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 1/3] 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 2/3] 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 3/3] 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, + }) }) })