3`. When an autonomous goal round calls `blocked`, the plugin mechanically requires at least that many admitted rounds; the configured value also appears in model guidance. The runtime cannot determine whether those rounds encountered the same blocking condition, so semantic equivalence remains a model judgment. This count is deliberately separate from the goal's generous continuation cap. +`blockedAfterConsecutiveRounds` is a validated positive safe-integer configuration with default `3`. When an autonomous goal round calls `blocked`, the plugin mechanically requires at least that many admitted rounds and a non-empty explanation; the configured value also appears in model guidance. The runtime cannot determine whether those rounds encountered the same blocking condition, so semantic equivalence remains a model judgment. This count is deliberately separate from the goal's generous continuation cap. ## Testing -Unit coverage pins registration and disposal, exclusive scheduling, generated prompt policy, generic presentation, direct-human creation in a non-English turn, exact/stale/non-running agent and driver checks, live-child rejection, resumed-fork root authority, steering, mismatched initiators, read/create/edit/pause/resume behavior, rearming after a session-start edge, authority-before-conditional-argument failures, exact goal-round completion, autonomous-only terminal stopping, the configured blocking threshold, and immediate human blocking. A keyless Loader/stdio process test mounts the real goal, tool, loop, and persistence plugins through `cordis.yml`, drives scripted model tool calls through a human pause and assistant acknowledgment, and reads the JSONL externally to verify the model-visible create/pause snapshots, structured tool results, and configured prompt text. +Unit coverage pins registration and disposal, exclusive scheduling, generated prompt policy, generic presentation, direct-human creation in a non-English turn, exact/stale/non-running agent and driver checks, live-child rejection, resumed-fork root authority, steering, mismatched initiators, read/create/edit/pause/resume behavior, conditional blocker explanations, rearming after a session-start edge, authority-before-conditional-argument failures, exact goal-round completion, autonomous-only terminal stopping, the configured blocking threshold, and immediate human blocking. A keyless replay snapshot mounts the goal domain and tools into the real headless one-shot application, drives `create_goal` and `get_goal` through the shipped loop and persistence stack, pins its stream-json transcript, and inspects the externally persisted goal change. The echo-agent fixture is intentionally not used as an application-UX surrogate. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md index c0d289271d..0861960035 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md @@ -16,9 +16,9 @@ Status: implemented ### 工具与模型契约 -`get_goal()` 返回当前目标或 `null`。非空结果包含用于比较并交换的 id 与修订号、目标描述、持久阶段、已接纳和最大目标回合数，以及进程本地激活态观察。`create_goal(objective, max_goal_rounds?)` 创建一个长时间运行的同会话目标。`update_goal(goal_id, revision, action, objective?, max_goal_rounds?)` 支持 `edit`、`pause`、`resume`、`complete` 和 `blocked`；替换字段仅对 `edit` 有效。 +`get_goal()` 返回当前目标或 `null`。非空结果包含用于比较并交换的 id 与修订号、目标描述、持久阶段、已接纳和最大目标回合数、可能存在的阻塞原因，以及进程本地激活态观察。`create_goal(objective, max_goal_rounds?)` 创建一个长时间运行的同会话目标。`update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` 支持 `edit`、`pause`、`resume`、`complete` 和 `blocked`；替换字段仅对 `edit` 有效，非空的 `blocked_reason` 仅在 `blocked` 时必填，并以稳定代码 `model-reported` 持久化。 -提示词告诉模型：它可以从任何措辞或语言的直接人类请求中推断目标意图，但不应把常规单轮工作转换为目标。更新前必须读取当前目标，并复制准确的 id 和修订号。对于恢复或派生后处于活跃但未激活状态的目标，人类在语义上要求继续即可成为执行 `resume` 的依据。只有目标已经实现时才能标记完成，困难或不确定性本身不构成阻塞。 +提示词告诉模型：它可以从任何措辞或语言的直接人类请求中推断目标意图，但不应把常规单轮工作转换为目标。更新前必须读取当前目标，并复制准确的 id 和修订号。对于恢复或派生后处于活跃但未激活状态的目标，人类在语义上要求继续即可成为执行 `resume` 的依据。只有目标已经实现时才能标记完成，困难或不确定性本身不构成阻塞；阻塞报告必须说明具体条件。 三个工具都采用独占执行，使模型排序的批次可以观察此前变更及其新修订号。结果为紧凑 JSON。ACP 展示是参数的纯函数，使用通用读取或变更卡片；激活态仅作为实时观察返回，绝不会写入回放状态。 @@ -34,11 +34,11 @@ Status: implemented ### 阻塞阈值 -`blockedAfterConsecutiveRounds` 是经过校验的正安全整数配置，默认值为 `3`。自主目标回合调用 `blocked` 时，插件会机械地要求至少已经接纳该数量的回合；配置值也会出现在模型指导中。运行时无法判断这些回合是否遇到了语义上相同的阻塞条件，因此语义等价性仍由模型判断。该计数特意与目标的宽裕继续执行上限分离。 +`blockedAfterConsecutiveRounds` 是经过校验的正安全整数配置，默认值为 `3`。自主目标回合调用 `blocked` 时，插件会机械地要求至少已经接纳该数量的回合并提供非空说明；配置值也会出现在模型指导中。运行时无法判断这些回合是否遇到了语义上相同的阻塞条件，因此语义等价性仍由模型判断。该计数特意与目标的宽裕继续执行上限分离。 ## 测试 -单元测试固定注册与释放、独占调度、生成的提示词策略、通用展示、非英语轮次中的直接人类创建、精确/陈旧/非运行中智能体与驱动检查、实时子智能体拒绝、恢复后派生根的权限、steering、发起者不匹配、读取/创建/编辑/暂停/恢复行为、会话启动边沿后的重新激活、权限先于条件参数失败、准确目标回合的完成、仅自主回合触发终止、可配置阻塞阈值，以及人类立即阻塞。无密钥 Loader/stdio 进程测试通过 `cordis.yml` 挂载真实的目标、工具、循环和持久化插件，驱动脚本化模型工具调用经过人类暂停与智能体确认，并从外部读取 JSONL，以验证模型可见的创建/暂停快照、结构化工具结果和配置后的提示词文本。 +单元测试固定注册与释放、独占调度、生成的提示词策略、通用展示、非英语轮次中的直接人类创建、精确/陈旧/非运行中智能体与驱动检查、实时子智能体拒绝、恢复后派生根的权限、steering、发起者不匹配、读取/创建/编辑/暂停/恢复行为、条件式阻塞说明、会话启动边沿后的重新激活、权限先于条件参数失败、准确目标回合的完成、仅自主回合触发终止、可配置阻塞阈值，以及人类立即阻塞。无密钥回放快照把目标领域和工具挂载到真实的 headless 单次运行应用中，通过随附循环与持久化栈驱动 `create_goal` 和 `get_goal`，固定 stream-json 转录，并检查外部持久化的目标变更。这里有意不把 echo-agent 测试夹具当作应用 UX 的替代品。 ## 考虑过的替代方案 diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index febcf6a4bb..0244e39629 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -423,7 +423,7 @@ Source: [`packages/goal/tool-goal/src/index.ts`](../packages/goal/tool-goal/src/ ### `get_goal` -Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. +Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. ```json { @@ -436,7 +436,7 @@ Source: [`packages/goal/tool-goal/src/index.ts`](../packages/goal/tool-goal/src/ ### `update_goal` -Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. +Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. ```json { @@ -468,6 +468,10 @@ Update the exact current goal revision. edit, pause, and resume require a direct "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/echo-agent/tests/fixtures/goal/tool-goal/cordis.yml b/examples/echo-agent/tests/fixtures/goal/tool-goal/cordis.yml deleted file mode 100644 index fa63160399..0000000000 --- a/examples/echo-agent/tests/fixtures/goal/tool-goal/cordis.yml +++ /dev/null @@ -1,26 +0,0 @@ -# Test-only composition: drive all three goal tools through a real root agent. -- id: scripted-llm - name: './scripted-llm.ts' - -- id: bash - name: '@deepseek-ai/dsh-bash-local' - -- id: goal - name: '@deepseek-ai/dsh-goal' - config: - defaultMaxGoalRounds: 11 - -- id: tool-goal - name: '@deepseek-ai/dsh-tool-goal' - config: - blockedAfterConsecutiveRounds: 3 - -- id: stdio-agent - name: '@deepseek-ai/dsh-stdio-demo' - config: - provider: goal-script - model: goal-script - persona: 'Execute the deterministic goal-tool composition test.' - welcome: 'goal-tools e2e ready.' - persistenceRoot: './.sessions' - workspaceContext: false diff --git a/examples/echo-agent/tests/fixtures/goal/tool-goal/scripted-llm.ts b/examples/echo-agent/tests/fixtures/goal/tool-goal/scripted-llm.ts deleted file mode 100644 index 310737050d..0000000000 --- a/examples/echo-agent/tests/fixtures/goal/tool-goal/scripted-llm.ts +++ /dev/null @@ -1,88 +0,0 @@ -/** Deterministic adapter that creates, reads, pauses, then acknowledges one goal. */ - -import type { Context } from 'cordis' -import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -import type { GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm' - -interface GoalState { - readonly id: string - readonly revision: number -} - -/** Text from the latest ordinary user message, excluding raw goal-state context. */ -function latestPrompt(messages: readonly Message[]): { index: number; text: string } { - for (let index = messages.length - 1; index >= 0; index -= 1) { - const message = messages[index] - if (message?.role !== 'user') continue - const text = message.content - .filter(block => block.type === 'text' && !block.text.startsWith('')) - .map(block => block.type === 'text' ? block.text : '') - .join('\n') - if (text.length > 0) return { index, text } - } - return { index: -1, text: '' } -} - -/** Parse the latest domain snapshot rendered into history. */ -function latestGoal(messages: readonly Message[]): GoalState | undefined { - for (const message of [...messages].reverse()) { - for (const block of [...message.content].reverse()) { - if (block.type !== 'text' || !block.text.startsWith('')) continue - const json = block.text.slice(''.length, -''.length) - const value = JSON.parse(json) as { goal?: GoalState } - if (value.goal !== undefined) return value.goal - } - } - return undefined -} - -/** Names of tool calls recorded after the latest ordinary prompt. */ -function callsAfter(messages: readonly Message[], index: number): string[] { - return messages.slice(index + 1).flatMap(message => message.content) - .filter(block => block.type === 'tool-call') - .map(block => block.type === 'tool-call' ? block.name : '') -} - -/** Emit one tool-call response. */ -async function* toolCall(name: string, args: object): AsyncIterable { - const id = CallId(`call-${name}`) - const raw = JSON.stringify(args) - yield { type: 'block-start', index: 0, blockType: 'tool-call' } - yield { type: 'tool-call-delta', index: 0, id, name, argumentsDelta: raw } - yield { type: 'block-end', index: 0, block: { type: 'tool-call', id, name, arguments: raw } } - yield { type: 'finish', reason: { kind: 'tool-calls' } } -} - -/** Emit one terminal text response. */ -async function* textReply(text: string): AsyncIterable { - yield { type: 'block-start', index: 0, blockType: 'text' } - yield { type: 'text-delta', index: 0, text } - yield { type: 'block-end', index: 0, block: { type: 'text', text } } - yield { type: 'finish', reason: { kind: 'stop' } } -} - -class GoalScriptAdapter extends LlmAdapter { - override stream(options: GenerateOptions): AsyncIterable { - const prompt = latestPrompt(options.messages) - const calls = callsAfter(options.messages, prompt.index) - if (prompt.text === 'start' && !calls.includes('create_goal')) { - return toolCall('create_goal', { objective: 'Finish the composed goal-tool proof', max_goal_rounds: 7 }) - } - if (prompt.text === 'start' && !calls.includes('get_goal')) return toolCall('get_goal', {}) - if (prompt.text === 'start') return textReply('GOAL CREATED') - if (prompt.text === 'pause' && !calls.includes('update_goal')) { - const goal = latestGoal(options.messages) - if (goal === undefined) throw new Error('scripted goal state missing') - return toolCall('update_goal', { goal_id: goal.id, revision: goal.revision, action: 'pause' }) - } - if (prompt.text === 'pause') return textReply('GOAL PAUSED') - return textReply('UNEXPECTED PROMPT') - } -} - -export const name = 'goal-tool-scripted-llm' -export const inject = ['llm'] - -export function apply(ctx: Context): void { - ctx.llm.registerAdapter(['goal-script'], new GoalScriptAdapter()) -} diff --git a/examples/headless-agent/goal.cordis.snapshot.yml b/examples/headless-agent/goal.cordis.snapshot.yml new file mode 100644 index 0000000000..185d3dd11e --- /dev/null +++ b/examples/headless-agent/goal.cordis.snapshot.yml @@ -0,0 +1,13 @@ +# Replay counterpart to goal.cordis.yml; only the live model is replaced. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./goal.cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - insert: + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' + diff --git a/examples/headless-agent/goal.cordis.yml b/examples/headless-agent/goal.cordis.yml new file mode 100644 index 0000000000..01f1726100 --- /dev/null +++ b/examples/headless-agent/goal.cordis.yml @@ -0,0 +1,12 @@ +# Add the persisted goal domain and its model-facing tools to the real one-shot app. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - insert: + - id: goal + name: '@deepseek-ai/dsh-goal' + - id: tool-goal + name: '@deepseek-ai/dsh-tool-goal' + diff --git a/examples/headless-agent/tests/headless.snapshot.ts b/examples/headless-agent/tests/headless.snapshot.ts index dc448b9b23..d799c6250d 100644 --- a/examples/headless-agent/tests/headless.snapshot.ts +++ b/examples/headless-agent/tests/headless.snapshot.ts @@ -11,10 +11,12 @@ import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-l import { describe, expect, it } from 'vitest' const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') -const scenarioDir = join(snapshotsDir, 'advanced-toolchain') -const sessionFixture = join(scenarioDir, 'session.jsonl') -const streamExpected = join(scenarioDir, 'stream-json.expected.jsonl') -const configPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url)) +const advancedScenarioDir = join(snapshotsDir, 'advanced-toolchain') +const advancedSessionFixture = join(advancedScenarioDir, 'session.jsonl') +const advancedStreamExpected = join(advancedScenarioDir, 'stream-json.expected.jsonl') +const advancedConfigPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url)) +const goalScenarioDir = join(snapshotsDir, 'goal-tools') +const goalConfigPath = fileURLToPath(new URL('../goal.cordis.snapshot.yml', import.meta.url)) const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) const refreshing = process.env.DSH_SNAPSHOT === 'refresh' @@ -70,12 +72,36 @@ function normalizeHeadlessStream(rawStdout: string, cwd: string): string { return normalizeStdout(`${normalizedRecords.map(record => JSON.stringify(record)).join('\n')}\n`, context) } -async function advancedPrompt(): Promise { - const input = JSON.parse(await readFile(join(scenarioDir, 'input.json'), 'utf8')) as { +/** Zero durable goal timestamps inside both metadata records and rendered XML JSON. */ +function normalizeGoalTimestamps(value: unknown): unknown { + if (typeof value === 'string') { + return value.replace(/("(?:createdAt|updatedAt|clearedAt)":)\d+/g, '$10') + } + if (Array.isArray(value)) return value.map(normalizeGoalTimestamps) + if (value !== null && typeof value === 'object') { + return Object.fromEntries(Object.entries(value).map(([key, item]) => [ + key, + ['createdAt', 'updatedAt', 'clearedAt'].includes(key) && typeof item === 'number' + ? 0 + : normalizeGoalTimestamps(item), + ])) + } + return value +} + +/** Normalize the stream's durable goal timestamps after the shared scrubbers. */ +function normalizeGoalStream(rawStdout: string, cwd: string): string { + return parseJsonl(normalizeHeadlessStream(rawStdout, cwd)) + .map(record => JSON.stringify(normalizeGoalTimestamps(record))) + .join('\n') + '\n' +} + +async function scenarioPrompt(dir: string, label: string): Promise { + const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as { steps?: { op?: unknown; text?: unknown }[] } const prompt = input.steps?.find(step => step.op === 'prompt')?.text - if (typeof prompt !== 'string') throw new Error('advanced-toolchain input has no prompt step') + if (typeof prompt !== 'string') throw new Error(`${label} input has no prompt step`) return prompt } @@ -90,24 +116,27 @@ async function persistedLogs(cwd: string): Promise { describe('headless stream-json snapshots', () => { it('replays the advanced toolchain through the one-shot app', async () => { - const prompt = await advancedPrompt() + const prompt = await scenarioPrompt(advancedScenarioDir, 'advanced-toolchain') const expectedSessions = await Promise.all([ - sessionFixture, - join(scenarioDir, 'session.1.jsonl'), - join(scenarioDir, 'session.2.jsonl'), + advancedSessionFixture, + join(advancedScenarioDir, 'session.1.jsonl'), + join(advancedScenarioDir, 'session.2.jsonl'), ].map(file => readFile(file, 'utf8'))) let runCwd = '' const result = await runLoaderSmoke({ label: 'advanced headless stream-json snapshot', tempDirPrefix: 'headless-snapshot-advanced-', binScript, - configPath, - binArgs: ['--config', configPath, '--output-format', 'stream-json', prompt], + configPath: advancedConfigPath, + binArgs: ['--config', advancedConfigPath, '--output-format', 'stream-json', prompt], tsconfigPath, env: { DSH_SNAPSHOT: 'replay', - DSH_SNAPSHOT_FILE: sessionFixture, - DSH_SNAPSHOT_CHILD_FILES: [join(scenarioDir, 'session.1.jsonl'), join(scenarioDir, 'session.2.jsonl')].join(delimiter), + DSH_SNAPSHOT_FILE: advancedSessionFixture, + DSH_SNAPSHOT_CHILD_FILES: [ + join(advancedScenarioDir, 'session.1.jsonl'), + join(advancedScenarioDir, 'session.2.jsonl'), + ].join(delimiter), NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '), }, prepare: (cwd) => { runCwd = cwd }, @@ -134,6 +163,56 @@ describe('headless stream-json snapshots', () => { expect(result.stderr).toBe('') const normalized = normalizeHeadlessStream(result.stdout, runCwd) + if (refreshing) await writeFile(advancedStreamExpected, normalized) + expect(normalized).toBe(await readFile(advancedStreamExpected, 'utf8')) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + + it('replays persisted goal tools through the one-shot app', async () => { + const prompt = await scenarioPrompt(goalScenarioDir, 'goal-tools') + const streamExpected = join(goalScenarioDir, 'stream-json.expected.jsonl') + let runCwd = '' + const result = await runLoaderSmoke({ + label: 'goal tools headless stream-json snapshot', + tempDirPrefix: 'headless-snapshot-goal-tools-', + binScript, + configPath: goalConfigPath, + binArgs: ['--config', goalConfigPath, '--output-format', 'stream-json', prompt], + tsconfigPath, + env: { + DSH_SNAPSHOT: 'replay', + DSH_SNAPSHOT_FILE: join(goalScenarioDir, 'session.jsonl'), + DSH_SNAPSHOT_OVERRIDE: join(goalScenarioDir, 'replay.override.json'), + NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '), + }, + prepare: (cwd) => { runCwd = cwd }, + inspect: async (cwd) => { + const logs = await persistedLogs(cwd) + expect(logs).toHaveLength(1) + const records = parseJsonl(logs[0]?.content ?? '') + const calls = records.filter(record => record.type === 'tool/call') + .map(record => (record.data as JsonObject | undefined)?.name) + expect(calls).toEqual(['create_goal', 'get_goal']) + const goalChanges = records.filter((record) => { + if (record.type !== 'context/message') return false + const data = record.data as JsonObject | undefined + const meta = data?.meta as JsonObject | undefined + return meta?.kind === 'goal/change' + }) + expect(goalChanges).toHaveLength(1) + const data = goalChanges[0]?.data as JsonObject | undefined + const meta = data?.meta as JsonObject | undefined + const goal = meta?.goal as JsonObject | undefined + expect(meta?.operation).toBe('create') + expect(goal).toMatchObject({ + objective: 'Finish the headless goal-tool snapshot proof', + phase: 'active', + maxGoalRounds: 7, + }) + }, + }) + + expect(result.stderr).toBe('') + const normalized = normalizeGoalStream(result.stdout, runCwd) if (refreshing) await writeFile(streamExpected, normalized) expect(normalized).toBe(await readFile(streamExpected, 'utf8')) }, LOADER_SMOKE_TEST_TIMEOUT_MS) diff --git a/examples/headless-agent/tests/snapshots/goal-tools/input.json b/examples/headless-agent/tests/snapshots/goal-tools/input.json new file mode 100644 index 0000000000..cb0b3bbd82 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/goal-tools/input.json @@ -0,0 +1,9 @@ +{ + "steps": [ + { + "op": "prompt", + "text": "Create a durable goal to finish the snapshot proof, then inspect it." + } + ] +} + diff --git a/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json b/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json new file mode 100644 index 0000000000..7e4fd90c6c --- /dev/null +++ b/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json @@ -0,0 +1,33 @@ +[ + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "tool-call" }, + { "type": "tool-call-delta", "index": 0, "id": "call_goal_create", "name": "create_goal", "argumentsDelta": "{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}" }, + { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_create", "name": "create_goal", "arguments": "{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}" } }, + { "type": "usage", "usage": { "inputTokens": 20, "outputTokens": 8 } }, + { "type": "finish", "reason": { "kind": "tool-calls" } } + ] + }, + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "tool-call" }, + { "type": "tool-call-delta", "index": 0, "id": "call_goal_get", "name": "get_goal", "argumentsDelta": "{}" }, + { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_get", "name": "get_goal", "arguments": "{}" } }, + { "type": "usage", "usage": { "inputTokens": 30, "outputTokens": 4 } }, + { "type": "finish", "reason": { "kind": "tool-calls" } } + ] + }, + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "text" }, + { "type": "text-delta", "index": 0, "text": "GOAL READY" }, + { "type": "block-end", "index": 0, "block": { "type": "text", "text": "GOAL READY" } }, + { "type": "usage", "usage": { "inputTokens": 35, "outputTokens": 2 } }, + { "type": "finish", "reason": { "kind": "stop" } } + ] + } +] + diff --git a/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl b/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl new file mode 100644 index 0000000000..b6e9ad7e70 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl @@ -0,0 +1,34 @@ +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Create a durable goal to finish the snapshot proof, then inspect it."