diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml
new file mode 100644
index 0000000000..fd97351a0e
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-19-model-facing-goal-tools.md: 2ef77b53cd8b95c9cdffd12e20c723fb1cff3a5d
+2026-07-19-model-facing-goal-tools.zh.md: 08619600355c71ccd30d608e3c4e5a7fba753d4e
diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md
new file mode 100644
index 0000000000..2ef77b53cd
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md
@@ -0,0 +1,66 @@
+# Agent Note: Model-facing same-session goal tools
+
+Status: implemented
+
+English | [中文](2026-07-19-model-facing-goal-tools.zh.md)
+
+## Problem
+
+The persisted goal domain deliberately exposes lifecycle verbs to plugins, not directly to a model. A model still needs a small control surface for discovering the current goal, creating one from human intent, and changing its lifecycle. Prompt guidance alone cannot establish who authorized a mutation: a subagent, injected plugin message, stale model turn, or resumed session could all produce the same tool arguments.
+
+The surface also needs to preserve the separation between durable state and live execution authority. A restored or forked session can replay an active goal but starts disarmed; a later human request such as “continue” should let the model rearm it without requiring a literal command phrase. Conversely, an admitted autonomous goal round must be able to report completion or a persistent blocker without gaining permission to edit, pause, resume, or replace the human objective.
+
+## Decision
+
+`@deepseek-ai/dsh-tool-goal` in `packages/goal/tool-goal/` contributes three exclusive tools and one system-prompt policy section over `ctx.goals`: `get_goal`, `create_goal`, and `update_goal`. The names and read-create-update shape follow Codex's compact goal tool surface while the authority rules use this repository's public agent, session, tool, and goal seams.
+
+### 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, 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; 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.
+
+An autonomous goal round that successfully reports completion or blocking contributes the existing terminal `agent/turn-stop` decision for that physical turn, preventing an unnecessary follow-up request. Direct-human mutations do not contribute a terminal stop: the assistant can acknowledge the change, and concurrent human steering remains available to ordinary continuation folding.
+
+### Execution authority
+
+Every call requires an `exec.agent` that is the exact running object in `AgentRegistry`, is the current inherited driver initiator, and has an open turn. These are execution-time checks and cannot be bypassed by prompt injection or hand-authored tool arguments.
+
+Create, edit, pause, and resume additionally require an accepted user message or user steering event in the current turn of a runtime-root agent. Root ownership is derived from the live agent graph rather than durable fork ancestry: a resumed fork can receive direct human authority, while a live child remains a subagent and cannot mutate these states. User source is a host attestation: `Agent.send()` and `steer()` default an omitted source to `{ kind: 'user' }`, so non-human producers must label their own content. The runtime proves provenance, not whether the human's wording semantically warrants creation or resumption; that interpretation remains with the model.
+
+Complete and blocked accept either direct-human authority or the exact current goal round. Goal-round authority requires a goal-sourced `user/message` whose goal id, revision, and round all equal the folded current goal. It grants only the two terminal reports. Direct human authority may stop a goal immediately.
+
+### 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 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, 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
+
+- **Rely on prompt instructions for authority** — rejected because text can guide model judgment but cannot authenticate the live caller, turn, or source event.
+- **Expose every goal-service verb as a separate tool** — rejected because a compact read/create/update surface reduces schema cost and keeps compare-and-set behavior uniform.
+- **Require exact command phrases** — rejected because natural-language intent, including languages other than English, should be interpreted by the model; execution authority depends on provenance rather than spelling.
+- **Authorize from persisted root or fork metadata** — rejected because a fork that becomes an independently resumed top-level session should accept new human authority, while a currently owned child should not.
+- **Let autonomous rounds edit or resume the goal** — rejected because continuation authority is narrower than authority to redefine or restart the human objective.
+- **Treat the blocked threshold as an evaluator** — rejected because event counts cannot prove that an obstacle is semantically unchanged or truly terminal.
+
+## Consequences
+
+- Models receive a stable, compact lifecycle surface without direct access to the goal service.
+- State-changing calls are constrained by live runtime provenance as well as durable compare-and-set references.
+- Human requests can create and rearm goals through ordinary natural language, while restored sessions remain inert until such input arrives.
+- Goal rounds can finish or report a repeated blocker but cannot broaden their own mandate.
+- Deployment policy selects the blocking lower bound; the same resolved value controls enforcement and prompt guidance.
+
+## Known limitations and deferred work
+
+- Semantic classification of a substantial goal, a request to continue, objective completion, and the same blocking condition remains model judgment. An independent evaluator or completion certificate is deferred.
+- These tools mutate goal state but do not schedule goal rounds, classify abnormal driver stops, or cancel an active turn; the same-session driver owns those behaviors.
+- Goal-round authority is dormant unless a separately mounted continuation driver admits goal-sourced user turns; this tool package never manufactures that authority itself.
+- Human slash-command discovery and rendering are deferred to the command-surface layer.
+- A scope can hide tool registrations while leaving the independently registered prompt section visible unless the deployment scopes both together.
diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md
new file mode 100644
index 0000000000..0861960035
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md
@@ -0,0 +1,66 @@
+# Agent Note: 面向模型的同会话目标工具
+
+Status: implemented
+
+[English](2026-07-19-model-facing-goal-tools.md) | 中文
+
+## 问题
+
+持久目标领域有意把生命周期动词提供给插件，而不直接提供给模型。模型仍然需要一个小型控制面，用于发现当前目标、根据人类意图创建目标并改变其生命周期。仅靠提示词指导无法确定是谁授权了一次变更：子智能体、注入的插件消息、陈旧的模型轮次或恢复后的会话都可能产生相同的工具参数。
+
+该表面还需要保持持久状态与实时执行权限之间的分离。恢复或 fork（派生）后的会话可以回放活跃目标，但初始处于未激活状态；后续人类提出“继续”之类的请求时，模型应能重新激活目标，而无需用户使用字面命令。相反，已接纳的自主目标回合必须能够报告完成或持续阻塞，却不能因此获得编辑、暂停、恢复或替换人类目标的权限。
+
+## 决策
+
+位于 `packages/goal/tool-goal/` 的 `@deepseek-ai/dsh-tool-goal` 在 `ctx.goals` 之上贡献三个独占工具和一个系统提示词策略段：`get_goal`、`create_goal` 与 `update_goal`。工具名称和读取—创建—更新形态遵循 Codex 的紧凑目标工具表面，而权限规则使用本仓库公共的 agent（智能体）、会话、工具与目标接缝。
+
+### 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、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；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。
+
+自主目标回合成功报告完成或阻塞后，插件会为该物理轮次贡献现有的终止型 `agent/turn-stop` 决策，避免再发起一次不必要的模型请求。直接人类发起的变更不会贡献终止决策：智能体可以确认该变更，并且并发的人类 steering（转向）仍可参与普通的继续执行折叠。
+
+### 执行权限
+
+每次调用都要求存在 `exec.agent`，且它必须是 `AgentRegistry` 中完全相同的运行中对象、当前继承的驱动发起者，并处于开放轮次内。这些检查在执行时进行，不能通过提示词注入或手写工具参数绕过。
+
+创建、编辑、暂停与恢复还要求运行时根智能体的当前轮次已经接纳一条用户消息或用户 steering（转向）事件。根所有权来自实时智能体图，而非持久的 fork 祖先关系：恢复后的派生会话可以接收新的直接人类权限，实时子智能体则仍然是子智能体，不能改变这些状态。用户来源是宿主的证明：`Agent.send()` 和 `steer()` 会把省略的来源默认为 `{ kind: 'user' }`，因此非人类生产者必须标注自己的内容。运行时证明来源，而不判断人类措辞在语义上是否足以创建或恢复目标；该解释仍由模型完成。
+
+完成与阻塞既接受直接人类权限，也接受准确的当前目标回合。目标回合权限要求存在一条来源为目标的 `user/message`，其中目标 id、修订号和回合都与折叠后的当前目标相等。它只授予这两种终止报告权限。直接人类权限可以立即停止目标。
+
+### 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、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
+
+- **依赖提示词指令实施权限**——不予采纳，因为文本可以指导模型判断，却不能认证实时调用者、轮次或来源事件。
+- **把每个目标服务动词分别暴露为工具**——不予采纳，因为紧凑的读取/创建/更新表面可以降低模式成本，并保持统一的比较并交换行为。
+- **要求精确命令短语**——不予采纳，因为自然语言意图（包括英语以外的语言）应由模型解释；执行权限取决于来源，而不是拼写。
+- **根据持久的根或派生元数据授权**——不予采纳，因为成为独立恢复顶层会话的派生应接受新的人类权限，而当前仍受所有权约束的子智能体则不应接受。
+- **允许自主回合编辑或恢复目标**——不予采纳，因为继续执行权限比重新定义或重启人类目标的权限更窄。
+- **把阻塞阈值当作评估器**——不予采纳，因为事件计数无法证明障碍在语义上未改变或确实不可继续。
+
+## 后果
+
+- 模型获得稳定而紧凑的生命周期表面，无需直接访问目标服务。
+- 改变状态的调用同时受到实时运行时来源与持久比较并交换引用的约束。
+- 人类可以通过普通自然语言请求创建和重新激活目标，而恢复后的会话在收到此类输入前保持静止。
+- 目标回合可以完成或报告重复阻塞，但不能自行扩大任务权限。
+- 部署策略选择阻塞下限；同一个解析后的值同时控制执行与提示词指导。
+
+## 已知限制与延期工作
+
+- 是否属于重大目标、是否要求继续、目标是否完成以及阻塞条件是否相同，仍由模型进行语义分类。独立评估器或完成证书予以延期。
+- 这些工具会改变目标状态，但不调度目标回合、不分类异常驱动停止，也不取消活跃轮次；这些行为由同会话驱动器负责。
+- 除非另行挂载的继续执行驱动器接纳了目标来源的用户轮次，否则目标回合权限路径处于休眠状态；本工具包本身不会制造这种权限。
+- 面向人类的斜杠命令发现与渲染延期到命令表面层。
+- 若部署没有同时设定两个注册项的作用域，某个作用域可能隐藏工具注册，却保留独立注册的提示词段。
diff --git a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.i18n.yaml
new file mode 100644
index 0000000000..2859ffb99b
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-19-persisted-same-session-goal-domain.md: 00600b2c49646ebd3b692154ef945eb79a33b032
+2026-07-19-persisted-same-session-goal-domain.zh.md: 6a554438d0d70a5b4ccbf7b6ee77853af9c9ce69
diff --git a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md
new file mode 100644
index 0000000000..00600b2c49
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md
@@ -0,0 +1,63 @@
+# Agent Note: Persisted same-session goal domain
+
+Status: implemented
+
+English | [中文](2026-07-19-persisted-same-session-goal-domain.zh.md)
+
+## Problem
+
+A long-running objective outlives one prompt, turn, or model request. Treating that objective as an in-memory loop variable loses it on process restart, while putting it only in UI state makes model behavior impossible to reconstruct. Treating every session turn as progress also charges unrelated human messages against an automatic-work budget.
+
+Durable lifecycle and permission to continue are different facts. A session may retain an active objective after restart or fork, but silently starting work when a user opens that session is surprising. The domain needs replayable state without persisted auto-execution authority, and it must remain a plugin on the public agent/session seams rather than a special case in the concrete loop.
+
+## 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`; `create()` materializes it internally before mutation rather than exposing resolution as another service verb.
+
+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 model-visible `context/message` containing a versioned full snapshot; the session projects that content verbatim. 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.
+
+When `Agent.inject()` defers a mutation inside an active tool batch, the service overlays the accepted payload in process memory so a later mutation can use its new revision. Reconciliation removes only an exact matching payload when the FIFO append becomes visible; reentrant append observers project each mutation exactly once. Incremental replay advances its cursor after each valid event and remains positioned at the first corrupt event, so later reads report the same durable fault. The durable log remains authoritative after restart.
+
+### 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 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.
+
+### Service boundary
+
+The service accepts only the exact live `Agent` object registered under its id. Successful mutation injection emits the scoped `goal/changed` event with contained listener failures. Policy consumers use this service plus the public `Agent` interface and `agent/*` events; the goal domain does not import or modify `dsh-agent-loop`.
+
+## Testing
+
+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
+
+- **Store goals in a separate database or session header** — rejected because the session log already supplies ordering, persistence, fork prefixes, and reconstructability; a second store introduces atomicity and lineage questions.
+- **Use hidden log-only events** — rejected because durable state that changes future model behavior must be model-visible and reconstructable under the repository's logging invariant.
+- **Persist activation and restart automatically** — rejected because opening or resuming a session must wait for human input; durable phase records status, not fresh authority to spend resources.
+- **Count all session turns as goal rounds** — rejected because one session can contain human clarification, inspection, and unrelated work; only goal-attributed continuation turns consume this budget.
+- **Add goal state or a generic loop abstraction to `dsh-agent-loop`** — rejected because state and continuation policy can compose through existing plugins, `Agent` verbs, and events without privileging the shipped loop implementation.
+
+## Consequences
+
+- Goal history survives persistence, resume, compaction of unrelated nodes, and session fork as ordinary session data.
+- 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; policy consumers map round, token, currency, time, and provider limits to blocked reasons when they stop work.
+
+## Known limitations and deferred work
+
+- This domain records state but does not schedule goal rounds, cancel active turns, or classify abnormal stops.
+- The actor that records `complete` or `blocked` is authoritative; an independent evaluator or completion certificate is deferred to a policy consumer.
+- There is one current goal per session; parallel objective graphs and cross-session goal storage are absent.
+- Plugins share one trusted process boundary. Direct session writers can counterfeit goal records; strict replay detects inconsistency and fails goal access at the offending record, but does not isolate plugins or repair the log.
+- `GOAL_CHANGE_VERSION` has no pre-release compatibility promise or migration path.
diff --git a/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.zh.md b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.zh.md
new file mode 100644
index 0000000000..6a554438d0
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.zh.md
@@ -0,0 +1,63 @@
+# Agent Note: 持久的同会话目标领域
+
+Status: implemented
+
+[English](2026-07-19-persisted-same-session-goal-domain.md) | 中文
+
+## 问题
+
+长时间运行的目标会跨越单个提示词、轮次或模型请求。若把该目标视为内存中的循环变量，进程重启时就会丢失；若只存放在 UI 状态中，又无法重建模型行为。若把会话中的每个轮次都视为目标进度，与自动工作无关的人类消息也会消耗预算。
+
+持久生命周期与继续执行的权限是两个不同事实。会话在重启或 fork（派生）后可以保留活跃目标，但用户打开会话时静默启动工作并不符合直觉。该领域需要可回放的状态，却不能持久化自动执行权限；它还必须作为公共 agent（智能体）与会话接缝上的插件存在，而不是具体循环中的特例。
+
+## 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`；`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` 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()` 追加一条模型可见的 `context/message`，其中包含带版本的完整快照；会话会将其内容原样投射给模型。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。
+
+当 `Agent.inject()` 在活跃工具批次中延迟变更时，服务会在进程内叠加已接受的载荷，使后续变更可以使用新的修订号。FIFO 追加可见后，协调过程只移除完全匹配的载荷；重入的追加观察器对每次变更只投影一次。增量回放会在每个有效事件后推进游标，并停留在首个损坏事件处，因此后续读取会报告同一个持久故障。重启后仍以持久日志为准。
+
+### 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，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。
+
+### 服务边界
+
+服务只接受在对应 id 下注册的同一个实时 `Agent` 对象。成功注入变更后，它会发出带作用域的 `goal/changed` 事件，并隔离监听器失败。策略消费者通过本服务、公共 `Agent` 接口和 `agent/*` 事件工作；目标领域既不导入也不修改 `dsh-agent-loop`。
+
+## 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、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
+
+- **把目标存入独立数据库或会话头**——不予采纳，因为会话日志已经提供顺序、持久化、fork 前缀与可重建性；第二份存储会引入原子性和谱系问题。
+- **使用模型不可见的纯日志事件**——不予采纳，因为会改变后续模型行为的持久状态必须满足仓库日志不变量，保持模型可见且可重建。
+- **持久化激活态并自动重启**——不予采纳，因为打开或恢复会话时必须等待人类输入；持久阶段记录状态，而不是再次消耗资源的授权。
+- **把所有会话轮次都计为目标回合**——不予采纳，因为同一会话可以包含人类澄清、检查和无关工作；只有归属于目标的继续执行轮次才消耗该预算。
+- **向 `dsh-agent-loop` 添加目标状态或通用循环抽象**——不予采纳，因为状态与继续执行策略可以通过现有插件、`Agent` 动词和事件组合，而无需赋予默认循环实现特权。
+
+## 后果
+
+- 目标历史作为普通会话数据，在持久化、恢复、无关节点压缩和会话 fork 后继续保留。
+- 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；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
+
+- 本领域记录状态，但不调度目标回合、不取消活跃轮次，也不分类异常停止。
+- 记录 `complete` 或 `blocked` 的参与者具有最终权威；独立评估器或完成证书延期到策略消费者中实现。
+- 每个会话只有一个当前目标；不存在并行目标图和跨会话目标存储。
+- 插件共享同一个受信任的进程边界。直接写入会话的插件可以伪造目标记录；严格回放会检测不一致并在违规记录处使目标访问失败，但不会隔离插件或修复日志。
+- `GOAL_CHANGE_VERSION` 在首次发布前不承诺兼容性，也不提供迁移路径。
diff --git a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.i18n.yaml
new file mode 100644
index 0000000000..0addad9e97
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-19-plugin-command-registration.md: a207c6257bd4e9e4013f1abb661dd967ed2a52dc
+2026-07-19-plugin-command-registration.zh.md: e21d187ded0ee0f4daa370655994eb306fb1c5fd
diff --git a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md
new file mode 100644
index 0000000000..a207c6257b
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md
@@ -0,0 +1,81 @@
+# Agent Note: Plugin-owned human command registration
+
+Status: implemented
+
+English | [中文](2026-07-19-plugin-command-registration.zh.md)
+
+## Problem
+
+The TUI owns seven slash commands, while ACP defines a standard command catalog and invocation shape. Keeping command names, help text, autocomplete, dispatch, and cancellation inside each adapter makes every new command an adapter edit, prevents optional plugins from contributing commands, and lets the two front doors drift. Treating slash input as an ordinary model prompt is also unsafe: a user-visible direct action can unexpectedly consume tokens or let the model reinterpret an unknown command.
+
+A shared mechanism must remain a UI concern rather than a model tool or agent-loop branch. It also needs exact per-agent visibility, HMR-safe removal, per-session ACP discovery, direct result rendering, and request-scoped cancellation without adding command text or output to model history.
+
+## Decision
+
+`@deepseek-ai/dsh-commands` in `packages/ui/commands/` is the product command registry. The terminal and ACP app bundles mount it beside their consuming front door, and the SDK project helper emits the same service when scaffolding ACP directly; the executor-less, UI-less agent spine remains independent. TUI and ACP inject the service, while command producers depend only on the registry and any domain they operate.
+
+### Registry contract
+
+A `CommandDefinition` contains a lowercase name without `/`, a non-empty description, an optional unstructured-input hint, and an abortable handler. Registration validates and detaches the metadata, freezes the effective definition, and returns the exact Cordis effect disposer. Duplicate names fail within one layer. Every adapter consuming the registry sees every effective definition; a command plugin that cannot operate in a deployment omits its registration there instead of encoding adapter identities in the shared domain.
+
+`list(agent)` returns immutable name-sorted descriptors after scoped shadowing. `find(agent, name)` resolves the effective definition. `execute(agent, line, signal)` parses and runs a known definition, returning a detached `success` or `error` result; invalid syntax and unknown names return `undefined` so the adapter owns its direct error text.
+
+`parseCommand(line)` requires `/` at byte zero, a lowercase ASCII name containing letters, digits, `_`, or `-`, then whitespace or end-of-input. It preserves the complete adapter-delivered suffix as `rawInput`, including separator whitespace. Command-specific plugins own every further grammar decision.
+
+### Scope and lifecycle
+
+An unscoped registration is global. A command-injected plugin mounted beneath an agent context inherits that agent's scope key and lifetime, so its definition shadows a same-named global only for that exact agent. The child declares its own `commands` injection because `agent.ctx` intentionally inherits the core agent-loop dependency surface; adding a UI service to the loop merely to enable scoped registration would invert the dependency graph.
+
+Registration and removal emit the unfiltered, non-vetoing `commands/change` registry notification. Adapters recompute each live agent's effective view rather than trying to infer which sessions a change affects. The registry contains and logs each observer failure independently, so a broken UI refresh cannot roll back another plugin's mutation or starve a later observer. Cordis ownership removes definitions when their producer, UI instance, or agent scope unloads, so HMR cannot leave stale discovery entries or handlers.
+
+### Direct dispatch and cancellation
+
+Commands run in a human-only command plane. Their input does not become `user/message`, their output does not become a session event, and neither is sent to the model. A handler receives the exact target agent, raw input, and request-owned `AbortSignal`. The registry stops awaiting an uncooperative handler when the signal aborts; the handler remains responsible for stopping external side effects already started.
+
+Expected handler failures return `CommandResult.error`. Thrown or malformed results remain adapter-visible command failures, not model messages. This boundary deliberately separates UI output from durable domain mutation: a goal command may change `ctx.goals`, for example, but the goal service owns that persisted state.
+
+### TUI mapping
+
+The TUI registers `help`, `clear`, `cancel`, `reasoning`, `tools`, `redraw`, and `exit` as agent-scoped command definitions instead of switching on strings. Its autocomplete and help view read the live catalog, so plugin commands appear and disappear with their effects. Any submitted line beginning with `/` stays in the command plane; unknown input produces a terminal warning rather than falling through to `Agent.send()` or `Agent.steer()`.
+
+Each submitted command owns an `AbortController`. TUI disposal aborts outstanding dispatches, removes the local definitions, and waits for the command-producing fiber before completing teardown.
+
+### ACP mapping
+
+The bridge follows the current [ACP v1 slash-command contract](https://agentclientprotocol.com/protocol/v1/slash-commands). `session/new` and `session/load` emit the exact agent's full `available_commands_update` snapshot; a new session's RPC response introduces its server-generated id before the snapshot is enqueued. Every registry change emits a replacement snapshot for each live session. Names, descriptions, and optional unstructured-input hints map directly to `AvailableCommand`.
+
+ACP permits a command prompt to contain additional supported content blocks. The bridge applies its ordinary lossless `text` and `resource_link` flattening, then enters the command plane when the result starts with `/`. Unsupported prompt blocks are rejected by the existing capability boundary. Known commands execute directly; unknown or malformed slash input returns a direct error and never reaches the model. Successful text, expected errors, and thrown-failure diagnostics stream as live `agent_message_chunk` output and settle `end_turn`.
+
