Merge branch 'codex/goal-session' into codex/commands

.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

.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
 

.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
 

.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: 744d55aee275b8dd4c71f628f685372f62c818bf
-2026-07-19-persisted-same-session-goal-domain.zh.md: 3e00d7af53abf801f8b92e8c7de879d91a62d503
+2026-07-19-persisted-same-session-goal-domain.md: 96a3b2c71b2eae27f028e61e7325fe7fa0bca521
+2026-07-19-persisted-same-session-goal-domain.zh.md: ae61dd1172dbb1864255476b78d68b4e46b37ccf

.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 `<goal_state>...</goal_state>` 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 `<goal_state>...</goal_state>` content must agree exactly. This descriptive delimiter follows the repository's existing `<workspace_context>` 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. `GoalService.disarm(agent)` also lets a lifecycle owner remove process-local authority without a session event, revision change, or `goal/changed` notification. Resume, fork, and continuation-driver replacement 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 and lifecycle-owner disarming, 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 and lifecycle-owner disarming, 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
 

.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 `<goal_state>...</goal_state>` 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 `<goal_state>...</goal_state>` 内容完全一致。这个描述性分隔符沿用了仓库已有的 `<workspace_context>` 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。`GoalService.disarm(agent)` 还允许生命周期所有者移除进程内权限，而不写入会话事件、不改变修订号，也不发出 `goal/changed` 通知。因此，恢复、fork 和继续执行驱动器替换都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、会话启动与生命周期所有者解除激活、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、会话启动与生命周期所有者解除激活、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
 

.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.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-same-session-goal-round-driver.md: 94c0a870c46d6b7f618faf3f0a4b01c141bec358
-2026-07-19-same-session-goal-round-driver.zh.md: 9fdff05ffb722ef683bc06acee606f7897e5afc6
+2026-07-19-same-session-goal-round-driver.md: b970ba7f6d136c0442430c3d738cdc66fa5ae6d7
+2026-07-19-same-session-goal-round-driver.zh.md: a441ec56223235b489a63f262733e8c26a0f4220

.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.md

@@ -20,7 +20,7 @@ The plugin has no configuration. `maxGoalRounds` is resolved and persisted by `d
 
 ### Reservation and admission
 
-When an agent is idle, has no competing queued work, and its current goal is `active` plus `armed`, the driver checkpoints pending goal mutations and rechecks every predicate after the await. If `roundsStarted` already equals `maxGoalRounds`, it records `budget-limited`. Otherwise it reserves the exact identity `{ goalId, revision, round: roundsStarted + 1 }` and the complete rendered prompt before calling `Agent.send()` with `GoalMessageSource`. The prompt JSON-quotes the objective so multiline or tag-like text remains an unambiguous data value inside the familiar frame.
+When an agent is idle, has no competing queued work, and its current goal is `active` plus `armed`, the driver checkpoints pending goal mutations and rechecks every predicate after the await. If `roundsStarted` already equals `maxGoalRounds`, it records `blocked` with code `round-limit`. Otherwise it reserves the exact identity `{ goalId, revision, round: roundsStarted + 1 }` and the complete rendered prompt before calling `Agent.send()` with `GoalMessageSource`. The prompt JSON-quotes the objective so multiline or tag-like text remains an unambiguous data value inside the familiar frame.
 
 The `agent/prompt-submit` waterfall is the admission fence. A positive goal source is allowed only when it exactly matches the driver's pending identity and content, the live goal still has that id and revision, activation remains armed, and the round is still the next number. The plugin checks once before delegating and again after downstream hooks return. This second check prevents an async hook from editing or pausing the goal while still admitting the old prompt.
 
@@ -40,10 +40,10 @@ The driver classifies one closed goal-owned turn as follows:
 |---|---|
 | durable `completed` | continue while active/armed and under cap |
 | cancellation of a reserved/admitted goal round, or its `aborted` result | pause and disarm |
-| `error` with code `RATE_LIMIT` | mark `usage-limited` |
-| other `error` | block |
-| `max-tokens` | block |
-| non-stale `rejected` | block |
+| `error` with code `RATE_LIMIT` | block with code `usage-limited` |
+| other `error` | block with code `turn-error` |
+| `max-tokens` | block with code `max-tokens` |
+| non-stale `rejected` | block with code `prompt-rejected` |
 | failed durability checkpoint | disarm without changing durable phase |
 | `disposed` or `interrupted` | disarm |
 | plugin-added unknown result | block for inspection |
@@ -70,7 +70,7 @@ An inbox acceptance can win the microtask race immediately before plugin unload
 
 The unit suite uses the real agent loop and session service with only the model scripted. It covers exact sequential admission and cap enforcement, load/resume inertness, every outcome classification, rate limiting, request errors, max tokens, downstream prompt veto, pre-admission and in-flight cancellation, unrelated-human cancellation, failed-pause fallback, human-input ordering, queued and downstream revision races, forged goal attribution, failed mutation and turn checkpoints including a later one-shot injection, scheduler and custom-agent failures, session-start reset, exact lifecycle retirement, and queued/running plugin teardown. The new driver source has per-file 100% statement, branch, function, and line coverage.
 
-A keyless Loader/stdio process test mounts the real goal domain, goal tools, goal driver, agent loop, persistence, and deterministic adapter through `cordis.yml`. One human turn creates a two-round goal; round one stops normally; round two reads the exact ref and completes it. The external JSONL assertion proves one session, round sources `1, 2`, unchanged round revision, final complete revision, five model steps, and no extra request after the terminal completion tool.
+A keyless ACP snapshot mounts the shipped editor app with the real goal domain, goal tools, goal driver, agent loop, persistence, and replay adapter through `cordis.yml`. One human turn creates and inspects a two-round goal, the first automatic turn stops normally, and ACP cancellation of a deliberately stalled second round records a durable pause. The normalized wire transcript and external JSONL assertions prove one session, round sources `1, 2`, the lifecycle mutation, and exact replay accounting without using `echo-agent` as an application surrogate.
 
 The core cancellation test proves notification order and containment: observers run only for effective cancellation, can queue replacement work before the inbox clear, cannot veto later observers by throwing, and an idle call emits nothing.
 