}],"source":{"kind":"user"}},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"context/message","seq":12,"time":0,"data":{"content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"envelope":"raw","meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":30,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":31,"time":0,"data":{"turn":1,"step":3}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":32,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} +{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":85,"outputTokens":14}} diff --git a/knip.json b/knip.json index eb4eff3a9f..9b7b511c44 100644 --- a/knip.json +++ b/knip.json @@ -11,7 +11,6 @@ "entry": [ "echo-agent/src/*.ts", "echo-agent/tests/fixtures/goal/goal/seed-goal.ts", - "echo-agent/tests/fixtures/goal/tool-goal/scripted-llm.ts", "headless-agent/tests/fixtures/cli-mock-llm.ts", "tui-agent/tests/fixtures/tui-scripted-llm.ts", "*/tests/**/*.e2e.ts", diff --git a/packages/goal/tool-goal/README.md b/packages/goal/tool-goal/README.md index 1ac03ac04a..3b97d7aa82 100644 --- a/packages/goal/tool-goal/README.md +++ b/packages/goal/tool-goal/README.md @@ -4,9 +4,9 @@ The model-facing control surface for [`ctx.goals`](../goal/README.md): `get_goal ## Tools -- `get_goal()` returns the current goal or `null`, including the compare-and-set id/revision, durable phase, admitted/capped goal rounds, and current process-local activation. +- `get_goal()` returns the current goal or `null`, including the compare-and-set id/revision, durable phase, admitted/capped goal rounds, any blocker reason, and current process-local activation. - `create_goal(objective, max_goal_rounds?)` creates one goal from a direct top-level human turn. The model may infer long-running goal intent without an exact command phrase; non-human turns and subagents are rejected at execution. -- `update_goal(goal_id, revision, action, objective?, max_goal_rounds?)` supports `edit`, `pause`, `resume`, `complete`, and `blocked`. Replacements belong only to `edit`. +- `update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` supports `edit`, `pause`, `resume`, `complete`, and `blocked`. Replacements belong only to `edit`; `blocked_reason` is required only for `blocked` and is persisted with the stable code `model-reported`. All calls are exclusive, so a model-ordered batch observes earlier mutations and their new revisions. ACP and other clients receive pure generic cards: read for `get_goal`, other for mutations. @@ -18,7 +18,7 @@ Execution requires the exact live `exec.agent`, its inherited `AgentRegistry` in `{ kind: 'user' }` is a host attestation. `Agent.send()` and `steer()` assign it when their caller omits a source, so plugins, schedulers, and other non-human producers must pass their own source rather than inheriting human authority. -Complete and blocked also accept the exact current goal round: a goal-sourced `user/message` whose id, revision, and round equal the folded current goal. A goal-round blocked call is mechanically rejected until `blockedAfterConsecutiveRounds`; the model judges whether the same condition actually persisted. Direct human authority may stop a goal immediately. +Complete and blocked also accept the exact current goal round: a goal-sourced `user/message` whose id, revision, and round equal the folded current goal. A goal-round blocked call is mechanically rejected until `blockedAfterConsecutiveRounds`; the model judges whether the same condition actually persisted and must describe it in `blocked_reason`. Direct human authority may stop a goal immediately. ## Config @@ -42,7 +42,7 @@ A fixed goal policy says when semantic human intent warrants creation, requires ##### Goal policy ```markdown -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. ``` #### Token effect diff --git a/packages/goal/tool-goal/src/index.ts b/packages/goal/tool-goal/src/index.ts index cd105b3705..075264f93e 100644 --- a/packages/goal/tool-goal/src/index.ts +++ b/packages/goal/tool-goal/src/index.ts @@ -51,7 +51,8 @@ const CREATE_DESCRIPTION = const GET_DESCRIPTION = 'Read the current same-session goal, including its exact id/revision, objective, phase, completed ' - + 'continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.' + + 'continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. ' + + 'Call this before updating a goal.' /** Render policy guidance with its deployment-selected blocked threshold. */ function guidance(blockedAfter: number): string { @@ -62,7 +63,8 @@ function guidance(blockedAfter: number): string { + 'a human asks to continue or resume in any wording or language, use update_goal action ' + 'resume to rearm it. Mark complete only when the objective is actually achieved. Mark ' + `blocked only after the same blocking condition persists for at least ${blockedAfter} ` - + 'consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.' + + 'consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, ' + + 'or useful remaining work is not blocked.' } /** Validate config even when apply is called directly outside Loader normalization. */ @@ -97,6 +99,7 @@ function renderGoal(goal: GoalView | undefined): string { phase: goal.phase, roundsStarted: goal.roundsStarted, maxGoalRounds: goal.maxGoalRounds, + ...goal.blockedReason === undefined ? {} : { blockedReason: goal.blockedReason }, }, activation: goal.activation, }) @@ -183,7 +186,7 @@ export function apply(ctx: Context, config: Config): void { description: 'Update the exact current goal revision. edit, pause, and resume require a direct ' + 'top-level human request. During an automatic continuation of the current goal, complete ' + 'and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains ' - + 'responsible for judging that the same condition persisted across those rounds.', + + 'responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.', parameters: { goal_id: { type: 'string', required: true, description: 'Exact id returned by get_goal.' }, revision: { type: 'number', required: true, description: 'Exact positive revision returned by get_goal.' }, @@ -195,6 +198,10 @@ export function apply(ctx: Context, config: Config): void { }, objective: { type: 'string', description: 'Replacement objective; valid only with action edit.' }, max_goal_rounds: { type: 'number', description: 'Replacement cap; valid only with action edit.' }, + blocked_reason: { + type: 'string', + description: 'Concrete blocking condition; required only with action blocked.', + }, }, execute(args, exec) { const execution = goalToolExecution(ctx, exec) @@ -205,6 +212,9 @@ export function apply(ctx: Context, config: Config): void { } if (args.action === 'edit') { requireDirectHuman(ctx, execution) + if (args.blocked_reason !== undefined) { + throw new HarnessError('blocked_reason is valid only with action blocked', 'GOAL_TOOL_INVALID_UPDATE') + } const goal = ctx.goals.edit(execution.agent, ref, replacements) observeMutation(terminalTurns, execution, false) return Promise.resolve([{ @@ -214,9 +224,9 @@ export function apply(ctx: Context, config: Config): void { } if (args.action === 'pause' || args.action === 'resume') { requireDirectHuman(ctx, execution) - if (args.objective !== undefined || args.max_goal_rounds !== undefined) { + if (args.objective !== undefined || args.max_goal_rounds !== undefined || args.blocked_reason !== undefined) { throw new HarnessError( - 'objective and max_goal_rounds are valid only with action edit', + 'objective and max_goal_rounds are valid only with action edit; blocked_reason is valid only with action blocked', 'GOAL_TOOL_INVALID_UPDATE', ) } @@ -233,6 +243,13 @@ export function apply(ctx: Context, config: Config): void { 'GOAL_TOOL_INVALID_UPDATE', ) } + if (args.action === 'complete' && args.blocked_reason !== undefined) { + throw new HarnessError('blocked_reason is valid only with action blocked', 'GOAL_TOOL_INVALID_UPDATE') + } + if (args.action === 'blocked' + && (args.blocked_reason === undefined || args.blocked_reason.trim().length === 0)) { + throw new HarnessError('blocked_reason is required with action blocked', 'GOAL_TOOL_INVALID_UPDATE') + } if (args.action === 'blocked' && authority.kind === 'goal-round' && authority.goal.roundsStarted < resolved.blockedAfterConsecutiveRounds) { throw new HarnessError( @@ -243,14 +260,17 @@ export function apply(ctx: Context, config: Config): void { } const goal = args.action === 'complete' ? ctx.goals.complete(execution.agent, ref) - : ctx.goals.block(execution.agent, ref) + : ctx.goals.block(execution.agent, ref, { + code: 'model-reported', + message: args.blocked_reason as string, + }) observeMutation(terminalTurns, execution, authority.kind === 'goal-round') return Promise.resolve([{ type: 'text', text: renderGoal(goal) }]) }, presentCall: args => present( `${args.action === 'blocked' ? 'Mark' : args.action.charAt(0).toUpperCase() + args.action.slice(1)} goal`, 'other', - args.objective ?? args.goal_id, + args.blocked_reason ?? args.objective ?? args.goal_id, ), })) } diff --git a/packages/goal/tool-goal/tests/tool-goal.e2e.ts b/packages/goal/tool-goal/tests/tool-goal.e2e.ts deleted file mode 100644 index b19a4ee851..0000000000 --- a/packages/goal/tool-goal/tests/tool-goal.e2e.ts +++ /dev/null @@ -1,127 +0,0 @@ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { mkdtemp, readFile, readdir, rm } from 'node:fs/promises' -import { tmpdir } from 'node:os' -import { join } from 'node:path' -import { fileURLToPath } from 'node:url' -import { afterEach, describe, expect, it } from 'vitest' -import { decodeGoalChange } from '@deepseek-ai/dsh-goal' -import type { SessionEvent } from '@deepseek-ai/dsh-session' -import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke' - -const binScript = fileURLToPath(new URL('../../../examples/stdio-demo/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL( - '../../../../examples/echo-agent/tests/fixtures/goal/tool-goal/cordis.yml', - import.meta.url, -)) -const repoTsconfig = fileURLToPath(new URL('../../../../tsconfig.json', import.meta.url)) -const PROCESS_TIMEOUT_MS = 30_000 -const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000 -const PAUSED_RESULT = '"phase":"paused"' - -let child: ChildProcessWithoutNullStreams | undefined -let workdir: string | undefined - -afterEach(async () => { - if (child !== undefined && child.exitCode === null) child.kill('SIGKILL') - child = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined -}) - -async function jsonlFiles(dir: string): Promise { - const entries = await readdir(dir, { withFileTypes: true }) - const paths = await Promise.all(entries.map(async (entry) => { - const path = join(dir, entry.name) - if (entry.isDirectory()) return jsonlFiles(path) - return entry.isFile() && entry.name.endsWith('.jsonl') ? [path] : [] - })) - return paths.flat() -} - -async function runComposition(): Promise<{ stdout: string; stderr: string }> { - workdir = await mkdtemp(join(tmpdir(), 'goal-tools-e2e-')) - const cwd = workdir - return new Promise((resolve, reject) => { - const launch = resolveExampleLaunch({ - srcBin: binScript, - configArgs: [configPath], - tsconfigPath: repoTsconfig, - exposeInternals: true, - env: { - DSH_HOME: join(cwd, '.dsh'), - DSH_AGENTS_HOME: join(cwd, '.agents'), - }, - }) - const proc = spawn(launch.command, launch.args, { - cwd, - env: { ...process.env, ...launch.env }, - stdio: ['pipe', 'pipe', 'pipe'], - }) - child = proc - let stdout = '' - let stderr = '' - let pauseSent = false - let inputClosed = false - proc.stdout.setEncoding('utf8') - proc.stdout.on('data', (chunk: string) => { - stdout += chunk - if (!pauseSent && stdout.includes('GOAL CREATED') && stdout.includes('\n> ')) { - pauseSent = true - proc.stdin.write('pause\n') - } - const pausedAt = stdout.indexOf(PAUSED_RESULT) - if (!inputClosed && pausedAt >= 0 && stdout.indexOf('\n> ', pausedAt) >= 0) { - inputClosed = true - proc.stdin.end() - } - }) - proc.stderr.setEncoding('utf8') - proc.stderr.on('data', (chunk: string) => { stderr += chunk }) - - const timer = setTimeout(() => { - proc.kill('SIGKILL') - reject(new Error( - `goal-tools e2e did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`, - )) - }, PROCESS_TIMEOUT_MS) - proc.on('exit', (code) => { - clearTimeout(timer) - if (code === 0) resolve({ stdout, stderr }) - else reject(new Error(`goal-tools e2e exited ${String(code)}. stdout:\n${stdout}\nstderr:\n${stderr}`)) - }) - proc.on('error', (error) => { clearTimeout(timer); reject(error) }) - proc.stdin.write('start\n') - }) -} - -describe('goal tools through a real Loader, app, and stdio process', () => { - it('creates, reads, and pauses one root goal with durable tool and state records', async () => { - const { stdout, stderr } = await runComposition() - expect(stderr).not.toContain('UNHANDLED') - expect(stdout).toContain('goal-tools e2e ready.') - expect(stdout).toContain('GOAL CREATED') - expect(stdout).toContain(PAUSED_RESULT) - expect(stdout).toContain('GOAL PAUSED') - - const logs = await jsonlFiles(join(workdir as string, '.sessions')) - expect(logs).toHaveLength(1) - const lines = (await readFile(logs[0] as string, 'utf8')).trimEnd().split('\n') - const events = lines.slice(1).map(line => JSON.parse(line) as SessionEvent) - const calls = events.filter(event => event.type === 'tool/call') - expect(calls.map(event => event.data.name)).toEqual(['create_goal', 'get_goal', 'update_goal']) - const results = events.filter(event => event.type === 'tool/result') - expect(results).toHaveLength(3) - expect(results.every(event => !event.data.isError)).toBe(true) - - const changes = events - .filter(event => event.type === 'context/message' && event.data.source.kind === 'goal') - .map(event => event.type === 'context/message' ? decodeGoalChange(event.data.meta) : undefined) - expect(changes.map(change => change?.operation)).toEqual(['create', 'pause']) - expect(changes[1]).toMatchObject({ goal: { phase: 'paused', revision: 2, maxGoalRounds: 7 } }) - expect(JSON.stringify(changes)).not.toContain('activation') - - const headers = events.filter(event => event.type === 'request/header') - expect(JSON.stringify(headers)).toContain('infer goal intent') - expect(JSON.stringify(headers)).toContain('at least 3 consecutive goal rounds') - }, TEST_TIMEOUT_MS) -}) diff --git a/packages/goal/tool-goal/tests/tool-goal.spec.ts b/packages/goal/tool-goal/tests/tool-goal.spec.ts index 044fe2369a..cd45c145c7 100644 --- a/packages/goal/tool-goal/tests/tool-goal.spec.ts +++ b/packages/goal/tool-goal/tests/tool-goal.spec.ts @@ -135,8 +135,8 @@ describe('goal tool registration and presentation', () => { card: 'generic', title: 'Create goal', kind: 'other', rawInput: 'ship', }) expect(ctx.tools.get('update_goal')?.presentCall?.({ - goal_id: 'goal-1', revision: 2, action: 'blocked', - })).toEqual({ card: 'generic', title: 'Mark goal', kind: 'other', rawInput: 'goal-1' }) + goal_id: 'goal-1', revision: 2, action: 'blocked', blocked_reason: 'Waiting for a human choice.', + })).toEqual({ card: 'generic', title: 'Mark goal', kind: 'other', rawInput: 'Waiting for a human choice.' }) expect(ctx.tools.get('update_goal')?.presentCall?.({ goal_id: 'goal-1', revision: 2, action: 'resume', })).toEqual({ card: 'generic', title: 'Resume goal', kind: 'other', rawInput: 'goal-1' }) @@ -391,6 +391,26 @@ describe('goal tool state transitions', () => { max_goal_rounds: 2, }, root.agent) expect(terminalUpdate.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE') + const blockedWithoutReason = await execute(ctx, 'update_goal', { + goal_id: created.id, revision: created.revision, action: 'blocked', + }, root.agent) + expect(blockedWithoutReason.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE') + const blockedWithEmptyReason = await execute(ctx, 'update_goal', { + goal_id: created.id, revision: created.revision, action: 'blocked', blocked_reason: ' ', + }, root.agent) + expect(blockedWithEmptyReason.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE') + const completeWithReason = await execute(ctx, 'update_goal', { + goal_id: created.id, revision: created.revision, action: 'complete', blocked_reason: 'Not a blocker.', + }, root.agent) + expect(completeWithReason.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE') + const editWithReason = await execute(ctx, 'update_goal', { + goal_id: created.id, + revision: created.revision, + action: 'edit', + objective: 'still valid', + blocked_reason: 'Not valid for edit.', + }, root.agent) + expect(editWithReason.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE') const malformedRef = await execute(ctx, 'update_goal', { goal_id: '', revision: 0, action: 'edit', objective: 'x', }, root.agent) @@ -423,16 +443,26 @@ describe('goal tool state transitions', () => { for (let round = 1; round <= 2; round += 1) { turn = openTurn(root, { kind: 'goal', goalId: ref.id, revision: ref.revision, round }) const result = await execute(ctx, 'update_goal', { - goal_id: ref.id, revision: ref.revision, action: 'blocked', + goal_id: ref.id, + revision: ref.revision, + action: 'blocked', + blocked_reason: 'The required credential is still unavailable.', }, root.agent) expect(result.error?.code).toBe('GOAL_TOOL_BLOCK_THRESHOLD') closeTurn(root, turn) } openTurn(root, { kind: 'goal', goalId: ref.id, revision: ref.revision, round: 3 }) const blocked = await execute(ctx, 'update_goal', { - goal_id: ref.id, revision: ref.revision, action: 'blocked', + goal_id: ref.id, + revision: ref.revision, + action: 'blocked', + blocked_reason: 'The required credential is still unavailable.', }, root.agent) - expect(resultGoal(blocked)).toMatchObject({ phase: 'blocked', roundsStarted: 3 }) + expect(resultGoal(blocked)).toMatchObject({ + phase: 'blocked', + blockedReason: { code: 'model-reported', message: 'The required credential is still unavailable.' }, + roundsStarted: 3, + }) }) it('lets direct human authority block before the model threshold', async () => { @@ -440,8 +470,18 @@ describe('goal tool state transitions', () => { openTurn(root, { kind: 'user' }) const created = ctx.goals.create(root.agent, { objective: 'human stop' }) const blocked = await execute(ctx, 'update_goal', { - goal_id: created.id, revision: created.revision, action: 'blocked', + goal_id: created.id, + revision: created.revision, + action: 'blocked', + blocked_reason: 'The user asked to stop until a prerequisite is available.', }, root.agent) - expect(resultGoal(blocked)).toMatchObject({ phase: 'blocked', roundsStarted: 0 }) + expect(resultGoal(blocked)).toMatchObject({ + phase: 'blocked', + blockedReason: { + code: 'model-reported', + message: 'The user asked to stop until a prerequisite is available.', + }, + roundsStarted: 0, + }) }) }) From 23330b7a7d00fa6f4f058423aea57d4552792808 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 17:35:01 +0800 Subject: [PATCH 04/11] chore(goal): remove retired e2e dependencies --- knip.json | 2 +- packages/goal/tool-goal/package.json | 1 - pnpm-lock.yaml | 3 --- 3 files changed, 1 insertion(+), 5 deletions(-) diff --git a/knip.json b/knip.json index 9b7b511c44..8fa18dc524 100644 --- a/knip.json +++ b/knip.json @@ -72,7 +72,7 @@ "project": ["src/**/*.ts", "tests/**/*.ts"] }, "packages/goal/tool-goal": { - "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], + "entry": ["tests/**/*.spec.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, "packages/code-runtime/code-runtime-worker": { diff --git a/packages/goal/tool-goal/package.json b/packages/goal/tool-goal/package.json index 28cd6839f8..b9b4912cf4 100644 --- a/packages/goal/tool-goal/package.json +++ b/packages/goal/tool-goal/package.json @@ -38,7 +38,6 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-goal": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", - "@deepseek-ai/dsh-loader-smoke": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 957e3d05dd..9f7a641df7 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -425,9 +425,6 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm - '@deepseek-ai/dsh-loader-smoke': - specifier: workspace:^ - version: link:../../support/loader-smoke '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session From 4e7a2c732f77834e2dc5d03e3861e4a0c18bd132 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 17:41:22 +0800 Subject: [PATCH 05/11] fix(commands): remove adapter surface filtering --- ...7-19-plugin-command-registration.i18n.yaml | 4 +- .../2026-07-19-plugin-command-registration.md | 11 ++-- ...26-07-19-plugin-command-registration.zh.md | 11 ++-- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 23 +++---- docs/core-data-structures/commands.md | 19 ++---- docs/event-producer-consumer.md | 2 +- docs/glossary.md | 1 - .../cordis/tool-cordis/src/api-catalog.ts | 24 +++---- packages/ui/acp/src/index.ts | 4 +- packages/ui/acp/tests/commands.spec.ts | 5 +- packages/ui/commands/README.md | 4 +- packages/ui/commands/src/index.ts | 56 ++++------------- packages/ui/commands/tests/commands.spec.ts | 63 ++++++++----------- packages/ui/tui/src/index.ts | 13 +--- packages/ui/tui/tests/tui.spec.ts | 11 +--- scripts/type-equiv.manifest.json | 1 - website/zh-CN/api/harness/commands.md | 48 +++++++------- website/zh-CN/api/harness/events.md | 2 +- 19 files changed, 112 insertions(+), 192 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.i18n.yaml index 48d880e666..7294638f1a 100644 --- a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.