+One model prompt or direct command may be in flight per ACP session, independently across sessions. `session/cancel` aborts the direct command when one owns the request; it calls `Agent.cancel()` only for an agent prompt, so cancelling a command cannot destroy unrelated queued or injected agent work. Connection teardown aborts commands and then disposes the owned agents.
+
+## Testing
+
+The registry suite covers syntax boundaries, immutable normalization, runtime metadata validation, deterministic sorting, global and scoped shadowing, duplicate rejection, exact disposal, contained change-notification failures, direct invocation, expected and malformed results, synchronous and asynchronous failure, and every abort timing edge at per-file 100% statement, branch, function, and line coverage.
+
+TUI tests exercise all migrated built-ins, live plugin discovery, help/autocomplete refresh, direct results, unknown-command rejection, raw-input delivery, definition removal, startup rollback, and disposal cancellation. ACP tests use the real SDK connection, agent factory, loop, and JSONL persistence to verify create/load snapshots, dynamic updates, scoped multi-session catalogs, supported-block flattening, direct success/error/failure, unknown-command isolation, cancellation, and the absence of model requests or session messages. The SDK helper suite pins direct-ACP composition. Keyless ACP and terminal snapshots pin the new protocol and rendered transcript shapes.
+
+## Alternatives considered
+
+- **Keep adapter-local switches** — rejected because optional plugins cannot contribute discovery and behavior without editing every front door.
+- **Represent human commands as model tools** — rejected because discovery and direct invocation are human UI behavior; routing through the model adds latency, token cost, and reinterpretation.
+- **Put the registry in the core agent spine** — rejected because headless and JSON-RPC agents do not consume it, while the two UI app bundles can compose it explicitly.
+- **Make `dsh-agent-loop` inject commands** — rejected because the loop does not execute or discover human commands. Agent-scoped producers declare the UI dependency in a child plugin instead.
+- **Attach adapter masks to each definition** — rejected because support is a composition fact, not command-domain state. Every composed adapter exposes a registered command; an incompatible plugin omits registration in that deployment.
+- **Send unknown slash input to the model** — rejected because typoed or unavailable direct actions must fail predictably rather than change execution planes.
+- **Persist generic command input and output** — rejected because adapter notices are not model-visible state. A handler that changes durable behavior calls the owning domain API, which records its own events.
+- **Restrict ACP commands to one text block** — rejected because ACP v1 permits accompanying content; the bridge already has a lossless accepted-block translation.
+
+## Consequences
+
+- Command producers are ordinary removable plugins, and TUI/ACP share one validated catalog and dispatch contract.
+- Agent-specific definitions retain existing flat scope and shadow semantics without a core-to-UI dependency.
+- Unknown slash input and command output are deterministic UI behavior with zero direct model tokens.
+- ACP clients receive current per-session snapshots after creation, load, registration, and HMR removal.
+- Direct command cancellation is isolated from model-turn cancellation.
+
+## Known limitations and deferred work
+
+- Input metadata is ACP's current unstructured text hint. Typed forms, argument schemas, and completion providers remain command-owned or require a later protocol extension.
+- Generic command output is live-only and is not reconstructed after TUI restart or ACP reconnect.
+- Registry cancellation stops awaiting immediately, but external work stops only when a handler cooperates with its signal.
+- The headless CLI and JSON-RPC SDK front doors do not expose the command plane; only TUI and ACP consume it.
diff --git a/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.zh.md b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.zh.md
new file mode 100644
index 0000000000..e21d187ded
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.zh.md
@@ -0,0 +1,81 @@
+# Agent Note: 插件拥有的人类命令注册
+
+Status: implemented
+
+[English](2026-07-19-plugin-command-registration.md) | 中文
+
+## 问题
+
+TUI 拥有七个斜杠命令，而 ACP 定义了标准命令目录与调用形态。如果命令名、帮助文本、自动补全、分派和取消都留在各适配器内部，每个新命令都需要修改适配器，可选插件无法贡献命令，两个前端也会逐渐偏离。把斜杠输入当作普通模型提示同样不安全：用户可见的直接操作可能意外消耗 token，或让模型重新解释未知命令。
+
+共享机制必须仍是 UI 关注点，而不是模型工具或智能体循环分支。它还需要精确的逐智能体可见性、可安全 HMR 移除、逐会话 ACP 发现、直接结果渲染和请求作用域取消，同时不得把命令文本或输出加入模型历史。
+
+## 决策
+
+位于 `packages/ui/commands/` 的 `@deepseek-ai/dsh-commands` 是产品命令注册表。终端与 ACP 应用 bundle（组合包）把它挂载在消费该服务的前端旁，SDK 项目 helper（辅助器）在直接搭建 ACP 时也会生成同一服务；无执行器、无 UI 的智能体 spine（主干）保持独立。TUI 与 ACP 注入该服务，命令生产者只依赖注册表及其操作的领域。
+
+### 注册表契约
+
+`CommandDefinition` 包含不带 `/` 的小写名称、非空描述、可选的非结构化输入提示，以及可取消处理器。注册会校验并分离元数据、冻结有效定义，并返回准确的 Cordis effect disposer（副作用释放器）。同一层中的重复名称会失败。每个消费该注册表的适配器都能看到所有有效定义；若命令插件无法在某种部署中运行，它就不在该部署中注册，而不是把适配器身份编码进共享领域。
+
+`list(agent)` 在作用域遮蔽后返回不可变、按名称排序的描述符。`find(agent, name)` 解析有效定义。`execute(agent, line, signal)` 解析并运行已知定义，返回分离后的 `success` 或 `error` 结果；无效语法和未知名称返回 `undefined`，由适配器拥有直接错误文本。
+
+`parseCommand(line)` 要求 `/` 位于第零字节，后接由字母、数字、`_` 或 `-` 组成的小写 ASCII 名称，并以空白或输入末尾结束。它把适配器交付的完整后缀保留为 `rawInput`，包括分隔空白。每个命令插件自行拥有后续语法决策。
+
+### 作用域与生命周期
+
+无作用域注册是全局注册。挂载在智能体上下文之下并注入 `commands` 的插件会继承该智能体的作用域键与生命周期，因此其定义仅为该准确智能体遮蔽同名全局定义。子插件自行声明 `commands` 注入，因为 `agent.ctx` 有意只继承核心智能体循环的依赖界面；仅为了实现作用域注册而让循环依赖 UI 服务会倒置依赖图。
+
+注册和移除会发出未过滤、不可否决的 `commands/change` 注册表通知。适配器重新计算每个实时智能体的有效视图，而不尝试推断某次变更影响哪些会话。注册表会分别隔离并记录每个观察者失败，因此损坏的 UI 刷新无法回滚另一插件的变更，也无法阻止后续观察者。Cordis 所有权会在生产者、UI 实例或智能体作用域卸载时移除定义，因此 HMR 不会留下陈旧的发现项或处理器。
+
+### 直接分派与取消
+
+命令在仅面向人类的命令平面中运行。输入不会成为 `user/message`，输出不会成为会话事件，两者都不会发送给模型。处理器接收准确的目标智能体、原始输入和请求拥有的 `AbortSignal`。信号中止时，注册表不再等待不合作的处理器；处理器仍负责停止已经启动的外部副作用。
+
+预期的处理器失败返回 `CommandResult.error`。抛出的异常或格式错误的结果仍是适配器可见的命令失败，而不是模型消息。该边界有意分离 UI 输出与持久领域变更：例如目标命令可以改变 `ctx.goals`，但持久状态由目标服务拥有。
+
+### TUI 映射
+
+TUI 把 `help`、`clear`、`cancel`、`reasoning`、`tools`、`redraw` 和 `exit` 注册为智能体作用域命令定义，不再对字符串执行 switch。自动补全与帮助视图读取实时目录，因此插件命令会随其副作用出现和消失。任何以 `/` 开头的提交行都留在命令平面；未知输入产生终端警告，不会落入 `Agent.send()` 或 `Agent.steer()`。
+
+每个提交的命令拥有一个 `AbortController`。TUI 释放会中止未完成的分派、移除本地定义，并等待命令生产者 fiber（纤程）后再完成清理。
+
+### ACP 映射
+
+桥接遵循当前的 [ACP v1 斜杠命令契约](https://agentclientprotocol.com/protocol/v1/slash-commands)。`session/new` 与 `session/load` 发出准确智能体的完整 `available_commands_update` 快照；新会话的 RPC 响应会先引入服务端生成的 id，随后快照才会入队。每次注册表变更都会为每个实时会话发出替换快照。名称、描述和可选非结构化输入提示直接映射到 `AvailableCommand`。
+
+ACP 允许命令提示携带额外的受支持内容块。桥接应用普通的无损 `text` 与 `resource_link` 扁平化，然后在结果以 `/` 开头时进入命令平面。不支持的提示块由现有能力边界拒绝。已知命令直接执行；未知或格式错误的斜杠输入返回直接错误，绝不会到达模型。成功文本、预期错误和抛出失败的诊断作为实时 `agent_message_chunk` 输出流式发送，并以 `end_turn` 结束请求。
+
+每个 ACP 会话同时只能有一个模型提示或直接命令进行中，各会话彼此独立。当直接命令拥有请求时，`session/cancel` 会中止它；只有智能体提示才调用 `Agent.cancel()`，因此取消命令不会销毁无关的排队或注入智能体工作。连接清理会先中止命令，再释放所拥有的智能体。
+
+## 测试
+
+注册表测试覆盖语法边界、不可变规范化、运行时元数据校验、确定性排序、全局与作用域遮蔽、重复拒绝、准确释放、变更通知失败隔离、直接调用、预期和格式错误结果、同步与异步失败，以及每种中止时序边沿；该源文件达到逐文件 100% 语句、分支、函数和行覆盖率。
+
+TUI 测试覆盖全部迁移后的内置命令、实时插件发现、帮助与自动补全刷新、直接结果、未知命令拒绝、原始输入交付、定义移除、启动回滚和释放取消。ACP 测试使用真实 SDK 连接、智能体工厂、循环与 JSONL 持久化，验证创建/加载快照、动态更新、作用域多会话目录、受支持块扁平化、直接成功/错误/失败、未知命令隔离、取消，以及不存在模型请求或会话消息。SDK helper 测试固定直接 ACP 组合。无密钥 ACP 与终端快照固定新的协议和渲染记录形态。
+
+## 考虑过的替代方案
+
+- **保留适配器本地 switch**——不予采纳，因为可选插件无法贡献发现与行为，除非修改每个前端。
+- **把人类命令表示为模型工具**——不予采纳，因为发现与直接调用属于人类 UI 行为；经由模型路由会增加延迟、token 成本和重新解释。
+- **把注册表放入核心智能体主干**——不予采纳，因为无头和 JSON-RPC 智能体不消费它，而两个 UI 应用组合包可以显式组合它。
+- **让 `dsh-agent-loop` 注入 commands**——不予采纳，因为循环不执行也不发现人类命令。智能体作用域生产者改为在子插件中声明 UI 依赖。
+- **为每个定义附加适配器掩码**——不予采纳，因为支持能力是组合事实，而不是命令领域状态。每个已组合适配器都暴露已注册命令；不兼容插件不会在该部署中注册。
+- **把未知斜杠输入发送给模型**——不予采纳，因为输入错误或不可用的直接操作必须可预测地失败，而不能改变执行平面。
+- **持久化通用命令输入与输出**——不予采纳，因为适配器提示不是模型可见状态。改变持久行为的处理器会调用拥有该状态的领域 API，由后者记录自己的事件。
+- **把 ACP 命令限制为单个文本块**——不予采纳，因为 ACP v1 允许附带内容，而桥接已有无损的已接纳块转换。
+
+## 后果
+
+- 命令生产者是普通的可移除插件，TUI 与 ACP 共享一个经过校验的目录和分派契约。
+- 智能体特定定义保留现有扁平作用域与遮蔽语义，不引入核心到 UI 的依赖。
+- 未知斜杠输入与命令输出是确定性 UI 行为，直接模型 token 成本为零。
+- ACP 客户端在创建、加载、注册和 HMR 移除后收到当前的逐会话快照。
+- 直接命令取消与模型轮次取消彼此隔离。
+
+## 已知限制与延期工作
+
+- 输入元数据仅为 ACP 当前的非结构化文本提示。类型化表单、参数模式和补全提供器仍由命令拥有，或需要后续协议扩展。
+- 通用命令输出仅实时存在，TUI 重启或 ACP 重新连接后不会重建。
+- 注册表取消会立即停止等待，但外部工作只有在处理器配合信号时才会停止。
+- 无头 CLI 与 JSON-RPC SDK 前端不暴露命令平面；只有 TUI 和 ACP 消费它。
diff --git a/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.i18n.yaml
new file mode 100644
index 0000000000..f28ec1e2b7
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-19-same-session-goal-round-driver.md: 34d59456b5a8b54c92aba581da0ff22ea045b626
+2026-07-19-same-session-goal-round-driver.zh.md: dc2afd1ce18a45964bc1db04121211a9958445f3
diff --git a/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.md b/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.md
new file mode 100644
index 0000000000..34d59456b5
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.md
@@ -0,0 +1,100 @@
+# Agent Note: Same-session goal-round driver
+
+Status: implemented
+
+English | [中文](2026-07-19-same-session-goal-round-driver.zh.md)
+
+## Problem
+
+The goal domain can retain an objective and the model-facing tools can mutate its lifecycle, but neither should decide when another model turn begins. A continuation driver must bridge active goal state to the ordinary agent loop without adding goal-specific branches to `dsh-agent-loop`, inventing a second conversation, or treating every human turn as an autonomous iteration.
+
+That bridge has concurrency and durability obligations. Human input, cancellation, a goal edit, persistence failure, session restart, plugin unload, and a downstream prompt policy can all race a pending continuation. A naive `goal/changed -> agent.send()` listener can admit obsolete work, run alongside a human prompt, spend beyond the cap, or restart from replay without new authority.
+
+## Decision
+
+`@deepseek-ai/dsh-goal-session` in `packages/goal/goal-session/` is a policy plugin over `ctx.goals`, the public `Agent` interface, and durable session events. It imports no concrete agent-loop implementation. For each exact live `Agent`, it owns process-local scheduling state and may reserve at most one automatic round.
+
+The hierarchy is Goal → Goal Round → Turn → Step. A goal round is the outer continuation policy iteration; it becomes one goal-sourced session turn, and that turn can contain any number of ordinary model/tool steps. Human turns in the same session are not goal rounds and never increment `roundsStarted`.
+
+The plugin has no configuration. `maxGoalRounds` is resolved and persisted by `dsh-goal`, and the same-condition blocking threshold is resolved and prompted by `dsh-tool-goal`. Repeating those tunables in the driver would create multiple owners for one policy.
+
+### 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 `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.
+
+Only the resulting `user/message` is an admitted round and advances the goal fold. A stale reservation becomes a durable `prompt/blocked` plus zero-step rejected turn, but the driver marks it stale and does not charge the round. A downstream policy rejection that is not caused by staleness blocks the goal rather than retrying around policy.
+
+### Human work and revision races
+
+`agent/queued` distinguishes the driver's complete accepted record from every other prompt. Ordinary work already queued before a reservation prevents scheduling. Ordinary work queued while an automatic prompt is pending makes that reservation stale, so a mixed batch admits the human prompt but rejects the automatic one. Ordinary work arriving after the goal round was admitted remains queued for its own next turn; continuation is reconsidered only when the agent later becomes idle.
+
+A goal mutation during a round advances its durable revision. Settlement of the older revision cannot overwrite that mutation. The driver discards the old attempt outcome, reads the new projection, and continues only if the new revision is still active and armed. This makes model-recorded completion, pause, block, and edit authoritative over the physical turn's later close reason.
+
+### Settlement
+
+The driver classifies one closed goal-owned turn as follows:
+
+| Turn result | Action |
+|---|---|
+| 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` or `QUOTA` | 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 |
+
+No abnormal outcome requests an automatic retry. A later human prompt can ask to continue in any language; the model reads the stopped goal and uses the goal tool's resume action, which records a new revision and arms continuation.
+
+### Durability and cancellation seam
+
+Every `goal/changed` notification creates a checkpoint obligation. The driver awaits `ctx.sessions.flush(session)` before reserving work, then checks for a newer mutation, agent lifecycle change, or competing prompt. Turn-end flush failure is reported by the existing `agent/error` notification after `turn/end`; the driver finds that exact closed turn even when a concurrent one-shot injection appended a later turn, associates the failure with the exact attempt, and disarms before the next idle decision.
+
+Broad cancellation previously exposed only its effects after queues were cleared or the request aborted. The public agent vocabulary now includes observe-only `agent/cancel-requested(agent, reason)`. The concrete loop emits it for effective cancellation before either action; fused notification containment means a broken listener cannot veto cancellation. The goal driver uses this edge to clear its reservation before the loop destroys the queued-work evidence. When that reservation is a queued or admitted goal attempt, cancellation durably pauses the goal; when cancellation belongs to unrelated human work with no goal attempt, it only removes process-local activation. If the pause mutation throws, the driver falls back to disarming rather than allowing cancelled automatic work to restart.
+
+This is a coordination notification, not a second stop API. `Agent.cancel()` remains the only public broad cancellation verb, idle calls remain no-ops, and custom `Agent` implementations that claim the interface must honor the event ordering if consumers depend on it.
+
+### Process lifecycle
+
+`GoalService.disarm(agent)` removes only process-local activation. It writes no session event, changes no revision, and emits no goal mutation. The driver calls it while loading over existing agents, on durability uncertainty, and before teardown; a later `resume` is the durable activation edge visible to the model.
+
+The driver's event listeners and quiescent close are nested in one ordered Cordis effect. Cordis unloads sibling effects concurrently, so separate listener and cleanup registrations could remove the prompt fence while an async disposer was still draining. The composite effect first closes admission, disarms goals, cancels an admitted attempt, and awaits both agent and driver quiescence; only then does it unregister its listeners.
+
+An inbox acceptance can win the microtask race immediately before plugin unload begins. In that case the turn and even its first request may start and the round remains durably charged; once unload starts, cancellation aborts it, no following round is scheduled, and the goal remains active but disarmed. Pretending that already-observed admission never happened would corrupt replay accounting.
+
+## Testing
+
+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 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.
+
+## Alternatives considered
+
+- **Add a goal loop inside `dsh-agent-loop`** — rejected because the public queue, prompt, session, cancellation, and status seams are sufficient, and a concrete-loop branch would privilege one policy.
+- **Use `agent/turn-continuation` to make every round another step** — rejected because a goal round is an outer policy iteration and must have its own durable user prompt, turn boundary, round count, and failure settlement.
+- **Persist a pending reservation** — rejected because a crash cannot prove that queued process memory had reached admission; only the durable `user/message` consumes the round.
+- **Retry provider or persistence errors automatically** — rejected because retry policy spends resources and needs explicit authority; stopped phases plus later human resume are simpler and observable.
+- **Fork conversation history or spawn a fresh agent for every round** — rejected for this package because the goal is explicitly same-session work. Fresh-agent Ralph execution remains a separate workflow plugin built from subagent and workflow primitives.
+- **Reuse every session turn as the round counter** — rejected because human clarification and unrelated work share the session but not the automatic-work budget.
+
+## Consequences
+
+- Goal continuation remains a removable plugin and the concrete loop gains only a generic observe-before-cancel notification.
+- Replay can reconstruct every admitted round from its exact goal source and prompt; rejected reservations cannot create phantom budget use.
+- Human messages and lifecycle mutations win documented races without corrupting the revision or counter.
+- Resume and fork remain inert until semantic human intent causes the model to record a resume mutation.
+- Conservative failure mapping can require manual continuation after transient failures, but it never hides an automatic retry.
+
+## Known limitations and deferred work
+
+- Completion evidence and semantic blocker equivalence remain model judgments. An independent evaluator, completion certificate, or verifier-driven stop policy is deferred to a separate policy plugin.
+- This package does not provide Ralph-style fresh-agent attempts, context reset, cross-round evaluator feedback, or workflow-level parallelism; those belong to the separate Ralph workflow tool.
+- Cordis unload begins asynchronously. An already accepted inbox item may enter one charged round and start one request before teardown cancellation takes effect; the closing drain prevents every subsequent round.
+- `maxGoalRounds` is only an admitted-round limit. Token, currency, wall-clock, and provider-usage budgets require independent policy.
+- A custom `Agent` implementation must produce the documented session events, status edges, cancel notification, and quiescence semantics; structural TypeScript compatibility alone cannot verify runtime ordering.
diff --git a/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.zh.md b/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.zh.md
new file mode 100644
index 0000000000..dc2afd1ce1
--- /dev/null
+++ b/.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.zh.md
@@ -0,0 +1,100 @@
+# Agent Note: 同会话目标回合驱动器
+
+Status: implemented
+
+[English](2026-07-19-same-session-goal-round-driver.md) | 中文
+
+## 问题
+
+目标领域可以保留目标，模型可见工具也可以变更其生命周期，但两者都不应决定下一个模型轮次何时开始。继续执行驱动器必须把活跃目标状态连接到普通 agent（智能体）循环，同时不能向 `dsh-agent-loop` 添加目标专用分支、创建第二段对话，也不能把每个人类轮次都视为自主迭代。
+
+这层连接还承担并发与持久性义务。人类输入、取消、目标编辑、持久化失败、会话重启、插件卸载以及下游提示词策略都可能与待处理的继续执行发生竞争。简单的 `goal/changed -> agent.send()` 监听器可能接纳过期工作、与人类提示词同时运行、超出上限消耗资源，或在回放后未经新授权自行重启。
+
+## 决策
+
+位于 `packages/goal/goal-session/` 的 `@deepseek-ai/dsh-goal-session` 是构建在 `ctx.goals`、公共 `Agent` 接口和持久会话事件之上的策略插件。它不导入具体 agent-loop 实现。对于每个完全相同的实时 `Agent`，它维护进程内调度状态，并且最多保留一个自动回合预留。
+
+层次关系为目标（Goal）→ 目标回合（Goal Round）→ 轮次（Turn）→ 步骤（Step）。目标回合是外层继续执行策略的一次迭代；它会成为一个归属于目标的会话轮次，而该轮次可以包含任意数量的普通模型或工具步骤。同一会话中的人类轮次不是目标回合，也绝不会增加 `roundsStarted`。
+
+该插件没有配置项。`maxGoalRounds` 由 `dsh-goal` 解析并持久化；“相同阻塞条件”的门槛由 `dsh-tool-goal` 解析并写入提示词。若驱动器重复声明这些可调值，一个策略就会出现多个所有者。
+
+### 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。
+
+只有最终产生的 `user/message` 才是已接纳目标回合，并推进目标折叠。过期预留会生成持久的 `prompt/blocked` 和零步骤 rejected 轮次，但驱动器会把它标记为过期，不消耗回合数。若下游策略拒绝并非由过期导致，目标会进入 blocked，而不会绕过该策略自动重试。
+
+### 人类工作与修订竞争
+
+`agent/queued` 会区分驱动器自己的完整已接受记录与其他所有提示词。预留之前已经排队的普通工作会阻止调度；自动提示词待处理时进入的普通工作会使该预留过期，因此混合批次只接纳人类提示词而拒绝自动提示词。目标回合已经接纳后到达的普通工作会保留在队列中，成为下一个独立轮次；只有 agent 再次空闲后才重新考虑继续执行。
+
+目标在回合内发生变更时会推进持久修订号。旧修订的结算不得覆盖该变更。驱动器会丢弃旧尝试的结果、读取新投影，并且只在新修订仍为 active 与 armed 时继续。因此，模型记录的完成、暂停、阻塞和编辑相对于物理轮次稍后的关闭原因具有最终权威。
+
+### 结算
+
+驱动器按下表分类一个已经关闭、归属于目标的轮次：
+
+| 轮次结果 | 动作 |
+|---|---|
+| 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` 或 `QUOTA` 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 |
+
+异常结果都不会请求自动重试。之后的人类提示词可以用任何语言要求继续；模型读取已停止目标并调用目标工具的 resume 动作，记录新修订并重新激活继续执行。
+
+### 持久性与取消接缝
+
+每次 `goal/changed` 通知都会产生一个检查点义务。驱动器在预留工作前等待 `ctx.sessions.flush(session)`，随后检查是否出现了更新的变更、agent 生命周期变化或竞争提示词。轮次结束时的 flush 失败会在 `turn/end` 之后通过现有 `agent/error` 通知报告；即使并发的一次性注入已追加后续轮次，驱动器仍会找到该精确的已关闭轮次，把失败关联到精确尝试，并在下一次空闲决策前解除激活。
+
+广义取消此前只在队列已清除或请求已中止后暴露结果。公共 agent 词汇现在新增只观察的 `agent/cancel-requested(agent, reason)`。具体循环仅在取消有效时发出该事件，并且发生在清除队列和中止步骤之前；融合通知会隔离失败，因此损坏的监听器不能否决取消。目标驱动器利用该边沿在循环销毁排队工作证据前清除预留。若该预留是排队中或已接纳的目标尝试，取消会持久暂停目标；若取消属于没有目标尝试的无关人类工作，则只移除进程内激活态。若暂停变更抛错，驱动器会回退到解除激活，避免已取消的自动工作重新启动。
+
+该通知是协调事件，不是第二个停止 API。`Agent.cancel()` 仍是唯一的公共广义取消动词，空闲调用仍是无操作；若消费者依赖此接缝，自定义 `Agent` 实现就必须满足该事件顺序。
+
+### 进程生命周期
+
+`GoalService.disarm(agent)` 只移除进程内激活态。它不写会话事件、不改变修订号，也不发出目标变更。驱动器在加载到已有 agent、持久性存在不确定性以及卸载前调用该方法；之后的 `resume` 才是模型可见的持久激活边沿。
+
+驱动器的事件监听器和静止关闭嵌套在同一个有序 Cordis effect 中。Cordis 会并发卸载同级 effect；若监听器和清理分别注册，异步 disposer 仍在排空时提示词栅栏就可能已被移除。组合 effect 会先关闭接纳、解除目标激活、取消已接纳尝试，并等待 agent 与驱动器都达到静止；之后才注销监听器。
+
+紧邻插件开始卸载前，收件箱接纳可能赢得微任务竞争。在这种情况下，轮次甚至首个请求都可能已经开始，且该回合仍会持久计费；卸载一旦开始，取消就会中止它，不会再调度后续回合，目标保持 active 但 disarmed。若假装已经观测到的接纳从未发生，就会破坏回放计数。
+
+## 测试
+
+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 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。
+
+## 考虑过的替代方案
+
+- **在 `dsh-agent-loop` 内添加目标循环**——不予采纳，因为公共队列、提示词、会话、取消和状态接缝已经足够，具体循环分支还会赋予某种策略特权。
+- **使用 `agent/turn-continuation` 把每个回合变成另一个步骤**——不予采纳，因为目标回合是外层策略迭代，必须拥有自己的持久用户提示词、轮次边界、回合计数和失败结算。
+- **持久化待处理预留**——不予采纳，因为崩溃无法证明进程内队列已经达到接纳点；只有持久 `user/message` 才消耗回合。
+- **自动重试提供方或持久化错误**——不予采纳，因为重试会消耗资源，需要显式授权；停止阶段加之后的人类恢复更简单，也可观察。
+- **每回合 fork 对话历史或生成新 agent**——本包不采用，因为此目标明确属于同会话工作。新 agent 的 Ralph 执行仍是基于 subagent 与 workflow 原语的独立工作流插件。
+- **把每个会话轮次当作回合计数**——不予采纳，因为人类澄清和无关工作共享会话，但不共享自动工作预算。
+
+## 后果
+
+- 目标继续执行仍是可移除插件，具体循环只新增一个通用的“取消前观察”通知。
+- 回放可以从精确目标来源和提示词重建每个已接纳回合；被拒绝的预留不会产生虚假的预算消耗。
+- 人类消息和生命周期变更可以在有文档约束的竞争中胜出，而不破坏修订号或计数器。
+- 恢复和 fork 在语义上的人类意图促使模型记录 resume 变更之前始终保持惰性。
+- 保守的失败映射可能要求在暂时性错误后手动继续，但绝不会隐藏自动重试。
+
+## 已知限制与延期工作
+
+- 完成证据和阻塞条件的语义等价性仍由模型判断。独立评估器、完成证书或由验证器驱动的停止策略延期到独立策略插件。
+- 本包不提供 Ralph 风格的新 agent 尝试、上下文重置、跨回合评估反馈或工作流级并行；它们属于独立的 Ralph 工作流工具。
+- Cordis 卸载异步开始。已经被收件箱接受的条目可能先进入一个计费回合并启动一个请求，之后卸载取消才生效；关闭排空会阻止所有后续回合。
+- `maxGoalRounds` 只是已接纳回合上限。token、费用、挂钟时间和提供方使用预算需要独立策略。
+- 自定义 `Agent` 实现必须产生文档规定的会话事件、状态边沿、取消通知和静止语义；仅凭 TypeScript 结构兼容无法验证运行时顺序。
diff --git a/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md
index c44201b4e6..b05dd22357 100644
--- a/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md
+++ b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md
@@ -12,9 +12,9 @@ The boundary bought package metadata, workspace and tsconfig references, module-
 