.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.zh.md

@@ -20,7 +20,7 @@ Status: implemented
 
 ### 预留与接纳
 
-当 agent 空闲、没有竞争中的排队工作，且当前目标为 `active` 加 `armed` 时，驱动器会先检查点持久化待处理的目标变更，并在等待之后重新校验所有条件。若 `roundsStarted` 已等于 `maxGoalRounds`，它会记录 `budget-limited`；否则，它会先预留精确身份 `{ goalId, revision, round: roundsStarted + 1 }` 和完整渲染提示词，再以 `GoalMessageSource` 调用 `Agent.send()`。提示词用 JSON 引号编码目标描述，使多行或类似标签的文本在熟悉框架中仍是无歧义的数据值。
+当 agent 空闲、没有竞争中的排队工作，且当前目标为 `active` 加 `armed` 时，驱动器会先检查点持久化待处理的目标变更，并在等待之后重新校验所有条件。若 `roundsStarted` 已等于 `maxGoalRounds`，它会记录代码为 `round-limit` 的 `blocked`；否则，它会先预留精确身份 `{ goalId, revision, round: roundsStarted + 1 }` 和完整渲染提示词，再以 `GoalMessageSource` 调用 `Agent.send()`。提示词用 JSON 引号编码目标描述，使多行或类似标签的文本在熟悉框架中仍是无歧义的数据值。
 
 `agent/prompt-submit` 瀑布是接纳栅栏。正数目标来源只有在完全匹配驱动器待处理的身份和内容、实时目标仍具有相同 id 与修订号、激活态仍为 armed，并且该回合仍是下一个编号时才会获准。插件在委托下游监听器前检查一次，在下游返回后再检查一次。第二次检查防止异步钩子编辑或暂停目标后，旧提示词仍被接纳。
 
@@ -40,10 +40,10 @@ Status: implemented
 |---|---|
 | 持久的 `completed` | 目标仍 active/armed 且未到上限时继续 |
 | 取消已预留/接纳的目标回合，或该回合产生 `aborted` 结果 | 暂停并解除激活 |
-| 代码为 `RATE_LIMIT` 的 `error` | 标记为 `usage-limited` |
-| 其他 `error` | 阻塞 |
-| `max-tokens` | 阻塞 |
-| 非过期的 `rejected` | 阻塞 |
+| 代码为 `RATE_LIMIT` 的 `error` | 以 `usage-limited` 代码阻塞 |
+| 其他 `error` | 以 `turn-error` 代码阻塞 |
+| `max-tokens` | 以 `max-tokens` 代码阻塞 |
+| 非过期的 `rejected` | 以 `prompt-rejected` 代码阻塞 |
 | 持久检查点失败 | 解除激活，但不改变持久阶段 |
 | `disposed` 或 `interrupted` | 解除激活 |
 | 插件新增的未知结果 | 阻塞并等待检查 |
@@ -70,7 +70,7 @@ Status: implemented
 
 单元测试使用真实 agent loop 与会话服务，只对模型编写脚本。覆盖内容包括精确连续接纳和上限执行、加载与恢复的惰性、所有结果分类、限流、请求错误、最大 token、下游提示词否决、接纳前与执行中取消、无关人类工作取消、暂停失败回退、人类输入排序、排队时与下游修订竞争、伪造目标来源、变更与轮次检查点失败（包括后续一次性注入）、调度器与自定义 agent 失败、会话启动重置、精确生命周期退出，以及排队中和运行中的插件卸载。新驱动器源码达到逐文件 100% 语句、分支、函数和行覆盖率。
 
-无密钥 Loader/stdio 进程测试通过 `cordis.yml` 挂载真实目标领域、目标工具、目标驱动器、agent loop、持久化和确定性适配器。一个人类轮次创建两回合目标；第一回合正常停止；第二回合读取精确引用并完成目标。测试从外部检查 JSONL，证明只有一个会话、回合来源依次为 `1, 2`、回合修订号不变、最终完成修订正确、共有五个模型步骤，并且终止性的完成工具后没有额外请求。
+无密钥 ACP 快照通过 `cordis.yml` 挂载已发布的编辑器应用，以及真实目标领域、目标工具、目标驱动器、agent loop、持久化和回放适配器。一个人类轮次创建并检查一个两回合目标；第一个自动轮次正常停止，ACP 随后取消刻意停滞的第二个回合并记录持久暂停。规范化线协议和外部 JSONL 断言证明只有一个会话、回合来源依次为 `1, 2`、生命周期变更与回放计数精确，并且没有把 `echo-agent` 当作应用替身。
 
 核心取消测试固定通知顺序与隔离：只有有效取消才会通知；观察者可以在清空收件箱前排入替代工作；抛错不能阻止后续观察者；空闲调用不会发出事件。
 

docs/cordis-catalog/events.md

@@ -510,7 +510,7 @@ 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/*`
 

docs/cordis-catalog/services.md

@@ -528,13 +528,6 @@ 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.
@@ -599,25 +592,10 @@ 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.
- */
-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.
+ * @param reason - policy-owned stable code and human-readable explanation.
+ * @returns the blocked view with its durable reason.
  */
-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.
@@ -628,9 +606,9 @@ 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:135`](../../packages/goal/goal/src/index.ts)
 
 ## `ctx.llm` — `LlmService`
 

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 {

docs/event-producer-consumer.md

@@ -29,7 +29,7 @@ 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-session`](../packages/goal/goal-session) |
+| `goal/changed` | `emit` | [`packages/goal/goal/src/types.ts:167`](../packages/goal/goal/src/types.ts) | [`goal`](../packages/goal/goal) (`emit`) | [`goal-session`](../packages/goal/goal-session) |
 | `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) |

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. <a id="goal-round"></a>
 - **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.
 

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": [

examples/acp-agent/goal.cordis.snapshot.yml

@@ -0,0 +1,19 @@
+# Replay counterpart to goal.cordis.yml; only the live model is replaced.
+- id: base
+  name: '@cordisjs/plugin-include'
+  config:
+    path: ./goal.cordis.yml
+    patches:
+      - id: llm-deepseek
+        name: '@deepseek-ai/dsh-llm-deepseek'
+        disabled: true
+      - insert:
+          - id: llm-replay
+            name: '@deepseek-ai/dsh-llm-replay'
+            config:
+              providers:
+                - id: deepseek
+                  name: DeepSeek
+                  models:
+                    - id: deepseek-v4-flash
+                    - id: deepseek-v4-pro

examples/acp-agent/goal.cordis.yml

@@ -0,0 +1,13 @@
+# Add the persisted same-session goal stack to the shipped ACP app.
+- id: base
+  name: '@cordisjs/plugin-include'
+  config:
+    path: ./cordis.yml
+    patches:
+      - insert:
+          - id: goal
+            name: '@deepseek-ai/dsh-goal'
+          - id: tool-goal
+            name: '@deepseek-ai/dsh-tool-goal'
+          - id: goal-session
+            name: '@deepseek-ai/dsh-goal-session'