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 -2026-07-19-plugin-command-registration.md: 821f22405fd6a4bc0b8bfd3c5edf773be844899d -2026-07-19-plugin-command-registration.zh.md: 7a2ed82eb1a8f55d4d701a68c4053e5d412b7d04 +2026-07-19-plugin-command-registration.md: c414f8183e100f712a552828992d108193fc33cf +2026-07-19-plugin-command-registration.zh.md: 3cd820c55ec30f3b2f6cf471376abfd8edd8ac5e diff --git a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md index 821f22405f..c414f8183e 100644 --- a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md +++ b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md @@ -16,9 +16,9 @@ A shared mechanism must remain a UI concern rather than a model tool or agent-lo ### Registry contract -A `CommandDefinition` contains a lowercase name without `/`, a non-empty description, an optional unstructured-input hint, an optional non-empty surface list, and an abortable handler. Omitted surfaces resolve to `tui` plus `acp`. Registration validates and detaches the metadata, freezes the effective definition, and returns the exact Cordis effect disposer. Duplicate names fail within one layer. +A `CommandDefinition` contains a lowercase name without `/`, a non-empty description, an optional unstructured-input hint, and an abortable handler. Registration validates and detaches the metadata, freezes the effective definition, and returns the exact Cordis effect disposer. Duplicate names fail within one layer. Every adapter consuming the registry sees every effective definition; a command plugin that cannot operate in a deployment omits its registration there instead of encoding adapter identities in the shared domain. -`list(agent, surface)` returns immutable name-sorted descriptors after surface filtering and scoped shadowing. `find(agent, surface, name)` resolves the effective definition. `execute(agent, surface, line, signal)` parses and runs a visible definition, returning a detached `success` or `error` result; invalid syntax, unknown names, and hidden definitions return `undefined` so the adapter owns its direct error text. +`list(agent)` returns immutable name-sorted descriptors after scoped shadowing. `find(agent, name)` resolves the effective definition. `execute(agent, line, signal)` parses and runs a known definition, returning a detached `success` or `error` result; invalid syntax and unknown names return `undefined` so the adapter owns its direct error text. `parseCommand(line)` requires `/` at byte zero, a lowercase ASCII name containing letters, digits, `_`, or `-`, then whitespace or end-of-input. It preserves the complete adapter-delivered suffix as `rawInput`, including separator whitespace. Command-specific plugins own every further grammar decision. @@ -30,13 +30,13 @@ Registration and removal emit the unfiltered, non-vetoing `commands/change` regi ### Direct dispatch and cancellation -Commands run in a human-only command plane. Their input does not become `user/message`, their output does not become a session event, and neither is sent to the model. A handler receives the exact target agent, surface, raw input, and request-owned `AbortSignal`. The registry stops awaiting an uncooperative handler when the signal aborts; the handler remains responsible for stopping external side effects already started. +Commands run in a human-only command plane. Their input does not become `user/message`, their output does not become a session event, and neither is sent to the model. A handler receives the exact target agent, raw input, and request-owned `AbortSignal`. The registry stops awaiting an uncooperative handler when the signal aborts; the handler remains responsible for stopping external side effects already started. Expected handler failures return `CommandResult.error`. Thrown or malformed results remain adapter-visible command failures, not model messages. This boundary deliberately separates UI output from durable domain mutation: a goal command may change `ctx.goals`, for example, but the goal service owns that persisted state. ### TUI mapping -The TUI registers `help`, `clear`, `cancel`, `reasoning`, `tools`, `redraw`, and `exit` as agent-scoped command definitions instead of switching on strings. Its autocomplete and help view read the live `tui` catalog, so plugin commands appear and disappear with their effects. Any submitted line beginning with `/` stays in the command plane; unknown input produces a terminal warning rather than falling through to `Agent.send()` or `Agent.steer()`. +The TUI registers `help`, `clear`, `cancel`, `reasoning`, `tools`, `redraw`, and `exit` as agent-scoped command definitions instead of switching on strings. Its autocomplete and help view read the live catalog, so plugin commands appear and disappear with their effects. Any submitted line beginning with `/` stays in the command plane; unknown input produces a terminal warning rather than falling through to `Agent.send()` or `Agent.steer()`. Each submitted command owns an `AbortController`. TUI disposal aborts outstanding dispatches, removes the local definitions, and waits for the command-producing fiber before completing teardown. @@ -50,7 +50,7 @@ One model prompt or direct command may be in flight per ACP session, independent ## Testing -The registry suite covers syntax boundaries, immutable normalization, runtime metadata validation, default and explicit surfaces, deterministic sorting, global and scoped shadowing, duplicate rejection, exact disposal, contained change-notification failures, direct invocation, expected and malformed results, synchronous and asynchronous failure, and every abort timing edge at per-file 100% statement, branch, function, and line coverage. +The registry suite covers syntax boundaries, immutable normalization, runtime metadata validation, deterministic sorting, global and scoped shadowing, duplicate rejection, exact disposal, contained change-notification failures, direct invocation, expected and malformed results, synchronous and asynchronous failure, and every abort timing edge at per-file 100% statement, branch, function, and line coverage. TUI tests exercise all migrated built-ins, live plugin discovery, help/autocomplete refresh, direct results, unknown-command rejection, raw-input delivery, definition removal, startup rollback, and disposal cancellation. ACP tests use the real SDK connection, agent factory, loop, and JSONL persistence to verify create/load snapshots, dynamic updates, scoped multi-session catalogs, supported-block flattening, direct success/error/failure, unknown-command isolation, cancellation, and the absence of model requests or session messages. The SDK helper suite pins direct-ACP composition. Keyless ACP and terminal snapshots pin the new protocol and rendered transcript shapes. @@ -60,6 +60,7 @@ TUI tests exercise all migrated built-ins, live plugin discovery, help/autocompl - **Represent human commands as model tools** — rejected because discovery and direct invocation are human UI behavior; routing through the model adds latency, token cost, and reinterpretation. - **Put the registry in the core agent spine** — rejected because headless and JSON-RPC agents do not consume it, while the two UI app bundles can compose it explicitly. - **Make `dsh-agent-loop` inject commands** — rejected because the loop does not execute or discover human commands. Agent-scoped producers declare the UI dependency in a child plugin instead. +- **Attach adapter masks to each definition** — rejected because support is a composition fact, not command-domain state. Every composed adapter exposes a registered command; an incompatible plugin omits registration in that deployment. - **Send unknown slash input to the model** — rejected because typoed or unavailable direct actions must fail predictably rather than change execution planes. - **Persist generic command input and output** — rejected because adapter notices are not model-visible state. A handler that changes durable behavior calls the owning domain API, which records its own events. - **Restrict ACP commands to one text block** — rejected because ACP v1 permits accompanying content; the bridge already has a lossless accepted-block translation. diff --git a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.zh.md b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.zh.md index 7a2ed82eb1..3cd820c55e 100644 --- a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.zh.md @@ -16,9 +16,9 @@ TUI 拥有七个斜杠命令，而 ACP 定义了标准命令目录与调用形 ### 注册表契约 -`CommandDefinition` 包含不带 `/` 的小写名称、非空描述、可选的非结构化输入提示、可选的非空界面列表，以及可取消处理器。省略界面时解析为 `tui` 与 `acp`。注册会校验并分离元数据、冻结有效定义，并返回准确的 Cordis effect disposer（副作用释放器）。同一层中的重复名称会失败。 +`CommandDefinition` 包含不带 `/` 的小写名称、非空描述、可选的非结构化输入提示，以及可取消处理器。注册会校验并分离元数据、冻结有效定义，并返回准确的 Cordis effect disposer（副作用释放器）。同一层中的重复名称会失败。每个消费该注册表的适配器都能看到所有有效定义；若命令插件无法在某种部署中运行，它就不在该部署中注册，而不是把适配器身份编码进共享领域。 -`list(agent, surface)` 在界面过滤与作用域遮蔽后返回不可变、按名称排序的描述符。`find(agent, surface, name)` 解析有效定义。`execute(agent, surface, line, signal)` 解析并运行可见定义，返回分离后的 `success` 或 `error` 结果；无效语法、未知名称和对该界面隐藏的定义返回 `undefined`，由适配器拥有直接错误文本。 +`list(agent)` 在作用域遮蔽后返回不可变、按名称排序的描述符。`find(agent, name)` 解析有效定义。`execute(agent, line, signal)` 解析并运行已知定义，返回分离后的 `success` 或 `error` 结果；无效语法和未知名称返回 `undefined`，由适配器拥有直接错误文本。 `parseCommand(line)` 要求 `/` 位于第零字节，后接由字母、数字、`_` 或 `-` 组成的小写 ASCII 名称，并以空白或输入末尾结束。它把适配器交付的完整后缀保留为 `rawInput`，包括分隔空白。每个命令插件自行拥有后续语法决策。 @@ -30,13 +30,13 @@ TUI 拥有七个斜杠命令，而 ACP 定义了标准命令目录与调用形 ### 直接分派与取消 -命令在仅面向人类的命令平面中运行。输入不会成为 `user/message`，输出不会成为会话事件，两者都不会发送给模型。处理器接收准确的目标智能体、界面、原始输入和请求拥有的 `AbortSignal`。信号中止时，注册表不再等待不合作的处理器；处理器仍负责停止已经启动的外部副作用。 +命令在仅面向人类的命令平面中运行。输入不会成为 `user/message`，输出不会成为会话事件，两者都不会发送给模型。处理器接收准确的目标智能体、原始输入和请求拥有的 `AbortSignal`。信号中止时，注册表不再等待不合作的处理器；处理器仍负责停止已经启动的外部副作用。 预期的处理器失败返回 `CommandResult.error`。抛出的异常或格式错误的结果仍是适配器可见的命令失败，而不是模型消息。该边界有意分离 UI 输出与持久领域变更：例如目标命令可以改变 `ctx.goals`，但持久状态由目标服务拥有。 ### TUI 映射 -TUI 把 `help`、`clear`、`cancel`、`reasoning`、`tools`、`redraw` 和 `exit` 注册为智能体作用域命令定义，不再对字符串执行 switch。自动补全与帮助视图读取实时 `tui` 目录，因此插件命令会随其副作用出现和消失。任何以 `/` 开头的提交行都留在命令平面；未知输入产生终端警告，不会落入 `Agent.send()` 或 `Agent.steer()`。 +TUI 把 `help`、`clear`、`cancel`、`reasoning`、`tools`、`redraw` 和 `exit` 注册为智能体作用域命令定义，不再对字符串执行 switch。自动补全与帮助视图读取实时目录，因此插件命令会随其副作用出现和消失。任何以 `/` 开头的提交行都留在命令平面；未知输入产生终端警告，不会落入 `Agent.send()` 或 `Agent.steer()`。 每个提交的命令拥有一个 `AbortController`。TUI 释放会中止未完成的分派、移除本地定义，并等待命令生产者 fiber（纤程）后再完成清理。 @@ -50,7 +50,7 @@ ACP 允许命令提示携带额外的受支持内容块。桥接应用普通的 ## 测试 -注册表测试覆盖语法边界、不可变规范化、运行时元数据校验、默认和显式界面、确定性排序、全局与作用域遮蔽、重复拒绝、准确释放、变更通知失败隔离、直接调用、预期和格式错误结果、同步与异步失败，以及每种中止时序边沿；该源文件达到逐文件 100% 语句、分支、函数和行覆盖率。 +注册表测试覆盖语法边界、不可变规范化、运行时元数据校验、确定性排序、全局与作用域遮蔽、重复拒绝、准确释放、变更通知失败隔离、直接调用、预期和格式错误结果、同步与异步失败，以及每种中止时序边沿；该源文件达到逐文件 100% 语句、分支、函数和行覆盖率。 TUI 测试覆盖全部迁移后的内置命令、实时插件发现、帮助与自动补全刷新、直接结果、未知命令拒绝、原始输入交付、定义移除、启动回滚和释放取消。ACP 测试使用真实 SDK 连接、智能体工厂、循环与 JSONL 持久化，验证创建/加载快照、动态更新、作用域多会话目录、受支持块扁平化、直接成功/错误/失败、未知命令隔离、取消，以及不存在模型请求或会话消息。SDK helper 测试固定直接 ACP 组合。无密钥 ACP 与终端快照固定新的协议和渲染记录形态。 @@ -60,6 +60,7 @@ TUI 测试覆盖全部迁移后的内置命令、实时插件发现、帮助与 - **把人类命令表示为模型工具**——不予采纳，因为发现与直接调用属于人类 UI 行为；经由模型路由会增加延迟、token 成本和重新解释。 - **把注册表放入核心智能体主干**——不予采纳，因为无头和 JSON-RPC 智能体不消费它，而两个 UI 应用组合包可以显式组合它。 - **让 `dsh-agent-loop` 注入 commands**——不予采纳，因为循环不执行也不发现人类命令。智能体作用域生产者改为在子插件中声明 UI 依赖。 +- **为每个定义附加适配器掩码**——不予采纳，因为支持能力是组合事实，而不是命令领域状态。每个已组合适配器都暴露已注册命令；不兼容插件不会在该部署中注册。 - **把未知斜杠输入发送给模型**——不予采纳，因为输入错误或不可用的直接操作必须可预测地失败，而不能改变执行平面。 - **持久化通用命令输入与输出**——不予采纳，因为适配器提示不是模型可见状态。改变持久行为的处理器会调用拥有该状态的领域 API，由后者记录自己的事件。 - **把 ACP 命令限制为单个文本块**——不予采纳，因为 ACP v1 允许附带内容，而桥接已有无损的已接纳块转换。 diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index f05d78e9eb..e0f2e924f0 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -426,7 +426,7 @@ A command was registered or unregistered. This is an unfiltered registry notific 'commands/change'(): void ``` -Source: [`packages/ui/commands/src/index.ts:94`](../../packages/ui/commands/src/index.ts) +Source: [`packages/ui/commands/src/index.ts:83`](../../packages/ui/commands/src/index.ts) ## `fs/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index cac512b59d..85cadd1de1 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -347,42 +347,39 @@ Human-command registry. Plain-context definitions are global; definitions regist ```ts cordis-catalog /** * Register a global or calling-agent-scoped command. - * @param definition - discovery metadata, surface mask, and direct UI handler. + * @param definition - discovery metadata and direct UI handler. * @returns the exact effect disposer that unregisters this definition. */ register(definition: CommandDefinition): () => void /** - * List the effective immutable command descriptors for one agent and surface. + * List the effective immutable command descriptors for one agent. * @param agent - exact receiving agent and scoped-layer key. - * @param surface - UI adapter requesting discovery metadata. - * @returns name-sorted descriptors after scoped shadowing and surface filtering. + * @returns name-sorted descriptors after scoped shadowing. */ -list(agent: Agent, surface: CommandSurface): readonly CommandDescriptor[] +list(agent: Agent): readonly CommandDescriptor[] /** * Resolve one effective command definition. * @param agent - exact receiving agent and scoped-layer key. - * @param surface - UI adapter performing the lookup. * @param name - command name without a slash. - * @returns the scoped shadow or global definition when visible on the surface. + * @returns the scoped shadow or global definition. */ -find(agent: Agent, surface: CommandSurface, name: string): CommandDefinition | undefined +find(agent: Agent, name: string): CommandDefinition | undefined /** * Parse and execute a known command without sending it to the model. * @param agent - exact receiving agent. - * @param surface - dispatching UI adapter. * @param line - complete slash-command line. * @param signal - cancellation signal owned by the UI request. - * @returns a detached result, or `undefined` when syntax/name/surface does not resolve. + * @returns a detached result, or `undefined` when syntax or name does not resolve. */ -async execute( agent: Agent, surface: CommandSurface, line: string, signal: AbortSignal, ): Promise +async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise ``` -Types: [Agent](../core-data-structures/core.md) · [CommandDefinition](../core-data-structures/commands.md) · [CommandDescriptor](../core-data-structures/commands.md) · [CommandResult](../core-data-structures/commands.md) · [CommandSurface](../core-data-structures/commands.md) +Types: [Agent](../core-data-structures/core.md) · [CommandDefinition](../core-data-structures/commands.md) · [CommandDescriptor](../core-data-structures/commands.md) · [CommandResult](../core-data-structures/commands.md) -Source: [`packages/ui/commands/src/index.ts:235`](../../packages/ui/commands/src/index.ts) +Source: [`packages/ui/commands/src/index.ts:207`](../../packages/ui/commands/src/index.ts) ## `ctx.compact` — `CompactService` (abstract seam) diff --git a/docs/core-data-structures/commands.md b/docs/core-data-structures/commands.md index e8fd7ec497..c33b27ce1c 100644 --- a/docs/core-data-structures/commands.md +++ b/docs/core-data-structures/commands.md @@ -4,14 +4,9 @@ The human-command seam of [`dsh-commands`](../../packages/ui/commands). TUI and Source: [`packages/ui/commands/src/index.ts`](../../packages/ui/commands/src/index.ts) -## Surface and input metadata +## Input metadata -A definition selects one or more adapter identities. The shipped identities are `tui` and `acp`; the string intersection keeps the registry extensible without widening editor autocomplete to plain `string`. ACP currently exposes one unstructured-input hint. - -```ts type-equiv -/** A UI adapter capable of listing and executing human commands. */ -type CommandSurface = 'tui' | 'acp' | (string & {}) -``` +ACP currently exposes one unstructured-input hint. Command availability follows plugin composition: every adapter consuming the registry sees every effective definition. ```ts type-equiv /** Immutable command input metadata compatible with ACP unstructured input. */ @@ -23,7 +18,7 @@ interface CommandInputDescriptor { ## Definition -`CommandDefinition` is the plugin-authored registration. Omitted surfaces resolve to both shipped adapters; the registry validates and freezes a detached effective definition. +`CommandDefinition` is the plugin-authored registration. The registry validates and freezes a detached effective definition. ```ts type-equiv /** Plugin-owned command registration. */ @@ -34,8 +29,6 @@ interface CommandDefinition { readonly description: string /** Optional free-form input hint advertised to capable clients. */ readonly input?: CommandInputDescriptor - /** Surfaces exposing this command; omission means both shipped surfaces. */ - readonly surfaces?: readonly CommandSurface[] /** Execute against the receiving agent without sending the command to the model. */ readonly handler: (invocation: CommandInvocation) => CommandResult | Promise } @@ -50,8 +43,6 @@ The adapter owns cancellation and passes the exact target agent. `rawInput` begi interface CommandInvocation { /** Exact agent whose human-facing surface received the command. */ readonly agent: Agent - /** UI adapter that dispatched the command. */ - readonly surface: CommandSurface /** Exact text following the registered command name, including separator whitespace. */ readonly rawInput: string /** Cancellation signal owned by the dispatching UI request. */ @@ -68,7 +59,7 @@ type CommandResult = ## Discovery and parsing views -Adapters receive handler-free immutable descriptors after scope resolution and surface filtering. `parseCommand()` returns `ParsedCommand` before registry resolution; syntax-valid input can still name an unavailable command. +Adapters receive handler-free immutable descriptors after scope resolution. `parseCommand()` returns `ParsedCommand` before registry resolution; syntax-valid input can still name an unavailable command. ```ts type-equiv /** Handler-free immutable command view returned to UI adapters. */ @@ -79,8 +70,6 @@ interface CommandDescriptor { readonly description: string /** Optional free-form input hint advertised to capable clients. */ readonly input?: CommandInputDescriptor - /** Surfaces on which this definition is visible. */ - readonly surfaces: readonly CommandSurface[] } ``` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 9acbbbb348..0e02626b85 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -25,7 +25,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:302`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | | `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:312`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`tool-goal`](../packages/goal/tool-goal) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | -| `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:94`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`tui`](../packages/ui/tui) | +| `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:83`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`tui`](../packages/ui/tui) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:61`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:70`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:53`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/glossary.md b/docs/glossary.md index ffb900d7b5..19daaa29dd 100644 --- a/docs/glossary.md +++ b/docs/glossary.md @@ -26,7 +26,6 @@ FIXME(glossary-completeness): Expand this glossary before the first release so i - **human command** — a slash-prefixed instruction interpreted and executed by a human-facing adapter through `ctx.commands`, without becoming a model message. It is distinct from a model-facing tool and from shell command execution through `ctx.bash`. - **command plane** — discovery, parsing, dispatch, cancellation, and result rendering owned by UI adapters and command plugins. Command output is UI state unless the handler separately mutates a durable domain. -- **command surface** — the adapter identity used to filter definitions, such as `tui` or `acp`; one scoped definition may shadow a same-named global command for its exact agent. ## loop hierarchy diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 8047af2834..b3701290d6 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -204,19 +204,19 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ methods: [ { signature: 'register(definition: CommandDefinition): () => void', - jsDoc: '/**\n * Register a global or calling-agent-scoped command.