 ## Decision
 
-The helper lives in `@deepseek-ai/dsh-stdio` as the terminal-channel plugin (`packages/ui/stdio/src/index.ts`): `createStdioChat`, its `StdioRuntime` test seam, and its unit tests (`packages/ui/stdio/tests/stdio.spec.ts`, `readline.spec.ts`) moved with it, so EOF handling, rendering, disposal, and piped-vs-TTY behavior stay unit-covered under the per-file coverage gate without hijacking process globals. The module keeps the named `name`/`inject`/`Config`/`apply` export shape — the contract the app's `ctx.plugin(uiStdio, …)` mount consumes — and the keyless Loader-path smokes in `examples/echo-agent` and `examples/repl-agent` keep proving the composed tree boots through the real Loader (the stdio package's plugin-shape unit suite pins the explicit `unwrapExports` assertion, since a bundle without `inject` would boot past a stray default rather than crash).
+At the time, the helper moved into `@deepseek-ai/dsh-stdio` as the terminal-channel plugin. `createStdioChat`, its `StdioRuntime` test seam, and its unit tests moved with it, keeping EOF handling, rendering, disposal, and piped-vs-TTY behavior under the per-file coverage gate without hijacking process globals. The module kept the named `name`/`inject`/`Config`/`apply` export shape consumed by the app mount, while the then-current Echo and REPL Loader smokes proved the composed tree and the plugin-shape suite pinned explicit `unwrapExports` behavior. The superseding removal note above owns the current package and example state.
 
-The `packages/support/ui-stdio` package is gone: manifest, tsconfig references, module-graph rows, and README rows deleted; the doc comments that named the package (the example e2e module docs, `packages/README.md`, the support and todo READMEs, [the ui group README](../../../../packages/ui/README.md)) describe the in-package module.
+The earlier support helper package was removed: its manifest, tsconfig references, module-graph rows, and README rows disappeared, while the remaining documentation described the in-package module.
 