examples/acp-agent/tests/goal.snapshot.ts

@@ -0,0 +1,112 @@
+import { readFile, writeFile } from 'node:fs/promises'
+import { dirname, join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import {
+  normalizeSessionLog,
+  normalizeStdout,
+  runScenario,
+  scrubRequestHeaders,
+  type AgentUnderTest,
+  type InputScript,
+  type NormalizeContext,
+} from '@deepseek-ai/dsh-acp-snapshot'
+import { foldGoal } from '@deepseek-ai/dsh-goal'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import { describe, expect, it } from 'vitest'
+
+const scenarioDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots/goal-session')
+const fixtureFile = join(scenarioDir, 'session.jsonl')
+const overrideFile = join(scenarioDir, 'replay.override.json')
+const stdoutExpected = join(scenarioDir, 'stdout.expected.jsonl')
+const sessionExpected = join(scenarioDir, 'session.expected.jsonl')
+const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
+
+const agent: AgentUnderTest = {
+  binScript: fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url)),
+  configPath: fileURLToPath(new URL('../goal.cordis.yml', import.meta.url)),
+  tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)),
+}
+
+interface JsonObject {
+  [key: string]: unknown
+}
+
+/** Parse non-empty records from one JSONL artifact. */
+function parseJsonl(content: string): JsonObject[] {
+  return content.split('\n').filter(line => line.trim().length > 0)
+    .map(line => JSON.parse(line) as JsonObject)
+}
+
+/** Zero durable goal timestamps inside 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 one persisted goal log after the shared snapshot scrubbers. */
+function normalizeGoalLog(content: string, context: NormalizeContext): string {
+  return parseJsonl(scrubRequestHeaders(normalizeSessionLog(content, context)))
+    .map(record => JSON.stringify(normalizeGoalTimestamps(record)))
+    .join('\n') + '\n'
+}
+
+describe('ACP same-session goal snapshot', () => {
+  it('runs exact automatic rounds in the shipped application and persists cancellation', async () => {
+    const input = JSON.parse(await readFile(join(scenarioDir, 'input.json'), 'utf8')) as InputScript
+    const result = await runScenario(input, {
+      agent,
+      mode: 'replay',
+      fixtureFile,
+      overrideFile,
+      configPath: agent.configPath,
+    })
+
+    expect(result.stderr).toBe('')
+    expect(result.sessionLogs).toHaveLength(1)
+    const log = result.sessionLogs[0]
+    if (log === undefined) throw new Error('goal snapshot did not persist its ACP session')
+    const records = parseJsonl(log.content)
+    const events = records.slice(1) as unknown as SessionEvent[]
+    const calls = events.filter(event => event.type === 'tool/call').map(event => event.data.name)
+    expect(calls).toEqual(['create_goal', 'get_goal'])
+    const rounds = events.flatMap(event => event.type === 'user/message' && event.data.source.kind === 'goal'
+      ? [event.data.source.round]
+      : [])
+    expect(rounds).toEqual([1, 2])
+    expect(foldGoal(events)).toMatchObject({
+      goal: {
+        objective: 'Finish the ACP goal-session snapshot proof',
+        phase: 'paused',
+        revision: 2,
+        maxGoalRounds: 2,
+      },
+      roundsStarted: 2,
+    })
+
+    const context: NormalizeContext = {
+      sessionIds: [result.sessionId, log.id].filter((id): id is string => id !== undefined),
+      cwd: result.cwd,
+    }
+    const stdout = normalizeStdout(result.rawStdout, context)
+    const session = normalizeGoalLog(log.content, context)
+    if (refreshing) {
+      await Promise.all([
+        writeFile(stdoutExpected, stdout),
+        writeFile(sessionExpected, session),
+      ])
+    }
+    expect(stdout).toBe(await readFile(stdoutExpected, 'utf8'))
+    expect(session).toBe(await readFile(sessionExpected, 'utf8'))
+  })
+})

examples/acp-agent/tests/snapshots/goal-session/input.json

@@ -0,0 +1,12 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    {
+      "op": "promptAndWaitForAgentMessage",
+      "text": "Create a durable two-round goal for the ACP snapshot, inspect it, then report readiness.",
+      "waitForText": "partial"
+    },
+    { "op": "cancel" }
+  ]
+}

examples/acp-agent/tests/snapshots/goal-session/replay.override.json

@@ -0,0 +1,43 @@
+[
+  {
+    "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 ACP goal-session snapshot proof\",\"max_goal_rounds\":2}" },
+      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_create", "name": "create_goal", "arguments": "{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}" } },
+      { "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" } }
+    ]
+  },
+  {
+    "kind": "chunks",
+    "chunks": [
+      { "type": "block-start", "index": 0, "blockType": "text" },
+      { "type": "text-delta", "index": 0, "text": "GOAL ROUND ONE" },
+      { "type": "block-end", "index": 0, "block": { "type": "text", "text": "GOAL ROUND ONE" } },
+      { "type": "usage", "usage": { "inputTokens": 40, "outputTokens": 3 } },
+      { "type": "finish", "reason": { "kind": "stop" } }
+    ]
+  },
+  { "kind": "hang" }
+]