\n * @param definition - discovery metadata, surface mask, and direct UI handler.\n * @returns the exact effect disposer that unregisters this definition.\n */', + jsDoc: '/**\n * Register a global or calling-agent-scoped command.\n * @param definition - discovery metadata and direct UI handler.\n * @returns the exact effect disposer that unregisters this definition.\n */', }, { - signature: 'list(agent: Agent, surface: CommandSurface): readonly CommandDescriptor[]', - jsDoc: '/**\n * List the effective immutable command descriptors for one agent and surface.\n * @param agent - exact receiving agent and scoped-layer key.\n * @param surface - UI adapter requesting discovery metadata.\n * @returns name-sorted descriptors after scoped shadowing and surface filtering.\n */', + signature: 'list(agent: Agent): readonly CommandDescriptor[]', + jsDoc: '/**\n * List the effective immutable command descriptors for one agent.\n * @param agent - exact receiving agent and scoped-layer key.\n * @returns name-sorted descriptors after scoped shadowing.\n */', }, { - signature: 'find(agent: Agent, surface: CommandSurface, name: string): CommandDefinition | undefined', - jsDoc: '/**\n * Resolve one effective command definition.\n * @param agent - exact receiving agent and scoped-layer key.\n * @param surface - UI adapter performing the lookup.\n * @param name - command name without a slash.\n * @returns the scoped shadow or global definition when visible on the surface.\n */', + signature: 'find(agent: Agent, name: string): CommandDefinition | undefined', + jsDoc: '/**\n * Resolve one effective command definition.\n * @param agent - exact receiving agent and scoped-layer key.\n * @param name - command name without a slash.\n * @returns the scoped shadow or global definition.\n */', }, { - signature: 'async execute( agent: Agent, surface: CommandSurface, line: string, signal: AbortSignal, ): Promise', - jsDoc: '/**\n * Parse and execute a known command without sending it to the model.\n * @param agent - exact receiving agent.\n * @param surface - dispatching UI adapter.\n * @param line - complete slash-command line.\n * @param signal - cancellation signal owned by the UI request.\n * @returns a detached result, or `undefined` when syntax/name/surface does not resolve.\n */', + signature: 'async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise', + jsDoc: '/**\n * Parse and execute a known command without sending it to the model.\n * @param agent - exact receiving agent.\n * @param line - complete slash-command line.\n * @param signal - cancellation signal owned by the UI request.\n * @returns a detached result, or `undefined` when syntax or name does not resolve.\n */', }, ], }, @@ -1127,11 +1127,11 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CommandDefinition', - declaration: 'export interface CommandDefinition {\n readonly name: string;\n readonly description: string;\n readonly input?: CommandInputDescriptor;\n readonly surfaces?: readonly CommandSurface[];\n readonly handler: (invocation: CommandInvocation) => CommandResult | Promise;\n}', + declaration: 'export interface CommandDefinition {\n readonly name: string;\n readonly description: string;\n readonly input?: CommandInputDescriptor;\n readonly handler: (invocation: CommandInvocation) => CommandResult | Promise;\n}', }, { name: 'CommandDescriptor', - declaration: 'export interface CommandDescriptor {\n readonly name: string;\n readonly description: string;\n readonly input?: CommandInputDescriptor;\n readonly surfaces: readonly CommandSurface[];\n}', + declaration: 'export interface CommandDescriptor {\n readonly name: string;\n readonly description: string;\n readonly input?: CommandInputDescriptor;\n}', }, { name: 'CommandInputDescriptor', @@ -1139,16 +1139,12 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CommandInvocation', - declaration: 'export interface CommandInvocation {\n readonly agent: Agent;\n readonly surface: CommandSurface;\n readonly rawInput: string;\n readonly signal: AbortSignal;\n}', + declaration: 'export interface CommandInvocation {\n readonly agent: Agent;\n readonly rawInput: string;\n readonly signal: AbortSignal;\n}', }, { name: 'CommandResult', declaration: 'export type CommandResult = {\n readonly kind: \'success\';\n readonly text?: string;\n} | {\n readonly kind: \'error\';\n readonly text: string;\n};', }, - { - name: 'CommandSurface', - declaration: 'export type CommandSurface = \'tui\' | \'acp\' | (string & {});', - }, { name: 'CompactAgentContext', declaration: 'export interface CompactAgentContext {\n session: Session;\n options: {\n provider?: string;\n model?: string;\n };\n}', diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 459dc50a43..2f075a7ccc 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -514,7 +514,7 @@ export function apply(ctx: Context, config: AcpConfig): void { } /** Project the effective registry view onto ACP discovery metadata. */ - const availableCommands = (agent: Agent): AvailableCommand[] => commands.list(agent, 'acp').map(command => ({ + const availableCommands = (agent: Agent): AvailableCommand[] => commands.list(agent).map(command => ({ name: command.name, description: command.description, ...command.input === undefined ? {} : { input: { hint: command.input.hint } }, @@ -905,7 +905,7 @@ export function apply(ctx: Context, config: AcpConfig): void { const controller = new AbortController() rec.commandAbort = controller try { - const result = await commands.execute(rec.agent, 'acp', commandLine, controller.signal) + const result = await commands.execute(rec.agent, commandLine, controller.signal) if (result !== undefined && result.text !== undefined && result.text !== '') { notify({ sessionId: rec.agent.session.id, diff --git a/packages/ui/acp/tests/commands.spec.ts b/packages/ui/acp/tests/commands.spec.ts index 946ee67950..71aae1ea64 100644 --- a/packages/ui/acp/tests/commands.spec.ts +++ b/packages/ui/acp/tests/commands.spec.ts @@ -55,7 +55,6 @@ describe('ACP plugin commands', () => { const dispose = harness.ctx.commands.register({ name: 'alpha', description: 'Alpha command', - surfaces: ['acp'], handler: () => ({ kind: 'success' }), }) await vi.waitFor(() => { @@ -126,7 +125,7 @@ describe('ACP plugin commands', () => { }) expect(response.stopReason).toBe('end_turn') - expect(seen).toHaveBeenCalledWith(expect.objectContaining({ surface: 'acp', rawInput: ' raw args ' })) + expect(seen).toHaveBeenCalledWith(expect.objectContaining({ rawInput: ' raw args ' })) expect(messageText(harness, sessionId)).toContain('DIRECT RESULT') const updatesAfterText = harness.sessionUpdates.length await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: '/silent' }] }) @@ -260,7 +259,7 @@ describe('ACP plugin commands', () => { if (agentA === undefined) throw new Error('session A has no agent') await agentA.ctx.inject(['commands'], (commandCtx) => { commandCtx.commands.register({ - name: 'private', description: 'Only session A', surfaces: ['acp'], + name: 'private', description: 'Only session A', handler: () => ({ kind: 'success', text: 'A ONLY' }), }) }) diff --git a/packages/ui/commands/README.md b/packages/ui/commands/README.md index 5b6c8b9425..6e0efa458b 100644 --- a/packages/ui/commands/README.md +++ b/packages/ui/commands/README.md @@ -4,9 +4,9 @@ Plugin-owned human-command registry shared by the TUI and ACP adapters. The [plu ## Service contract -`ctx.commands.register(definition)` registers one lowercase command name, description, optional ACP-compatible unstructured-input hint, optional surface list, and abortable handler. A plain-context registration is global. A command-producing plugin mounted beneath `agent.ctx` declares its own `commands` injection and creates an exact agent-scoped definition; it shadows a global definition with the same name. This child-injection shape preserves the agent scope without making the core agent loop depend on a UI service. Duplicate names within one layer fail during registration. Every disposer is the exact Cordis effect disposer, and registration or removal notifies every `commands/change` observer so live adapters can refresh discovery; observer failures are logged and cannot veto the registry mutation or starve later observers. +`ctx.commands.register(definition)` registers one lowercase command name, description, optional ACP-compatible unstructured-input hint, and abortable handler. A registered command is available to every composed command adapter; a plugin that is incompatible with a deployment does not register there. A plain-context registration is global. A command-producing plugin mounted beneath `agent.ctx` declares its own `commands` injection and creates an exact agent-scoped definition; it shadows a global definition with the same name. This child-injection shape preserves the agent scope without making the core agent loop depend on a UI service. Duplicate names within one layer fail during registration. Every disposer is the exact Cordis effect disposer, and registration or removal notifies every `commands/change` observer so live adapters can refresh discovery; observer failures are logged and cannot veto the registry mutation or starve later observers. -`list(agent, surface)` returns immutable, name-sorted descriptors after scoped shadowing and surface filtering. `find(agent, surface, name)` returns the corresponding definition. `execute(agent, surface, line, signal)` uses `parseCommand()` and runs only a known command, returning `undefined` for invalid syntax, unknown names, or commands hidden from that surface. +`list(agent)` returns immutable, name-sorted descriptors after scoped shadowing. `find(agent, name)` returns the corresponding definition. `execute(agent, line, signal)` uses `parseCommand()` and runs only a known command, returning `undefined` for invalid syntax or unknown names. `parseCommand()` recognizes a slash at byte zero, a lowercase name containing letters, digits, `_`, or `-`, and either end-of-input or whitespace. It returns every byte after the name as `rawInput`, including separator whitespace; consumers own their command-specific grammar and may normalize only what that grammar permits. diff --git a/packages/ui/commands/src/index.ts b/packages/ui/commands/src/index.ts index 529dea11b4..16e665e71f 100644 --- a/packages/ui/commands/src/index.ts +++ b/packages/ui/commands/src/index.ts @@ -11,11 +11,6 @@ import type { ScopeKey } from '@deepseek-ai/dsh-scope' export const name = 'commands' const COMMAND_NAME = /^[a-z][a-z0-9_-]*$/u -const SURFACE_NAME = /^[a-z][a-z0-9-]*$/u -const DEFAULT_SURFACES = ['tui', 'acp'] as const - -/** A UI adapter capable of listing and executing human commands. */ -export type CommandSurface = 'tui' | 'acp' | (string & {}) /** Immutable command input metadata compatible with ACP unstructured input. */ export interface CommandInputDescriptor { @@ -27,8 +22,6 @@ export interface CommandInputDescriptor { export interface CommandInvocation { /** Exact agent whose human-facing surface received the command. */ readonly agent: Agent - /** UI adapter that dispatched the command. */ - readonly surface: CommandSurface /** Exact text following the registered command name, including separator whitespace. */ readonly rawInput: string /** Cancellation signal owned by the dispatching UI request. */ @@ -48,8 +41,6 @@ export interface CommandDefinition { readonly description: string /** Optional free-form input hint advertised to capable clients. */ readonly input?: CommandInputDescriptor - /** Surfaces exposing this command; omission means both shipped surfaces. */ - readonly surfaces?: readonly CommandSurface[] /** Execute against the receiving agent without sending the command to the model. */ readonly handler: (invocation: CommandInvocation) => CommandResult | Promise } @@ -62,8 +53,6 @@ export interface CommandDescriptor { readonly description: string /** Optional free-form input hint advertised to capable clients. */ readonly input?: CommandInputDescriptor - /** Surfaces on which this definition is visible. */ - readonly surfaces: readonly CommandSurface[] } /** Syntactically valid slash command before registry resolution. */ @@ -75,7 +64,7 @@ export interface ParsedCommand { } interface RegisteredCommand { - readonly definition: CommandDefinition & { readonly surfaces: readonly CommandSurface[] } + readonly definition: CommandDefinition readonly descriptor: CommandDescriptor } @@ -175,33 +164,16 @@ function normalizeDefinition(definition: CommandDefinition): RegisteredCommand { } input = Object.freeze({ hint: rawInput.hint }) } - const surfaces = [...(definition.surfaces ?? DEFAULT_SURFACES)] - if (surfaces.length === 0) { - throw new TypeError(`command "${definition.name}" must expose at least one surface`) - } - const unique = new Set() - for (const surface of surfaces) { - if (!SURFACE_NAME.test(surface)) { - throw new TypeError(`command "${definition.name}" surface "${surface}" must match ${String(SURFACE_NAME)}`) - } - if (unique.has(surface)) { - throw new TypeError(`command "${definition.name}" surface "${surface}" is duplicated`) - } - unique.add(surface) - } - const frozenSurfaces = Object.freeze(surfaces) const normalized = Object.freeze({ name: definition.name, description: definition.description, ...input === undefined ? {} : { input }, - surfaces: frozenSurfaces, handler: definition.handler, }) const descriptor = Object.freeze({ name: normalized.name, description: normalized.description, ...normalized.input === undefined ? {} : { input: normalized.input }, - surfaces: normalized.surfaces, }) return { definition: normalized, descriptor } } @@ -242,7 +214,7 @@ export class CommandService extends Service { /** * Register a global or calling-agent-scoped command. - * @param definition - discovery metadata, surface mask, and direct UI handler. + * @param definition - discovery metadata and direct UI handler. * @returns the exact effect disposer that unregisters this definition. */ register(definition: CommandDefinition): () => void { @@ -268,14 +240,12 @@ export class CommandService extends Service { } /** - * List the effective immutable command descriptors for one agent and surface. + * List the effective immutable command descriptors for one agent. * @param agent - exact receiving agent and scoped-layer key. - * @param surface - UI adapter requesting discovery metadata. - * @returns name-sorted descriptors after scoped shadowing and surface filtering. + * @returns name-sorted descriptors after scoped shadowing. */ - list(agent: Agent, surface: CommandSurface): readonly CommandDescriptor[] { + list(agent: Agent): readonly CommandDescriptor[] { return Object.freeze([...this.view(agent).values()] - .filter(command => command.definition.surfaces.includes(surface)) .map(command => command.descriptor) // Names are unique in the effective view, so equality is impossible. .sort((left, right) => left.name < right.name ? -1 : 1)) @@ -284,35 +254,31 @@ export class CommandService extends Service { /** * Resolve one effective command definition. * @param agent - exact receiving agent and scoped-layer key. - * @param surface - UI adapter performing the lookup. * @param name - command name without a slash. - * @returns the scoped shadow or global definition when visible on the surface. + * @returns the scoped shadow or global definition. */ - find(agent: Agent, surface: CommandSurface, name: string): CommandDefinition | undefined { - const command = this.view(agent).get(name) - return command?.definition.surfaces.includes(surface) === true ? command.definition : undefined + find(agent: Agent, name: string): CommandDefinition | undefined { + return this.view(agent).get(name)?.definition } /** * Parse and execute a known command without sending it to the model. * @param agent - exact receiving agent. - * @param surface - dispatching UI adapter. * @param line - complete slash-command line. * @param signal - cancellation signal owned by the UI request. - * @returns a detached result, or `undefined` when syntax/name/surface does not resolve. + * @returns a detached result, or `undefined` when syntax or name does not resolve. */ async execute( agent: Agent, - surface: CommandSurface, line: string, signal: AbortSignal, ): Promise { const parsed = parseCommand(line) if (parsed === undefined) return undefined const command = this.view(agent).get(parsed.name) - if (command === undefined || !command.definition.surfaces.includes(surface)) return undefined + if (command === undefined) return undefined if (signal.aborted) throw abortError(signal) - const invocation = Object.freeze({ agent, surface, rawInput: parsed.rawInput, signal }) + const invocation = Object.freeze({ agent, rawInput: parsed.rawInput, signal }) const output = command.definition.handler(invocation) return normalizeResult(parsed.name, await withAbort(Promise.resolve(output), signal)) } diff --git a/packages/ui/commands/tests/commands.spec.ts b/packages/ui/commands/tests/commands.spec.ts index e3da186492..839ccb0297 100644 --- a/packages/ui/commands/tests/commands.spec.ts +++ b/packages/ui/commands/tests/commands.spec.ts @@ -44,7 +44,7 @@ describe('parseCommand()', () => { }) describe('CommandService', () => { - it('lists immutable global descriptors with default surfaces and ACP input metadata', async () => { + it('lists immutable global descriptors with input metadata', async () => { const ctx = await mount() const { agent } = await mintAgentScope(ctx, 'a') const definition: CommandDefinition = { @@ -55,20 +55,17 @@ describe('CommandService', () => { } ctx.commands.register(definition) - const listed = ctx.commands.list(agent, 'acp') + const listed = ctx.commands.list(agent) expect(listed).toEqual([{ name: 'inspect', description: 'Inspect state', input: { hint: '' }, - surfaces: ['tui', 'acp'], }]) expect(Object.isFrozen(listed)).toBe(true) expect(Object.isFrozen(listed[0])).toBe(true) expect(Object.isFrozen(listed[0]?.input)).toBe(true) - expect(Object.isFrozen(listed[0]?.surfaces)).toBe(true) - expect(ctx.commands.find(agent, 'tui', 'inspect')).toMatchObject({ name: 'inspect' }) - expect(ctx.commands.find(agent, 'other', 'inspect')).toBeUndefined() - expect(ctx.commands.find(agent, 'tui', 'missing')).toBeUndefined() + expect(ctx.commands.find(agent, 'inspect')).toMatchObject({ name: 'inspect' }) + expect(ctx.commands.find(agent, 'missing')).toBeUndefined() }) it('sorts distinct effective command names', async () => { @@ -77,7 +74,7 @@ describe('CommandService', () => { ctx.commands.register(command('zeta')) ctx.commands.register(command('alpha')) ctx.commands.register(command('middle')) - expect(ctx.commands.list(agent, 'tui').map(item => item.name)).toEqual(['alpha', 'middle', 'zeta']) + expect(ctx.commands.list(agent).map(item => item.name)).toEqual(['alpha', 'middle', 'zeta']) }) it('uses agent-scoped shadows and removes them with their scope', async () => { @@ -85,17 +82,16 @@ describe('CommandService', () => { const { scope, agent } = await mintAgentScope(ctx, 'a') const other = { id: 'other' as SessionId } as Agent ctx.commands.register(command('shared', 'global')) - scope.ctx.commands.register({ ...command('shared', 'scoped'), surfaces: ['tui'] }) + scope.ctx.commands.register(command('shared', 'scoped')) - expect(ctx.commands.list(agent, 'tui').map(item => item.name)).toEqual(['shared']) - expect(ctx.commands.list(agent, 'acp')).toEqual([]) - expect(ctx.commands.find(agent, 'tui', 'shared')?.handler).toBeDefined() - expect(ctx.commands.list(other, 'acp').map(item => item.name)).toEqual(['shared']) - expect(await ctx.commands.execute(agent, 'tui', '/shared', new AbortController().signal)) + expect(ctx.commands.list(agent).map(item => item.name)).toEqual(['shared']) + expect(ctx.commands.find(agent, 'shared')?.handler).toBeDefined() + expect(ctx.commands.list(other).map(item => item.name)).toEqual(['shared']) + expect(await ctx.commands.execute(agent, '/shared', new AbortController().signal)) .toEqual({ kind: 'success', text: 'scoped' }) await scope.dispose() - expect((await ctx.commands.execute(agent, 'tui', '/shared', new AbortController().signal))?.text).toBe('global') + expect((await