 ## Alternatives considered
 
diff --git a/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.i18n.yaml b/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.i18n.yaml
new file mode 100644
index 0000000000..743d50cc5e
--- /dev/null
+++ b/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-16-harness-level-loop.md: 97041b1c08d5fb85a222824ee6d8dfd55e74f4bd
+2026-07-16-harness-level-loop.zh.md: 6460254b07b0e185ff2a40c415d34bd25b6ad925
diff --git a/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.md b/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.md
new file mode 100644
index 0000000000..97041b1c08
--- /dev/null
+++ b/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.md
@@ -0,0 +1,343 @@
+# Agent Note: harness-level goal-based loop
+
+Status: proposed
+
+English | [中文](2026-07-16-harness-level-loop.zh.md)
+
+## Problem
+
+`packages/core/agent-loop` runs only the inner loop: reasoning plus tool calls within one turn, ending when the model returns `end_turn`. Its README explicitly writes "No built-in turn budget"—budget is a gap it acknowledges itself. Cross-round scheduling falls on the harness layer: iterating until tests all pass, revising drafts against a rubric, splitting a PRD into beads and driving them one by one, running unattended for a whole night. None of these tasks has a first-class implementation today.
+
+The existing code offers three "just enough to run" alternatives, none of them adequate:
+
+| Alternative | Problem |
+|---|---|
+| A `packages/workflow` script expressing `while (!done)` | The README explicitly writes "No token-budget vocabulary" and "No journaling or resume"; the parent turn blocks until the script settles. Fine for orchestration lasting minutes, unusable for tasks lasting hours |
+| An external shell `while :; do dsh-sdk …; done` | Ralph-style scheduling can be written this way today. It lacks a shared vocabulary for stop condition, budget, and evaluator, so every user reinvents them; the loop itself has no durable object for post-hoc diagnosis or recovery |
+| The `sendMessage`/`resume` capabilities on the `packages/subagent` seam | The README explicitly writes "Runtime steering and continuation are seam-only capabilities". There is no model-facing consumer, so the model can only start a fresh subagent |
+
+Three typical use cases. **Automated fix**: a failing test suite in front of you, and you want a process to keep modifying code, running tests, and modifying again against the failure messages, until everything is green or the budget cap is hit. **Rubric-driven iterative revision**: a document, code, or translation must meet a set of scoring criteria; the loop repeatedly adjusts, an independent evaluator scores, and the loop stops when the criteria are met or the round budget is exhausted. **Unattended long runs**: for example, porting a repository from one tech stack to another overnight, kicked off before leaving work and reviewed the next morning, with the budget as the only safety net. Common shape across all three: minutes to hours, evaluator decides success, budget is a hard constraint, and post-run review and recovery are required.
+
+## Proposal
+
+**Loops come in four trigger shapes**, distinguished by who starts a round and when:
+
+| Shape | Who triggers | When | Existing comparable | This RFC |
+|---|---|---|---|---|
+| **turn-based** | The user sends a message in the session | Every user reply | `packages/core/agent-loop`'s existing reasoning-plus-tools cycle within one turn | Not covered; already implemented |
+| **goal-based** | The user or the agent specifies "run until some condition" | One start, evaluator decides when to stop | Claude Code's `/goal`, Codex's `/goal`, the Ralph family | **This RFC covers it** |
+| **time-based** | A scheduler | On cron or fixed interval | Claude Code's `/loop` (periodic), `/schedule` | Deferred to a `dsh-schedule` RFC |
+| **proactive** | The agent itself | When the agent realizes during reasoning that a loop is needed | The proactive tier in Anthropic ClaudeDevs's four-way taxonomy | **Naturally included** (an agent calling the `loop` tool is already proactive) |
+
+This RFC only **adds a capability seam `packages/loop/`** for the goal-based shape. Proactive reuses the same `loop` tool—an agent invocation is a trigger by itself, with no extra machinery. Time-based needs an independent scheduler package and belongs to a separate RFC; this RFC only reserves a hook on the cordis leaf trigger surface for the future `dsh-schedule` integration.
+
+Three packages:
+
+- `@deepseek-ai/dsh-loop`: types, the `LoopDriver` service, the `StopCondition` discriminated union, the Phase 1 service definitions (`Evaluator` / `BudgetPolicy` / `RoundHandoff`), and the event schema; `GoalReflector` joins in Phase 2 with its first caller
+- `@deepseek-ai/dsh-loop-driver`: the default driver implementation
+- `@deepseek-ai/dsh-loop-tool`: the model-facing `loop` tool plus the CLI `dsh-sdk loop`
+
+The design is organized around four concrete problems, addressed by service seams or explicit driver policies in the phase where each has a caller:
+
+1. A long-running loop that goes wrong leaves no systematic diagnosis or recovery. **Loop as an independent session** addresses this.
+2. Whether the PASS at loop end is trustworthy determines whether hours of work are wasted. An architecture where the same LLM both generates and self-evaluates is not trustworthy on its face. **Making Evaluator and Budget into service seams** addresses this.
+3. Short and long tasks need opposite memory strategies; hardcoding one mode makes the other class of scenario unusable. **Making RoundHandoff into a service seam** addresses this.
+4. The user's initial goal is not always correct. An agent stubbornly pursuing a wrong goal exhausts the budget doing wrong work. **Goal concern events and policies cover Phase 1; the GoalReflector service arrives with the Phase 2 `reflect` path**.
+
+Beyond the four seams, one principle threads through the whole document: **one loop handles one atomic goal**. Large goals should be split into several small loops chained in sequence, not stuffed into one loop with the evaluator judging multiple things. A rule of thumb for whether granularity is right: if you cannot say what a finished loop actually accomplished, granularity is too large and should be split. Phase 2 adds a `loop_split` model-facing tool so the agent can split an oversized goal itself.
+
+Terminology: **inner loop** refers to the existing per-turn reasoning-and-tools cycle in `packages/core/agent-loop`; **harness loop** refers to the outer scheduler introduced by this RFC, iterating around the inner loop. This RFC does not modify `agent-loop`, matching AGENTS.md's "Plugins, not loop changes".
+
+`StopCondition` is a discriminated union with `assertNever` closing the switch:
+
+```ts
+interface EvaluatorReport { criteria: readonly { name: string; pass: boolean; evidence: readonly string[] }[] }
+
+type StopCondition =
+  | { kind: 'goal-met'; evidence: EvaluatorReport }
+  | { kind: 'budget-cap'; scope: 'usd' | 'tokens' | 'rounds'; observed: number; maximum: number }
+  | { kind: 'stuck'; pattern: 'repeat-action' | 'no-progress' | 'error-loop' }
+  | { kind: 'approval-required'; reason: string }
+  | { kind: 'user-cancel' }
+
+export {}
+```
+
+### Loop as an independent session
+
+Once a long-running loop goes wrong, the user has no systematic diagnostic method. A failure hours in leaves only scattered log files to sift through. Discovering that some middle round went off track and wanting to roll back to re-run means starting over from scratch. An agent wanting to consult its own experience from past loops has no API to reach it.
+
+The driver opens an independent loop-session (a new session id) for each loop. Every round's inputs, inner-loop results, evaluator reports, and stop decisions are persisted as session events, reusing the SQLite backend from `packages/session-persistence`. This yields three diagnostic and replay capabilities.
+
+- **Replay conversation from a recorded round**: while the source session is live, discover round 78 went off and fork the round-77 event prefix with a different prompt or evaluator; persisted replay needs a separate trusted load-and-seed path. Both forms replay conversation state against the current workspace, not the files and external side effects that existed at round 77
+- **Post-hoc diagnosis**: through the existing `ctx.sessionQuery` exact-read service, inspect the round where the evaluator started hanging on the same criterion
+- **Meta-loop learning**: the proposed [SQLite FTS5 search](2026-07-10-sqlite-session-query-provider.md) can later find related historical loops before a new run—"have I fixed a similar bug before? Which round did it fail on?"
+
+Claude Code's and Codex's `/goal` are one-off objects: discarded when the run ends, so the agent starts from zero when facing a similar problem again.
+
+**Storage and recovery boundary**. A few KB of events per round, roughly 100–500 KB per 100-round loop; thousands of loops reach GB scale. Mitigated by the `logDetail: 'summary' | 'full'` config, defaulting to `full` with long-run users able to switch to `summary`. Persisting all intermediate state also writes generated keys, passwords, and similar secrets to disk—the same class of risk as an ordinary session but amplified 10–100×, and the README calls this out clearly. Exact live and persisted reads already exist through `ctx.sessionQuery`; FTS5 is an optional discovery improvement, not a Phase 1 dependency. Exact execution-world restore is not promised: `SessionStore.fork()` accepts a live session, and session events do not restore files, processes, environment, or external side effects. Restoring those requires a separate Git/worktree/checkpoint design.
+
+### Pluggable Evaluator and Budget
+
+A loop's value ultimately depends on whether the final PASS is trustworthy. If the evaluator can be hacked or hallucinates PASS, hours of work are wasted. An architecture where the same LLM both generates and self-evaluates is not trustworthy on its face: the model has the means to talk itself into PASS. Even letting an independent subagent be the evaluator only mitigates the problem; as long as the evaluator is still an LLM, it retains a systematic bias for the same class of content—an independent subagent is a mitigation, not a cure.
+
+Trustworthy evaluation needs both a deterministic judgment mechanism and an isolation boundary appropriate to the threat model: shell exit code, static analysis, or an external service avoids LLM self-judgment, while a separate worktree, read-only mount, container, or remote service prevents the worker from rewriting evaluator inputs. Only the user knows which checks and boundary to use: `pytest` commands differ by project, companies have private compliance checkers, and some teams also run internal lint. No number of built-in evaluators can cover them all. Evaluator therefore must be a seam the user can plug into.
+
+Budget is the same story: product-level spending guardrails are opaque, and cannot be adjusted for team policy (personal card, team splitting, per-PR settlement).
+
+`Evaluator` and `BudgetPolicy` are both exposed as cordis service seams, with users injecting them as plugins. `Goal` must carry an `EvaluatorSpec` at an explicit tier; the driver refuses to start a loop without a paired evaluator—vague goals ("write good code") cannot enter the loop system:
+
+```ts
+interface RubricItem { name: string; description: string }
+interface EvaluatorContract { readonly name: string }
+
+type CriteriaSpec =
+  | { kind: 'single-metric'; name: string }
+  | { kind: 'rubric'; criteria: RubricItem[] }
+  | { kind: 'contract'; interface: EvaluatorContract }
+
+type ExecutorSpec =
+  | { kind: 'shell'; command: string }
+  | { kind: 'llm-judge'; rubric: string; model: string }
+  | { kind: 'provider'; name: string; config?: unknown }
+
+type IsolationSpec = 'same-workspace' | 'separate-worktree' | 'container' | 'remote'
+
+interface EvaluatorSpec {
+  criteria: CriteriaSpec
+  executor: ExecutorSpec
+  isolation: IsolationSpec
+}
+
+export {}
+```
+
+**Why explicit dimensions instead of letting the user pass any function?** The spec forces the user, at start time, to declare what is judged, what executes the judgment, and what isolation boundary protects it. A free function looks flexible, but in practice it lets evaluator strength quietly regress—the user thinks they're doing a deterministic isolated check when they've actually written a same-workspace LLM judgment. In long-run scenarios the cost is hours wasted.
+
+Criteria shape, executor, and isolation are orthogonal rather than a trust ladder: a rubric may be checked by shell, an LLM, or an external service, and a contract may run in the same workspace or in a container. `llm-judge` remains the weakest executor for soft goals where there truly is no hard signal (revision, translation quality). The documentation explicitly notes "this executor cannot defend against targeted adversarial input; long unattended runs require at least one deterministic evaluator with an isolation boundary appropriate to the threat model".
+
+The driver enforces four structural constraints, not delegated to Evaluator implementations. Isolation strength remains an explicit property of the configured provider rather than a claim the driver can manufacture.
+
+**Preventing "the same agent both generates and self-evaluates"**:
+
+1. **fresh subagent for LLM evaluation**: an LLM evaluator opens a fresh subagent (via `dsh-subagent`'s `spawn`) each round, not inheriting the main loop's context
+
+**Preventing the evaluator subagent itself from being subverted**:
+
+2. **scoped tool set**: an LLM evaluator's model-facing tool set is stripped by the driver to reads only, with write tools disabled (reusing `SubagentProvider`'s `toolFilter`). This reduces accidental mutation but is not process isolation: shell, code runtimes, or another capability can still write unless the configured isolation boundary prevents it
+
+**Preventing the evaluator report itself from deceiving the driver**:
+
+3. **PASS can only flip via an evaluator report**: the `goal-met` StopCondition can only come from the evaluator; the driver and the main agent cannot construct it directly
+4. **Default-FAIL**: the driver maintains each criterion's pass state at `false` internally; only an evaluator report with non-empty evidence is allowed to flip it to `true`. The evaluator cannot get the driver to accept a `{pass: true}` return with no evidence
+
+Together, the four ensure that evaluator conclusions are structurally evidence-driven rather than confidence-driven. They do not stop the main agent from modifying evaluator inputs in a shared workspace.
+
+**Phase 1 ships three backends**:
+
+- `loop-evaluator-shell` implements `single-metric`: runs a shell command, `exit 0` = pass
+- `loop-evaluator-rubric-judge` implements `llm-judge`: a prewritten rubric plus LLM scoring, soft goals only
+- `loop-budget-preflight`: before each round starts, estimate `(promptTokens + overhead + estOutputTokens) / 1M × pricePerMTok`; refuse to start if the estimate exceeds `perRoundUsd`. The estimation model comes from MartinLoop `policy.ts:551-596`
+
+A `PricingProvider` service injects the pricing table; a test seam can override it, and it is not hardcoded into the driver (AGENTS.md "No hardcoded tunables in plugins"). A resolved budget carries `maxRounds`, optional `maxTokens` and `maxUsd`, and optional `perRoundUsd`. The driver checks per-round admission before starting work, then accumulates worker, evaluator, compaction, and reflector usage after every request. A token or USD cap may overrun by one in-flight request because usage arrives after completion; the `budget-cap` result reports `observed` and `maximum`. The `rubric` and `contract` criteria shapes get built-in executors in Phase 2; Phase 1 exposes the shapes so third-party plugins can integrate first.
+
+**Limitation**: `same-workspace` plus a read-only model-facing tool set is not hard isolation. The current `packages/fs` policy enforces read-before-edit and version guards, not path denial, and bash or code runtimes can bypass filesystem tools. Defending against targeted adversarial input requires a boundary across every mutation channel—such as a read-only mount, isolated worktree, container, or remote evaluator. The two-container approach (the evaluator's definition files are entirely inaccessible to the main agent, the route Anthropic patch.py takes) remains a Phase 3 item. See Risks.
+
+### Pluggable RoundHandoff
+
+How context passes between rounds is a dilemma. Preserving the full prior conversation (continue) reads more coherently, but the conversation keeps growing and eventually hits the context ceiling, and errors from a prior round contaminate every subsequent round. Starting each round from scratch (fresh) avoids the contamination, but has to re-understand context every time. A 3-round revision loop and an 80-round overnight bug-fix loop need opposite strategies. Claude Code and Codex both hardcode one mode, so users cannot switch by task type.
+
+Made a service seam:
+
+```ts
+interface ContinuationRun {
+  readonly id: string
+  resume?(prompt: string): Promise<ContinuationRun>
+}
+
+interface PreviousRound {
+  result: unknown
+  evaluator: { criteria: readonly { name: string; pass: boolean; evidence: readonly string[] }[] }
+  tokenUsage: number
+  summary: string
+  sessionId: string
+  run?: ContinuationRun
+}
+
+interface RoundContext { loopId: string; round: number; previous: PreviousRound }
+
+type NextRoundSpec =
+  | { mode: 'fresh'; prompt: string }
+  | { mode: 'continue'; run: ContinuationRun; prompt: string }
+
+interface RoundHandoff {
+  buildNextRound(prev: RoundContext, signal: AbortSignal): Promise<NextRoundSpec>
+}
+
+export {}
+```
+
+Phase 1 ships the fresh backend; Phase 2 adds the two continuation backends after provider continuation exists:
+
+| Backend | Phase | Scenario | Mechanism |
+|---|---|---|---|
+| `handoff-fresh-with-summary` (default) | Phase 1 | Long runs, unattended | Open a fresh subagent each round, injecting only a progress summary as a system prompt append |
+| `handoff-continue-with-compaction` (recommended middle) | Phase 2 | Medium length, 5–20 rounds | Retain the full conversation up to a token threshold; over the threshold, reuse [`packages/compact`](../../../../packages/compact/README.md) to compress into a summary, using summary + last K rounds as the starting point |
+| `handoff-continue-raw` (advanced) | Phase 2 | ≤5 rounds, short tasks, testing | Plain continuation without truncation |
+
+**Why default to fresh?** Every long-run loop that actually succeeded (repomirror, Kimi ralph-loop, autoresearch) uses fresh. Placing important loop state outside the context window under driver management is the correct posture for long runs. `handoff-continue-raw` violates this experience, and the README explicitly notes it is not suitable for long runs.
+
+**Why is only this repo able to build the middle tier?** `handoff-continue-with-compaction` depends on a compaction seam—the competitors don't have one; only this repo's `packages/compact` provides that infrastructure.
+
+**Why a seam rather than a three-choice flag?** Users can write 20-line plugins expressing hybrid strategies like "continue for the first 5 rounds, then fresh", or "auto-compact once when context hits 50%", without waiting for main-library support.
+
+**Limitation**: `continue-with-compaction` depends on the compression quality of `packages/compact`; compression itself may write hallucinated information into the summary and propagate it forward. The README recommends fresh for long runs. The three backends' boundaries may confuse new users about which to pick; the `dsh-sdk loop` CLI defaults to fresh, so users don't have to understand the differences before hitting a concrete problem.
+
+### Pluggable GoalReflector
+
+The goal the user gives at loop start is not always accurate. It may be based on a wrong assumption (asking the agent to implement a feature with a since-deprecated API), it may not be clear enough (the agent discovers a clarification is needed only mid-work), or it may be invalidated by later information. Current loop-execution frameworks treat the goal as a contract frozen at start; the agent can only push down the original path, and the result is exhausting the budget on the wrong direction.
+
+Phase 2 makes this a service seam, with responsibility separated from `Evaluator`: the evaluator asks "did we reach the goal", the reflector asks "is the goal still the same goal". Phase 1 carries concern events plus the `stop` and `notify-continue` driver policies without registering an unused `GoalReflector` service.
+
+```ts
+interface RoundContext { loopId: string; round: number }
+interface GoalConcern { concern: string; severity: 'low' | 'medium' | 'high' }
+
+interface GoalReflector {
+  reflect(ctx: RoundContext, concerns: GoalConcern[]): Promise<GoalReflection>
+}
+
+type GoalReflection =
+  | { kind: 'continue' }                              // goal 仍有效
+  | { kind: 'revise'; newGoal: string; why: string }  // 建议修正 goal
+  | { kind: 'stop-for-human'; reason: string }        // 需要人拍板
+
+export {}
+```
+
+**Concerns have three sources**. Phase 1 ships the first two; the `GoalReflector` service and periodic source arrive together in Phase 2:
+
+- **Agent-initiated**: via the model-facing tool `loop_flag_concern({ concern, severity })`. An agent that realizes during investigation that "the library the user assumed has been deprecated" can raise directly
+- **Driver heuristic**: when budget passes 50% and zero criteria have passed, the driver auto-raises a `no-progress-toward-goal` concern
+- **Periodic reflector subagent** (Phase 2): every N rounds, run an independent read-only subagent to re-audit goal validity, following the same isolation approach as the evaluator
+
+**Response strategy is controlled by the `onGoalConcern` config**. The four settings correspond to different philosophies about loop use; users choose by their team's collaboration style, and the driver takes no default stance:
+
+- `'stop'` (Phase 1 default): any concern triggers `StopCondition: approval-required`, and a human decides. A loop should never proceed on its own in the face of uncertainty—suitable for cautious teams and for high-impact loop scenarios
+- `'notify-continue'` (Phase 1): record an ordinary `loop/goal-concern` session event, then continue; a human reviews at the end. ACP has no general high-priority marker, so dedicated concern rendering is deferred with the ACP command infrastructure. The loop internal is not interrupted—suitable for unattended long runs
+- `'reflect'` (Phase 2): call `GoalReflector` to decide continue, revise, or stop. Delegates the initial judgment to an independent agent in place of a human—suitable for teams with moderate autonomy
+- Not registering a `GoalReflector` and leaving `onGoalConcern` unset = the most hands-off tier: the loop stops only on traditional stop conditions
+
+**Why default to `stop`?** In unattended scenarios, stopping one extra time is safer than running for hours in the wrong direction. Users who explicitly want unattended can switch to `notify-continue`.
+
+A concern is itself just an ordinary session event, composing naturally with the persistence capability described earlier: a later replay can seed a new conversation from the round where the concern surfaced and swap the goal. This does not roll the workspace back to that round.
+
+**Abuse and loss protection**. An agent could raise a concern every round; the mitigation is the `severity` field plus a minimal rate limit on the driver side (same-concern dedup within 30 seconds). The cost of that abuse is that the agent stalls itself and cannot make progress, so the incentive is weak. Once a goal has been revised, the original goal is lost; each revise persists a `loop/goal-revised` session event with rationale, and later replay can select any historical goal version without claiming workspace restoration.
+
+### User surface
+
+Four trigger surfaces share one driver:
+
+- **Agent-side tool**: `loop({ goal, evaluator, maxRounds, maxUsd, onGoalConcern })` registers `kind: 'loop'` through `ctx.tasks`, returns the task id immediately, and runs the harness loop in the background. `task_output`, `task_list`, and `task_kill` provide collection and cancellation. Inside a running loop, the internal agent can call `loop_flag_concern({ concern, severity })` to raise a concern proactively. ACP rendering intent is `generic`. An agent-initiated call is proactive triggering with no extra machinery
+- **CLI**: `dsh-sdk loop <prompt> --stop <shell-cmd> --max-rounds N --max-usd X --handoff fresh` is human-initiated startup, the most typical Ralph-style usage
+- **cordis leaf**: declare a resident loop as a leaf in `cordis.yml`, with future `dsh-schedule` RFC integration for periodic triggering
+- **ACP slash command**: `/loop <goal>` (and `/loop-flag-concern`) starts directly from within the editor or client's current session. Semantically equivalent to a human typing `dsh-sdk loop` in a shell, but happens within the ongoing ACP session context, letting the loop result inject back into the session
+
+The ACP slash command depends on: `packages/ui/acp`'s `available_commands_update` surface is currently unbuilt ([acp-feature-support.md](../../../../packages/ui/acp/acp-feature-support.md)). Once the harness's slash-command infrastructure lands, `/loop` and `/loop-flag-concern` only need to be registered against that infrastructure; the driver and tool interfaces do not change. This RFC reserves the names and specifies the argument shape, but does not commit the infrastructure itself—that belongs to a separate ACP catch-up RFC.
+
+The default system prompt carries two behavioral instructions, distributed with every built-in `loop` tool:
+
+1. No writing of `TODO`, `FAKE`, or `PLACEHOLDER` placeholders to superficially pass the evaluator
+2. No writing of empty `try/except` or `catch(_)` blocks so the evaluator ignores errors
+
+Neither can be enforced at the seam layer; both are prompt-layer guidance and must not be described as hard constraints. Users may customize the system prompt; evaluators that require these rules must check them explicitly.
+
+### Relationship with existing code
+
+Direct reuse without modification:
+
+- `packages/subagent`'s `spawn` provider, `toolFilter`, and `persona`—the loop spawns a subagent per round; an LLM evaluator gets a scoped model-facing tool set, not a process-isolation guarantee
+- `packages/tasks`—the model-facing loop is a `loop` task producer and reuses owner isolation, `task_output`/`task_list`/`task_kill`, completion notices, cancellation, and awaited cleanup
+- The SQLite backend from `packages/session-persistence`—the loop-session persists
+- `packages/session-query`—exact live and persisted session reads for post-hoc diagnosis
+- `packages/compact`—the implementation basis for `handoff-continue-with-compaction`
+- `packages/todo`—an optional progress representation in single-session continue mode
+- If [ToolExecution.reportProgress](2026-07-13-stream-workflow-progress-through-tool-calls.md) lands first, the loop tool can use it for per-round UI updates
+
+Not touched: `packages/core/agent-loop` (the inner-loop semantics stay the same); `packages/workflow` (DAG orchestration vs. iterating one goal is an orthogonal relationship; the two READMEs cross-link in their "Related" section to describe the boundary).
+
+One dependency is not yet landed:
+
+- The ACP slash-command infrastructure (the `available_commands_update` surface)—see User surface. Before the infrastructure lands, the slash-command trigger is absent while the other three trigger surfaces work as normal
+
+The proposed [SQLite FTS5 search](2026-07-10-sqlite-session-query-provider.md) is an optional Phase 2 discovery improvement over the existing exact-read query service, not a dependency for Phase 1 event access.
+
+Continuation work can be deferred to Phase 2: the `SubagentRun.sendMessage` and `resume` methods exist as optional seam capabilities, but the current `subagent-spawn` provider deliberately exposes neither. The two `handoff-continue-*` backends therefore require provider implementations, capability checks, ownership tests, and a consumer surface—not only a new argument on `packages/subagent-tool`. Phase 1 ships only `handoff-fresh-with-summary` and does not touch subagent continuation.
+
+### Phasing
+
+**Phase 1** (the scope this RFC commits): the three-package seam; `StopCondition`; the orthogonal criteria/executor/isolation `EvaluatorSpec`, with built-in implementations for shell and LLM-judge execution and rubric/contract criteria shapes open for integration; Default-FAIL enforcement; evaluator and cumulative-budget backends; `handoff-fresh-with-summary`; `ctx.tasks` integration; the `loop_flag_concern` tool; the no-progress heuristic; the `onGoalConcern: 'stop' | 'notify-continue'` pair; the CLI; the tool; and the default system-prompt guidance. **Not included**: the SQLite FTS5 search surface, the ACP slash-command trigger surface (depends on the `available_commands_update` infrastructure), subagent continuation provider/tool work, the `GoalReflector` service, the stuck detector, the Reflector subagent, the `loop_split` tool, and built-in executors for every rubric/contract combination.
+
+**Phase 2**: the SQLite FTS5 search surface; the stuck detector (reproducing OpenHands's five patterns); subagent continuation provider implementations, capability checks, and consumer surface (unlocking the two continue handoffs); the `GoalReflector` service and Reflector subagent; the `onGoalConcern: 'reflect'` tier; the `loop_split` model-facing tool; and built-in executors for additional rubric/contract combinations.
+
+**Phase 3**: agent fleet (N parallel loops for the same goal, best result wins); integration with `dsh-schedule`; two-container evaluator isolation (evaluator definition files entirely inaccessible to the main agent, defending against reward hacking).
+
+## Alternatives considered
+
+**Extend `packages/core/agent-loop`**: add an "iterate on end_turn until goal" switch to the inner loop. Rejected—AGENTS.md says "new behavior goes on documented extension seams; changing agent-loop requires updating docs/architecture.md". The harness loop needs state across sessions and across agents; stuffing it into the inner loop tangles session semantics into two mixed layers.
+
+**Ship a single slash command `/loop` (Claude Code clone)**: minimal implementation. Rejected—the slash-command layer does not resolve the harness/inner boundary; the four design points (queryable session, tiered evaluator, pluggable handoff, pluggable goal reflector) have nowhere to sit at the slash-command layer, and every capability this RFC commits is lost.
+
+**Fully outsource to `packages/workflow`**: express the loop as a workflow node with a back edge. Rejected—workflow lacks first-class semantics for iteration, StopCondition, and Evaluator; forcing it means the evaluator has to masquerade as a phase, violating the architectural-isolation requirement that the evaluator be independent of the producer; the budget guardrail in workflow is phase-level rather than round-level, and the granularities do not match.
+