examples/acp-agent/tests/snapshots/goal-session/session.expected.jsonl

@@ -0,0 +1,53 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
+{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Create a durable two-round goal for the ACP snapshot, inspect it, then report readiness."}],"source":{"kind":"user"}},"surfaceOp":"append"}
+{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"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 ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}}
+{"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 ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}}}
+{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}
+{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"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 ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
+{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}
+{"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 ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
+{"type":"context/message","seq":12,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":2},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"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 ACP goal-session snapshot proof","phase":"active","maxGoalRounds":2},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}
+{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}
+{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}
+{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"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":"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":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}
+{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"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":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}
+{"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 ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}
+{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}
+{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}
+{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}
+{"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":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}
+{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"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":"step/end","seq":31,"time":0,"data":{"turn":1,"step":3}}
+{"type":"turn/end","seq":32,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
+{"type":"turn/start","seq":33,"time":0,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1}}}}
+{"type":"user/message","seq":34,"time":0,"data":{"content":[{"type":"text","text":"<goal_round>\nObjective: \"Finish the ACP goal-session snapshot proof\"\nRound: 1/2\n\nContinue working toward the objective in this same session. Treat the current workspace, tool results, and durable session state as authoritative; inspect them instead of assuming earlier narration is still current. Make concrete progress and verify the result. Before claiming completion, gather evidence that the whole objective is achieved, read the current goal, and mark it complete. If work remains, leave the goal active for the next round. Follow the configured goal-tool policy before reporting a blocker.\n</goal_round>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1}},"surfaceOp":"append"}
+{"type":"step/start","seq":35,"time":0,"data":{"turn":2,"step":1}}
+{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"GOAL ROUND ONE"}}}
+{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL ROUND ONE"}}}}
+{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":3}}}}
+{"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":41,"time":0,"data":{"turn":2,"step":1,"content":[{"type":"text","text":"GOAL ROUND ONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":40,"outputTokens":3}},"sourceEventSeqs":[36,37,38,39,40],"surfaceOp":"append"}
+{"type":"step/end","seq":42,"time":0,"data":{"turn":2,"step":1}}
+{"type":"turn/end","seq":43,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}
+{"type":"turn/start","seq":44,"time":0,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2}}}}
+{"type":"user/message","seq":45,"time":0,"data":{"content":[{"type":"text","text":"<goal_round>\nObjective: \"Finish the ACP goal-session snapshot proof\"\nRound: 2/2\n\nContinue working toward the objective in this same session. Treat the current workspace, tool results, and durable session state as authoritative; inspect them instead of assuming earlier narration is still current. Make concrete progress and verify the result. Before claiming completion, gather evidence that the whole objective is achieved, read the current goal, and mark it complete. If work remains, leave the goal active for the next round. Follow the configured goal-tool policy before reporting a blocker.\n</goal_round>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2}},"surfaceOp":"append"}
+{"type":"step/start","seq":46,"time":0,"data":{"turn":3,"step":1}}
+{"type":"assistant/chunk","seq":47,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}}
+{"type":"context/message","seq":49,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"paused\",\"maxGoalRounds\":2},\"roundsStarted\":2,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":2,"round":0},"envelope":"raw","meta":{"kind":"goal/change","version":1,"operation":"pause","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal-session snapshot proof","phase":"paused","maxGoalRounds":2},"roundsStarted":2,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}
+{"type":"step/end","seq":50,"time":0,"data":{"turn":3,"step":1}}
+{"type":"turn/end","seq":51,"time":0,"data":{"turn":3,"reason":{"kind":"aborted","reason":"session/cancel"}}}

examples/acp-agent/tests/snapshots/goal-session/session.jsonl

@@ -0,0 +1 @@
+{"type":"session","version":0,"id":"goal-session-placeholder","createdAt":0,"cwd":"/tmp/goal-session-placeholder"}

examples/acp-agent/tests/snapshots/goal-session/stdout.expected.jsonl

@@ -0,0 +1,10 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_create","title":"Create goal","kind":"other","status":"in_progress","rawInput":"Finish the ACP goal-session snapshot proof"}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_create","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_get","title":"Read current goal","kind":"read","status":"in_progress"}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_get","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GOAL READY"}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GOAL ROUND ONE"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}}

examples/echo-agent/tests/fixtures/goal/goal-session/cordis.yml

@@ -1,25 +0,0 @@
-# Test-only composition: one human turn creates a goal, then the driver runs two rounds.
-- id: scripted-llm
-  name: './scripted-llm.ts'
-
-- id: bash
-  name: '@deepseek-ai/dsh-bash-local'
-
-- id: goal
-  name: '@deepseek-ai/dsh-goal'
-
-- id: tool-goal
-  name: '@deepseek-ai/dsh-tool-goal'
-
-- id: goal-session
-  name: '@deepseek-ai/dsh-goal-session'
-
-- id: stdio-agent
-  name: '@deepseek-ai/dsh-stdio-demo'
-  config:
-    provider: goal-session-script
-    model: goal-session-script
-    persona: 'Execute the deterministic same-session goal-round proof.'
-    welcome: 'goal-session e2e ready.'
-    persistenceRoot: './.sessions'
-    workspaceContext: false

examples/echo-agent/tests/fixtures/goal/goal-session/scripted-llm.ts

@@ -1,104 +0,0 @@
-/** Deterministic model for the same-session goal-round composition proof. */
-
-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 and position of the latest human or goal-round prompt. */
-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('<goal_state>'))
-      .map(block => block.type === 'text' ? block.text : '')
-      .join('\n')
-    if (text.includes('<goal_round>') || text === 'start') return { index, text }
-  }
-  return { index: -1, text: '' }
-}
-
-/** Parse the latest durable goal snapshot retained in request 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('<goal_state>')) continue
-      const json = block.text.slice('<goal_state>'.length, -'</goal_state>'.length)
-      const value = JSON.parse(json) as { goal?: GoalState }
-      if (value.goal !== undefined) return value.goal
-    }
-  }
-  return undefined
-}
-
-/** Tool names already recorded after the prompt that owns this physical turn. */
-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 deterministic tool call, optionally with visible progress text. */
-async function* toolCall(name: string, args: object, text?: string): AsyncIterable<StreamChunk> {
-  let index = 0
-  if (text !== undefined) {
-    yield { type: 'block-start', index, blockType: 'text' }
-    yield { type: 'text-delta', index, text }
-    yield { type: 'block-end', index, block: { type: 'text', text } }
-    index += 1
-  }
-  const id = CallId(`call-${name}`)
-  const raw = JSON.stringify(args)
-  yield { type: 'block-start', index, blockType: 'tool-call' }
-  yield { type: 'tool-call-delta', index, id, name, argumentsDelta: raw }
-  yield { type: 'block-end', index, 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<StreamChunk> {
-  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 GoalSessionScriptAdapter extends LlmAdapter {
-  override stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
-    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: 'Complete two deterministic same-session rounds',
-        max_goal_rounds: 2,
-      })
-    }
-    if (prompt.text === 'start') return textReply('GOAL CREATED')
-    if (prompt.text.includes('Round: 1/2')) return textReply('ROUND ONE')
-    if (prompt.text.includes('Round: 2/2') && !calls.includes('get_goal')) {
-      return toolCall('get_goal', {})
-    }
-    if (prompt.text.includes('Round: 2/2') && !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: 'complete',
-      }, 'ROUND TWO COMPLETE')
-    }
-    return textReply('UNEXPECTED GOAL-SESSION REQUEST')
-  }
-}
-
-export const name = 'goal-session-scripted-llm'
-export const inject = ['llm']
-
-export function apply(ctx: Context): void {
-  ctx.llm.registerAdapter(['goal-session-script'], new GoalSessionScriptAdapter())
-}

examples/echo-agent/tests/fixtures/goal/tool-goal/cordis.yml

@@ -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

examples/echo-agent/tests/fixtures/goal/tool-goal/scripted-llm.ts

@@ -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('<goal_state>'))
-      .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('<goal_state>')) continue
-      const json = block.text.slice('<goal_state>'.length, -'</goal_state>'.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<StreamChunk> {
-  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<StreamChunk> {
-  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<StreamChunk> {
-    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())
-}

examples/headless-agent/goal.cordis.snapshot.yml

@@ -0,0 +1,12 @@
+# 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'

examples/headless-agent/goal.cordis.yml

@@ -0,0 +1,11 @@
+# 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'