ctx.commands.execute(agent, '/shared', new AbortController().signal))?.text).toBe('global') }) it('rejects duplicates within one layer while allowing a scoped shadow', async () => { @@ -124,14 +120,14 @@ describe('CommandService', () => { ctx.on('commands/change', afterFailures) const removeContained = ctx.commands.register(command('contained')) const { agent } = await mintAgentScope(ctx, 'a') - expect(ctx.commands.find(agent, 'tui', 'contained')).toBeDefined() + expect(ctx.commands.find(agent, 'contained')).toBeDefined() expect(afterFailures).toHaveBeenCalledTimes(1) await vi.waitFor(() => { expect(warn).toHaveBeenCalledWith('commands/change listener threw: Error: observer threw') expect(warn).toHaveBeenCalledWith('commands/change listener rejected: Error: observer rejected') }) removeContained() - expect(ctx.commands.find(agent, 'tui', 'contained')).toBeUndefined() + expect(ctx.commands.find(agent, 'contained')).toBeUndefined() expect(afterFailures).toHaveBeenCalledTimes(2) }) @@ -155,22 +151,20 @@ describe('CommandService', () => { const ctx = await mount() const { agent } = await mintAgentScope(ctx, 'a') const seen = vi.fn(() => ({ kind: 'success' as const, text: 'ok' })) - ctx.commands.register({ name: 'run', description: 'Run it', surfaces: ['acp'], handler: seen }) + ctx.commands.register({ name: 'run', description: 'Run it', handler: seen }) const controller = new AbortController() - const result = await ctx.commands.execute(agent, 'acp', '/run untouched ', controller.signal) + const result = await ctx.commands.execute(agent, '/run untouched ', controller.signal) expect(result).toEqual({ kind: 'success', text: 'ok' }) expect(Object.isFrozen(result)).toBe(true) expect(seen).toHaveBeenCalledWith(expect.objectContaining({ agent, - surface: 'acp', rawInput: ' untouched ', signal: controller.signal, })) - await expect(ctx.commands.execute(agent, 'tui', '/run', controller.signal)).resolves.toBeUndefined() - await expect(ctx.commands.execute(agent, 'acp', 'run', controller.signal)).resolves.toBeUndefined() - await expect(ctx.commands.execute(agent, 'acp', '/missing', controller.signal)).resolves.toBeUndefined() + await expect(ctx.commands.execute(agent, 'run', controller.signal)).resolves.toBeUndefined() + await expect(ctx.commands.execute(agent, '/missing', controller.signal)).resolves.toBeUndefined() }) it('stops awaiting an aborted handler and handles an already-aborted signal', async () => { @@ -183,18 +177,18 @@ describe('CommandService', () => { handler: () => new Promise((resolve) => { release = resolve }), }) const running = new AbortController() - const promise = ctx.commands.execute(agent, 'tui', '/wait', running.signal) + const promise = ctx.commands.execute(agent, '/wait', running.signal) running.abort('operator cancelled command') await expect(promise).rejects.toThrow('operator cancelled command') release({ kind: 'success', text: 'late' }) const already = new AbortController() already.abort(new Error('already gone')) - await expect(ctx.commands.execute(agent, 'tui', '/wait', already.signal)).rejects.toThrow('already gone') + await expect(ctx.commands.execute(agent, '/wait', already.signal)).rejects.toThrow('already gone') const defaultReason = new AbortController() defaultReason.abort({ source: 'test' }) - await expect(ctx.commands.execute(agent, 'tui', '/wait', defaultReason.signal)).rejects.toThrow('command aborted') + await expect(ctx.commands.execute(agent, '/wait', defaultReason.signal)).rejects.toThrow('command aborted') }) it('propagates an asynchronously rejected handler', async () => { @@ -205,7 +199,7 @@ describe('CommandService', () => { description: 'Reject', handler: () => Promise.reject(new Error('handler rejected')), }) - await expect(ctx.commands.execute(agent, 'tui', '/reject', new AbortController().signal)) + await expect(ctx.commands.execute(agent, '/reject', new AbortController().signal)) .rejects.toThrow('handler rejected') ctx.commands.register({ @@ -214,7 +208,7 @@ describe('CommandService', () => { // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors -- exercise untyped plugin normalization handler: () => Promise.reject('not an Error'), }) - await expect(ctx.commands.execute(agent, 'tui', '/reject-value', new AbortController().signal)) + await expect(ctx.commands.execute(agent, '/reject-value', new AbortController().signal)) .rejects.toThrow('command handler rejected with a non-Error value: not an Error') const hostile = { toString(): string { throw new Error('cannot render') } } @@ -224,7 +218,7 @@ describe('CommandService', () => { // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors -- exercise hostile plugin normalization handler: () => Promise.reject(hostile), }) - await expect(ctx.commands.execute(agent, 'tui', '/reject-hostile', new AbortController().signal)) + await expect(ctx.commands.execute(agent, '/reject-hostile', new AbortController().signal)) .rejects.toMatchObject({ message: 'command handler rejected with a non-Error value: ', cause: hostile, @@ -243,7 +237,7 @@ describe('CommandService', () => { return { kind: 'success' } }, }) - await expect(ctx.commands.execute(agent, 'tui', '/self-abort', controller.signal)) + await expect(ctx.commands.execute(agent, '/self-abort', controller.signal)) .rejects.toThrow('aborted in handler') }) @@ -255,7 +249,7 @@ describe('CommandService', () => { description: 'Denied', handler: () => ({ kind: 'error', text: 'not now' }), }) - const result = await ctx.commands.execute(agent, 'tui', '/denied', new AbortController().signal) + const result = await ctx.commands.execute(agent, '/denied', new AbortController().signal) expect(result).toEqual({ kind: 'error', text: 'not now' }) expect(Object.isFrozen(result)).toBe(true) @@ -264,7 +258,7 @@ describe('CommandService', () => { description: 'No output', handler: () => ({ kind: 'success' }), }) - const silent = await ctx.commands.execute(agent, 'tui', '/silent', new AbortController().signal) + const silent = await ctx.commands.execute(agent, '/silent', new AbortController().signal) expect(silent).toEqual({ kind: 'success' }) expect(Object.isFrozen(silent)).toBe(true) }) @@ -273,9 +267,6 @@ describe('CommandService', () => { [{ ...command('Bad') }, /command name/], [{ ...command('empty-description'), description: ' ' }, /description/], [{ ...command('empty-hint'), input: { hint: '' } }, /input hint/], - [{ ...command('no-surface'), surfaces: [] }, /at least one surface/], - [{ ...command('bad-surface'), surfaces: ['ACP'] }, /surface/], - [{ ...command('duplicate-surface'), surfaces: ['tui', 'tui'] }, /duplicated/], [{ ...command('bad-handler'), handler: undefined }, /handler/], ] as const)('rejects invalid definition %#', async (definition, expected) => { const ctx = await mount() @@ -298,6 +289,6 @@ describe('CommandService', () => { description: 'Broken', handler: () => output as never, }) - await expect(ctx.commands.execute(agent, 'tui', '/broken', new AbortController().signal)).rejects.toThrow(expected) + await expect(ctx.commands.execute(agent, '/broken', new AbortController().signal)).rejects.toThrow(expected) }) }) diff --git a/packages/ui/tui/src/index.ts b/packages/ui/tui/src/index.ts index 2fe7398931..83432b91d4 100644 --- a/packages/ui/tui/src/index.ts +++ b/packages/ui/tui/src/index.ts @@ -1144,7 +1144,7 @@ export function createTuiChat( } const showHelp = (): void => { - const commandLines = ctx.commands.list(agent, 'tui').map((command) => { + const commandLines = ctx.commands.list(agent).map((command) => { const input = command.input === undefined ? '' : ` ${command.input.hint}` return `/${command.name}${input} — ${command.description}` }) @@ -1162,7 +1162,7 @@ export function createTuiChat( const refreshCommandAutocomplete = (): void => { editor.setAutocompleteProvider(new CombinedAutocompleteProvider( - ctx.commands.list(agent, 'tui').map(command => ({ + ctx.commands.list(agent).map(command => ({ name: command.name, description: command.description, })), @@ -1179,19 +1179,16 @@ export function createTuiChat( commandCtx.commands.register({ name: 'help', description: 'Show keyboard shortcuts and commands', - surfaces: ['tui'], handler: () => { showHelp(); return { kind: 'success' } }, }) commandCtx.commands.register({ name: 'clear', description: 'Clear the transcript view (session history is unchanged)', - surfaces: ['tui'], handler: () => { chat.clear(); requestRender(); return { kind: 'success' } }, }) commandCtx.commands.register({ name: 'cancel', description: 'Cancel the active turn', - surfaces: ['tui'], handler: () => { if (agent.status !== 'running') return { kind: 'error', text: 'The agent is already idle.' } agent.cancel('cancelled from terminal') @@ -1201,25 +1198,21 @@ export function createTuiChat( commandCtx.commands.register({ name: 'reasoning', description: 'Toggle reasoning blocks', - surfaces: ['tui'], handler: () => { toggleReasoning(); return { kind: 'success' } }, }) commandCtx.commands.register({ name: 'tools', description: 'Expand or collapse all tool cards', - surfaces: ['tui'], handler: () => { toggleTools(); return { kind: 'success' } }, }) commandCtx.commands.register({ name: 'redraw', description: 'Invalidate components and redraw the terminal', - surfaces: ['tui'], handler: () => { ui.invalidate(); ui.requestRender(true); return { kind: 'success' } }, }) commandCtx.commands.register({ name: 'exit', description: 'Exit after the active turn reaches idle', - surfaces: ['tui'], handler: () => { requestExit(); return { kind: 'success' } }, }) }) @@ -1227,7 +1220,7 @@ export function createTuiChat( const runCommand = (text: string): void => { const controller = new AbortController() commandControllers.add(controller) - void ctx.commands.execute(agent, 'tui', text, controller.signal).then( + void ctx.commands.execute(agent, text, controller.signal).then( (result) => { if (disposed) return if (result === undefined) { diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index be67e117cd..50280d61b9 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -442,13 +442,11 @@ describe('pi-tui chat lifecycle and transcript', () => { name: 'plugin-check', description: 'Run a plugin command', input: { hint: '' }, - surfaces: ['tui'], handler, }) result.ctx.commands.register({ name: 'plugin-fail', description: 'Fail a plugin command', - surfaces: ['tui'], handler: () => { throw new Error('plugin command exploded') }, }) @@ -459,7 +457,6 @@ describe('pi-tui chat lifecycle and transcript', () => { expect(handler).toHaveBeenCalledTimes(1) const invocation = handler.mock.calls[0]?.[0] expect(invocation?.agent).toBe(result.agent) - expect(invocation?.surface).toBe('tui') // pi-tui's Editor owns terminal-line normalization and removes trailing // spaces before onSubmit; the registry preserves the adapter-delivered line. expect(invocation?.rawInput).toBe(' value') @@ -472,10 +469,10 @@ describe('pi-tui chat lifecycle and transcript', () => { result.terminal.send('\r') await tick() expect(result.terminal.output).toContain('/plugin-check — Run a plugin command') - expect(result.ctx.commands.list(result.agent, 'tui').map(command => command.name)).toContain('help') + expect(result.ctx.commands.list(result.agent).map(command => command.name)).toContain('help') await result.controller.dispose() - expect(result.ctx.commands.list(result.agent, 'tui').map(command => command.name)).toEqual([ + expect(result.ctx.commands.list(result.agent).map(command => command.name)).toEqual([ 'plugin-check', 'plugin-fail', ]) @@ -490,7 +487,6 @@ describe('pi-tui chat lifecycle and transcript', () => { result.ctx.commands.register({ name: 'wait-plugin', description: 'Wait until disposal', - surfaces: ['tui'], handler: ({ signal }) => { commandSignal = signal started() @@ -518,7 +514,6 @@ describe('pi-tui chat lifecycle and transcript', () => { result.ctx.commands.register({ name: 'late-success', description: 'Resolve while the TUI closes', - surfaces: ['tui'], handler: () => new Promise((resolve) => { resolveCommand = resolve started() @@ -1027,7 +1022,7 @@ describe('terminal mounting', () => { expect(() => createTuiChat(ctx, { sessionId: 'failed-start-session', color: false }, { terminal, exit: vi.fn() })) .toThrow('terminal startup failed') await tick() - expect(ctx.commands.list(ctx.agents.get(SessionId('failed-start-session'))!, 'tui')).toEqual([]) + expect(ctx.commands.list(ctx.agents.get(SessionId('failed-start-session'))!)).toEqual([]) expect(terminal.stopped).toBe(1) expect(terminal.progress).toEqual([false, true, false]) await expect(ctx.userInteraction.ask({ questions: [{ id: 'late', question: 'Late?' }] })) diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 02755f19ae..83005c9bb8 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -39,7 +39,6 @@ { "doc": "docs/core-data-structures/goal.md", "symbol": "EditGoalRequest", "source": "packages/goal/goal/src/types.ts" }, { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalChanged", "source": "packages/goal/goal/src/types.ts" }, - { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandSurface", "source": "packages/ui/commands/src/index.ts" }, { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandInputDescriptor", "source": "packages/ui/commands/src/index.ts" }, { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandDefinition", "source": "packages/ui/commands/src/index.ts" }, { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandInvocation", "source": "packages/ui/commands/src/index.ts" }, diff --git a/website/zh-CN/api/harness/commands.md b/website/zh-CN/api/harness/commands.md index e59a2203da..3b92682dac 100644 --- a/website/zh-CN/api/harness/commands.md +++ b/website/zh-CN/api/harness/commands.md @@ -6,14 +6,14 @@ Human-command registry. Plain-context definitions are global; definitions registered through a command-injected child of an agent context shadow globals for that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L235) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L207) ### ctx.commands.register(definition) ```ts website-api /** * Register a global or calling-agent-scoped command. - * @param definition - discovery metadata, surface mask, and direct UI handler. + * @param definition - discovery metadata and direct UI handler. * @returns the exact effect disposer that unregisters this definition. */ register(definition: CommandDefinition): () => void @@ -21,77 +21,71 @@ register(definition: CommandDefinition): () => void Register a global or calling-agent-scoped command. -- `definition` — discovery metadata, surface mask, and direct UI handler. +- `definition` — discovery metadata and direct UI handler. **Returns** the exact effect disposer that unregisters this definition. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L248) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L220) -### ctx.commands.list(agent, surface) +### ctx.commands.list(agent) ```ts website-api /** - * List the effective immutable command descriptors for one agent and surface. + * List the effective immutable command descriptors for one agent. * @param agent - exact receiving agent and scoped-layer key. - * @param surface - UI adapter requesting discovery metadata. - * @returns name-sorted descriptors after scoped shadowing and surface filtering. + * @returns name-sorted descriptors after scoped shadowing. */ -list(agent: Agent, surface: CommandSurface): readonly CommandDescriptor[] +list(agent: Agent): readonly CommandDescriptor[] ``` -List the effective immutable command descriptors for one agent and surface. +List the effective immutable command descriptors for one agent. - `agent` — exact receiving agent and scoped-layer key. -- `surface` — UI adapter requesting discovery metadata. -**Returns** name-sorted descriptors after scoped shadowing and surface filtering. +**Returns** name-sorted descriptors after scoped shadowing. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L276) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L247) -### ctx.commands.find(agent, surface, name) +### ctx.commands.find(agent, name) ```ts website-api /** * Resolve one effective command definition. * @param agent - exact receiving agent and scoped-layer key. - * @param surface - UI adapter performing the lookup. * @param name - command name without a slash. - * @returns the scoped shadow or global definition when visible on the surface. + * @returns the scoped shadow or global definition. */ -find(agent: Agent, surface: CommandSurface, name: string): CommandDefinition | undefined +find(agent: Agent, name: string): CommandDefinition | undefined ``` Resolve one effective command definition. - `agent` — exact receiving agent and scoped-layer key. -- `surface` — UI adapter performing the lookup. - `name` — command name without a slash. -**Returns** the scoped shadow or global definition when visible on the surface. +**Returns** the scoped shadow or global definition. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L291) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L260) -### ctx.commands.execute(agent, surface, line, signal) +### ctx.commands.execute(agent, line, signal) ```ts website-api /** * Parse and execute a known command without sending it to the model. * @param agent - exact receiving agent. - * @param surface - dispatching UI adapter. * @param line - complete slash-command line. * @param signal - cancellation signal owned by the UI request. - * @returns a detached result, or `undefined` when syntax/name/surface does not resolve. + * @returns a detached result, or `undefined` when syntax or name does not resolve. */ -async execute( agent: Agent, surface: CommandSurface, line: string, signal: AbortSignal, ): Promise +async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise ``` Parse and execute a known command without sending it to the model. - `agent` — exact receiving agent. -- `surface` — dispatching UI adapter. - `line` — complete slash-command line. - `signal` — cancellation signal owned by the UI request. -**Returns** a detached result, or `undefined` when syntax/name/surface does not resolve. +**Returns** a detached result, or `undefined` when syntax or name does not resolve. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L304) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L271) diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index 18f202f773..e9266114b1 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -490,7 +490,7 @@ Ask composed answerers for one decision. Return an outcome to claim the request A command was registered or unregistered. This is an unfiltered registry notification because a global or scoped change may affect any UI view. Observer failures are contained and cannot veto the registry mutation. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L94) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L83) ## fs/* From 4e747942360e9800b3c6a2f570bdd76fde0814f0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 17:44:57 +0800 Subject: [PATCH 06/11] test(goal): isolate the ACP lifecycle snapshot --- .../goal-session/input.json | 0 .../goal-session/replay.override.json | 0 .../goal-session/session.expected.jsonl | 0 .../goal-session/session.jsonl | 0 .../goal-session/stdout.expected.jsonl | 0 examples/acp-agent/tests/goal.snapshot.ts | 4 +++- knip.json | 2 +- packages/goal/goal-session/package.json | 1 - pnpm-lock.yaml | 9 +++------ 9 files changed, 7 insertions(+), 9 deletions(-) rename examples/acp-agent/tests/{snapshots => goal-snapshots}/goal-session/input.json (100%) rename examples/acp-agent/tests/{snapshots => goal-snapshots}/goal-session/replay.override.json (100%) rename examples/acp-agent/tests/{snapshots => goal-snapshots}/goal-session/session.expected.jsonl (100%) rename examples/acp-agent/tests/{snapshots => goal-snapshots}/goal-session/session.jsonl (100%) rename examples/acp-agent/tests/{snapshots => goal-snapshots}/goal-session/stdout.expected.jsonl (100%) diff --git a/examples/acp-agent/tests/snapshots/goal-session/input.json b/examples/acp-agent/tests/goal-snapshots/goal-session/input.json similarity index 100% rename from examples/acp-agent/tests/snapshots/goal-session/input.json rename to examples/acp-agent/tests/goal-snapshots/goal-session/input.json diff --git a/examples/acp-agent/tests/snapshots/goal-session/replay.override.json b/examples/acp-agent/tests/goal-snapshots/goal-session/replay.override.json similarity index 100% rename from examples/acp-agent/tests/snapshots/goal-session/replay.override.json rename to examples/acp-agent/tests/goal-snapshots/goal-session/replay.override.json diff --git a/examples/acp-agent/tests/snapshots/goal-session/session.