+**Hardcode a binary choice between A (fresh) and B (continue)**: the Ralph school and the LoopTroop school each have strong scenarios. Rejected—Pluggable RoundHandoff proposes a seam plus three built-in backends that cover both schools and allow hybrids.
+
+**Skip the evaluator seam, ship a few built-ins**: lighter. Rejected—the core value of Pluggable Evaluator and Budget is that team-private evaluators can extend the system. Hardcoding leaves long unattended users no option but to modify the main library.
+
+**Accept a free function that lacks an explicit `EvaluatorSpec`**: allow users to pass any `(result) => boolean`. Rejected—the criteria/executor/isolation dimensions force users to declare at start time what is judged, what runs the judgment, and what boundary protects it, preventing quiet regression to a weaker setup. A free function looks flexible but lets evaluator strength quietly regress, and the cost is heavy in long-run scenarios.
+
+**Introduce an independent memory engine (Beads / dex-style)**: an established approach to external state. Rejected—`packages/session-persistence` plus the existing exact-read `ctx.sessionQuery` already cover Phase 1 diagnosis, while SQLite FTS5 can add search later; the payoff of a new engine is far smaller than the maintenance cost.
+
+**Fold goal reflection into the Evaluator seam** (have the evaluator return "criteria are impossible"): rejected—it conflates "was the goal achieved" with "is the goal still correct", which are orthogonal concerns. `Evaluator` should stay independent, read-only, and simple.
+
+**Only ever add an event for goal-concern, no seam**: lighter. Phase 1 does use the event plus `stop`/`notify` policies; rejected as the final design because the Phase 2 `reflect` path needs a replaceable response strategy. The seam lands with that first caller rather than ahead of it.
+
+**Ship the full Reflector subagent in Phase 1**: more complete. Rejected—`loop_flag_concern` tool plus no-progress heuristic plus the two-policy `onGoalConcern` already covers 80% of scenarios; running an independent subagent every round is expensive, and introducing it on demand in Phase 2 is more sensible.
+
+**Do not ship `loop_split`; let users split themselves**: Phase 1 already does. Phase 2 adds it because long-run scenarios reveal that agents receiving an oversized goal will run it directly rather than split it, so explicit tool guidance is needed.
+
+## Acceptance criteria
+
+- The three packages `packages/loop/{loop,loop-driver,loop-tool}` are built as a capability seam; `dsh-loop` exports only types and registry
+- `StopCondition` discrimination covers all branches (unit); `assertNever` closes the switch at compile time
+- The Phase 1 services `Evaluator`, `BudgetPolicy`, and `RoundHandoff` can each be replaced by an external plugin (fixture: inject a mock implementation, driver calls it correctly); no `GoalReflector` service is registered before the Phase 2 `reflect` consumer exists
+- `EvaluatorSpec`'s criteria/executor/isolation dimensions converge at compile time; the driver refuses to start a loop without a paired evaluator (fixture: `loop({ goal, evaluator: undefined })` returns a configuration error immediately)
+- Default-FAIL fixture: when the evaluator report returns `{criterion, pass: true, evidence: []}`, the driver refuses that criterion flip and records an `evaluator/invalid-report` session event
+- `RoundHandoff` receives the previous result, evaluator report, token usage, summary, session id, optional run handle, and cancellation signal; Phase 1's `fresh-with-summary` has unit coverage plus one pass-path e2e, while continuation backend tests wait for Phase 2 provider support
+- `dsh-sdk loop` CLI e2e: given a goal plus a 3-round cap plus one shell evaluator, both the pass and exhaustion paths return a structured stop cause with a semantic exit code
+- Evaluator scoping fixture: the main agent has fs.write while an LLM evaluator's model-facing tool set does not; the result and documentation still label `same-workspace` as non-isolated, and no `protectedPaths` guarantee is exposed
+- Budget fixtures cover `perRoundUsd` admission plus cumulative `maxRounds`, `maxTokens`, and `maxUsd` across worker and evaluator usage; an in-flight overrun emits `budget-cap` with `observed` and `maximum`
+- Goal concern fixture: `loop_flag_concern` is callable from the main agent and yields an ordinary `loop/goal-concern` session event; under `onGoalConcern: 'stop'` an `approval-required` StopCondition is emitted; under `'notify-continue'` the loop continues without nonexistent ACP priority metadata; the no-progress heuristic fires once when budget exceeds 50% with zero passes (with rate-limit dedup)
+- The default system-prompt guidance (no TODO/FAKE/PLACEHOLDER, no empty catch) is distributed with the built-in `loop` tool, and a snapshot covers the prompt content without treating it as enforcement
+- Each round's prompt, inner-loop result, evaluator report, and stop decision appear as session events and are readable through the existing exact-read `ctx.sessionQuery`; FTS5 search remains Phase 2
+- Model-facing loop startup returns a `loop` task id immediately; `task_output`, `task_list`, `task_kill`, parent-agent disposal, cancellation, producer reload, and service disposal cover owner isolation and awaited quiescence
+- The "Related" sections in `packages/loop/README.md` and `packages/workflow/README.md` cross-link and describe the "when to use workflow vs. when to use loop" boundary clearly
+- Unit 100% / snapshot / e2e / doc-sync / verify-module-graph / build / hygiene all green; the ACP rendering intent (`generic`) of the new tool has a snapshot
+
+## Risks
+
+**Conversation replay is not workspace restore**. Exact session reads already exist, and FTS5 improves historical discovery rather than enabling correctness. Replaying a round prefix against the current workspace can diagnose or redirect a run, but reproducing the execution world at that round requires Git/worktree/checkpoint support and an explicit policy for external side effects.
+
+**The boundary between `packages/workflow` and loop is a recurring FAQ**. "Is multi-round a loop or a workflow?"—both READMEs must state clearly: workflow is "steps known, agent to run undecided, parallel or serial orchestration"; loop is "agent decided, round count undecided, evaluator decides when to stop". Unclear docs cause users to pick the wrong one.
+
+**Evaluator reverse-optimization (reward hacking)**. In a sufficiently long loop, the agent can identify the evaluator's pattern and optimize against it—for example, discovering that "as long as `assert True` appears in a test file, it PASSes" and bypassing real completion that way. Phase 1's `same-workspace` mode does not prevent the agent from modifying tests or evaluator configuration through bash, code runtimes, or another write channel; the current `packages/fs` policy is not a path-isolation boundary. Users needing adversarial strength must choose an isolated worktree, read-only mount, container, or remote evaluator. Phase 3's two-container approach keeps the evaluator runtime (binary, rubric, dependency libraries) entirely inaccessible to the main agent, matching what Anthropic patch.py does.
+
+**Placeholder faking and over-defensive code**. Agents sometimes write `# TODO: implement` to sneak through a test, or write large amounts of `try/except: pass` to make the evaluator superficially PASS. These do not belong to the evaluator layer; they are prompt and training issues at the agent-generation stage. The two default system-prompt instructions in User surface are guidance only; users who add "static-check-forbid TODO and empty catch" rules to a custom evaluator get enforceable coverage. This class of problem cannot be cured at the seam layer.
+
+**Budget estimation drift and in-flight overrun**. Pricing can change, and cumulative token/USD usage becomes exact only after each worker, evaluator, compaction, or reflector request reports usage. Preflight protects a single round; cumulative caps stop the next request and may exceed the configured maximum by one in-flight request. The README reports both observed and maximum values and states that provider billing remains authoritative.
+
+**Background tasks are process-local**. `ctx.tasks` gives the model-facing loop owner isolation, generic collection/cancellation, completion notices, and awaited cleanup. Parent-agent or service disposal cancels and awaits the loop; a process crash cannot run cleanup, and durable restart remains outside Phase 1.
+
+**Long-run loop log growth**. A 100-round loop reaches MB scale for one session. `logDetail: 'summary'` is a safety net but Phase 1 defaults to `full`; Phase 2 adds summary semantics.
+
+**Pre-release allows direct evolution**. `SESSION_FORMAT_VERSION=0`; the `LoopRoundEvent` schema can change at any time. Backends reject old formats rather than maintain compatibility, matching the pre-release stance at the top of AGENTS.md.
diff --git a/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.zh.md b/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.zh.md
new file mode 100644
index 0000000000..6460254b07
--- /dev/null
+++ b/.agents/notes/proposed/feature/2026-07-16-harness-level-loop.zh.md
@@ -0,0 +1,343 @@
+# Agent Note: harness 层 goal-based loop
+
+Status: proposed
+
+[English](2026-07-16-harness-level-loop.md) | 中文
+
+## 问题
+
+`packages/core/agent-loop` 只跑 inner loop：一次 turn 内推理加工具循环，模型返回 `end_turn` 就结束。其 README 明确写「No built-in turn budget」——预算是它自己承认的 gap。跨轮次调度落在 harness 层：跑到测试全绿、按 rubric 反复改稿、把 PRD 拆成 bead 逐个推进、无人值守跑一整晚。这几类任务今天都没有一等公民的实现。
+
+现有代码里有三种「能凑合跑」的替代，都不够用：
+
+| 替代 | 问题 |
+|---|---|
+| `packages/workflow` 脚本表达 `while (!done)` | README 明写「No token-budget vocabulary」和「No journaling or resume」；父 turn 阻塞到脚本 settle。能跑几分钟的编排，跑不了几小时的长期任务 |
+| 外部 shell `while :; do dsh-sdk …; done` | Ralph 风格的调度今天就能这么写。缺共享的 stop condition、budget、evaluator 词汇，每个使用者各自重发明；循环本身没有持久化对象可供事后诊断或恢复 |
+| `packages/subagent` seam 的 `sendMessage`/`resume` | README 明写「Runtime steering and continuation are seam-only capabilities」。没有 model-facing consumer，模型只能起 fresh 子会话 |
+
+典型使用场景有三类。**自动化修复**：面前一个失败的测试套件，希望一个进程持续修改代码、跑测试、根据失败信息再修改，直到全绿或触达预算上限。**按 rubric 迭代改稿**：一份文档、代码或翻译需要满足打分标准，循环反复调整、独立评估者打分、直到达标或耗尽轮数。**无人值守长跑**：例如通宵把一个仓库从一种技术栈移植到另一种，下班前启动第二天回来看结果，全程只有预算兜底。三类共同的形态：几分钟到几小时、evaluator 决定成败、预算是硬约束、跑完还需要能回看和恢复。
+
+## 提案
+
+**Loop 有四种触发形态**，按谁在什么时候启动一轮划分：
+
+| 形态 | 谁触发 | 何时触发 | 现有对标 | 本 RFC |
+|---|---|---|---|---|
+| **turn-based** | 用户在会话里发一条消息 | 每一轮用户回复 | `packages/core/agent-loop` 现有一次 turn 内的推理与工具循环 | 不覆盖，已有实现 |
+| **goal-based** | 用户或 agent 明确指定「跑到某条件为止」 | 一次启动，evaluator 判停 | Claude Code 的 `/goal`、Codex 的 `/goal`、Ralph 家族 | **本 RFC 覆盖** |
+| **time-based** | scheduler | 按 cron 或时间间隔 | Claude Code 的 `/loop`（周期性）、`/schedule` | 延后到 `dsh-schedule` RFC |
+| **proactive** | agent 自己 | agent 在推理中意识到需要开一个 loop 时 | Anthropic ClaudeDevs 4 类分类里的 proactive 档 | **本 RFC 自然包含**（agent 调 `loop` tool 就是 proactive） |
+
+本 RFC 只**新增 capability seam `packages/loop/`** 处理 goal-based 一种。proactive 复用同一 `loop` tool，agent 主动调用即触发，无需额外机制。time-based 需要独立的 scheduler package，属于另一份 RFC 的事情；本 RFC 只在 cordis leaf 触发面预留跟未来 `dsh-schedule` 联动的钩子。
+
+三个包：
+
+- `@deepseek-ai/dsh-loop`：类型、`LoopDriver` service、`StopCondition` 判别联合、Phase 1 service 定义（`Evaluator` / `BudgetPolicy` / `RoundHandoff`）、事件 schema；`GoalReflector` 在 Phase 2 与首个调用方一起加入
+- `@deepseek-ai/dsh-loop-driver`：默认 driver 实现
+- `@deepseek-ai/dsh-loop-tool`：model-facing `loop` tool + CLI `dsh-sdk loop`
+
+设计围绕四个具体问题展开，在每项能力出现调用方的 phase 中通过 service seam 或显式 driver policy 解决：
+
+1. 长跑 loop 出问题后缺诊断和恢复手段。**loop 作为独立 session** 解决。
+2. loop 结束时的 PASS 是否可信决定几小时工作是否作废。同一个 LLM 既生成又自评的架构本身就不可信。**Evaluator 与 Budget 做成 service seam** 解决。
+3. 短任务和长任务需要的记忆策略相反，硬编一种模式会让另一类场景不可用。**RoundHandoff 做成 service seam** 解决。
+4. 用户初始给的 goal 未必始终正确。agent 沿着错的目标蛮干会耗尽预算做错事。**Phase 1 用 goal concern event 与 policy 处理；GoalReflector service 随 Phase 2 的 `reflect` 路径一起加入**。
+
+四条 seam 之外还有一条贯穿全文的原则：**一个 loop 只处理一个原子目标**。大目标拆成若干小 loop 串联，不塞进一个 loop 让 evaluator 判定多件事。判定 granularity 是否合适的经验规则：如果 loop 跑完说不清它到底做完了什么，granularity 就太大，应当拆。Phase 2 补 `loop_split` model-facing tool 让 agent 收到过大 goal 时能自己拆。
+
+术语约定：**inner loop** 指 `packages/core/agent-loop` 一次 turn 的推理与工具循环；**harness loop** 指本 RFC 引入的外层调度器，围绕 inner loop 反复迭代。本 RFC 不改 `agent-loop`，符合 AGENTS.md「Plugins, not loop changes」。
+
+`StopCondition` 是 discriminated union，`assertNever` 收口：
+
+```ts
+interface EvaluatorReport { criteria: readonly { name: string; pass: boolean; evidence: readonly string[] }[] }
+
+type StopCondition =
+  | { kind: 'goal-met'; evidence: EvaluatorReport }
+  | { kind: 'budget-cap'; scope: 'usd' | 'tokens' | 'rounds'; observed: number; maximum: number }
+  | { kind: 'stuck'; pattern: 'repeat-action' | 'no-progress' | 'error-loop' }
+  | { kind: 'approval-required'; reason: string }
+  | { kind: 'user-cancel' }
+
+export {}
+```
+
+### Loop 作为独立 session
+
+长跑 loop 一旦出错，用户没有系统的诊断手段。跑几小时后失败，只能翻散落的日志文件。发现中间某一轮走偏想倒回去重跑，只能从头开始。agent 想参考自己过去 loop 的经验也没有可用的 API。
+
+Driver 为每个 loop 开一个独立的 loop-session（新的 session id）。每轮的输入、inner-loop 结果、evaluator 报告、stop 决策都作为 session event 落盘，复用 `packages/session-persistence` 的 SQLite backend。得到三种诊断与 replay 能力。
+
+- **从已记录轮次 replay 对话**：源 session 仍 live 时，发现第 78 轮偏航，可以 fork 第 77 轮的 event prefix，换 prompt 或 evaluator；已持久化 session 的 replay 还需要独立的受信任 load-and-seed 路径。两者都只会基于当前工作区 replay 对话状态，不会恢复第 77 轮的文件与外部副作用
+- **事后诊断**：通过现有 `ctx.sessionQuery` 精确读取 service 检查 evaluator 从哪一轮开始一直挂在同条 criterion 上
+- **元循环学习**：拟议中的 [SQLite FTS5 search](2026-07-10-sqlite-session-query-provider.md) 后续可以在新 loop 启动前找到相关历史 loop——「我以前 fix 过类似的 bug 吗？失败在哪一轮？」
+
+Claude Code、Codex 的 `/goal` 是一次性对象：跑完就丢，agent 下次遇到同类问题从零开始。
+
+**存储与恢复边界**。每轮几 KB events，100 轮 loop 约 100–500 KB；跑几千个 loop 会到 GB 级。`logDetail: 'summary' | 'full'` 配置缓解，默认 `full`，长跑用户可切 `summary`。中间态全持久化会把生成过的 key、密码一并落盘，跟普通 session 是同一类风险但量放大 10–100 倍，README 明确提示。通过 `ctx.sessionQuery` 的精确 live 与已持久化读取已经存在；FTS5 是可选的发现能力增强，不是 Phase 1 依赖。本 RFC 不承诺精确恢复执行世界：`SessionStore.fork()` 只接受 live session，而 session event 不会恢复文件、进程、环境或外部副作用。这需要单独的 Git/worktree/checkpoint 设计。
+
+### 可插拔的 Evaluator 与 Budget
+
+loop 的价值最终取决于结束时的 PASS 是否可信。如果 evaluator 会被 hack 或幻觉 PASS，前面几小时的工作全部作废。同一个 LLM 既生成又自评的架构本身就不可信：模型有条件说服自己 PASS。即便让独立 subagent 做 evaluator，只要 evaluator 还是 LLM，就仍然对同类内容有系统性偏好——独立 subagent 只是缓解不是根治。
+
+可信评估同时需要确定性的判断机制，以及与 threat model 匹配的隔离边界：shell exit code、静态分析或外部服务避免 LLM 自评；独立 worktree、只读 mount、容器或远程服务防止 worker 改写 evaluator 输入。具体检查和边界只有用户知道：不同项目 `pytest` 命令不同、公司有私有合规检查器、有些团队还要跑内部 lint。主库无论内置几种都覆盖不全。所以 evaluator 必须做成用户可以自己接入的 seam。
+
+预算方面同理：产品级的花费护栏是黑盒，无法按团队策略调整（个人卡、团队分摊、按 PR 结算）。
+
+`Evaluator` 和 `BudgetPolicy` 都作为 cordis service seam 暴露。`Goal` 必须携带一个明确档位的 `EvaluatorSpec`，driver 拒绝启动没有 evaluator 配对的 loop——含糊的目标（"把代码写好"）不能进入 loop 系统：
+
+```ts
+interface RubricItem { name: string; description: string }
+interface EvaluatorContract { readonly name: string }
+
+type CriteriaSpec =
+  | { kind: 'single-metric'; name: string }
+  | { kind: 'rubric'; criteria: RubricItem[] }
+  | { kind: 'contract'; interface: EvaluatorContract }
+
+type ExecutorSpec =
+  | { kind: 'shell'; command: string }
+  | { kind: 'llm-judge'; rubric: string; model: string }
+  | { kind: 'provider'; name: string; config?: unknown }
+
+type IsolationSpec = 'same-workspace' | 'separate-worktree' | 'container' | 'remote'
+
+interface EvaluatorSpec {
+  criteria: CriteriaSpec
+  executor: ExecutorSpec
+  isolation: IsolationSpec
+}
+
+export {}
+```
+
+**为什么使用显式维度，而不是让用户传自由函数？** spec 强制用户在启动时声明评估什么、由什么执行判断，以及什么隔离边界保护它。自由函数看起来灵活，实际让 evaluator 强度隐性下沉——用户以为在做确定性隔离检查，实际写的是同工作区 LLM 判断。长跑场景下代价是几小时白跑。
+
+criteria shape、executor 与 isolation 是三个正交维度，不是可信度阶梯：rubric 可以由 shell、LLM 或外部服务检查，contract 也可以在同一工作区或容器中运行。`llm-judge` 仍是最弱的 executor，仅用于确实无硬信号的软目标（改稿、翻译质量）。文档明确标注「此 executor 不能挡定向对抗，长跑无人值守场景至少需要一个确定性 evaluator，并配合与 threat model 匹配的隔离边界」。
+
+Driver 强制四条结构约束，不下放给 Evaluator 实现。隔离强度仍是已配置提供方的显式属性，不是 driver 能凭空制造的保证。
+
+**防「同一个 agent 既生成又自评」**：
+
+1. **LLM 评估使用 fresh subagent**：LLM evaluator 每轮开 fresh subagent（用 `dsh-subagent` 的 `spawn`），不继承主循环 context
+
+**防 evaluator subagent 自身被 subverted**：
+
+2. **限制模型可见工具集**：LLM evaluator 的 model-facing tool set 被 driver 剥离到只保留读类工具，写类工具禁用（复用 `SubagentProvider` 的 `toolFilter`）。这会减少意外修改，但不是进程隔离：除非已配置隔离边界拦截，否则 shell、代码运行时或其他 capability 仍能写入
+
+**防 evaluator 报告本身欺骗 driver**：
+
+3. **PASS 只能由 evaluator 报告翻转**：`goal-met` StopCondition 只能来自 evaluator，driver 或主 agent 都不能直接构造
+4. **Default-FAIL**：driver 内部维护每个 criterion 的 pass 状态默认 `false`，只有 evaluator 报告里带非空 evidence 才允许翻 `true`；evaluator 无法通过返回 `{pass: true}` 而不给 evidence 让 driver 接受
+
+四条一起保证 evaluator 结论在结构上由证据推动，而不是由自信推动。它们不能阻止主 agent 在共享工作区中修改 evaluator 输入。
+
+**Phase 1 内置三个 backend**：
+
+- `loop-evaluator-shell` 实现 `single-metric`：跑 shell 命令，`exit 0` = pass
+- `loop-evaluator-rubric-judge` 实现 `llm-judge`：预写 rubric + LLM 打分，仅软目标
+- `loop-budget-preflight`：每轮启动前估 `(promptTokens + overhead + estOutputTokens) / 1M × pricePerMTok`，超 `perRoundUsd` 拒绝启动。估算模型来自 MartinLoop `policy.ts:551-596`
+
+`PricingProvider` 服务注入 pricing 表，test seam 可覆盖，不硬编到 driver 里（AGENTS.md「No hardcoded tunables in plugins」）。解析后的 budget 携带 `maxRounds`、可选 `maxTokens` 与 `maxUsd`，以及可选 `perRoundUsd`。driver 在启动工作前检查单轮准入，随后在每次请求后累计 worker、evaluator、compaction 和 reflector 用量。token 或 USD 上限可能被一个在途请求超出，因为 usage 在完成后才到达；`budget-cap` 结果同时报告 `observed` 与 `maximum`。`rubric` 与 `contract` criteria shape 在 Phase 2 补内置 executor，Phase 1 暴露这些 shape 让第三方插件先接。
+
+**局限**：`same-workspace` 加只读 model-facing tool set 不是硬隔离。当前 `packages/fs` policy 实施 read-before-edit 与版本保护，不是路径拒写；bash 或代码运行时可以绕过 filesystem tool。挡定向对抗需要覆盖所有写入通道的边界，例如只读 mount、隔离 worktree、容器或远程 evaluator。两容器方案（evaluator 定义文件对主 agent 完全不可访问，Anthropic patch.py 走的就是这条路）仍在 Phase 3。见 风险。
+
+### 可插拔的 RoundHandoff
+
+每轮之间如何传递 context 是一个两难。完整保留之前对话（continue）连续性好，但对话会持续增长最终撞上 context 上限，且上一轮的错误信息会污染后续每一轮。每轮从零开始（fresh）避免污染，但每次需要重新理解上下文。跑 3 轮改稿与跑 80 轮 overnight 修 bug 需要的策略是相反的。Claude Code、Codex 都硬编一种模式，用户没法按任务类型切换。
+
+做成 service seam：
+
+```ts
+interface ContinuationRun {
+  readonly id: string
+  resume?(prompt: string): Promise<ContinuationRun>
+}
+
+interface PreviousRound {
+  result: unknown
+  evaluator: { criteria: readonly { name: string; pass: boolean; evidence: readonly string[] }[] }
+  tokenUsage: number
+  summary: string
+  sessionId: string
+  run?: ContinuationRun
+}
+
+interface RoundContext { loopId: string; round: number; previous: PreviousRound }
+
+type NextRoundSpec =
+  | { mode: 'fresh'; prompt: string }
+  | { mode: 'continue'; run: ContinuationRun; prompt: string }
+
+interface RoundHandoff {
+  buildNextRound(prev: RoundContext, signal: AbortSignal): Promise<NextRoundSpec>
+}
+
+export {}
+```
+
+Phase 1 交付 fresh backend；Phase 2 在 provider continuation 存在后增加两个 continuation backend：
+
+| Backend | Phase | 场景 | 机制 |
+|---|---|---|---|
+| `handoff-fresh-with-summary`（默认） | Phase 1 | 长跑、无人值守 | 每轮开 fresh subagent，只注入一段 progress 摘要作 system prompt 附加段 |
+| `handoff-continue-with-compaction`（推荐中间档） | Phase 2 | 5–20 轮的中等长度 | 整段对话保留到 token 阈值，超了复用 [`packages/compact`](../../../../packages/compact/README.md) 压缩，摘要 + 最近 K 轮作起点 |
+| `handoff-continue-raw`（专业档） | Phase 2 | ≤5 轮短任务、测试 | 纯连续对话不裁剪 |
+
+**为什么默认 fresh？** 所有实际跑成的长跑 loop（repomirror、Kimi ralph-loop、autoresearch）用的都是 fresh。把重要 loop 状态放在 context window 外由 driver 管理是长跑的正确姿势。`handoff-continue-raw` 违反这条经验，README 明写长跑不适用。
+
+**为什么中间档只有我们能做？** `handoff-continue-with-compaction` 依赖 compaction seam——竞品都没有，只有本仓库 `packages/compact` 提供了这个基础设施。
+
+**为什么做成 seam 而不是三选一 flag？** 用户可以写 20 行插件表达「前 5 轮 continue、之后 fresh」这类混合策略，或表达「context 到 50% 自动 compact 一次」，不用等主库支持。
+
+**局限**：`continue-with-compaction` 依赖 `packages/compact` 的压缩质量，压缩本身可能把幻觉信息写进摘要传下去；README 建议长跑首选 fresh。三个 backend 的边界会让新用户不知道选哪个；`dsh-sdk loop` CLI 默认用 fresh，用户在遇到具体问题前不需要理解这些差别。
+
+### 可插拔的 GoalReflector
+
+用户在启动 loop 时给的目标不一定准确。可能基于错误假设（让 agent 用某个已经废弃的 API 实现功能），可能不够清晰（agent 在做的过程中才发现需要澄清），也可能被后来的信息证伪。现在的循环执行框架把 goal 当作启动时冻结的合约，agent 只能沿着原路蛮干，结果是在错的方向上耗尽预算。
+
+Phase 2 把它做成 service seam，与 `Evaluator` 职责分离：evaluator 问「是否达成目标」，reflector 问「目标是否还是那个目标」。Phase 1 只携带 concern event，以及 `stop` 与 `notify-continue` driver policy，不注册没有调用方的 `GoalReflector` service。
+
+```ts
+interface RoundContext { loopId: string; round: number }
+interface GoalConcern { concern: string; severity: 'low' | 'medium' | 'high' }
+
+interface GoalReflector {
+  reflect(ctx: RoundContext, concerns: GoalConcern[]): Promise<GoalReflection>
+}
+
+type GoalReflection =
+  | { kind: 'continue' }                              // goal 仍有效
+  | { kind: 'revise'; newGoal: string; why: string }  // 建议修正 goal
+  | { kind: 'stop-for-human'; reason: string }        // 需要人拍板
+
+export {}
+```
+
+**concern 有三种触发来源**。Phase 1 实现前两种；`GoalReflector` service 与周期性来源一起在 Phase 2 加入：
+
+- **agent 主动**：通过 model-facing tool `loop_flag_concern({ concern, severity })`。agent 在调研中意识到「用户假设的那个库已经废弃」时可以直接 raise
+- **driver 启发式**：预算过 50% 且零 criterion pass 时，driver 自动 raise `no-progress-toward-goal` concern
+- **周期性 reflector subagent**（Phase 2）：每 N 轮独立跑一个只读 subagent 复审 goal 有效性，与 evaluator 独立性遵循同一思路
+
+**响应策略通过 `onGoalConcern` 配置项**。这四种配置对应不同的 loop 使用哲学，用户按团队协作方式选，driver 不预设立场：
+
+- `'stop'`（Phase 1 默认）：任何 concern 都触发 `StopCondition: approval-required`，人拍板。loop 在遇到任何不确定性时都不应自己往下走，适合谨慎风格团队与影响面较大的 loop 场景
+- `'notify-continue'`（Phase 1）：记录普通 `loop/goal-concern` session event 后继续跑，人在结束时集中审阅。ACP 没有通用高优先级 marker，因此专用 concern 渲染与 ACP command 基础设施一起后置。loop 内部不打扰，适合无人值守长跑
+- `'reflect'`（Phase 2）：调 `GoalReflector` 决定 continue、revise 还是 stop。委派一个独立 agent 代替人做初步判断，适合中等自主度的团队
+- 不注册 `GoalReflector` 且 `onGoalConcern` 未设 = 最放手档，loop 只在传统 stop condition 触发时停
+
+**为什么默认选 `stop`？** 无人值守场景下宁可多停一次也不要在错方向上跑几小时。用户明确要无人值守可切 `notify-continue`。
+
+concern 本身就是普通 session event，跟前文的持久化 session 能力天然协同：后续 replay 可以从 concern 出现的轮次为新对话提供 seed，并替换 goal。这不会把工作区回滚到该轮。
+
+**滥用与丢失防护**。agent 可能每轮都 raise concern；缓解是 `severity` 字段和 driver 侧的最小 rate limit（同一 concern 30 秒内去重）。这种滥用的代价是 agent 卡住自己无法推进，动机不强。goal 被 revise 后原始 goal 会丢失；每次 revise 落 `loop/goal-revised` session event 带 rationale，后续 replay 可选任意历史 goal 版本，但不承诺恢复工作区。
+
+### 用户面
+
+四个触发面共享同一个 driver：
+
+- **agent 侧 tool**：`loop({ goal, evaluator, maxRounds, maxUsd, onGoalConcern })` 通过 `ctx.tasks` 注册 `kind: 'loop'`，立即返回 task id，并在后台运行 harness loop。`task_output`、`task_list` 和 `task_kill` 负责收集与取消。正在跑的 loop 内部 agent 可用 `loop_flag_concern({ concern, severity })` 主动发起 concern。ACP 渲染意图为 `generic`。agent 自主发起就是 proactive 触发，无需额外机制
+- **CLI**：`dsh-sdk loop <prompt> --stop <shell-cmd> --max-rounds N --max-usd X --handoff fresh`。人类主导启动，最典型的 Ralph 风格用法
+- **cordis leaf**：`cordis.yml` 里以 leaf 形式声明常驻循环，配合未来的 `dsh-schedule` RFC 可做周期性触发
+- **ACP slash command**：`/loop <goal>`（还有 `/loop-flag-concern`）在编辑器/客户端的当前会话里直接启动。语义等价于人类在 CLI 里敲 `dsh-sdk loop`，但发生在正在进行的 ACP session 上下文中，允许 loop 结果直接注入会话
+
+ACP slash command 的依赖：`packages/ui/acp` 的 `available_commands_update` 面目前是 unbuilt 状态（[acp-feature-support.md](../../../../packages/ui/acp/acp-feature-support.md)）。等 harness 的 slash command 基础设施落地，`/loop` 与 `/loop-flag-concern` 只需在该基础设施里注册；driver 与 tool 接口不变。本 RFC 保留名字并给出参数 shape，但不承诺基础设施本身——那属于独立的 ACP 补齐 RFC。
+
+默认 system prompt 里有两条行为指令，随所有内置 `loop` tool 一起分发：
+
+1. 不允许写 `TODO`、`FAKE`、`PLACEHOLDER` 占位符让 evaluator 表面通过
+2. 不允许写空的 `try/except` 或 `catch(_)` 让 evaluator 忽略错误
+
+这两条无法在 seam 层强制，只是 prompt 层 guidance，不能描述成硬约束。用户可以自定义 system prompt；需要强制这些规则的 evaluator 必须显式检查。
+
+### 与仓库现有代码的关系
+
+直接复用无需修改：
+
+- `packages/subagent` 的 `spawn` provider、`toolFilter`、`persona`——loop 每轮起 subagent；LLM evaluator 获得受限的 model-facing tool set，不获得进程隔离保证
+- `packages/tasks`——model-facing loop 是 `loop` task producer，复用 owner isolation、`task_output`/`task_list`/`task_kill`、完成通知、取消和 awaited cleanup
+- `packages/session-persistence` 的 SQLite backend——loop-session 落盘
+- `packages/session-query`——精确读取 live 与已持久化 session，用于事后诊断
+- `packages/compact`——`handoff-continue-with-compaction` 的实现基础
+- `packages/todo`——单会话 continue 模式下作为可选 progress 表达
+- 若 [ToolExecution.reportProgress](2026-07-13-stream-workflow-progress-through-tool-calls.md) 先落地，loop tool 可用它逐轮 UI 更新
+
+不动：`packages/core/agent-loop`（inner loop 语义保持）；`packages/workflow`（DAG 编排 vs. 迭代同 goal 是 orthogonal 关系，两个 README 在「Related」段互链说明边界）。
+
+依赖尚未落地的一处：
+
+- ACP slash command 基础设施（`available_commands_update` 面）——见 用户面。基础设施落地前，slash command 触发面缺席，其它三个触发面照常工作
+
+拟议中的 [SQLite FTS5 search](2026-07-10-sqlite-session-query-provider.md) 是现有 exact-read query service 之上的可选 Phase 2 发现能力增强，不是 Phase 1 event 访问的依赖。
+
+Continuation 工作可以延后到 Phase 2：`SubagentRun.sendMessage` 与 `resume` 方法作为可选 seam capability 存在，但当前 `subagent-spawn` provider 明确不暴露这两个方法。因此，两个 `handoff-continue-*` backend 需要 provider 实现、capability check、ownership 测试和 consumer surface，不只是给 `packages/subagent-tool` 增加参数。Phase 1 只交付 `handoff-fresh-with-summary`，不改 subagent continuation。
+
+### 分阶段
+
+**Phase 1**（本 RFC 承诺范围）：三包 seam；`StopCondition`；criteria／executor／isolation 三个正交维度的 `EvaluatorSpec`，其中 shell 与 LLM-judge execution 有内置实现，rubric／contract criteria shape 开放待接；Default-FAIL 强制；evaluator 与累计 budget backend；`handoff-fresh-with-summary`；`ctx.tasks` 集成；`loop_flag_concern` tool；no-progress 启发式；`onGoalConcern: 'stop' | 'notify-continue'` 二档；CLI；tool；默认 system prompt guidance。**不含**：SQLite FTS5 search 面、ACP slash command 触发面（依赖 `available_commands_update` 基础设施）、subagent continuation provider/tool 工作、`GoalReflector` service、stuck 检测器、Reflector subagent、`loop_split` tool，以及每种 rubric／contract 组合的内置 executor。
+
+**Phase 2**：SQLite FTS5 search 面；stuck 检测器（复现 OpenHands 5 种模式）；subagent continuation provider 实现、capability check 与 consumer surface（解锁两个 continue handoff）；`GoalReflector` service 与 Reflector subagent；`onGoalConcern: 'reflect'` 档；`loop_split` model-facing tool；更多 rubric／contract 组合的内置 executor。
+
+**Phase 3**：agent fleet（同 goal 派 N 个并行 loop 取最优）；与 `dsh-schedule` 集成；两容器 evaluator 隔离（evaluator 定义文件对主 agent 完全不可访问，防 reward 反向优化）。
+
+## 备选方案
+
+**扩 `packages/core/agent-loop`**：给 inner loop 加「iterate on end_turn until goal」开关。拒绝——AGENTS.md「新行为走文档化扩展 seam；改 agent-loop 需要更新 docs/architecture.md」。harness loop 需要跨 session、跨 agent 的状态，塞进 inner loop 会把 session 语义拧成两层混合。
+
+**只做一个 slash command `/loop`（Claude Code 复刻）**：实现最简。拒绝——slash-command 层不解决 harness/inner 边界；四条设计要点（可查询 session、分档 evaluator、可插拔 handoff、可插拔 goal reflector）在 slash-command 层没有承载点，本 RFC 承诺的能力全部丢失。
+
+**全权外包给 `packages/workflow`**：把 loop 表达成带回边的 workflow 节点。拒绝——workflow 缺 iteration、StopCondition、Evaluator 的一等公民语义。硬用会把 evaluator 冒充成一个 phase，违反 evaluator 独立于 producer 的架构隔离要求；预算护栏在 workflow 是 phase-level 而非 round-level，粒度对不上。
+
+**A（fresh）vs. B（continue）硬编二选一**：Ralph 派和 LoopTroop 派各自都有强场景。拒绝——可插拔的 RoundHandoff 提出 seam + 三档内置 backend 涵盖两派并允许 hybrid。
+
+**不做 evaluator seam，内置几种够用**：更轻。拒绝——可插拔的 Evaluator 与 Budget 的核心价值是团队或私有 evaluator 可扩展。写死后长跑无人值守场景的用户只能改主库。
+
+**接受不带显式 `EvaluatorSpec` 的自由函数**：允许用户传任意 `(result) => boolean`。拒绝——criteria／executor／isolation 维度强制用户在启动时声明评估什么、由什么执行判断、由什么边界保护，防止不知不觉滑到更弱的配置。自由函数看起来灵活，实际让 evaluator 强度隐性下沉，长跑场景代价大。
+
+**引入独立记忆引擎（Beads / dex-style）**：外部化状态的成熟做法。拒绝——`packages/session-persistence` 加现有 exact-read `ctx.sessionQuery` 已经覆盖 Phase 1 诊断，SQLite FTS5 后续可以补 search；新引擎收益远小于维护成本。
+
+**goal reflection 塞进 Evaluator seam**（让 evaluator 返回「criteria 不可能满足」）：拒绝——混淆「是否成功」和「目标是否正确」两个正交问题。`Evaluator` 应保持独立、只读、简单。
+
+**goal-concern 永远只做 event 不做 seam**：更轻。Phase 1 确实使用 event 加 `stop`／`notify` policy；作为最终设计仍拒绝，因为 Phase 2 的 `reflect` 路径需要可替换响应策略。seam 与首个调用方一起落地，不提前出现。
+
+**Phase 1 就上完整 Reflector subagent**：更全。拒绝——`loop_flag_concern` tool + no-progress 启发式 + 二档 policy 覆盖 80% 场景；每轮跑独立 subagent 成本高，Phase 2 按需引入更合理。
+
+**不做 `loop_split`，用户自己拆**：Phase 1 已经如此。Phase 2 加是因为长跑场景发现 agent 收到过大 goal 会直接跑而不是自己拆，需要显式工具引导。
+
+## 验收标准
+
+- `packages/loop/{loop,loop-driver,loop-tool}` 三包按 capability seam 建成；`dsh-loop` 只导 types 与 registry
+- `StopCondition` 判别覆盖所有分支（单元），`assertNever` 编译期收口
+- Phase 1 的 `Evaluator`、`BudgetPolicy`、`RoundHandoff` 三条 service 都能被外部插件替换（fixture：注入 mock 实现，driver 正确调用）；Phase 2 `reflect` consumer 出现前不注册 `GoalReflector` service
+- `EvaluatorSpec` 的 criteria／executor／isolation 维度在编译期收敛；driver 拒绝启动没有 evaluator 配对的 loop（fixture：`loop({ goal, evaluator: undefined })` 立即返回配置错误）
+- Default-FAIL fixture：evaluator 报告返回 `{criterion, pass: true, evidence: []}` 时 driver 拒绝该 criterion 翻转、记 `evaluator/invalid-report` session event
+- `RoundHandoff` 接收上一轮 result、evaluator report、token usage、summary、session id、可选 run handle 和 cancellation signal；Phase 1 的 `fresh-with-summary` 有单元覆盖与一个 pass-path e2e，continuation backend 测试等待 Phase 2 provider 支持
+- `dsh-sdk loop` CLI e2e：给定 goal + 3 轮上限 + 一个 shell evaluator，通过与耗尽两条路径都返回结构化 stop cause 并 exit code 语义化
+- Evaluator scope fixture：主 agent 有 fs.write，LLM evaluator 的 model-facing tool set 没有；结果与文档仍把 `same-workspace` 标记为未隔离，不暴露 `protectedPaths` 保证
+- Budget fixture 覆盖 `perRoundUsd` 准入，以及跨 worker 与 evaluator usage 累计的 `maxRounds`、`maxTokens`、`maxUsd`；在途超限 emit 带 `observed` 与 `maximum` 的 `budget-cap`
+- Goal concern fixture：`loop_flag_concern` 可从主 agent 调用并产出普通 `loop/goal-concern` session event；`onGoalConcern: 'stop'` 下 emit `approval-required` StopCondition；`'notify-continue'` 下继续跑且不携带不存在的 ACP priority metadata；no-progress 启发式在预算超 50% 且零 pass 时自动触发一次（rate-limit 去重）
+- 默认 system prompt guidance（无 TODO/FAKE/PLACEHOLDER、无空 catch）随内置 `loop` tool 一起分发，snapshot 覆盖 prompt 内容但不把它当作强制机制
+- 每轮的 prompt、inner-loop 结果、evaluator report、stop 决策都以 session event 出现，并可通过现有 exact-read `ctx.sessionQuery` 读取；FTS5 search 留在 Phase 2
+- model-facing loop 启动后立即返回 `loop` task id；`task_output`、`task_list`、`task_kill`、父 agent dispose、取消、producer reload 和 service dispose 覆盖 owner isolation 与 awaited quiescence
+- `packages/loop/README.md` 和 `packages/workflow/README.md` 的「Related」段互链清楚「何时用 workflow、何时用 loop」的边界
+- 单元 100% / snapshot / e2e / doc-sync / verify-module-graph / build / hygiene 全绿；新增 tool 的 ACP 渲染意图（`generic`）有 snapshot
+
+## 风险
+
+**对话 replay 不是工作区恢复**。精确 session 读取已经存在，FTS5 改善历史发现能力，不决定正确性。基于当前工作区 replay 某一轮 prefix 可以诊断或改变运行方向，但复现该轮执行世界需要 Git/worktree/checkpoint 支持，以及针对外部副作用的显式 policy。
+
+**`packages/workflow` 与 loop 的边界是持续答疑热点**。「多轮是 loop 还是 workflow」两个 README 必须写清楚：workflow 是「步骤已知、agent 未定、并串行编排」；loop 是「agent 已定、轮数未定、evaluator 判停」。文档不清晰会让用户混用错档。
+
+**evaluator 反向优化（reward hacking）**。足够长的 loop 里 agent 有条件识别 evaluator 的模式并针对性优化，例如发现「只要测试文件里出现 `assert True` 就 PASS」从而绕过实质完成。Phase 1 的 `same-workspace` 模式不能阻止 agent 通过 bash、代码运行时或其他写入通道修改测试或 evaluator 配置；当前 `packages/fs` policy 不是路径隔离边界。需要对抗强度的用户必须选择隔离 worktree、只读 mount、容器或远程 evaluator。Phase 3 的两容器方案让 evaluator 整个运行时（二进制、rubric、依赖库）对主 agent 完全不可访问，Anthropic patch.py 走的就是这条路。
+
+**占位符伪造与过度防御码**。agent 有时会写 `# TODO: implement` 让测试勉强通过，或写大量 `try/except: pass` 让 evaluator 表面 PASS。这些不属于 evaluator 层的问题，而是 agent 生成阶段的 prompt 与训练问题。用户面 段的两条默认 system prompt 指令只是 guidance；用户在自定义 evaluator 中加入「静态检查禁止 TODO 与空 catch」才能获得可强制覆盖。这类问题不是 seam 层能根治的。
+
+**预算估算漂移与在途超限**。pricing 可能变化，累计 token／USD usage 只能在每次 worker、evaluator、compaction 或 reflector 请求报告 usage 后精确。preflight 保护单轮；累计上限会停止下一个请求，但可能被一个在途请求超出。README 同时报告 observed 与 maximum，并说明 provider 账单才是权威。
+
+**后台 task 只存在于当前进程**。`ctx.tasks` 为 model-facing loop 提供 owner isolation、通用收集／取消、完成通知和 awaited cleanup。父 agent 或 service dispose 会取消并等待 loop；进程 crash 无法执行 cleanup，持久重启不在 Phase 1 范围内。
+
+**长跑 loop 日志膨胀**。跑 100 轮 loop 单 session 上 MB 级。`logDetail: 'summary'` 兜底但 Phase 1 默认 `full`，Phase 2 再补 summary 语义。
+
+**pre-release 允许直接演进**。`SESSION_FORMAT_VERSION=0`，`LoopRoundEvent` schema 可随时改；后端拒收旧格式而非兼容，与 AGENTS.md 顶部 pre-release stance 一致。
diff --git a/docs/architecture.md b/docs/architecture.md
index 321612c814..25fd1a5105 100644
--- a/docs/architecture.md
+++ b/docs/architecture.md
@@ -1,10 +1,10 @@
 # DeepSeek Harness Architecture
 