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<string> {
-  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, '$10')
+  }
+  if (Array.isArray(value)) return value.map(normalizeGoalTimestamps)
+  if (value !== null && typeof value === 'object') {
+    return Object.fromEntries(Object.entries(value).map(([key, item]) => [
+      key,
+      ['createdAt', 'updatedAt', 'clearedAt'].includes(key) && typeof item === 'number'
+        ? 0
+        : normalizeGoalTimestamps(item),
+    ]))
+  }
+  return value
+}
+
+/** Normalize the stream's durable goal timestamps after the shared scrubbers. */
+function normalizeGoalStream(rawStdout: string, cwd: string): string {
+  return parseJsonl(normalizeHeadlessStream(rawStdout, cwd))
+    .map(record => JSON.stringify(normalizeGoalTimestamps(record)))
+    .join('\n') + '\n'
+}
+
+async function scenarioPrompt(dir: string, label: string): Promise<string> {
+  const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as {
     steps?: { op?: unknown; text?: unknown }[]
   }
   const prompt = input.steps?.find(step => step.op === 'prompt')?.text
-  if (typeof prompt !== 'string') throw new Error('advanced-toolchain input has no prompt step')
+  if (typeof prompt !== 'string') throw new Error(`${label} input has no prompt step`)
   return prompt
 }
 
@@ -90,24 +116,27 @@ async function persistedLogs(cwd: string): Promise<PersistedLog[]> {
 
 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)

examples/headless-agent/tests/snapshots/goal-tools/input.json

@@ -0,0 +1,8 @@
+{
+  "steps": [
+    {
+      "op": "prompt",
+      "text": "Create a durable goal to finish the snapshot proof, then inspect it."
+    }
+  ]
+}

examples/headless-agent/tests/snapshots/goal-tools/replay.override.json

@@ -0,0 +1,32 @@
+[
+  {
+    "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" } }
+    ]
+  }
+]

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_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"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}}

knip.json

@@ -11,8 +11,6 @@
       "entry": [
         "echo-agent/src/*.ts",
         "echo-agent/tests/fixtures/goal/goal/seed-goal.ts",
-        "echo-agent/tests/fixtures/goal/goal-session/scripted-llm.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",

packages/cordis/tool-cordis/src/api-catalog.ts

@@ -276,10 +276,6 @@ 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 */',
@@ -309,16 +305,8 @@ 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',
@@ -1201,10 +1189,6 @@ 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}',
@@ -1305,13 +1289,17 @@ 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',
@@ -1319,7 +1307,7 @@ 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',

packages/goal/goal-session/README.md

@@ -29,11 +29,11 @@ The retained prompt names the JSON-quoted objective and `round/maxGoalRounds`, t
 
 | Durable turn outcome | Goal action | Automatic retry |
 |---|---|---|
-| `completed` with goal still active and armed | admit the next round, or mark `budget-limited` at the cap | yes |
+| `completed` with goal still active and armed | admit the next round, or block with code `round-limit` at the cap | yes |
 | cancellation of a reserved/admitted goal round, or its `aborted` outcome | `paused` | no |
 | cancellation with no goal-round attempt | keep durable phase; disarm activation | no |
-| `error` with `RATE_LIMIT` | `usage-limited` | no |
-| other `error`, `max-tokens`, or a non-stale prompt rejection | `blocked` | no |
+| `error` with `RATE_LIMIT` | `blocked` with code `usage-limited` | no |
+| other `error`, `max-tokens`, or a non-stale prompt rejection | `blocked` with a diagnostic code and message | no |
 | durability failure, disposal, interruption, or unknown future outcome | disarm or block for inspection | no |
 
 A goal mutation made during its round supersedes settlement of the older revision. Completion, pause, blocking, and edits therefore remain authoritative even if the physical turn closes afterward. No abnormal result is retried automatically.
@@ -67,5 +67,5 @@ Append-only within an epoch: each admitted round extends the existing conversati
 - **No independent evaluator** — the model-facing goal policy decides when evidence is sufficient for completion and whether a blocker is semantically unchanged; evaluator-backed certification remains deferred.
 - **Same-session execution only** — this package deliberately does not spawn a fresh agent, fork a session prefix, or implement Ralph-style independent attempts; that workflow belongs to its own plugin layer.
 - **Accepted-queue unload race** — Cordis plugin unload is asynchronous. A goal prompt already accepted by the agent inbox can begin and consume its round before unload starts; teardown then cancels the request, disarms the goal, and awaits quiescence. No later round starts.
-- **Round cap, not resource budget** — token, currency, time, and provider quota policies remain independent; `RATE_LIMIT` only maps an observed provider stop into `usage-limited`.
+- **Round cap, not resource budget** — token, currency, time, and provider quota policies remain independent; `RATE_LIMIT` only maps an observed provider stop into the blocked reason code `usage-limited`.
 - **No abnormal auto-retry** — transient provider and persistence failures require a later human-authorized resume rather than an implicit retry policy.

packages/goal/goal-session/src/index.ts

@@ -143,11 +143,8 @@ export function apply(ctx: Context): void {
       case 'pause':
         ctx.goals.pause(state.agent, ref)
         return
-      case 'usage-limited':
-        ctx.goals.markUsageLimited(state.agent, ref)
-        return
       case 'blocked':
-        ctx.goals.block(state.agent, ref)
+        ctx.goals.block(state.agent, ref, { code: outcome.code, message: outcome.message })
         return
       case 'disarm':
         ctx.goals.disarm(state.agent)
@@ -190,7 +187,7 @@ export function apply(ctx: Context): void {
       if (goal !== undefined && goal.id === attempt.goalId && goal.revision === attempt.revision
         && goal.phase === 'active' && goal.activation === 'armed') {
         const outcome = attempt.phase === 'queued' && attempt.rejectedReason !== undefined && !attempt.stale
-          ? { kind: 'blocked', reason: 'rejected', detail: attempt.rejectedReason } as const
+          ? { kind: 'blocked', code: 'prompt-rejected', message: attempt.rejectedReason } as const
           : classifyGoalRound(attempt.reason, durable)
         if (!attempt.stale) applyOutcome(state, goal, outcome)
       }
@@ -200,7 +197,10 @@ export function apply(ctx: Context): void {
     const goal = currentGoal(state)
     if (goal === undefined || goal.phase !== 'active' || goal.activation !== 'armed') return
     if (goal.roundsStarted >= goal.maxGoalRounds) {
-      ctx.goals.markBudgetLimited(agent, goalRef(goal))
+      ctx.goals.block(agent, goalRef(goal), {
+        code: 'round-limit',
+        message: `Goal reached its configured limit of ${goal.maxGoalRounds} rounds.`,
+      })
       return
     }
 