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl similarity index 100% rename from examples/acp-agent/tests/snapshots/goal-session/session.expected.jsonl rename to examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl diff --git a/examples/acp-agent/tests/snapshots/goal-session/session.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/session.jsonl similarity index 100% rename from examples/acp-agent/tests/snapshots/goal-session/session.jsonl rename to examples/acp-agent/tests/goal-snapshots/goal-session/session.jsonl diff --git a/examples/acp-agent/tests/snapshots/goal-session/stdout.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl similarity index 100% rename from examples/acp-agent/tests/snapshots/goal-session/stdout.expected.jsonl rename to examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl diff --git a/examples/acp-agent/tests/goal.snapshot.ts b/examples/acp-agent/tests/goal.snapshot.ts index 440eb66de6..42e3041721 100644 --- a/examples/acp-agent/tests/goal.snapshot.ts +++ b/examples/acp-agent/tests/goal.snapshot.ts @@ -14,7 +14,9 @@ import { foldGoal } from '@deepseek-ai/dsh-goal' import type { SessionEvent } from '@deepseek-ai/dsh-session' import { describe, expect, it } from 'vitest' -const scenarioDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots/goal-session') +// This lifecycle proof has goal-specific timestamp normalization and semantic +// assertions, so it owns a separate snapshot root from the generic ACP suite. +const scenarioDir = join(dirname(fileURLToPath(import.meta.url)), 'goal-snapshots/goal-session') const fixtureFile = join(scenarioDir, 'session.jsonl') const overrideFile = join(scenarioDir, 'replay.override.json') const stdoutExpected = join(scenarioDir, 'stdout.expected.jsonl') diff --git a/knip.json b/knip.json index bc531313dc..8ba86243ca 100644 --- a/knip.json +++ b/knip.json @@ -72,7 +72,7 @@ "project": ["src/**/*.ts", "tests/**/*.ts"] }, "packages/goal/goal-session": { - "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], + "entry": ["tests/**/*.spec.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, "packages/goal/tool-goal": { diff --git a/packages/goal/goal-session/package.json b/packages/goal/goal-session/package.json index c1493d017c..48a77019a3 100644 --- a/packages/goal/goal-session/package.json +++ b/packages/goal/goal-session/package.json @@ -34,7 +34,6 @@ "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-goal": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", - "@deepseek-ai/dsh-loader-smoke": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 907dd906e0..4e2acb48e7 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -511,6 +511,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-loader-smoke': + specifier: workspace:^ + version: link:../../support/loader-smoke '@deepseek-ai/dsh-scope': specifier: workspace:^ version: link:../../core/scope @@ -1006,9 +1009,6 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm - '@deepseek-ai/dsh-loader-smoke': - specifier: workspace:^ - version: link:../../support/loader-smoke '@deepseek-ai/dsh-scope': specifier: workspace:^ version: link:../../core/scope @@ -1036,9 +1036,6 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm - '@deepseek-ai/dsh-loader-smoke': - specifier: workspace:^ - version: link:../../support/loader-smoke '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session From 78560dbc917ce906ca631f56a44eafbf2c9557f5 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 17:52:21 +0800 Subject: [PATCH 07/11] test(commands): refresh ACP goal lifecycle snapshot --- .../tests/goal-snapshots/goal-session/stdout.expected.jsonl | 1 + 1 file changed, 1 insertion(+) diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl index 893629bef6..61602dc289 100644 --- a/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl +++ b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl @@ -1,5 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_create","title":"Create goal","kind":"other","status":"in_progress","rawInput":"Finish the ACP goal-session snapshot proof"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_create","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_get","title":"Read current goal","kind":"read","status":"in_progress"}}} From 015ad420af375aa17280962d15265351997ccdcf Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 18:06:22 +0800 Subject: [PATCH 08/11] fix(goal): align human commands with blocker reasons --- .../2026-07-19-human-goal-command.i18n.yaml | 4 +- .../feature/2026-07-19-human-goal-command.md | 8 ++-- .../2026-07-19-human-goal-command.zh.md | 8 ++-- ...26-07-19-model-facing-goal-tools.i18n.yaml | 4 +- .../examples/acp-demo/tests/acp-agent.spec.ts | 2 +- .../agent-spine-demo/tests/agent-core.spec.ts | 21 ++++++--- .../stdio-demo/tests/stdio-agent.spec.ts | 2 +- packages/goal/command-goal/README.md | 4 +- packages/goal/command-goal/src/index.ts | 12 ++--- .../command-goal/tests/command-goal.spec.ts | 44 +++++-------------- 10 files changed, 48 insertions(+), 61 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml index 78bb900b27..3505cfabca 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.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 -2026-07-19-human-goal-command.md: f458feae3bed8ef7b0ace6b8baaf5ae8b43e4cc8 -2026-07-19-human-goal-command.zh.md: 2fd79c2f50490e077cc69e93705a7b7bb242a082 +2026-07-19-human-goal-command.md: e2a59c3bddd7e135b0878cb59c964c3e7be64002 +2026-07-19-human-goal-command.zh.md: 0d6a0e22de091cd7a4a00ef59f1ac1b936c930f9 diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md index f458feae3b..e2a59c3bdd 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md @@ -12,7 +12,7 @@ The command must also respect the goal design's two kinds of state. Durable phas ## Decision -`@deepseek-ai/dsh-command-goal` in `packages/goal/command-goal/` is a command producer over `ctx.commands` and `ctx.goals`. It registers one global `goal` definition for the TUI and ACP surfaces. The handler receives the exact target agent from command dispatch, reads or mutates that agent's goal through the domain service, and returns direct plain-text UI output. It does not import either adapter or the concrete agent loop. +`@deepseek-ai/dsh-command-goal` in `packages/goal/command-goal/` is a command producer over `ctx.commands` and `ctx.goals`. It registers one global `goal` definition, so every command adapter in the composition discovers the same command; an incompatible app omits this producer rather than masking its registration at an adapter. The handler receives the exact target agent from command dispatch, reads or mutates that agent's goal through the domain service, and returns direct plain-text UI output. It does not import either adapter or the concrete agent loop. The command follows the compact Codex shape in the [public OpenAI Codex TUI dispatcher at commit `678157a`](https://github.com/openai/codex/blob/678157acaa819d5510adfe359abb5d0392cfe461/codex-rs/tui/src/chatwidget/slash_dispatch.rs#L750-L805): bare status, a free-form objective, and `clear`, `edit`, `pause`, or `resume` controls. The commit permalink makes the researched grammar durable even as Codex evolves. This repository keeps its own event-sourced state, round-count policy, and post-resume activation rule rather than copying Codex's SQLite, token budget, or automatic-resume behavior. @@ -30,7 +30,7 @@ Control words are ASCII-case-insensitive after outer whitespace trimming. They a ### Output and failure boundary -Status output omits branded ids and compare-and-set revisions because those are model/plugin coordination details rather than human controls. It includes activation because that fact changes whether work will continue. Command hints are derived from the exact state: an armed active goal offers pause, a disarmed active or resumable stopped goal offers resume, a budget-limited goal explains that the agent must raise `maxGoalRounds` before resume, and a completed goal offers replacement or clear. +Status output omits branded ids and compare-and-set revisions because those are model/plugin coordination details rather than human controls. It includes activation because that fact changes whether work will continue, and a blocked goal includes its durable policy code and human-readable explanation. Command hints are derived from the exact state: an armed active goal offers pause, a disarmed active or paused/blocked goal offers resume, and a completed goal offers replacement or clear. Expected `GoalError` failures become one stable, branded-id-free `CommandResult.error`, so domain diagnostics do not leak compare-and-set internals into the human surface and invalid operations never enter model history. The current status supplies the actionable state-specific recovery. Other exceptions remain adapter-visible command failures; treating programmer faults as ordinary domain errors would hide defects. The command handler performs only synchronous domain mutations, so request cancellation is decided by the command registry before the mutation begins and there is no escaped asynchronous side effect to unwind. @@ -40,11 +40,11 @@ Generic slash input, status text, and errors are not persisted. Successful goal `agent-spine-demo` accepts an optional `goals` composition object containing the goal-domain and model-tool owner configs. Omission or `false` leaves the stack unmounted. This explicit opt-in is important for headless one-shot callers: their result API settles one correlated physical turn and must not silently become a long-running logical goal operation. -The interactive app bundles make the opposite product choice. ACP defaults `goals` to the owner defaults and mounts the goal domain, model tools, same-session driver, command registry, and this producer. The terminal app enables the same goal stack by default but mounts the producer only for TUI mode; line-oriented stdio does not consume the command plane, so a typed `/goal` there remains an ordinary human prompt that the model may interpret through its separately authorized goal tools. Both apps accept `goals: false` as one coherent stack opt-out. The Python SDK runtime closure ships this producer alongside ACP, commands, and the goal stack so an external `cordis.yml` can compose the same command surface. +The interactive app bundles make the opposite product choice. ACP defaults `goals` to the owner defaults and mounts the goal domain, model tools, same-session driver, command registry, and this producer. The terminal app enables the same goal stack by default but mounts the producer only for TUI mode; line-oriented stdio does not consume the command plane, so a typed `/goal` there remains an ordinary human prompt that the model may interpret through its separately authorized goal tools. Both apps accept `goals: false` as one coherent stack opt-out. The Python SDK runtime closure ships this producer alongside ACP, commands, and the goal stack so an external `cordis.yml` can compose the same command. ## Testing -The producer suite uses the real command registry, goal service, agent registry, and session log. It covers Loader-safe exports, discovery on both surfaces, disposal, empty status, objective parsing, unfinished replacement refusal, inline edit, completed replacement, all missing-state controls, pause/resume/clear, every durable phase, armed/disarmed presentation, budget-exhaustion recovery guidance, sanitized domain errors, unexpected failures, and persisted mutation records. App composition tests cover explicit spine opt-in, TUI/ACP defaults, readline producer absence, coherent opt-out, forwarded domain/tool config, command discovery, the packaged-runtime closure, and the expanded model-tool assembly. The keyless ACP snapshots pin the resulting `/goal` discovery metadata and goal tool schemas in the shipped app composition. +The producer suite uses the real command registry, goal service, agent registry, and session log. It covers Loader-safe exports, registry discovery, disposal, empty status, objective parsing, unfinished replacement refusal, inline edit, completed replacement, all missing-state controls, pause/resume/clear, every durable phase, blocked code/explanation presentation, armed/disarmed presentation, sanitized domain errors, unexpected failures, and persisted mutation records. App composition tests cover explicit spine opt-in, TUI/ACP defaults, readline producer absence, coherent opt-out, forwarded domain/tool config, command discovery, the packaged-runtime closure, and the expanded model-tool assembly. A keyless snapshot boots the shipped ACP application, observes its advertised `/goal` metadata, invokes `/goal` directly, and pins the no-model-turn result; the surrounding ACP snapshots also pin the goal tool schemas in that composition. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md index 2fd79c2f50..0d6a0e22de 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -位于 `packages/goal/command-goal/` 的 `@deepseek-ai/dsh-command-goal` 是构建在 `ctx.commands` 与 `ctx.goals` 之上的命令生产方。它为 TUI 和 ACP 表面注册一个全局 `goal` 定义。处理器从命令分发接收准确的目标 agent（智能体），通过领域服务读取或改变该 agent 的目标，并返回直接的纯文本 UI 输出。它不导入任何适配器或具体 agent loop（智能体循环）。 +位于 `packages/goal/command-goal/` 的 `@deepseek-ai/dsh-command-goal` 是构建在 `ctx.commands` 与 `ctx.goals` 之上的命令生产方。它注册一个全局 `goal` 定义，因此组合中的每个命令适配器都会发现同一个命令；不兼容的应用应省略该生产方，而不是在适配器处屏蔽其注册。处理器从命令分发接收准确的目标 agent（智能体），通过领域服务读取或改变该 agent 的目标，并返回直接的纯文本 UI 输出。它不导入任何适配器或具体 agent loop（智能体循环）。 该命令遵循 [OpenAI Codex 公共仓库 `678157a` 提交中的 TUI 分发实现](https://github.com/openai/codex/blob/678157acaa819d5510adfe359abb5d0392cfe461/codex-rs/tui/src/chatwidget/slash_dispatch.rs#L750-L805)所呈现的紧凑形态：无参数状态查询、自由形式目标描述，以及 `clear`、`edit`、`pause` 或 `resume` 控制。固定到提交的链接使调研所得语法在 Codex 后续演进时仍可核验。本仓库保留自身的事件溯源状态、回合计数策略与恢复后激活规则，而不复制 Codex 的 SQLite、token 预算或自动恢复行为。 @@ -30,7 +30,7 @@ Status: implemented ### 输出与失败边界 -状态输出省略品牌化 id 与比较并交换修订号，因为它们属于模型/插件协调细节，而不是人类控制项。输出包含激活态，因为该事实会改变工作是否继续。命令提示从准确状态派生：已激活的活跃目标提供暂停，未激活的活跃目标或可恢复的停止目标提供恢复，受预算限制的目标说明 agent 必须先提高 `maxGoalRounds` 才能恢复，已完成目标则提供替换或清除。 +状态输出省略品牌化 id 与比较并交换修订号，因为它们属于模型/插件协调细节，而不是人类控制项。输出包含激活态，因为该事实会改变工作是否继续；被阻塞的目标还会包含其持久策略代码和面向人类的说明。命令提示从准确状态派生：已激活的活跃目标提供暂停，未激活的活跃目标或已暂停/被阻塞目标提供恢复，已完成目标则提供替换或清除。 预期的 `GoalError` 失败会变为一个稳定且不含品牌化 id 的 `CommandResult.error`，使领域诊断不会向人类表面泄露比较并交换内部细节，非法操作也绝不会进入模型历史。当前状态负责提供针对具体状态且可执行的恢复路径。其他异常仍是适配器可见的命令失败；若把程序缺陷当成普通领域错误，就会隐藏问题。命令处理器只执行同步领域变更，因此请求取消会在变更开始前由命令注册表决定，不存在需要回滚的外逸异步副作用。 @@ -40,11 +40,11 @@ Status: implemented `agent-spine-demo` 接受可选的 `goals` 组合对象，其中包含目标领域与模型工具的所有者配置。省略或设为 `false` 时不会挂载该栈。对无头单次调用方而言，明确选择加入非常重要：它们的结果 API 会在一个相关物理轮次后结束，不能静默变成长时间运行的逻辑目标操作。 -交互式应用包作出相反的产品选择。ACP 默认让 `goals` 使用所有者默认值，并挂载目标领域、模型工具、同会话驱动器、命令注册表与本生产方。终端应用默认启用相同目标栈，但只在 TUI 模式挂载本生产方；行式 stdio 不消费命令平面，因此在那里输入的 `/goal` 仍是普通人类提示词，模型可以通过独立授权的目标工具解释它。两个应用都接受 `goals: false` 作为一致的整体退出选项。Python SDK 运行时闭包把本生产方与 ACP、命令及目标栈一并交付，使外部 `cordis.yml` 能组合相同命令表面。 +交互式应用包作出相反的产品选择。ACP 默认让 `goals` 使用所有者默认值，并挂载目标领域、模型工具、同会话驱动器、命令注册表与本生产方。终端应用默认启用相同目标栈，但只在 TUI 模式挂载本生产方；行式 stdio 不消费命令平面，因此在那里输入的 `/goal` 仍是普通人类提示词，模型可以通过独立授权的目标工具解释它。两个应用都接受 `goals: false` 作为一致的整体退出选项。Python SDK 运行时闭包把本生产方与 ACP、命令及目标栈一并交付，使外部 `cordis.yml` 能组合相同命令。 ## 测试 -生产方测试套件使用真实命令注册表、目标服务、agent 注册表与会话日志。它覆盖 Loader 安全导出、两个表面的发现、资源释放、空状态、目标描述解析、拒绝未完成目标替换、行内编辑、已完成目标替换、所有缺失状态控制、暂停/恢复/清除、每个持久阶段、已激活/未激活展示、预算耗尽恢复提示、经净化的领域错误、意外失败与持久变更记录。应用组合测试覆盖显式主干选择加入、TUI/ACP 默认值、readline 不挂载生产方、一致退出、转发的领域/工具配置、命令发现、打包运行时闭包与扩展后的模型工具组装。无密钥 ACP 快照固定了交付应用组合中的 `/goal` 发现元数据和目标工具 schema。 +生产方测试套件使用真实命令注册表、目标服务、agent 注册表与会话日志。它覆盖 Loader 安全导出、注册表发现、资源释放、空状态、目标描述解析、拒绝未完成目标替换、行内编辑、已完成目标替换、所有缺失状态控制、暂停/恢复/清除、每个持久阶段、阻塞代码/说明展示、已激活/未激活展示、经净化的领域错误、意外失败与持久变更记录。应用组合测试覆盖显式主干选择加入、TUI/ACP 默认值、readline 不挂载生产方、一致退出、转发的领域/工具配置、命令发现、打包运行时闭包与扩展后的模型工具组装。一个无密钥快照会启动交付的 ACP 应用，观察其公布的 `/goal` 元数据，直接调用 `/goal`，并固定不经过模型轮次的结果；周边 ACP 快照还会固定该组合中的目标工具 schema。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml index fd97351a0e..e53c591aa5 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.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 -2026-07-19-model-facing-goal-tools.md: 2ef77b53cd8b95c9cdffd12e20c723fb1cff3a5d -2026-07-19-model-facing-goal-tools.zh.md: 08619600355c71ccd30d608e3c4e5a7fba753d4e +2026-07-19-model-facing-goal-tools.md: 7cc3907d708115207e166455ea988120a03d768b +2026-07-19-model-facing-goal-tools.zh.md: 1a381160354d6a2a24f957f41bc9e375c1ab01ca diff --git a/packages/examples/acp-demo/tests/acp-agent.spec.ts b/packages/examples/acp-demo/tests/acp-agent.spec.ts index a9a1d6178d..b6886a7e12 100644 --- a/packages/examples/acp-demo/tests/acp-agent.spec.ts +++ b/packages/examples/acp-demo/tests/acp-agent.spec.ts @@ -96,7 +96,7 @@ describe('dsh-acp-demo composition', () => { sessionId: 'disabled-goals' as import('@deepseek-ai/dsh-session').SessionId, agentOptions: { provider: 'mock', model: 'mock' }, }) - expect(ctx.commands.find(handle.agent, 'acp', 'goal')).toBeUndefined() + expect(ctx.commands.find(handle.agent, 'goal')).toBeUndefined() await handle.dispose() await ctx.fiber.dispose() }) diff --git a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts index acb93f758b..6c8837652d 100644 --- a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts +++ b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts @@ -121,14 +121,16 @@ describe('dsh-agent-spine-demo bundle', () => { it('opts into the configured persisted-goal domain, tools, and same-session driver', async () => { const ctx = await mount({ workspaceContext: false, + agents: [{ id: SessionId('configured-goal'), provider: 'mock', model: 'mock' }], goals: { domain: { defaultMaxGoalRounds: 17 }, tool: { blockedAfterConsecutiveRounds: 5 }, }, }) - expect(ctx.goals.resolveCreate({ objective: 'configured' })).toEqual({ - objective: 'configured', - maxGoalRounds: 17, + const agent = ctx.agents.list()[0] + if (agent === undefined) throw new Error('configured goal test has no live agent') + expect(ctx.goals.create(agent, { objective: 'configured' })).toMatchObject({ + objective: 'configured', maxGoalRounds: 17, }) expect(['create_goal', 'get_goal', 'update_goal'].map(name => ctx.tools.get(name)?.name)) .toEqual(['create_goal', 'get_goal', 'update_goal']) @@ -199,11 +201,16 @@ describe('dsh-agent-spine-demo bundle', () => { it('uses owner defaults for a schema-bypassing empty goal opt-in', async () => { const ctx = new Context() - agentCore.apply(ctx, { workspaceContext: false, goals: {} }) + agentCore.apply(ctx, { + workspaceContext: false, + agents: [{ id: SessionId('defaulted-goal'), provider: 'mock', model: 'mock' }], + goals: {}, + }) await new Promise(resolve => setTimeout(resolve, 50)) - expect(ctx.goals.resolveCreate({ objective: 'defaulted' })).toEqual({ - objective: 'defaulted', - maxGoalRounds: 256, + const agent = ctx.agents.list()[0] + if (agent === undefined) throw new Error('default goal test has no live agent') + expect(ctx.goals.create(agent, { objective: 'defaulted' })).toMatchObject({ + objective: 'defaulted', maxGoalRounds: 256, }) expect(ctx.tools.get('get_goal')).toBeDefined() await ctx.fiber.dispose() diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index 2480cb704d..de8481da4f 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts @@ -153,7 +153,7 @@ describe('dsh-stdio-demo app', () => { expect(agent?.id).toBe(agent?.session.id) expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) - expect(ctx.commands.find(agent!, 'tui', 'goal')).toBeUndefined() + expect(ctx.commands.find(agent!, 'goal')).toBeUndefined() await ctx.fiber.dispose() }) diff --git a/packages/goal/command-goal/README.md b/packages/goal/command-goal/README.md index 2fa7323789..f766cd3ece 100644 --- a/packages/goal/command-goal/README.md +++ b/packages/goal/command-goal/README.md @@ -1,12 +1,12 @@ # @deepseek-ai/dsh-command-goal -Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md); TUI and ACP discover and execute it without a model turn. The [human goal-command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions. +Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers it; the shipped TUI and ACP execute it without a model turn. The [human goal-command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions. ## Command contract | Input | Result | |---|---| -| `/goal` | Show the current objective, durable phase, round count/cap, process-local activation, and valid next commands; show usage when no goal exists. | +| `/goal` | Show the current objective, durable phase, round count/cap, process-local activation, and valid next commands; a blocked goal also shows its policy code and explanation, while no goal shows usage. | | `/goal ` | Create and arm a goal, or replace a completed goal with a fresh identity. An unfinished goal is never replaced without an explicit clear. | | `/goal edit ` | Edit the current objective without changing its phase or activation. Editing a completed goal creates a fresh active goal. | | `/goal pause` | Pause an active goal and disarm continuation. | diff --git