-The **DeepSeek Harness SDK** builds agent harnesses on Cordis. The principle is simple: **everything is a plugin**. The shipped loop is one plugin, not a privileged kernel.
+The **DeepSeek Harness SDK** builds on Cordis: **everything is a plugin**, including the shipped loop.
 
 ## Overview
 
-A harness is one [Cordis](cordis-primer.md) context. Packages add services (`ctx.llm`, `ctx.tools`, `ctx.sessions`), typed events (`agent/request`, `tools/pre-execute`, `session/event`), and disposable prompt, tool, provider, adapter, and listener registrations.
+Harnesses are [Cordis](cordis-primer.md) contexts. Packages contribute services (`ctx.llm`, `ctx.tools`, `ctx.sessions`), typed events (`agent/request`, `tools/pre-execute`, `session/event`), and disposable prompts, tools, providers, adapters, and listeners.
 
 `packages/core/` groups the default agent flow; surrounding capabilities are equally first-class Cordis plugins.
 
@@ -36,6 +36,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages add services (`ctx
 | `ctx.subagents` | [`subagent/`](../packages/subagent/README.md) | named delegation providers |
 | `ctx.tasks` | [`tasks/`](../packages/tasks/README.md) | background task registry + generic `task_*` control tools |
 | `ctx.workflows` | [`workflow/`](../packages/workflow/README.md) | script-driven multi-agent orchestration |
+| `ctx.goals` | [`goal/`](../packages/goal/README.md) | persisted same-session goals |
 | `ctx.sessionPersistence` | [`session-persistence/`](../packages/session-persistence/README.md) | durable storage for session logs |
 | `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | live-preferred logical-corpus exact reads and relationship traces |
 
@@ -109,7 +110,7 @@ forever:
 
 Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt ownership](../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)).
 
-Tool-time context—including async `agent.inject()` notices and post-tool `additionalContexts`—settles, then follows recorded results. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering before signal closure. Leftovers become queued input. Terminal `agent/turn-stop` runs after continuation and steering folding, stays authoritative through turn close and flush, and discards later steering but preserves queued prompts.
+Tool-time context—including async `agent.inject()` notices and post-tool `additionalContexts`—settles after results. Steering drains; before signal closure, `agent/post-step` observes durable output, results, context, and steering. Leftovers queue. Terminal `agent/turn-stop` runs after continuation and steering folding, remains authoritative through close/flush, and discards later steering while preserving queued prompts.
 
 Pruning precedes summaries; overflow retries require durable progress. Bounded transient retries compose on `agent/request-error`; cancellation wins ([compaction](../.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md), [retry](../.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md)).
 
@@ -117,7 +118,7 @@ Pruning precedes summaries; overflow retries require durable progress. Bounded t
 
 The turn is the containment boundary. Adapter failures close the step, entering `agent/request-error` with the exact `Error`, `LlmFailure`, and retry history. Retry opens a numbered step; success clears history; exhaustion stores the failure on `turn/end`. Failed chunks commit no message or tool.
 
-Other failures use `agent/error`. Cancellation and disposal beat recovery; undispatched model tool calls receive synthetic `tool/call` and `ABORTED` result pairs before `turn/end`. `cancel()` clears queues and aborts active work; disposal awaits quiescence before unregistering.
+Other failures use `agent/error`. Cancellation beats recovery; undispatched calls get synthetic `ABORTED` results. Effective `cancel()` emits `agent/cancel-requested` before queue clearing or abort; observers cannot veto it, and idle calls emit nothing. Disposal awaits quiescence.
 
 Every session event is turn-enclosed. Reloading preserves an interrupted tail and closes it with a synthetic `interrupted` turn end. Failures after durable turn close report only through `agent/error` because no safe in-turn position remains. Each turn has one `TurnEndReason`; [TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap) owns the variants.
 
@@ -149,34 +150,36 @@ Streaming uses raw chunks and `BlockAssembler`. One `LlmAdapter.stream()` is one
 
 ### Capability Pattern
 
-A swappable capability usually splits into **interface / implementation / consumer**: the interface owns its `ctx` key and events, an implementation registers a backend, and a consumer exposes model behavior through tools or prompts. Bash is the reference; the [capability graph](capability-seams.md) shows every family.
+A swappable capability usually splits into **interface / implementation / consumer**: service/events, a backend, and model-facing tools/prompts. Bash is the reference; the [capability graph](capability-seams.md) maps each family.
 
-Some seams bend the template deliberately: LLM combines interface and consumer because adapters implement it; filesystem wraps provider primitives with policy; web keeps search/fetch provider registries behind one service; skills and subagents use named providers. Subagents spawn fresh, fork a completed-turn prefix, or use ACP children ([subagent.md](core-data-structures/subagent.md)).
+Exceptions combine layers: LLM interface/consumer; filesystem policy; web registries; named skill/subagent providers. Subagents spawn fresh, fork a completed-turn prefix, or use ACP children ([subagent.md](core-data-structures/subagent.md)).
 