@@ -228,7 +228,10 @@ export function apply(ctx: Context): void {
       const latest = currentGoal(state)
       if (latest !== undefined && latest.id === goal.id && latest.revision === goal.revision
         && latest.phase === 'active' && latest.activation === 'armed') {
-        ctx.goals.block(agent, goalRef(latest))
+        ctx.goals.block(agent, goalRef(latest), {
+          code: 'queue-failed',
+          message: `Could not queue goal round ${round}: ${renderThrown(error)}`,
+        })
       }
     }
   }

packages/goal/goal-session/src/outcome.ts

@@ -6,11 +6,10 @@ import type { TurnEndReason } from '@deepseek-ai/dsh-session'
 export type GoalRoundOutcome =
   | { readonly kind: 'continue' }
   | { readonly kind: 'pause'; readonly reason: string }
-  | { readonly kind: 'usage-limited'; readonly message: string }
   | {
     readonly kind: 'blocked'
-    readonly reason: 'error' | 'max-tokens' | 'rejected' | 'unknown'
-    readonly detail: string
+    readonly code: 'usage-limited' | 'turn-error' | 'max-tokens' | 'prompt-rejected' | 'unknown-turn-outcome'
+    readonly message: string
   }
   | { readonly kind: 'disarm'; readonly reason: 'durability-failed' | 'disposed' | 'interrupted' }
 
@@ -30,12 +29,12 @@ export function classifyGoalRound(reason: TurnEndReason, durable: boolean): Goal
       return { kind: 'pause', reason: reason.reason ?? 'cancelled' }
     case 'error':
       return reason.code === 'RATE_LIMIT'
-        ? { kind: 'usage-limited', message: reason.message }
-        : { kind: 'blocked', reason: 'error', detail: reason.message }
+        ? { kind: 'blocked', code: 'usage-limited', message: reason.message }
+        : { kind: 'blocked', code: 'turn-error', message: reason.message }
     case 'max-tokens':
-      return { kind: 'blocked', reason: 'max-tokens', detail: 'model output reached max tokens' }
+      return { kind: 'blocked', code: 'max-tokens', message: 'model output reached max tokens' }
     case 'rejected':
-      return { kind: 'blocked', reason: 'rejected', detail: reason.reason }
+      return { kind: 'blocked', code: 'prompt-rejected', message: reason.reason }
     case 'disposed':
       return { kind: 'disarm', reason: 'disposed' }
     case 'interrupted':
@@ -43,6 +42,10 @@ export function classifyGoalRound(reason: TurnEndReason, durable: boolean): Goal
     // TurnEndReason is merge-extensible. An unknown producer cannot opt into
     // automatic retry merely by adding a tag; stop for inspection instead.
     default:
-      return { kind: 'blocked', reason: 'unknown', detail: `unknown turn outcome: ${extensibleReason.kind}` }
+      return {
+        kind: 'blocked',
+        code: 'unknown-turn-outcome',
+        message: `unknown turn outcome: ${extensibleReason.kind}`,
+      }
   }
 }

packages/goal/goal-session/tests/goal-session.e2e.ts

@@ -1,138 +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 { foldGoal } 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/goal-session/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
-
-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
-})
-
-/** Recursively locate persistence JSONL files in one temporary root. */
-async function jsonlFiles(dir: string): Promise<string[]> {
-  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()
-}
-
-/** Run the complete deterministic human-turn plus two-round composition. */
-async function runComposition(): Promise<{ stdout: string; stderr: string }> {
-  workdir = await mkdtemp(join(tmpdir(), 'goal-session-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 inputClosed = false
-    proc.stdout.setEncoding('utf8')
-    proc.stdout.on('data', (chunk: string) => {
-      stdout += chunk
-      if (!inputClosed && stdout.includes('ROUND TWO COMPLETE') && stdout.includes('\n> ')) {
-        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-session 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-session e2e exited ${String(code)}. stdout:\n${stdout}\nstderr:\n${stderr}`))
-    })
-    proc.on('error', (error) => { clearTimeout(timer); reject(error) })
-    proc.stdin.write('start\n')
-  })
-}
-
-describe('same-session goal rounds through a real Loader, app, and stdio process', () => {
-  it('persists two exact rounds and stops the completion turn without another request', async () => {
-    const { stdout, stderr } = await runComposition()
-    expect(stderr).not.toContain('UNHANDLED')
-    expect(stdout).toContain('goal-session e2e ready.')
-    expect(stdout).toContain('GOAL CREATED')
-    expect(stdout).toContain('ROUND ONE')
-    expect(stdout).toContain('ROUND TWO COMPLETE')
-
-    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'])
-    expect(events.filter(event => event.type === 'step/start')).toHaveLength(5)
-    expect(events.filter(event => event.type === 'tool/result').every(event => !event.data.isError)).toBe(true)
-
-    const rounds = events.filter(event => event.type === 'user/message'
-      && event.data.source.kind === 'goal')
-    expect(rounds).toHaveLength(2)
-    const roundNumbers: number[] = []
-    const revisions: number[] = []
-    const prompts: string[] = []
-    for (const event of events) {
-      if (event.type !== 'user/message' || event.data.source.kind !== 'goal') continue
-      roundNumbers.push(event.data.source.round)
-      revisions.push(event.data.source.revision)
-      prompts.push(event.data.content.find(block => block.type === 'text')?.text ?? '')
-    }
-    expect(roundNumbers).toEqual([1, 2])
-    expect(revisions).toEqual([1, 1])
-    expect(prompts[0]).toContain('Round: 1/2')
-    expect(prompts[1]).toContain('Round: 2/2')
-
-    expect(foldGoal(events)).toMatchObject({
-      goal: {
-        objective: 'Complete two deterministic same-session rounds',
-        phase: 'complete',
-        revision: 2,
-        maxGoalRounds: 2,
-      },
-      roundsStarted: 2,
-    })
-  }, TEST_TIMEOUT_MS)
-})