a/packages/goal/command-goal/src/index.ts b/packages/goal/command-goal/src/index.ts index a8e73cba7e..93ed7923b8 100644 --- a/packages/goal/command-goal/src/index.ts +++ b/packages/goal/command-goal/src/index.ts @@ -48,8 +48,6 @@ function phaseLabel(phase: GoalPhase): string { case 'active': return 'active' case 'paused': return 'paused' case 'blocked': return 'blocked' - case 'usage-limited': return 'usage limited' - case 'budget-limited': return 'limited by round budget' case 'complete': return 'complete' /* v8 ignore next 2 -- GoalPhase is closed and every member is handled above */ default: return assertNever(phase, 'goal phase') @@ -66,10 +64,7 @@ function commandHint(goal: GoalView): string { switch (goal.phase) { case 'paused': case 'blocked': - case 'usage-limited': return '/goal edit , /goal resume, /goal clear' - case 'budget-limited': - return '/goal edit , /goal clear; after the agent raises the round cap, /goal resume' case 'complete': return '/goal , /goal clear' /* v8 ignore next 2 -- the active branch and every non-active phase are handled above */ @@ -79,11 +74,16 @@ function commandHint(goal: GoalView): string { /** Render direct UI output without exposing compare-and-set internals. */ function renderGoal(title: string, goal: GoalView): CommandResult { + const reason = goal.phase === 'blocked' ? goal.blockedReason : undefined + /* v8 ignore next -- durable replay guarantees every blocked goal carries its validated reason */ + if (goal.phase === 'blocked' && reason === undefined) throw new TypeError('blocked goal is missing its reason') + const blocker = reason === undefined ? [] : [`Blocker: ${reason.code}: ${reason.message}`] return { kind: 'success', text: [ title, `Status: ${phaseLabel(goal.phase)}`, + ...blocker, `Objective: ${goal.objective}`, `Rounds: ${goal.roundsStarted}/${goal.maxGoalRounds}`, `Activation: ${goal.activation}`, @@ -159,7 +159,7 @@ function executeGoalCommand(ctx: Context, invocation: CommandInvocation): Comman } } -/** Register the Codex-shaped `/goal` human command on TUI and ACP surfaces. */ +/** Register the Codex-shaped `/goal` command for every composed command adapter. */ export function apply(ctx: Context): void { ctx.commands.register({ name: 'goal', diff --git a/packages/goal/command-goal/tests/command-goal.spec.ts b/packages/goal/command-goal/tests/command-goal.spec.ts index a3d48857c4..71b1c59052 100644 --- a/packages/goal/command-goal/tests/command-goal.spec.ts +++ b/packages/goal/command-goal/tests/command-goal.spec.ts @@ -74,7 +74,6 @@ async function harness(): Promise { async function run(test: Harness, suffix = ''): Promise>>> { const result = await test.ctx.commands.execute( test.agent, - 'tui', `/goal${suffix}`, new AbortController().signal, ) @@ -87,20 +86,8 @@ function ref(goal: NonNullable>): GoalRef { return { id: goal.id, revision: goal.revision } } -/** Append one admitted goal round for budget-limited presentation coverage. */ -function appendRound(test: Harness, goal: NonNullable>): void { - const source = { kind: 'goal', goalId: goal.id, revision: goal.revision, round: 1 } as const - const turn = nextTurn(test.session) - test.session.append('turn/start', { turn, trigger: { kind: 'message', source } }) - test.session.append('user/message', { - content: [{ type: 'text', text: 'goal round' }], - source, - }, { surfaceOp: 'append' }) - test.session.append('turn/end', { turn, reason: { kind: 'completed' } }) -} - describe('@deepseek-ai/dsh-command-goal registration', () => { - it('registers one global TUI/ACP command with Loader-safe exports and disposes it', async () => { + it('registers one global command with Loader-safe exports and disposes it', async () => { const test = await harness() expect(commandGoal.name).toBe('command-goal') expect(commandGoal.inject).toEqual(['commands', 'goals']) @@ -108,16 +95,15 @@ describe('@deepseek-ai/dsh-command-goal registration', () => { const loader = Object.create(Loader.prototype) as Loader expect(loader.unwrapExports(commandGoal)).toBe(commandGoal) - expect(test.ctx.commands.list(test.agent, 'tui')).toContainEqual({ + expect(test.ctx.commands.list(test.agent)).toContainEqual({ name: 'goal', description: 'set or view the goal for a long-running task', input: { hint: '[|clear|edit |pause|resume]' }, - surfaces: ['tui', 'acp'], }) - expect(test.ctx.commands.find(test.agent, 'acp', 'goal')).toBeDefined() + expect(test.ctx.commands.find(test.agent, 'goal')).toBeDefined() await test.plugin.dispose() - expect(test.ctx.commands.find(test.agent, 'tui', 'goal')).toBeUndefined() + expect(test.ctx.commands.find(test.agent, 'goal')).toBeUndefined() }) }) @@ -227,22 +213,16 @@ describe('/goal human command', () => { expect((await run(test)).text).toContain('Status: paused') goal = test.ctx.goals.resume(test.agent, ref(goal)) - goal = test.ctx.goals.block(test.agent, ref(goal)) - expect((await run(test)).text).toContain('Status: blocked') + goal = test.ctx.goals.block(test.agent, ref(goal), { + code: 'upstream-unavailable', + message: 'Provider unavailable', + }) + const blocked = await run(test) + expect(blocked.text).toContain('Status: blocked') + expect(blocked.text).toContain('Blocker: upstream-unavailable: Provider unavailable') goal = test.ctx.goals.resume(test.agent, ref(goal)) - goal = test.ctx.goals.markUsageLimited(test.agent, ref(goal)) - expect((await run(test)).text).toContain('Status: usage limited') - - goal = test.ctx.goals.resume(test.agent, ref(goal)) - appendRound(test, goal) - goal = test.ctx.goals.get(test.agent)! - goal = test.ctx.goals.markBudgetLimited(test.agent, ref(goal)) - const limited = await run(test) - expect(limited.text).toContain('Status: limited by round budget') - expect(limited.text).toContain('after the agent raises the round cap, /goal resume') - - goal = test.ctx.goals.complete(test.agent, ref(goal)) + test.ctx.goals.complete(test.agent, ref(goal)) const complete = await run(test) expect(complete.text).toContain('Status: complete') expect(complete.text).toContain('Commands: /goal , /goal clear') From 283c78eec88c3d1e3720c9f2c19dd5de04bf5549 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 18:06:34 +0800 Subject: [PATCH 09/11] test(goal): refresh shipped ACP goal snapshots --- examples/acp-agent/goal.cordis.snapshot.yml | 19 ------------------- examples/acp-agent/goal.cordis.yml | 13 ------------- .../goal-session/stdout.expected.jsonl | 2 +- examples/acp-agent/tests/goal.snapshot.ts | 2 +- .../system-prompt.expected.md | 8 +++++--- .../tool-schemas.expected.json | 8 ++++++-- .../both-mode-turn/system-prompt.expected.md | 8 +++++--- .../both-mode-turn/tool-schemas.expected.json | 8 ++++++-- .../code-mode-turn/system-prompt.expected.md | 8 +++++--- .../system-prompt.expected.md | 8 +++++--- .../model-switching/system-prompt.expected.md | 4 ++-- .../tool-schemas.expected.json | 16 ++++++++++++---- .../system-prompt.expected.md | 4 ++-- .../tool-schemas.expected.json | 16 ++++++++++++---- .../skill-load/system-prompt.expected.md | 2 +- .../skill-load/tool-schemas.expected.json | 8 ++++++-- .../text-turn/system-prompt.expected.md | 2 +- .../text-turn/tool-schemas.expected.json | 8 ++++++-- .../system-prompt.expected.md | 2 +- .../tool-schemas.expected.json | 8 ++++++-- .../workspace-edit/system-prompt.expected.md | 2 +- .../workspace-edit/tool-schemas.expected.json | 8 ++++++-- 22 files changed, 90 insertions(+), 74 deletions(-) delete mode 100644 examples/acp-agent/goal.cordis.snapshot.yml delete mode 100644 examples/acp-agent/goal.cordis.yml diff --git a/examples/acp-agent/goal.cordis.snapshot.yml b/examples/acp-agent/goal.cordis.snapshot.yml deleted file mode 100644 index 89e1078117..0000000000 --- a/examples/acp-agent/goal.cordis.snapshot.yml +++ /dev/null @@ -1,19 +0,0 @@ -# Replay counterpart to goal.cordis.yml; only the live model is replaced. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./goal.cordis.yml - patches: - - id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - disabled: true - - insert: - - id: llm-replay - name: '@deepseek-ai/dsh-llm-replay' - config: - providers: - - id: deepseek - name: DeepSeek - models: - - id: deepseek-v4-flash - - id: deepseek-v4-pro diff --git a/examples/acp-agent/goal.cordis.yml b/examples/acp-agent/goal.cordis.yml deleted file mode 100644 index d077104bb8..0000000000 --- a/examples/acp-agent/goal.cordis.yml +++ /dev/null @@ -1,13 +0,0 @@ -# Add the persisted same-session goal stack to the shipped ACP app. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - - insert: - - id: goal - name: '@deepseek-ai/dsh-goal' - - id: tool-goal - name: '@deepseek-ai/dsh-tool-goal' - - id: goal-session - name: '@deepseek-ai/dsh-goal-session' diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl index 61602dc289..40f60aa7fa 100644 --- a/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl +++ b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_create","title":"Create goal","kind":"other","status":"in_progress","rawInput":"Finish the ACP goal-session snapshot proof"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_create","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_get","title":"Read current goal","kind":"read","status":"in_progress"}}} diff --git a/examples/acp-agent/tests/goal.snapshot.ts b/examples/acp-agent/tests/goal.snapshot.ts index 42e3041721..4bb01acd16 100644 --- a/examples/acp-agent/tests/goal.snapshot.ts +++ b/examples/acp-agent/tests/goal.snapshot.ts @@ -25,7 +25,7 @@ const refreshing = process.env.DSH_SNAPSHOT === 'refresh' const agent: AgentUnderTest = { binScript: fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url)), - configPath: fileURLToPath(new URL('../goal.cordis.yml', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md index e130790bdf..acdebe8036 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -70,7 +70,7 @@ declare const tools: { /** Optional positive safe-integer limit on automatic continuation rounds. */ max_goal_rounds?: number; }): Promise; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */ + /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { @@ -123,7 +123,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal(args: { /** Exact id returned by get_goal. */ goal_id: string; @@ -135,6 +135,8 @@ declare const tools: { objective?: string; /** Replacement cap; valid only with action edit. */ max_goal_rounds?: number; + /** Concrete blocking condition; required only with action blocked. */ + blocked_reason?: string; }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json index 55c1398f81..3a4f7ab7d8 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json @@ -124,7 +124,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -304,7 +304,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -334,6 +334,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md index 70de361b1d..271ac5e557 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -53,7 +53,7 @@ declare const tools: { /** Optional positive safe-integer limit on automatic continuation rounds. */ max_goal_rounds?: number; }): Promise; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */ + /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { @@ -106,7 +106,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal(args: { /** Exact id returned by get_goal. */ goal_id: string; @@ -118,6 +118,8 @@ declare const tools: { objective?: string; /** Replacement cap; valid only with action edit. */ max_goal_rounds?: number; + /** Concrete blocking condition; required only with action blocked. */ + blocked_reason?: string; }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json index 50d08b7946..e8a4d432ff 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -247,7 +247,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -277,6 +277,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md index 70de361b1d..271ac5e557 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -53,7 +53,7 @@ declare const tools: { /** Optional positive safe-integer limit on automatic continuation rounds. */ max_goal_rounds?: number; }): Promise; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */ + /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { @@ -106,7 +106,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal(args: { /** Exact id returned by get_goal. */ goal_id: string; @@ -118,6 +118,8 @@ declare const tools: { objective?: string; /** Replacement cap; valid only with action edit. */ max_goal_rounds?: number; + /** Concrete blocking condition; required only with action blocked. */ + blocked_reason?: string; }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md index c3fefc8b86..7b64ad8b0d 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md @@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -70,7 +70,7 @@ declare const tools: { /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ replace_all?: boolean; }): Promise; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */ + /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ get_goal(args: Record): Promise; /** Read a UTF-8 text file and return line-numbered content. */ read(args: { @@ -132,7 +132,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal(args: { /** Exact id returned by get_goal. */ goal_id: string; @@ -144,6 +144,8 @@ declare const tools: { objective?: string; /** Replacement cap; valid only with action edit. */ max_goal_rounds?: number; + /** Concrete blocking condition; required only with action blocked. */ + blocked_reason?: string; }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { diff --git a/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md index f81876701a..abcd608b39 100644 --- a/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -29,7 +29,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json index 113459eb86..a4c5307864 100644 --- a/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -231,7 +231,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -261,6 +261,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ @@ -411,7 +415,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -575,7 +579,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -605,6 +609,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md index 82335a7f1e..04d1fbe817 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. @@ -28,7 +28,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json index 113459eb86..a4c5307864 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -231,7 +231,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -261,6 +261,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ @@ -411,7 +415,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -575,7 +579,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -605,6 +609,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md index 87818d5b6d..4cd64a91f8 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json index 0d8966ec14..21542887b1 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -231,7 +231,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -261,6 +261,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md index 87818d5b6d..4cd64a91f8 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json index 0d8966ec14..21542887b1 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -231,7 +231,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -261,6 +261,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md index 6f49fcf1c2..dd965e4933 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md @@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json index ab8c4a3d20..322ac0eb8d 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json @@ -97,7 +97,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -285,7 +285,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -315,6 +315,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md index 4af39f6b4b..5879f004af 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md @@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json index ab8c4a3d20..322ac0eb8d 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json @@ -97,7 +97,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -285,7 +285,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -315,6 +315,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ From 9f6f87cf694c7915b58f9f353a289fe514fc2fd8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 18:18:08 +0800 Subject: [PATCH 10/11] test(ralph): snapshot fresh-agent rounds in headless app --- ...-fresh-agent-ralph-workflow-tool.i18n.yaml | 4 +- ...6-07-19-fresh-agent-ralph-workflow-tool.md | 2 +- ...7-19-fresh-agent-ralph-workflow-tool.zh.md | 2 +- .../headless-agent/ralph.cordis.snapshot.yml | 12 +++ .../headless-agent/tests/headless.snapshot.ts | 75 +++++++++++++++++++ .../tests/snapshots/ralph-loop/input.json | 8 ++ .../snapshots/ralph-loop/replay.override.json | 22 ++++++ .../snapshots/ralph-loop/session.1.jsonl | 6 ++ .../snapshots/ralph-loop/session.2.jsonl | 6 ++ .../tests/snapshots/ralph-loop/session.jsonl | 1 + .../ralph-loop/stream-json.expected.jsonl | 23 ++++++ 11 files changed, 157 insertions(+), 4 deletions(-) create mode 100644 examples/headless-agent/ralph.cordis.snapshot.yml create mode 100644 examples/headless-agent/tests/snapshots/ralph-loop/input.json create mode 100644 examples/headless-agent/tests/snapshots/ralph-loop/replay.override.json create mode 100644 examples/headless-agent/tests/snapshots/ralph-loop/session.1.jsonl create mode 100644 examples/headless-agent/tests/snapshots/ralph-loop/session.2.jsonl create mode 100644 examples/headless-agent/tests/snapshots/ralph-loop/session.jsonl create mode 100644 examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl diff --git a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.i18n.yaml index f0453085c5..9ef2bae475 100644 --- a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.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 -2026-07-19-fresh-agent-ralph-workflow-tool.md: 159ad7e39602d8b84ffafdb396ad1083f9c73009 -2026-07-19-fresh-agent-ralph-workflow-tool.zh.md: bb6025952ada35526459101d53b3ea1fea622163 +2026-07-19-fresh-agent-ralph-workflow-tool.md: 46816b8cc06f0acf5615ffb44035c79ea13b6794 +2026-07-19-fresh-agent-ralph-workflow-tool.zh.md: 188a0bf50a7a6a683cd6aa1004c4d78673d3631d diff --git a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md index 159ad7e396..46816b8cc0 100644 --- a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md +++ b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md @@ -46,7 +46,7 @@ ACP and terminal presentation use a generic `ralph` card whose raw input is the Unit tests cover config and call-cap resolution, provider capability rejection, fixed start-request routing and child ceiling, all successful terminal outcomes, ordinary child-failure envelopes, malformed and oversized boundary values, exact successful-result truncation, abort timing, disposal, render intent, prompt lifecycle, and namespace-plugin shape at per-file 100% coverage. Worker-engine tests prove synchronous provider-route validation, per-run child ceilings below the deployment ceiling, and that a provider override selects every child without changing the configured default, including the built `lib/worker.cjs` under plain Node. -A keyless real-stack integration drives the fixed script through the actual worker-thread engine, spawn provider, structured-output runtime, and agent loop. It proves distinct child identities, absent `seedLength`, inherited cwd, no parent-history markers in either child request, exact previous-report handoff only in the following round, one phase event, terminal completion, and disposal of both children. The same real stack covers blocker and round-limit outcomes, unnormalized and semantically invalid reports, oversized handoffs, ordinary child failure with the last good handoff, and cancellation to child quiescence. Tool tests pin generic call/result presentation, while ACP replay header snapshots pin the shipped schema and prompt-guidance transcript surface. +A keyless real-stack integration drives the fixed script through the actual worker-thread engine, spawn provider, structured-output runtime, and agent loop. It proves distinct child identities, absent `seedLength`, inherited cwd, no parent-history markers in either child request, exact previous-report handoff only in the following round, one phase event, terminal completion, and disposal of both children. The same real stack covers blocker and round-limit outcomes, unnormalized and semantically invalid reports, oversized handoffs, ordinary child failure with the last good handoff, and cancellation to child quiescence. A shipped keyless headless snapshot additionally boots the real `examples/headless-agent` composition, invokes `ralph`, pins the parent stream transcript, and inspects persisted logs for two distinct unseeded child sessions and the round-one handoff appearing only in round two. Tool tests pin generic call/result presentation, while ACP replay header snapshots pin the shipped schema and prompt-guidance transcript surface. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md index bb6025952a..188a0bf50a 100644 --- a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md @@ -46,7 +46,7 @@ ACP 和终端展示使用通用 `ralph` 卡片，并把目标作为原始输入 单元测试覆盖配置与调用上限解析、provider 能力拒绝、固定启动请求路由与子 agent 上限、全部成功终止结果、普通子 agent 失败外层值、畸形及过大边界值、成功结果精确截断、中止时序、处置、渲染意图、提示生命周期和命名空间插件形状，并达到逐文件 100% 覆盖率。工作流引擎测试证明 provider 路由会同步验证、每次运行的子 agent 上限可低于部署上限，并且 provider 覆盖会选择每个子 agent 且不改变配置默认值，其中包括普通 Node 下构建后的 `lib/worker.cjs`。 -一项无密钥真实栈集成测试通过实际工作线程引擎、spawn provider、结构化输出运行时和 agent loop 驱动固定脚本。它证明子 agent 标识不同、没有 `seedLength`、继承 cwd、两个子请求都不含父历史标记、上一份报告只精确出现在下一轮交接中、只产生一个阶段事件、终止完成以及两个子 agent 都被处置。同一真实栈还覆盖阻塞与轮次上限结果、未规范化及语义无效报告、过大交接、保留上一份有效交接的普通子 agent 失败，以及取消后达到子 agent 静止状态。工具测试固定通用调用/结果展示，而 ACP 重放请求头快照固定发布的 schema 与提示指导转录表面。 +一项无密钥真实栈集成测试通过实际工作线程引擎、spawn provider、结构化输出运行时和 agent loop 驱动固定脚本。它证明子 agent 标识不同、没有 `seedLength`、继承 cwd、两个子请求都不含父历史标记、上一份报告只精确出现在下一轮交接中、只产生一个阶段事件、终止完成以及两个子 agent 都被处置。同一真实栈还覆盖阻塞与轮次上限结果、未规范化及语义无效报告、过大交接、保留上一份有效交接的普通子 agent 失败，以及取消后达到子 agent 静止状态。一项已发布的无密钥无头快照还会启动真实的 `examples/headless-agent` 组合、调用 `ralph`、固定父级流式转录，并检查持久化日志中存在两个不同且无种子的子会话，且第一轮交接只出现在第二轮。工具测试固定通用调用/结果展示，而 ACP 重放请求头快照固定发布的 schema 与提示指导转录表面。 ## 考虑过的替代方案 diff --git a/examples/headless-agent/ralph.cordis.snapshot.yml b/examples/headless-agent/ralph.cordis.snapshot.yml new file mode 100644 index 0000000000..e84bdfed31 --- /dev/null +++ b/examples/headless-agent/ralph.cordis.snapshot.yml @@ -0,0 +1,12 @@ +# Replay counterpart to cordis.yml for the shipped Ralph-loop snapshot. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - insert: + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/headless-agent/tests/headless.snapshot.ts b/examples/headless-agent/tests/headless.snapshot.ts index d799c6250d..d8a36aab59 100644 --- a/examples/headless-agent/tests/headless.snapshot.ts +++ b/examples/headless-agent/tests/headless.snapshot.ts @@ -17,6 +17,8 @@ const advancedStreamExpected = join(advancedScenarioDir, 'stream-json.expected.j const advancedConfigPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url)) const goalScenarioDir = join(snapshotsDir, 'goal-tools') const goalConfigPath = fileURLToPath(new URL('../goal.cordis.snapshot.yml', import.meta.url)) +const ralphScenarioDir = join(snapshotsDir, 'ralph-loop') +const ralphConfigPath = fileURLToPath(new URL('../ralph.cordis.snapshot.yml', import.meta.url)) const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) const refreshing = process.env.DSH_SNAPSHOT === 'refresh' @@ -216,4 +218,77 @@ describe('headless stream-json snapshots', () => { if (refreshing) await writeFile(streamExpected, normalized) expect(normalized).toBe(await readFile(streamExpected, 'utf8')) }, LOADER_SMOKE_TEST_TIMEOUT_MS) + + it('replays two fresh Ralph rounds through the one-shot app', async () => { + const prompt = await scenarioPrompt(ralphScenarioDir, 'ralph-loop') + const streamExpected = join(ralphScenarioDir, 'stream-json.expected.jsonl') + let runCwd = '' + const result = await runLoaderSmoke({ + label: 'Ralph loop headless stream-json snapshot', + tempDirPrefix: 'headless-snapshot-ralph-loop-', + binScript, + configPath: ralphConfigPath, + binArgs: ['--config', ralphConfigPath, '--output-format', 'stream-json', prompt], + tsconfigPath, + env: { + DSH_SNAPSHOT: 'replay', + DSH_SNAPSHOT_FILE: join(ralphScenarioDir, 'session.jsonl'), + DSH_SNAPSHOT_OVERRIDE: join(ralphScenarioDir, 'replay.override.json'), + DSH_SNAPSHOT_CHILD_FILES: [ + join(ralphScenarioDir, 'session.1.jsonl'), + join(ralphScenarioDir, 'session.2.jsonl'), + ].join(delimiter), + NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '), + }, + prepare: (cwd) => { runCwd = cwd }, + inspect: async (cwd) => { + const logs = await persistedLogs(cwd) + expect(logs).toHaveLength(3) + const parent = logs.find(log => typeof log.header.parentSession !== 'string') + if (parent === undefined) throw new Error('Ralph snapshot did not persist its parent session') + const parentId = parent.header.id + expect(typeof parentId).toBe('string') + const children = logs.filter(log => typeof log.header.parentSession === 'string') + .sort((left, right) => Number(left.header.createdAt) - Number(right.header.createdAt)) + expect(children).toHaveLength(2) + expect(children.map(child => child.header.parentSession)).toEqual([parentId, parentId]) + expect(children.map(child => child.header.cwd)).toEqual([parent.header.cwd, parent.header.cwd]) + expect(children.map(child => child.header.seedLength)).toEqual([undefined, undefined]) + expect(new Set(children.map(child => child.header.id)).size).toBe(2) + + const parentRecords = parseJsonl(parent.content) + const parentCalls = parentRecords.filter(record => record.type === 'tool/call') + expect(parentCalls.map(record => (record.data as JsonObject | undefined)?.name)).toEqual(['ralph']) + const parentResult = parentRecords.find(record => record.type === 'tool/result') + const parentResultData = parentResult?.data as JsonObject | undefined + expect(parentResultData?.isError).toBe(false) + expect(JSON.stringify(parentResultData?.content)).toContain('reported completion after 2 rounds') + + const childRecords = children.map(child => parseJsonl(child.content)) + const childPrompts = childRecords.map((records) => { + const message = records.find(record => record.type === 'user/message') + return JSON.stringify((message?.data as JsonObject | undefined)?.content) + }) + expect(childPrompts[0]).toContain('Ralph round: 1 of 2.') + expect(childPrompts[0]).toContain('(none — this is the first round)') + expect(childPrompts[0]).not.toContain('ROUND_ONE_HANDOFF') + expect(childPrompts[1]).toContain('Ralph round: 2 of 2.') + expect(childPrompts[1]).toContain('ROUND_ONE_HANDOFF') + for (const childPrompt of childPrompts) { + expect(childPrompt).toContain('Prove two fresh Ralph rounds through the shipped headless app.') + expect(childPrompt).not.toContain('Run a two-round fresh-agent Ralph loop') + } + for (const records of childRecords) { + const calls = records.filter(record => record.type === 'tool/call') + expect(calls.map(record => (record.data as JsonObject | undefined)?.name)) + .toEqual(['structured_output']) + } + }, + }) + + expect(result.stderr).toBe('') + const normalized = normalizeHeadlessStream(result.stdout, runCwd) + if (refreshing) await writeFile(streamExpected, normalized) + expect(normalized).toBe(await readFile(streamExpected, 'utf8')) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) }) diff --git a/examples/headless-agent/tests/snapshots/ralph-loop/input.json b/examples/headless-agent/tests/snapshots/ralph-loop/input.json new file mode 100644 index 0000000000..42652a4ac5 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/ralph-loop/input.json @@ -0,0 +1,8 @@ +{ + "steps": [ + { + "op": "prompt", + "text": "Run a two-round fresh-agent Ralph loop to prove the shipped headless integration." + } + ] +} diff --git a/examples/headless-agent/tests/snapshots/ralph-loop/replay.override.json b/examples/headless-agent/tests/snapshots/ralph-loop/replay.override.json new file mode 100644 index 0000000000..1d7846f76b --- /dev/null +++ b/examples/headless-agent/tests/snapshots/ralph-loop/replay.override.json @@ -0,0 +1,22 @@ +[ + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "tool-call" }, + { "type": "tool-call-delta", "index": 0, "id": "call_ralph", "name": "ralph", "argumentsDelta": "{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}" }, + { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_ralph", "name": "ralph", "arguments": "{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}" } }, + { "type": "usage", "usage": { "inputTokens": 20, "outputTokens": 8 } }, + { "type": "finish", "reason": { "kind": "tool-calls" } } + ] + }, + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "text" }, + { "type": "text-delta", "index": 0, "text": "RALPH SNAPSHOT COMPLETE" }, + { "type": "block-end", "index": 0, "block": { "type": "text", "text": "RALPH SNAPSHOT COMPLETE" } }, + { "type": "usage", "usage": { "inputTokens": 30, "outputTokens": 4 } }, + { "type": "finish", "reason": { "kind": "stop" } } + ] + } +] diff --git a/examples/headless-agent/tests/snapshots/ralph-loop/session.1.jsonl b/examples/headless-agent/tests/snapshots/ralph-loop/session.1.jsonl new file mode 100644 index 0000000000..ca36330c36 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/ralph-loop/session.1.jsonl @@ -0,0 +1,6 @@ +{"type":"session","version":0,"id":"42222222-2222-4222-8222-222222222222","createdAt":1783951001000,"cwd":"/tmp/ralph-headless","parentSession":"41111111-1111-4111-8111-111111111111"} +{"type":"assistant/chunk","seq":0,"time":1783951001001,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":1,"time":1783951001002,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"round-one-report","name":"structured_output","argumentsDelta":"{\"status\":\"continue\",\"summary\":\"ROUND_ONE_HANDOFF\",\"evidence\":[\"Round one inspected the workspace.\"],\"nextSteps\":[\"Finish the snapshot objective.\"],\"blocker\":\"\"}"}}} +{"type":"assistant/chunk","seq":2,"time":1783951001003,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"round-one-report","name":"structured_output","arguments":"{\"status\":\"continue\",\"summary\":\"ROUND_ONE_HANDOFF\",\"evidence\":[\"Round one inspected the workspace.\"],\"nextSteps\":[\"Finish the snapshot objective.\"],\"blocker\":\"\"}"}}}} +{"type":"assistant/chunk","seq":3,"time":1783951001004,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":12}}}} +{"type":"assistant/chunk","seq":4,"time":1783951001005,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} diff --git a/examples/headless-agent/tests/snapshots/ralph-loop/session.2.jsonl b/examples/headless-agent/tests/snapshots/ralph-loop/session.2.jsonl new file mode 100644 index 0000000000..c722158098 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/ralph-loop/session.2.jsonl @@ -0,0 +1,6 @@ +{"type":"session","version":0,"id":"43333333-3333-4333-8333-333333333333","createdAt":1783951002000,"cwd":"/tmp/ralph-headless","parentSession":"41111111-1111-4111-8111-111111111111"} +{"type":"assistant/chunk","seq":0,"time":1783951002001,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":1,"time":1783951002002,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"round-two-report","name":"structured_output","argumentsDelta":"{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"}}} +{"type":"assistant/chunk","seq":2,"time":1783951002003,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"round-two-report","name":"structured_output","arguments":"{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"}}}} +{"type":"assistant/chunk","seq":3,"time":1783951002004,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":12}}}} +{"type":"assistant/chunk","seq":4,"time":1783951002005,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} diff --git a/examples/headless-agent/tests/snapshots/ralph-loop/session.jsonl b/examples/headless-agent/tests/snapshots/ralph-loop/session.jsonl new file mode 100644 index 0000000000..c452fb5fa8 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/ralph-loop/session.jsonl @@ -0,0 +1 @@ +{"type":"session","version":0,"id":"41111111-1111-4111-8111-111111111111","createdAt":1783951000000,"cwd":"/tmp/ralph-headless"} diff --git a/examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl b/examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl new file mode 100644 index 0000000000..727f84fd90 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl @@ -0,0 +1,23 @@ +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run a two-round fresh-agent Ralph loop to prove the shipped headless integration."}],"source":{"kind":"user"}},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_ralph","name":"ralph","argumentsDelta":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_ralph","content":[{"type":"text","text":"Ralph worker reported completion after 2 rounds.\nFinal report:\n{\n \"status\": \"complete\",\n \"summary\": \"The Ralph snapshot objective is complete.\",\n \"evidence\": [\n \"Two fresh rounds completed through the shipped app.\"\n ],\n \"nextSteps\": [],\n \"blocker\": \"\"\n}"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"RALPH SNAPSHOT COMPLETE"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"RALPH SNAPSHOT COMPLETE"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"RALPH SNAPSHOT COMPLETE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":20,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":21,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} +{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"RALPH SNAPSHOT COMPLETE","reason":{"kind":"completed"},"usage":{"inputTokens":50,"outputTokens":12}} From 07058e527cc87b81de4c2359bce67ff3244cf6a7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 18:32:21 +0800 Subject: [PATCH 11/11] fix(snapshot): isolate concurrent spill roots --- .../testing/2026-06-19-acp-snapshot-tests.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 14 ++++++++++-- .../support/acp-snapshot/src/normalize.ts | 2 +- .../tests/fixtures/fake-acp-agent.ts | 1 + .../acp-snapshot/tests/harness.spec.ts | 22 +++++++++++++++++++ .../acp-snapshot/tests/normalize.spec.ts | 15 +++++++++++++ 6 files changed, 52 insertions(+), 4 deletions(-) diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md index 5fc7479eaf..56a102f456 100644 --- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md @@ -57,7 +57,7 @@ Normalization replaces session, cwd, protocol-id, timestamp, path, and process v ### Isolation: normalization now, sandbox later -Tool determinism comes from a temporary cwd, scrubbed environment, fresh non-login shell, constrained commands, and normalization. It does not claim OS confinement. A sandboxed executor can replace the local backend through the existing [capability seam](../architecture/2026-06-13-capability-seams.md) if a stronger tier is needed. +Tool determinism comes from a temporary cwd, scrubbed environment, fresh non-login shell, constrained commands, and normalization. Concurrent replay runs own separate cwd, persistence, and fixed-length scenario-keyed spill roots, so one scenario's teardown cannot delete another's in-flight full-output recovery while real-path preview budgets remain stable. This tier does not claim OS confinement. A sandboxed executor can replace the local backend through the existing [capability seam](../architecture/2026-06-13-capability-seams.md) if a stronger tier is needed. ### The replay plugin is its own package diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index a6252d9aa3..9700f24702 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -18,8 +18,9 @@ import { cp, mkdtemp, readFile, readdir, rm } from 'node:fs/promises' import { existsSync } from 'node:fs' +import { createHash } from 'node:crypto' import { tmpdir } from 'node:os' -import { join, delimiter } from 'node:path' +import { basename, dirname, join, delimiter } from 'node:path' import { ClientSideConnection, PROTOCOL_VERSION, @@ -152,6 +153,13 @@ export interface RunOptions { configPath?: string } +/** Derive one stable, fixed-length spill root owned by this scenario. */ +function scenarioSpillRoot(fixtureFile: string): string { + const scenario = basename(dirname(fixtureFile)) + const key = createHash('sha256').update(scenario).digest('hex').slice(0, 9) + return `/tmp/dsh-acp-snap-${key}` +} + /** * Run a scenario end-to-end against a freshly-spawned subprocess. Owns the * child and its temp dirs; always tears them down. Returns the captured stdout @@ -166,7 +174,9 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-snap-sessions-')) // Fixed path length: spill-policy budgets the preview against the REAL path // before stdout normalization, so tmpdir() length differences churn expected outputs. - const spillRoot = '/tmp/dsh-acp-snapshot-spill' + // Scenario ownership also matters: replay runs concurrently, and one teardown + // must never delete another scenario's in-flight full-output recovery file. + const spillRoot = scenarioSpillRoot(opts.fixtureFile) // Everything past the temp-dir creation is followed by failure-safe cleanup, // so a failure in workspace seeding, spawn, or any step never leaks resources. let launched: LaunchedAcpTestAgent | undefined diff --git a/packages/support/acp-snapshot/src/normalize.ts b/packages/support/acp-snapshot/src/normalize.ts index 0c21046eb2..6671959b29 100644 --- a/packages/support/acp-snapshot/src/normalize.ts +++ b/packages/support/acp-snapshot/src/normalize.ts @@ -20,7 +20,7 @@ const LOCAL_SPILL_PATH_RE = new RegExp( 'g', ) const SNAPSHOT_SPILL_PATH_RE = new RegExp( - String.raw`/tmp/dsh-acp-snapshot-spill/session-[0-9a-f]{12}/[0-9a-f]{12}-([A-Za-z0-9._~-]+?)` + String.raw`/tmp/(?:dsh-acp-snap-[0-9a-f]{9}|dsh-acp-snapshot-spill)/session-[0-9a-f]{12}/[0-9a-f]{12}-([A-Za-z0-9._~-]+?)` + String.raw`(?=\. Use read with offset/limit|[\s)]|$)`, 'g', ) diff --git a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts index 43b5ee3fb3..277dc7565c 100644 --- a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts +++ b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts @@ -152,6 +152,7 @@ async function handlePrompt(id: number | string): Promise { mode: process.env.DSH_SNAPSHOT, override: process.env.DSH_SNAPSHOT_OVERRIDE ?? null, childFiles: process.env.DSH_SNAPSHOT_CHILD_FILES ?? null, + spillRoot: process.env.DSH_SNAPSHOT_SPILL_ROOT ?? null, })}`) } if (behavior.echoWorkspace === true) { diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 748b9e1606..2f54b7781d 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -60,6 +60,15 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] +function environmentEcho(rawStdout: string): Record { + const frames = rawStdout.trim().split('\n') + .map(line => JSON.parse(line) as { params?: { update?: { content?: { text?: unknown } } } }) + const text = frames.map(frame => frame.params?.update?.content?.text) + .find(value => typeof value === 'string' && value.startsWith('env:')) + if (typeof text !== 'string') throw new Error('fake ACP agent did not echo its environment') + return JSON.parse(text.slice('env:'.length)) as Record +} + describe('runScenario', () => { it('surfaces an asynchronous child spawn failure through startup and close', async () => { const { dir } = await scenario({}) @@ -309,6 +318,19 @@ describe('runScenario', () => { expect(result.rawStdout).toContain(JSON.stringify(childFiles.join(delimiter)).slice(1, -1)) }) + it('gives concurrent scenarios distinct equal-length spill roots', { timeout: 20_000 }, async () => { + const [first, second] = await Promise.all([scenario({ echoEnv: true }), scenario({ echoEnv: true })]) + const results = await Promise.all([first, second].map(({ fixtureFile }) => runScenario( + { steps: [...boot, { op: 'prompt', text: 'env?' }] }, + { agent: AGENT, mode: 'replay', fixtureFile }, + ))) + const roots = results.map(result => environmentEcho(result.rawStdout).spillRoot) + expect(roots.every(root => typeof root === 'string')).toBe(true) + expect(new Set(roots).size).toBe(2) + expect((roots[0] as string).length).toBe((roots[1] as string).length) + expect((roots[0] as string).length).toBe('/tmp/dsh-acp-snapshot-spill'.length) + }) + it('seeds the workspace dir into the temp cwd before the run', { timeout: 20_000 }, async () => { const { dir, fixtureFile } = await scenario({ echoWorkspace: true }) const workspaceDir = join(dir, 'workspace') diff --git a/packages/support/acp-snapshot/tests/normalize.spec.ts b/packages/support/acp-snapshot/tests/normalize.spec.ts index 2beaba5114..0ebfbe3255 100644 --- a/packages/support/acp-snapshot/tests/normalize.spec.ts +++ b/packages/support/acp-snapshot/tests/normalize.spec.ts @@ -139,6 +139,21 @@ describe('normalizeSessionLog', () => { expect(out).not.toContain('/tmp/dsh-acp-snapshot-spill') }) + it('scrubs scenario-owned snapshot spill paths', () => { + const ev = JSON.stringify({ + type: 'tool/result', seq: 2, time: 5, + data: { + content: [{ + type: 'text', + text: 'Full formatted result stored at: /tmp/dsh-acp-snap-012345678/session-c22bc3f1d2af/8a7b6c5d4e3f-bash.txt. Use read with offset/limit, or grep this path to search within it.', + }], + }, + }) + const out = normalizeSessionLog(`${header({ cwd: ctx.cwd })}\n${ev}\n`, ctx) + expect(out).toContain('{{spillLocator:bash.txt}}') + expect(out).not.toContain('/tmp/dsh-acp-snap-012345678') + }) + it('scrubs the session id in the header', () => { const out = normalizeSessionLog(`${header({ id: ctx.sessionIds[0] })}\n`, ctx) expect(out).toContain('{{sessionId}}')