 `dsh-workspace-context` composes baselines on `agent/session-prefix` and appends `ctx.fs`-discovered nested changes on `tools/post-execute`; its [decision](../.agents/notes/implemented/feature/2026-06-24-workspace-context.md) records isolation. `dsh-paths` owns shared paths.
 
 ### Bundles And Apps
 
-`dsh-agent-spine-demo` bundles the default spine ([README](../packages/examples/agent-spine-demo/README.md)). `dsh-tui-demo` owns the interactive full-screen terminal; `dsh-cli-demo` runs one persisted headless turn with format-pure stdout; `dsh-acp-demo` adds stdout-pure ACP over JSON-RPC ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` boots external `cordis.yml`; the Python SDK supplies its default only without an explicit config channel and drives `dsh-jsonrpc` over line-delimited JSON-RPC ([Python SDK](../python/README.md)). Deployments remain thin leaves with swappable backends and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)).
+`dsh-agent-spine-demo` bundles the default spine ([README](../packages/examples/agent-spine-demo/README.md)). `dsh-tui-demo` owns the interactive full-screen terminal and human-command registry; `dsh-cli-demo` runs one persisted headless turn with format-pure stdout; `dsh-acp-demo` adds stdout-pure ACP over JSON-RPC and the same command registry ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` boots external `cordis.yml`; the Python SDK supplies its default only without an explicit config channel and drives `dsh-jsonrpc` over line-delimited JSON-RPC ([Python SDK](../python/README.md)). Deployments remain thin leaves with swappable backends and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)).
 
 ### Where New Behavior Goes
 
-New behavior should attach to a documented extension point; changing the shipped loop requires updating this map.
+New behavior attaches to a documented extension point; a loop change updates this map.
 
 | Goal | Mechanism |
 |---|---|
 | Add a model provider | register an adapter on `ctx.llm` |
-| Add a model-facing capability | register a tool on `ctx.tools`; schemas flow into prompt assembly |
-| Add command execution | implement and register a `ctx.bash` backend |
-| Add a long-running/background capability | register the work on `ctx.tasks`; the generic `task_*` tools collect/stop it |
+| Add a model-facing capability | register on `ctx.tools`; schemas enter prompt assembly |
+| Add shell execution | implement and register a `ctx.bash` backend |
+| Add a human command | register on `ctx.commands`; adapters discover and dispatch it without a model turn |
+| Add background work | register on `ctx.tasks`; generic `task_*` tools collect or stop it |
 | Add filesystem access or policy | implement a `ctx.fs` provider or listen on `fs/*` policy events |
 | Confine spawned processes | a `ctx.sandbox` backend; consumers wrap their argv before spawning |
-| Intercept prompts, requests, model completion/failure, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` event; use serial `agent/turn-stop` for a monotonic terminal stop |
-| Add a session-stable request prefix outside history | compose it on `agent/session-prefix`, once per loop instance; logged on the request header |
+| Intercept a request, tool, or turn | use its `agent/*` or `tools/*` event; `agent/turn-stop` is the serial terminal stop |
+| Add a session-stable prefix outside history | compose `agent/session-prefix`; the request header logs it |
 | Add UI or editor integration | drive `ctx.agents` and render from `session/event` |
 | Add durable session state | add a `SessionEventMap` member and render/replay from the log |
+| Manage a same-session objective | use `ctx.goals`; continue through `Agent` and `agent/*` |
 | Fork a live session | use `ctx.sessions.fork(source, boundary?, childSessionId?)` |
-| Scope a tool, prompt section, or listener to ONE agent | register it through that agent's `agent.ctx` (see Agent Scope) |
+| Scope a registration to one agent | use that agent's `agent.ctx` (see Agent Scope) |
 
 The [extension cookbook](cookbook/extension-cookbook.md) carries plugin skeletons and the feature-to-seam map; step-by-step guides cover [packages](cookbook/adding-a-package.md), [tools](cookbook/adding-a-tool.md), [LLM adapters](cookbook/adding-an-llm-adapter.md), and [vendored packages](cookbook/adding-a-vendored-package.md).
 
diff --git a/docs/capability-seams.md b/docs/capability-seams.md
index 109d8ec441..8dfe27b5f8 100644
--- a/docs/capability-seams.md
+++ b/docs/capability-seams.md
@@ -48,6 +48,8 @@ flowchart LR
   pkg_user_interaction["user-interaction"]
   svc_userInteraction["ctx.userInteraction<br/>Human question/answer seam"]
   pkg_tui["tui"]
+  pkg_commands["commands"]
+  svc_commands["ctx.commands<br/>Human command registry"]
   pkg_skill["skill"]
   svc_skills["ctx.skills<br/>Skill provider registry"]
   pkg_skill_local["skill-local"]
@@ -55,6 +57,8 @@ flowchart LR
   pkg_tui_demo["tui-demo"]
   svc_agentLoop["ctx.agentLoop<br/>Concrete loop driver"]
   pkg_agent_spine_demo["agent-spine-demo"]
+  pkg_goal["goal"]
+  svc_goals["ctx.goals<br/>Same-session goal domain"]
   pkg_bash["bash"]
   svc_bash["ctx.bash<br/>Bash executor seam"]
   pkg_bash_local["bash-local"]
@@ -111,12 +115,14 @@ flowchart LR
   pkg_bash_sandbox --> svc_bash
   pkg_code_runtime --> svc_codeRuntime
   pkg_code_runtime_worker --> svc_codeRuntime
+  pkg_commands --> svc_commands
   pkg_compact --> svc_compact
   pkg_compact_basic --> svc_compact
   pkg_compact_tool_result_prune --> svc_toolResultPrune
   pkg_fs --> svc_fs
   pkg_fs_local --> svc_fs
   pkg_fs_sandbox --> svc_fs
+  pkg_goal --> svc_goals
   pkg_llm --> svc_llm
   pkg_llm_deepseek --> svc_llm
   pkg_llm_pi_ai --> svc_llm
@@ -165,6 +171,8 @@ flowchart LR
   svc_bash --> pkg_hooks_codex
   svc_bash --> pkg_tool_bash
   svc_codeRuntime --> pkg_tools
+  svc_commands --> pkg_acp
+  svc_commands --> pkg_tui
   svc_compact --> pkg_compact_basic
   svc_fs --> pkg_tool_fs
   svc_llm --> pkg_agent_loop
@@ -227,9 +235,11 @@ flowchart LR
 | `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. |
 | `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. |
 | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`tui`](../packages/ui/tui), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`tui`](../packages/ui/tui), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. |
+| `ctx.commands` | `core` | [`commands`](../packages/ui/commands) | - | [`tui`](../packages/ui/tui), [`acp`](../packages/ui/acp) | - | Plugins register direct human commands; TUI and ACP consume the same effective per-agent catalog without sending invocations to the model. |
 | `ctx.skills` | `seam` | [`skill`](../packages/skill/skill) | [`skill-local`](../packages/skill/skill-local) | [`tool-skill`](../packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. |
 | `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`tui-demo`](../packages/examples/tui-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles, the create/resume factory seam, and process-local initiator propagation. |
 | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. |
+| `ctx.goals` | `core` | [`goal`](../packages/goal/goal) | - | - | - | Folds revisioned objective state from the session log and keeps live continuation activation process-local. |
 | `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. |
 | `ctx.bashEnv` | `core` | [`tool-bash`](../packages/bash/tool-bash) | - | - | - | Plugins declare effect-scoped DSH_* facts; tool-bash collects one trusted snapshot per execution and the executor rebuilds the namespace. |
 | `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. |
diff --git a/docs/config-catalog.md b/docs/config-catalog.md
index 9394cf6e77..d011a7f41f 100644
--- a/docs/config-catalog.md
+++ b/docs/config-catalog.md
@@ -11,7 +11,7 @@ A `Requires:` line lists the service keys the plugin `inject`s: its `cordis.yml`
 
 ## `@deepseek-ai/dsh-acp`
 
-Requires: `agents` · `sessionPersistence` · `tools` · `userInteraction` · `llm` · `systemPrompt`
+Requires: `agents` · `commands` · `sessionPersistence` · `tools` · `userInteraction` · `llm` · `systemPrompt`
 
 ```ts config-catalog
 /** Plugin config: the agent template ACP sessions are created from. */
@@ -27,7 +27,7 @@ export interface AcpConfig {
 
 Depends on: `Stream` (`@agentclientprotocol/sdk`)
 
-Source: [`packages/ui/acp/src/index.ts:207`](../packages/ui/acp/src/index.ts)
+Source: [`packages/ui/acp/src/index.ts:247`](../packages/ui/acp/src/index.ts)
 
 ## `@deepseek-ai/dsh-acp-demo`
 
@@ -75,7 +75,7 @@ export interface Config {
 
 Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`JsonlCompression`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
 
-Source: [`packages/examples/acp-demo/src/index.ts:36`](../packages/examples/acp-demo/src/index.ts)
+Source: [`packages/examples/acp-demo/src/index.ts:37`](../packages/examples/acp-demo/src/index.ts)
 
 ## `@deepseek-ai/dsh-agent-loop`
 
@@ -358,6 +358,20 @@ Depends on: [`LocalConfig`](#deepseek-aidsh-fs-local)
 
 Source: [`packages/fs/fs-sandbox/src/index.ts:49`](../packages/fs/fs-sandbox/src/index.ts)
 
+## `@deepseek-ai/dsh-goal`
+
+Requires: `agents`
+
+```ts config-catalog
+/** Deployment defaults for goal creation. */
+export interface Config {
+  /** Total rounds used when a create request omits its own cap. */
+  defaultMaxGoalRounds?: number
+}
+```
+
+Source: [`packages/goal/goal/src/index.ts:56`](../packages/goal/goal/src/index.ts)
+
 ## `@deepseek-ai/dsh-hooks-claude`
 
 Requires: `bash`
@@ -1096,6 +1110,20 @@ export interface Config {
 
 Source: [`packages/fs/tool-fs-search/src/index.ts:62`](../packages/fs/tool-fs-search/src/index.ts)
 
+## `@deepseek-ai/dsh-tool-goal`
+
+Requires: `agents` · `goals` · `tools` · `systemPrompt`
+
+```ts config-catalog
+/** Model policy and hard lower bounds for goal-state updates. */
+export interface Config {
+  /** Minimum admitted goal rounds before the model may self-report `blocked`. */
+  blockedAfterConsecutiveRounds?: number
+}
+```
+
+Source: [`packages/goal/tool-goal/src/index.ts:27`](../packages/goal/tool-goal/src/index.ts)
+
 ## `@deepseek-ai/dsh-tool-skill`
 
 Requires: `tools` · `skills`
@@ -1244,7 +1272,7 @@ Source: [`packages/core/tools/src/index.ts:382`](../packages/core/tools/src/inde
 
 ## `@deepseek-ai/dsh-tui`
 
-Requires: `agents` · `userInteraction` · `tools`
+Requires: `agents` · `commands` · `userInteraction` · `tools`
 