packages/goal/goal-session/tests/goal-session.spec.ts

@@ -126,18 +126,18 @@ describe('goal-round outcome policy', () => {
     [{ kind: 'aborted', reason: 'operator stopped' }, true, { kind: 'pause', reason: 'operator stopped' }],
     [{ kind: 'aborted' }, true, { kind: 'pause', reason: 'cancelled' }],
     [{ kind: 'error', step: 1, message: 'slow down', code: 'RATE_LIMIT' }, true,
-      { kind: 'usage-limited', message: 'slow down' }],
+      { kind: 'blocked', code: 'usage-limited', message: 'slow down' }],
     [{ kind: 'error', step: 1, message: 'broken' }, true,
-      { kind: 'blocked', reason: 'error', detail: 'broken' }],
+      { kind: 'blocked', code: 'turn-error', message: 'broken' }],
     [{ kind: 'max-tokens' }, true,
-      { kind: 'blocked', reason: 'max-tokens', detail: 'model output reached max tokens' }],
+      { kind: 'blocked', code: 'max-tokens', message: 'model output reached max tokens' }],
     [{ kind: 'rejected', reason: 'policy' }, true,
-      { kind: 'blocked', reason: 'rejected', detail: 'policy' }],
+      { kind: 'blocked', code: 'prompt-rejected', message: 'policy' }],
     [{ kind: 'disposed' }, true, { kind: 'disarm', reason: 'disposed' }],
     [{ kind: 'interrupted' }, true, { kind: 'disarm', reason: 'interrupted' }],
     [{ kind: 'completed' }, false, { kind: 'disarm', reason: 'durability-failed' }],
     [{ kind: 'future-outcome' } as unknown as TurnEndReason, true,
-      { kind: 'blocked', reason: 'unknown', detail: 'unknown turn outcome: future-outcome' }],
+      { kind: 'blocked', code: 'unknown-turn-outcome', message: 'unknown turn outcome: future-outcome' }],
   ] as const)('maps %j without abnormal automatic retry', (reason, durable, expected) => {
     expect(goalSession.classifyGoalRound(reason, durable)).toEqual(expected)
   })
@@ -187,9 +187,13 @@ describe('same-session goal driving', () => {
     const test = await harness([textResponse('round one'), textResponse('round two')])
     const created = test.ctx.goals.create(test.agent, { objective: 'finish twice', maxGoalRounds: 2 })
 
-    const final = await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'budget-limited')
+    const final = await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'blocked')
 
     expect(final).toMatchObject({ id: created.id, roundsStarted: 2, activation: 'disarmed' })
+    expect(final?.blockedReason).toEqual({
+      code: 'round-limit',
+      message: 'Goal reached its configured limit of 2 rounds.',
+    })
     expect(test.adapter.requests).toHaveLength(2)
     const rounds: number[] = []
     for (const event of test.agent.session.events) {
@@ -219,21 +223,22 @@ describe('same-session goal driving', () => {
     expect(adapter.requests).toHaveLength(0)
 
     ctx.goals.resume(agent, created)
-    await waitForGoal(ctx, agent, goal => goal?.phase === 'budget-limited')
+    await waitForGoal(ctx, agent, goal => goal?.phase === 'blocked')
     expect(adapter.requests).toHaveLength(1)
   })
 
   it.each([
     ['rate limit', Object.assign(new Error('slow down'), { code: 'RATE_LIMIT' }), 'usage-limited'],
-    ['request error', new Error('provider broke'), 'blocked'],
-    ['max tokens', maxTokensResponse('unfinished'), 'blocked'],
-  ] as const)('stops after a %s without an automatic retry', async (_label, response, phase) => {
+    ['request error', new Error('provider broke'), 'turn-error'],
+    ['max tokens', maxTokensResponse('unfinished'), 'max-tokens'],
+  ] as const)('stops after a %s without an automatic retry', async (_label, response, code) => {
     const test = await harness([response])
     test.ctx.goals.create(test.agent, { objective: 'stop safely', maxGoalRounds: 8 })
 
-    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === phase)
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'blocked')
 
     expect(goal).toMatchObject({ roundsStarted: 1, activation: 'disarmed' })
+    expect(goal?.blockedReason?.code).toBe(code)
     expect(test.adapter.requests).toHaveLength(1)
   })
 
@@ -247,6 +252,7 @@ describe('same-session goal driving', () => {
     const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'blocked')
 
     expect(goal?.roundsStarted).toBe(0)
+    expect(goal?.blockedReason).toEqual({ code: 'prompt-rejected', message: 'deployment policy' })
     expect(test.adapter.requests).toHaveLength(0)
     expect(test.agent.session.events.some(event => event.type === 'prompt/blocked'
       && event.data.reason === 'deployment policy')).toBe(true)
@@ -305,7 +311,7 @@ describe('same-session goal driving', () => {
     test.ctx.goals.create(test.agent, { objective: 'continue after the human', maxGoalRounds: 1 })
     test.agent.send([{ type: 'text', text: 'human goes first' }])
 
-    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'budget-limited')
+    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'blocked')
 
     expect(test.adapter.requests).toHaveLength(2)
     expect(requestText(test.adapter.requests[0]!)).toContain('human goes first')
@@ -323,7 +329,7 @@ describe('same-session goal driving', () => {
     })
     test.ctx.goals.create(test.agent, { objective: 'yield to nested human input', maxGoalRounds: 1 })
 
-    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'budget-limited')
+    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'blocked')
 
     expect(test.adapter.requests).toHaveLength(2)
     expect(requestText(test.adapter.requests[0]!)).toContain('human joined the pending batch')
@@ -343,7 +349,7 @@ describe('same-session goal driving', () => {
     })
     test.ctx.goals.create(test.agent, { objective: 'old objective', maxGoalRounds: 1 })
 
-    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'budget-limited')
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'blocked')
 
     expect(goal).toMatchObject({ revision: 3, objective: 'new objective', roundsStarted: 1 })
     const blocked = test.agent.session.events.find(event => event.type === 'prompt/blocked')
@@ -370,7 +376,7 @@ describe('same-session goal driving', () => {
     })
     test.ctx.goals.create(test.agent, { objective: 'edit during admission', maxGoalRounds: 1 })
 
-    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'budget-limited')
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'blocked')
 
     expect(goal).toMatchObject({ objective: 'edited downstream', roundsStarted: 1 })
     expect(test.adapter.requests).toHaveLength(1)
@@ -442,6 +448,10 @@ describe('same-session goal driving', () => {
     const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'blocked')
 
     expect(goal).toMatchObject({ roundsStarted: 0, activation: 'disarmed' })
+    expect(goal?.blockedReason).toEqual({
+      code: 'queue-failed',
+      message: 'Could not queue goal round 1: queue rejected',
+    })
     expect(test.adapter.requests).toHaveLength(0)
   })
 
@@ -519,7 +529,7 @@ describe('same-session goal driving', () => {
     })
     test.ctx.goals.create(test.agent, { objective: 'retry stale admission', maxGoalRounds: 1 })
 
-    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'budget-limited')
+    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'blocked')
 
     expect(test.adapter.requests).toHaveLength(1)
     expect(test.agent.session.events.some(event => event.type === 'prompt/blocked'
@@ -669,7 +679,7 @@ describe('same-session goal driving', () => {
     expect(test.adapter.requests).toHaveLength(0)
 
     test.ctx.goals.resume(test.agent, created)
-    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'budget-limited')
+    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'blocked')
     expect(test.adapter.requests).toHaveLength(1)
   })
 

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). `disarm()` is the lifecycle-only exception: it removes process-local continuation authority without writing a revision or emitting a mutation.
+`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 internal. `disarm()` is the lifecycle-only exception: it removes process-local continuation authority without writing a revision or emitting a mutation.
 
-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_state>{"goal":...,"roundsStarted":...,"createdAt":...,"updatedAt":...}</goal_state>`; 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_state>{"goal":...,"roundsStarted":...,"createdAt":...,"updatedAt":...}</goal_state>`; 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 `<workspace_context>` 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
 

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<Exclude<GoalOperation, 'clear'>> = new Se
   'resume',
   'complete',
   'block',
-  'mark-usage-limited',
-  'mark-budget-limited',
-])
-const PHASES: ReadonlySet<GoalPhase> = new Set([
-  'active',
-  'paused',
-  'blocked',
-  'usage-limited',
-  'budget-limited',
-  'complete',
 ])
+const PHASES: ReadonlySet<GoalPhase> = 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')

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<string, unknown>
+    : 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.
@@ -169,7 +188,7 @@ 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') {
@@ -228,7 +247,7 @@ 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)
     }
@@ -255,7 +274,7 @@ export class GoalService extends Service {
       agent,
       ref,
       'complete',
-      ['active', 'paused', 'blocked', 'usage-limited', 'budget-limited'],
+      ['active', 'paused', 'blocked'],
       'complete',
       'disarmed',
     )
@@ -265,45 +284,20 @@ 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.
-   */
-  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.
+   * @param reason - policy-owned stable code and human-readable explanation.
+   * @returns the blocked view with its durable reason.
    */
-  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',
     )
   }
@@ -399,7 +393,13 @@ 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. */

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'
 

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,
     })
   })
 
@@ -301,18 +299,19 @@ 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)
@@ -321,15 +320,13 @@ 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')
@@ -347,32 +344,45 @@ 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')
   })
 
@@ -612,7 +622,16 @@ 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,
     }
@@ -708,9 +727,6 @@ 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()
 
@@ -796,6 +812,12 @@ 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 },
     ]

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

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,
     ),
   }))
 }

packages/goal/tool-goal/tests/tool-goal.e2e.ts

@@ -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<string[]> {
-  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)
-})

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,
+    })
   })
 })

packages/support/acp-snapshot/src/harness.ts

@@ -41,12 +41,15 @@ export type { AgentUnderTest } from './launcher.ts'
  * the client observes the selected update (`agent_message_chunk` by default),
  * then cancels and awaits completion. A named `waitForToolCallUpdate` keeps the
  * step open for a terminal tool update that may follow the prompt response.
+ * `promptAndWaitForAgentMessage` arms an exact text-chunk waiter before sending
+ * the prompt, then keeps the application live until that later update arrives.
  */
 export type InputStep =
   | { op: 'initialize'; terminalOutput?: boolean }
   | { op: 'newSession' }
   | { op: 'newSessionExpectError'; additionalDirectories?: string[] }
   | { op: 'prompt'; text: string }
+  | { op: 'promptAndWaitForAgentMessage'; text: string; waitForText: string }
   | { op: 'promptExpectError'; text: string }
   | {
     op: 'promptAndCancel'
@@ -331,6 +334,15 @@ async function runStep(
       await client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
       return
     }
+    case 'promptAndWaitForAgentMessage': {
+      const sessionId = getSessionId()
+      if (sessionId === undefined) throw new Error('snapshot-harness: promptAndWaitForAgentMessage before newSession')
+      const updateDone = waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk'
+        && update.content.type === 'text' && update.content.text === step.waitForText)
+      await client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
+      await updateDone
+      return
+    }
     case 'promptExpectError': {
       const sessionId = getSessionId()
       if (sessionId === undefined) throw new Error('snapshot-harness: promptExpectError before newSession')

packages/support/acp-snapshot/tests/harness.spec.ts

@@ -334,6 +334,21 @@ describe('runScenario', () => {
     expect(result.rawStdout.indexOf('thinking about it')).toBeLessThan(result.rawStdout.indexOf('cancelled'))
   })
 
+  it('promptAndWaitForAgentMessage keeps the app live through a matching later update', { timeout: 20_000 }, async () => {
+    const { fixtureFile } = await scenario({ prompt: 'respond' })
+    const result = await runScenario(
+      {
+        steps: [...boot, {
+          op: 'promptAndWaitForAgentMessage',
+          text: 'go',
+          waitForText: 'thinking about it',
+        }],
+      },
+      { agent: AGENT, mode: 'replay', fixtureFile },
+    )
+    expect(result.rawStdout).toContain('thinking about it')
+  })
+
   it('promptAndCancel can bracket cancellation with tool-call updates', { timeout: 20_000 }, async () => {
     const { fixtureFile } = await scenario({
       prompt: 'hang-until-cancel',

scripts/gen-cordis-catalog.ts

@@ -69,8 +69,8 @@ export const LINK_MAP: Record<string, string> = {
   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',

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" },
 

website/zh-CN/api/harness/events.md

@@ -587,7 +587,7 @@ 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/*
 

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#L135)
 
 ### 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#L161)
 
 ### ctx.goals.disarm(agent)
 
@@ -66,7 +47,7 @@ Remove process-local continuation authority without changing durable goal phase
 
 **Returns** a fresh disarmed view, or `undefined` when no goal is current.
 
-[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#L175)
 
 ### ctx.goals.create(agent, request)
 
@@ -88,7 +69,7 @@ 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#L190)
 
 ### ctx.goals.edit(agent, ref, request)
 
@@ -111,7 +92,7 @@ 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#L215)
 
 ### ctx.goals.pause(agent, ref)
 
@@ -132,7 +113,7 @@ 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#L236)
 
 ### ctx.goals.resume(agent, ref)
 
@@ -154,7 +135,7 @@ 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#L247)
 
 ### ctx.goals.complete(agent, ref)
 
@@ -175,68 +156,28 @@ 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#L272)
 
-### 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.
-
-[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L270)
-
-### 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#L280)
-
-### 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.
+**Returns** the blocked view with its durable reason.
 
 [Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L290)
 
@@ -259,4 +200,4 @@ 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#L317)
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L311)