 ```ts config-catalog
 /** Serializable plugin configuration. */
@@ -1276,7 +1304,7 @@ export interface TuiConfig {
 }
 ```
 
-Source: [`packages/ui/tui/src/index.ts:102`](../packages/ui/tui/src/index.ts)
+Source: [`packages/ui/tui/src/index.ts:103`](../packages/ui/tui/src/index.ts)
 
 ## `@deepseek-ai/dsh-tui-demo`
 
@@ -1320,7 +1348,7 @@ export interface Config {
 
 Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`JsonlCompression`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`uiTui`](../packages/ui/tui/src/index.ts)
 
-Source: [`packages/examples/tui-demo/src/index.ts:31`](../packages/examples/tui-demo/src/index.ts)
+Source: [`packages/examples/tui-demo/src/index.ts:32`](../packages/examples/tui-demo/src/index.ts)
 
 ## `@deepseek-ai/dsh-user-approval`
 
@@ -1517,7 +1545,9 @@ Source: [`packages/context/workspace-context/src/config.ts:16`](../packages/cont
 These load from a `cordis.yml` entry with no `config:` block; they declare no config surface.
 
 - `@deepseek-ai/dsh-agent` ([`packages/core/agent/src/index.ts`](../packages/core/agent/src/index.ts))
+- `@deepseek-ai/dsh-commands` ([`packages/ui/commands/src/index.ts`](../packages/ui/commands/src/index.ts))
 - `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts))
+- `@deepseek-ai/dsh-goal-session` — requires `agents` · `goals` · `sessions` ([`packages/goal/goal-session/src/index.ts`](../packages/goal/goal-session/src/index.ts))
 - `@deepseek-ai/dsh-invariants` — requires `sessions` ([`packages/support/invariants/src/index.ts`](../packages/support/invariants/src/index.ts))
 - `@deepseek-ai/dsh-llm` ([`packages/llm/llm/src/index.ts`](../packages/llm/llm/src/index.ts))
 - `@deepseek-ai/dsh-session` ([`packages/core/session/src/index.ts`](../packages/core/session/src/index.ts))
diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md
index 4cdef11bfd..a213c9e11a 100644
--- a/docs/cordis-catalog/events.md
+++ b/docs/cordis-catalog/events.md
@@ -13,6 +13,27 @@ Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `n
 
 ## `agent/*`
 
+### `agent/cancel-requested` — emit
+
+Effective broad cancellation was requested, before queued/steering work is cleared or the active step is aborted. This observe-only notification cannot veto cancellation; listener failures are contained.
+
+```ts cordis-catalog
+/**
+ * Effective broad cancellation was requested, before queued/steering work
+ * is cleared or the active step is aborted. This observe-only notification
+ * cannot veto cancellation; listener failures are contained.
+ * @param agent - the agent whose current work is being cancelled.
+ * @param reason - resolved cancellation reason, including the default.
+ * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
+ * @mode emit
+ */
+'agent/cancel-requested'(this: Scoped<Agent>, agent: Agent, reason: string): void
+```
+
+Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
+
+Source: [`packages/core/agent/src/types.ts:191`](../../packages/core/agent/src/types.ts)
+
 ### `agent/created` — emit
 
 A fully configured agent and live session were published. Setup is composition-only; `agent/session-start` is the first startup-driving seam. Synchronous listener failure vetoes publication, while returned-promise rejection is reported. Detach requested during dispatch waits until every creation listener has observed the stable entry.
@@ -33,7 +54,7 @@ A fully configured agent and live session were published. Setup is composition-o
 
 Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:150`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:153`](../../packages/core/agent/src/types.ts)
 
 ### `agent/disposed` — emit
 
@@ -53,7 +74,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef
 
 Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:159`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:162`](../../packages/core/agent/src/types.ts)
 
 ### `agent/error` — emit
 
@@ -75,7 +96,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w
 
 Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:315`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:328`](../../packages/core/agent/src/types.ts)
 
 ### `agent/post-step` — serial
 
@@ -98,7 +119,7 @@ Awaited serial checkpoint after the response, real or synthetic tool results, in
 
 Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:267`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:280`](../../packages/core/agent/src/types.ts)
 
 ### `agent/pre-step` — serial
 
@@ -121,7 +142,7 @@ Awaited serial checkpoint before `step/start`; appends land outside the pending
 
 Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:207`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:220`](../../packages/core/agent/src/types.ts)
 
 ### `agent/prompt-submit` — waterfall
 
@@ -142,7 +163,7 @@ Allow, rewrite, or block one claimed prompt before it becomes a user message. Ca
 
 Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) · [PromptDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:217`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:230`](../../packages/core/agent/src/types.ts)
 
 ### `agent/queued` — emit
 
@@ -163,7 +184,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already
 
 Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:178`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:181`](../../packages/core/agent/src/types.ts)
 
 ### `agent/request` — waterfall
 
@@ -186,7 +207,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha
 
 Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:229`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:242`](../../packages/core/agent/src/types.ts)
 
 ### `agent/request-error` — waterfall
 
@@ -212,7 +233,7 @@ Recover a model-request failure after its failed step has closed. `retry` opens
 
 Types: [Agent](../core-data-structures/core.md) · [LlmFailure](../core-data-structures/llm-streaming.md) · [RequestError](../core-data-structures/core.md) · [RequestErrorDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:282`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:295`](../../packages/core/agent/src/types.ts)
 
 ### `agent/session-prefix` — waterfall
 
@@ -238,7 +259,7 @@ Compose request-only messages placed before derived history. The frozen result i
 
 Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:244`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:257`](../../packages/core/agent/src/types.ts)
 
 ### `agent/session-start` — emit
 
@@ -260,7 +281,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to
 
 Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SessionStartSource](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/types.ts:191`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:204`](../../packages/core/agent/src/types.ts)
 
 ### `agent/status` — emit
 
@@ -280,7 +301,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no
 
 Types: [Agent](../core-data-structures/core.md) · [AgentStatus](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:168`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:171`](../../packages/core/agent/src/types.ts)
 
 ### `agent/step-result` — waterfall
 
@@ -302,7 +323,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va
 
 Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:255`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:268`](../../packages/core/agent/src/types.ts)
 
 ### `agent/turn-continuation` — waterfall
 
@@ -323,7 +344,7 @@ Override whether the turn continues. The default continues after tool calls or s
 
 Types: [Agent](../core-data-structures/core.md) · [ContinuationDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:292`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:305`](../../packages/core/agent/src/types.ts)
 
 ### `agent/turn-stop` — serial
 
@@ -344,7 +365,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a
 
 Types: [Agent](../core-data-structures/core.md) · [ContinuationStop](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md)
 
-Source: [`packages/core/agent/src/types.ts:302`](../../packages/core/agent/src/types.ts)
+Source: [`packages/core/agent/src/types.ts:315`](../../packages/core/agent/src/types.ts)
 
 ## `agent-loop/*`
 
@@ -390,6 +411,24 @@ Types: [ApprovalOutcome](../core-data-structures/approval.md) · [ApprovalReques
 
 Source: [`packages/ui/user-approval/src/index.ts:31`](../../packages/ui/user-approval/src/index.ts)
 
+## `commands/*`
+
+### `commands/change` — emit
+
+A command was registered or unregistered. This is an unfiltered registry notification because a global or scoped change may affect any UI view. Observer failures are contained and cannot veto the registry mutation.
+
+```ts cordis-catalog
+/**
+ * A command was registered or unregistered. This is an unfiltered registry
+ * notification because a global or scoped change may affect any UI view.
+ * Observer failures are contained and cannot veto the registry mutation.
+ * @mode emit
+ */
+'commands/change'(): void
+```
+
+Source: [`packages/ui/commands/src/index.ts:83`](../../packages/ui/commands/src/index.ts)
+
 ## `fs/*`
 
 ### `fs/edit-intent` — waterfall
@@ -451,6 +490,29 @@ Types: [FsTarget](../core-data-structures/filesystem.md) · [FsWriteIntent](../c
 
 Source: [`packages/fs/fs/src/index.ts:54`](../../packages/fs/fs/src/index.ts)
 
+## `goal/*`
+
+### `goal/changed` — emit
+
+Goal mutation accepted by one live agent. The matching context event is already appended or queued in that agent's active tool-batch FIFO. Listener failures are contained. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
+
+```ts cordis-catalog
+/**
+ * Goal mutation accepted by one live agent. The matching context event is
+ * already appended or queued in that agent's active tool-batch FIFO.
+ * Listener failures are contained.
+ * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
+ * @param agent - agent whose session owns the goal.
+ * @param change - fresh current projection or clear tombstone.
+ * @mode emit
+ */
+'goal/changed'(this: import('@deepseek-ai/dsh-scope').Scoped<Agent>, agent: Agent, change: GoalChanged): void
+```
+
+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:167`](../../packages/goal/goal/src/types.ts)
+
 ## `llm/*`
 
 ### `llm/stream` — waterfall
diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md
index a550b11caa..d27b483399 100644
--- a/docs/cordis-catalog/services.md
+++ b/docs/cordis-catalog/services.md
@@ -340,6 +340,47 @@ Types: [CodeRunRequest](../core-data-structures/code-runtime.md) · [CodeRunResu
 
 Source: [`packages/code-runtime/code-runtime/src/index.ts:30`](../../packages/code-runtime/code-runtime/src/index.ts)
 
+## `ctx.commands` — `CommandService`
+
+Human-command registry. Plain-context definitions are global; definitions registered through a command-injected child of an agent context shadow globals for that agent.
+
+```ts cordis-catalog
+/**
+ * Register a global or calling-agent-scoped command.
+ * @param definition - discovery metadata and direct UI handler.
+ * @returns the exact effect disposer that unregisters this definition.
+ */
+register(definition: CommandDefinition): () => void
+
+/**
+ * List the effective immutable command descriptors for one agent.
+ * @param agent - exact receiving agent and scoped-layer key.
+ * @returns name-sorted descriptors after scoped shadowing.
+ */
+list(agent: Agent): readonly CommandDescriptor[]
+
+/**
+ * Resolve one effective command definition.
+ * @param agent - exact receiving agent and scoped-layer key.
+ * @param name - command name without a slash.
+ * @returns the scoped shadow or global definition.
+ */
+find(agent: Agent, name: string): CommandDefinition | undefined
+
+/**
+ * Parse and execute a known command without sending it to the model.
+ * @param agent - exact receiving agent.
+ * @param line - complete slash-command line.
+ * @param signal - cancellation signal owned by the UI request.
+ * @returns a detached result, or `undefined` when syntax or name does not resolve.
+ */
+async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise<CommandResult | undefined>
+```
+
+Types: [Agent](../core-data-structures/core.md) · [CommandDefinition](../core-data-structures/commands.md) · [CommandDescriptor](../core-data-structures/commands.md) · [CommandResult](../core-data-structures/commands.md)
+
+Source: [`packages/ui/commands/src/index.ts:207`](../../packages/ui/commands/src/index.ts)
+
 ## `ctx.compact` — `CompactService` (abstract seam)
 
 Abstract compaction service. Implementations own trigger policy, retention, and summarization, and may consume a separate measurement service. A successful run replaces the selected surface span with one summary node and prevents concurrent compaction of the same session. Load one implementation per context as `ctx.compact`.
@@ -485,6 +526,93 @@ Types: [FsDirEntry](../core-data-structures/filesystem.md) · [FsEditOutcome](..
 
 Source: [`packages/fs/fs/src/index.ts:81`](../../packages/fs/fs/src/index.ts)
 
+## `ctx.goals` — `GoalService`
+
+Goal service (`ctx.goals`) backed exclusively by the owning session log.
+
+```ts cordis-catalog
+/**
+ * Read the current goal for one exact live agent.
+ * @param agent - owning live agent.
+ * @returns a fresh view or `undefined` when no goal is current.
+ * @throws {@link GoalError} when the agent is not the registry's live instance.
+ */
+get(agent: Agent): GoalView | undefined
+
+/**
+ * Remove process-local continuation authority without changing durable goal
+ * phase or revision. Lifecycle owners use this before unloading a driver;
+ * a later human-authorized {@link resume} records the new activation edge.
+ * @param agent - owning live agent.
+ * @returns a fresh disarmed view, or `undefined` when no goal is current.
+ */
+disarm(agent: Agent): GoalView | undefined
+
+/**
+ * Create and arm a goal. A completed goal may be replaced; every other
+ * current phase must be cleared or resumed instead.
+ * @param agent - owning live agent.
+ * @param request - objective and optional round cap.
+ * @returns the created live view.
+ */
+create(agent: Agent, request: CreateGoalRequest): GoalView
+
+/**
+ * Edit objective and/or round cap without changing phase.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @param request - at least one replacement field.
+ * @returns the edited view.
+ */
+edit(agent: Agent, ref: GoalRef, request: EditGoalRequest): GoalView
+
+/**
+ * Pause an active goal and disarm automatic continuation.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @returns the paused view.
+ */
+pause(agent: Agent, ref: GoalRef): GoalView
+
+/**
+ * Resume and arm a stopped goal, or rearm an active goal after a
+ * session-start edge, while its round budget still has capacity.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @returns the active view.
+ */
+resume(agent: Agent, ref: GoalRef): GoalView
+
+/**
+ * Mark a current non-complete goal complete and disarm it.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @returns the completed view.
+ */
+complete(agent: Agent, ref: GoalRef): GoalView
+
+/**
+ * Mark an active goal blocked and disarm it.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @param reason - policy-owned stable code and human-readable explanation.
+ * @returns the blocked view with its durable reason.
+ */
+block(agent: Agent, ref: GoalRef, reason: GoalBlockReason): GoalView
+
+/**
+ * Clear the current goal while retaining a durable tombstone and history.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @returns the tombstone ref whose revision is one past the cleared snapshot.
+ */
+clear(agent: Agent, ref: GoalRef): GoalRef
+```
+
+Types: [Agent](../core-data-structures/core.md) · [CreateGoalRequest](../core-data-structures/goal.md) · [EditGoalRequest](../core-data-structures/goal.md) · [GoalBlockReason](../core-data-structures/goal.md) · [GoalRef](../core-data-structures/goal.md) · [GoalView](../core-data-structures/goal.md)
+
+Source: [`packages/goal/goal/src/index.ts:135`](../../packages/goal/goal/src/index.ts)
+
 ## `ctx.llm` — `LlmService`
 
 The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.
diff --git a/docs/core-data-structures/commands.md b/docs/core-data-structures/commands.md
new file mode 100644
index 0000000000..c33b27ce1c
--- /dev/null
+++ b/docs/core-data-structures/commands.md
@@ -0,0 +1,84 @@
+# Human Commands
+
+The human-command seam of [`dsh-commands`](../../packages/ui/commands). TUI and ACP adapters use it to discover and directly execute plugin-owned commands for an exact agent without creating a model message. The [command Agent Note](../../.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md) owns dispatch and lifecycle rationale; the [package README](../../packages/ui/commands/README.md) owns composition and limitations.
+
+Source: [`packages/ui/commands/src/index.ts`](../../packages/ui/commands/src/index.ts)
+
+## Input metadata
+
+ACP currently exposes one unstructured-input hint. Command availability follows plugin composition: every adapter consuming the registry sees every effective definition.
+
+```ts type-equiv
+/** Immutable command input metadata compatible with ACP unstructured input. */
+interface CommandInputDescriptor {
+  /** Placeholder shown before the user supplies free-form input. */
+  readonly hint: string
+}
+```
+
+## Definition
+
+`CommandDefinition` is the plugin-authored registration. The registry validates and freezes a detached effective definition.
+
+```ts type-equiv
+/** Plugin-owned command registration. */
+interface CommandDefinition {
+  /** Lowercase command name without the leading slash. */
+  readonly name: string
+  /** Human-readable summary used in discovery UI. */
+  readonly description: string
+  /** Optional free-form input hint advertised to capable clients. */
+  readonly input?: CommandInputDescriptor
+  /** Execute against the receiving agent without sending the command to the model. */
+  readonly handler: (invocation: CommandInvocation) => CommandResult | Promise<CommandResult>
+}
+```
+
+## Invocation and result
+
+The adapter owns cancellation and passes the exact target agent. `rawInput` begins immediately after the parsed name and retains the adapter-delivered separator and suffix. Results are direct UI outcomes, not tool results or session events.
+
+```ts type-equiv
+/** Invocation passed to one registered command handler. */
+interface CommandInvocation {
+  /** Exact agent whose human-facing surface received the command. */
+  readonly agent: Agent
+  /** Exact text following the registered command name, including separator whitespace. */
+  readonly rawInput: string
+  /** Cancellation signal owned by the dispatching UI request. */
+  readonly signal: AbortSignal
+}
+```
+
+```ts type-equiv
+/** Expected command outcome rendered directly by the dispatching UI. */
+type CommandResult =
+  | { readonly kind: 'success'; readonly text?: string }
+  | { readonly kind: 'error'; readonly text: string }
+```
+
+## Discovery and parsing views
+
+Adapters receive handler-free immutable descriptors after scope resolution. `parseCommand()` returns `ParsedCommand` before registry resolution; syntax-valid input can still name an unavailable command.
+
+```ts type-equiv
+/** Handler-free immutable command view returned to UI adapters. */
+interface CommandDescriptor {
+  /** Lowercase command name without the leading slash. */
+  readonly name: string
+  /** Human-readable summary used in discovery UI. */
+  readonly description: string
+  /** Optional free-form input hint advertised to capable clients. */
+  readonly input?: CommandInputDescriptor
+}
+```
+
+```ts type-equiv
+/** Syntactically valid slash command before registry resolution. */
+interface ParsedCommand {
+  /** Lowercase command name without the leading slash. */
+  readonly name: string
+  /** Exact text following the command name. */
+  readonly rawInput: string
+}
+```
diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md
index 7bde39e920..888cd145b3 100644
--- a/docs/core-data-structures/core.md
+++ b/docs/core-data-structures/core.md
@@ -18,6 +18,8 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
 | [llm-streaming.md](llm-streaming.md) | the `StreamChunk` wire protocol + adapter contract, `BlockAssembler`, the `LlmAdapter` seam |
 | [token-meter.md](token-meter.md) | immutable scalar and positional replay measurements with consumed-log revisions |
 | [scope.md](scope.md) | scoped registration identity, dispatch carriers, and the owned `Scope` context |
+| [goal.md](goal.md) | persisted goal identity, lifecycle snapshots, activation, change records, and round attribution |
+| [commands.md](commands.md) | the human-command seam: definitions, adapter discovery, direct invocation, results, and parsing views |
 | [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, the turn-enclosure invariant |
 | [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` |
 | [session-query.md](session-query.md) | logical records, bounded exact-event reads, and relationship traces |
@@ -388,10 +390,10 @@ interface Agent {
 
   /**
    * Clear all queued and steering work, including items waiting to start, and
-   * abort the active step. The supplied reason is preserved across pre-step
-   * and active cancellation windows, and `whenIdle()` resolves after
-   * cancellation reaches quiescence. Idle cancellation is a no-op and does not
-   * arm a later cancel.
+   * abort the active step. An effective call first emits `agent/cancel-requested`
+   * with the resolved reason. That reason is preserved across pre-step and active
+   * cancellation windows, and `whenIdle()` resolves after cancellation reaches
+   * quiescence. Idle cancellation is a no-op and does not arm a later cancel.
    */
   cancel(reason?: string): void
 
diff --git a/docs/core-data-structures/goal.md b/docs/core-data-structures/goal.md
new file mode 100644
index 0000000000..d45847ba0f
--- /dev/null
+++ b/docs/core-data-structures/goal.md
@@ -0,0 +1,143 @@
+# Same-session goals
+
+Types shared by the event-sourced goal domain and its policy consumers. The [goal-domain Agent Note](../../.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md) owns the persistence and activation decisions; this page records the literal shapes from [`packages/goal/goal/src/types.ts`](../../packages/goal/goal/src/types.ts).
+
+## Identity and lifecycle
+
+`GoalId` is a [branded id](core.md#branded-ids). A caller mutates one exact revision through `GoalRef`; every accepted durable mutation increments the revision.
+
+```ts type-equiv
+/** Compare-and-set identity for one exact goal revision. */
+interface GoalRef {
+  /** Stable goal identity. */
+  readonly id: GoalId
+  /** Positive revision; every durable mutation increments it. */
+  readonly revision: number
+}
+```
+
+The durable phase answers what happened to the objective. Process-local activation separately answers whether a continuation consumer may start another round.
+
+```ts type-equiv
+/** Durable continuation phase. Activation is process-local and separate. */
+type GoalPhase =
+  | 'active'
+  | 'paused'
+  | 'blocked'
+  | '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 {
+  /** 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
+}
+```
+
+```ts type-equiv
+/** Current goal projection, including values derived from the session log. */
+interface GoalView extends GoalSnapshot {
+  /** Highest admitted round number for this goal. */
+  readonly roundsStarted: number
+  /** Epoch milliseconds of the create mutation. */
+  readonly createdAt: number
+  /** Epoch milliseconds of the latest mutation. */
+  readonly updatedAt: number
+  /** Process-local continuation eligibility; never persisted. */
+  readonly activation: GoalActivation
+}
+```
+
+## Durable changes
+
+Every mutation is a `context/message` whose metadata is either a complete snapshot or a clear tombstone. The version, metadata, goal source, and verbatim rendered content form one replay invariant.
+
+```ts type-equiv
+/** Full-snapshot goal mutation retained in a model-visible context event. */
+interface GoalSnapshotChangeMeta {
+  readonly kind: 'goal/change'
+  readonly version: 1
+  readonly operation: Exclude<GoalOperation, 'clear'>
+  readonly goal: GoalSnapshot
+  readonly roundsStarted: number
+  readonly createdAt: number
+  readonly updatedAt: number
+}
+```
+
+```ts type-equiv
+/** Tombstone retained when the current goal is cleared. */
+interface GoalClearChangeMeta {
+  readonly kind: 'goal/change'
+  readonly version: 1
+  readonly operation: 'clear'
+  readonly cleared: GoalRef
+  readonly clearedAt: number
+}
+```
+
+Goal state changes use round `0`. A continuation consumer attributes each admitted user-message turn with a positive, sequential round number and the current revision; replay rejects gaps, stale revisions, stopped phases, and cap overflow.
+
+```ts type-equiv
+/** Message attribution for durable goal state and continuation rounds. */
+interface GoalMessageSource {
+  readonly kind: 'goal'
+  readonly goalId: GoalId
+  readonly revision: number
+  /** Zero for state changes; positive for admitted continuation rounds. */
+  readonly round: number
+}
+```
+
+## Requests and notifications
+
+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. */
+interface CreateGoalRequest {
+  readonly objective: string
+  readonly maxGoalRounds?: number
+}
+```
+
+```ts type-equiv
+/** Fields changed by an edit; at least one must be present. */
+interface EditGoalRequest {
+  readonly objective?: string
+  readonly maxGoalRounds?: number
+}
+```
+
+```ts type-equiv
+/** Live notification after one goal mutation has been accepted for logging. */
+interface GoalChanged {
+  readonly operation: GoalOperation
+  readonly ref: GoalRef
+  /** Absent for a clear tombstone. */
+  readonly goal?: GoalView
+}
+```
+
+## Service behavior
+
+[`GoalService`](../../packages/goal/goal/src/index.ts) resolves creation defaults, folds strict replay, enforces exact-live-agent identity and compare-and-set mutations, overlays deferred injections, and emits contained `goal/changed` notifications. The package [README](../../packages/goal/goal/README.md) owns the callable and model-visible contract.
diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md
index 205b00cfa8..99acf07d24 100644
--- a/docs/event-producer-consumer.md
+++ b/docs/event-producer-consumer.md
@@ -8,29 +8,32 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | Event | Mode | Declared in | Dispatchers | Listeners |
 | --- | --- | --- | --- | --- |
 | `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`tui`](../packages/ui/tui) |
-| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:150`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`tui`](../packages/ui/tui) |
-| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:159`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`tui`](../packages/ui/tui) |
-| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:315`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`tui`](../packages/ui/tui) |
-| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:267`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic) |
-| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:207`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) |
-| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:217`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
-| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:178`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
-| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:229`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp) |
-| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:282`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic), [`llm-retry`](../packages/llm/llm-retry) |
-| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:244`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) |
-| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:191`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
-| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:168`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`tui`](../packages/ui/tui) |
-| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:255`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
-| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:292`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
-| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:302`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
+| `agent/cancel-requested` | `emit` | [`packages/core/agent/src/types.ts:191`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session) |
+| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:153`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) |
+| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:162`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) |
+| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:328`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) |
+| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:280`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic) |
+| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:220`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) |
+| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:230`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
+| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:181`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session) |
+| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:242`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp) |
+| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:295`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic), [`llm-retry`](../packages/llm/llm-retry) |
+| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:257`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) |
+| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:204`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
+| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:171`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session), [`invariants`](../packages/support/invariants), [`tui`](../packages/ui/tui) |
+| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:268`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
+| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:305`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
+| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:315`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`tool-goal`](../packages/goal/tool-goal) |
 | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) |
+| `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:83`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`tui`](../packages/ui/tui) |
 | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:62`](../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:71`](../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:54`](../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: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:44`](../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) |
-| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`token-meter`](../packages/llm/token-meter), [`tui`](../packages/ui/tui), [`workspace-context`](../packages/context/workspace-context) |
+| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`goal-session`](../packages/goal/goal-session), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`token-meter`](../packages/llm/token-meter), [`tui`](../packages/ui/tui), [`workspace-context`](../packages/context/workspace-context) |
 | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
 | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:139`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) |
 | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:113`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
diff --git a/docs/glossary.md b/docs/glossary.md
index 0bed6fc56e..e38c1f48b9 100644
--- a/docs/glossary.md
+++ b/docs/glossary.md
@@ -15,3 +15,20 @@ FIXME(glossary-completeness): Expand this glossary before the first release so i
 - **restriction / scope-local registration** — a restriction (`tools.restrict`) filters the GLOBAL tool surface for one scope (compose by intersection); scope-local registrations are merged after that filter. A filtered-away global tool is absent from the prompt AND refuses execution, indistinguishably from a nonexistent one.
 - **setup window** — the creation slot where a creator composes an agent's scoped world (`CreateAgentOptions.setup`): after the scope and agent object exist but before the agent or session is published, `agent/session-start` fires, or the first prompt is assembled. Setup registers; it never drives the agent.
 - **lineage** — parent/child facts carried as data (`parentSession`, durable `delegationDepth`, runtime `subagentDepth`); never affects visibility. <a id="lineage"></a>
+
+## goal
+
+- **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.
+
+## human command
+
+- **human command** — a slash-prefixed instruction interpreted and executed by a human-facing adapter through `ctx.commands`, without becoming a model message. It is distinct from a model-facing tool and from shell command execution through `ctx.bash`.
+- **command plane** — discovery, parsing, dispatch, cancellation, and result rendering owned by UI adapters and command plugins. Command output is UI state unless the handler separately mutates a durable domain.
+
+## loop hierarchy
+
+- **turn** — one drain of admitted input in a session, ending after the model and its tools stop or a terminal policy intervenes. <a id="turn"></a>
+- **step** — one model request plus the tool executions caused by its response; a turn contains one or more steps. <a id="step"></a>
+- **round** — an outer policy iteration containing a turn, such as a [goal round](#goal-round). Round counters belong to that policy and do not count every turn in a session. <a id="round"></a>
diff --git a/docs/module-graph.md b/docs/module-graph.md
index fe774feedc..928e13119d 100644
--- a/docs/module-graph.md
+++ b/docs/module-graph.md
@@ -29,6 +29,11 @@ flowchart TD
     pkg_system_prompt["system-prompt"]
     pkg_tools["tools"]
   end
+  subgraph group_goal["packages/goal"]
+    pkg_goal["goal"]
+    pkg_goal_session["goal-session"]
+    pkg_tool_goal["tool-goal"]
+  end
   subgraph group_bash["packages/bash"]
     pkg_bash["bash"]
     pkg_bash_local["bash-local"]
@@ -107,6 +112,7 @@ flowchart TD
   subgraph group_ui["packages/ui"]
     pkg_acp["acp"]
     pkg_app_boot["app-boot"]
+    pkg_commands["commands"]
     pkg_jsonrpc["jsonrpc"]
     pkg_permission["permission"]
     pkg_tool_ask_user["tool-ask-user"]
@@ -204,6 +210,11 @@ flowchart TD
   pkg_llm_retry --> pkg_llm
   pkg_llm_retry --> pkg_session
   pkg_llm_retry --> pkg_timeout
+  pkg_goal --> pkg_agent
+  pkg_goal --> pkg_brand
+  pkg_goal --> pkg_llm
+  pkg_goal --> pkg_scope
+  pkg_goal --> pkg_session
   pkg_bash_local --> pkg_bash
   pkg_bash_local --> pkg_timeout
   pkg_fs_local --> pkg_fs
@@ -231,6 +242,8 @@ flowchart TD
   pkg_invariants --> pkg_llm
   pkg_invariants --> pkg_scope
   pkg_invariants --> pkg_session
+  pkg_commands --> pkg_agent
+  pkg_commands --> pkg_scope
   pkg_user_approval --> pkg_agent
   pkg_user_approval --> pkg_brand
   pkg_user_approval --> pkg_llm
@@ -255,6 +268,10 @@ flowchart TD
   pkg_tools --> pkg_session
   pkg_tools --> pkg_system_prompt
   pkg_tools --> pkg_user_approval
+  pkg_goal_session --> pkg_agent
+  pkg_goal_session --> pkg_goal
+  pkg_goal_session --> pkg_llm
+  pkg_goal_session --> pkg_session
   pkg_bash_sandbox --> pkg_bash
   pkg_bash_sandbox --> pkg_bash_local
   pkg_bash_sandbox --> pkg_sandbox
@@ -275,6 +292,12 @@ flowchart TD
   pkg_agent_loop --> pkg_session_persistence
   pkg_agent_loop --> pkg_system_prompt
   pkg_agent_loop --> pkg_tools
+  pkg_tool_goal --> pkg_agent
+  pkg_tool_goal --> pkg_goal
+  pkg_tool_goal --> pkg_llm
+  pkg_tool_goal --> pkg_session
+  pkg_tool_goal --> pkg_system_prompt
+  pkg_tool_goal --> pkg_tools
   pkg_tool_bash --> pkg_agent
   pkg_tool_bash --> pkg_bash
   pkg_tool_bash --> pkg_home
@@ -341,6 +364,7 @@ flowchart TD
   pkg_agent_loop_testkit --> pkg_tools
   pkg_acp --> pkg_agent
   pkg_acp --> pkg_bash
+  pkg_acp --> pkg_commands
   pkg_acp --> pkg_llm
   pkg_acp --> pkg_llm_retry
   pkg_acp --> pkg_permission
@@ -404,6 +428,7 @@ flowchart TD
   pkg_jsonrpc --> pkg_subagent
   pkg_tui --> pkg_agent
   pkg_tui --> pkg_agent_loop
+  pkg_tui --> pkg_commands
   pkg_tui --> pkg_llm
   pkg_tui --> pkg_llm_retry
   pkg_tui --> pkg_session
@@ -441,6 +466,7 @@ flowchart TD
   pkg_acp_demo --> pkg_acp
   pkg_acp_demo --> pkg_agent_spine_demo
   pkg_acp_demo --> pkg_app_boot
+  pkg_acp_demo --> pkg_commands
   pkg_acp_demo --> pkg_session_persistence_jsonl
   pkg_acp_demo --> pkg_tools
   pkg_acp_demo --> pkg_user_interaction
@@ -457,6 +483,7 @@ flowchart TD
   pkg_tui_demo --> pkg_agent_loop
   pkg_tui_demo --> pkg_agent_spine_demo
   pkg_tui_demo --> pkg_app_boot
+  pkg_tui_demo --> pkg_commands
   pkg_tui_demo --> pkg_llm
   pkg_tui_demo --> pkg_session
   pkg_tui_demo --> pkg_session_persistence_jsonl
@@ -509,6 +536,7 @@ flowchart TD
 | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) |
 | [`sandbox-policy`](../packages/sandbox/sandbox-policy) | `sandbox` | [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) |
 | [`llm-retry`](../packages/llm/llm-retry) | `llm` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) |
+| [`goal`](../packages/goal/goal) | `goal` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) |
 | [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) |
 | [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) |
 | [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) |
@@ -520,16 +548,19 @@ flowchart TD
 | [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) |
 | [`session-query`](../packages/session-query/session-query) | `session-query` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) |
 | [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) |
+| [`commands`](../packages/ui/commands) | `ui` | [`agent`](../packages/core/agent), [`scope`](../packages/core/scope) |
 | [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
 | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) |
 | [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent) |
 | [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) |
 | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) |
+| [`goal-session`](../packages/goal/goal-session) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) |
 | [`fs-sandbox`](../packages/fs/fs-sandbox) | `fs` | [`fs`](../packages/fs/fs), [`fs-local`](../packages/fs/fs-local), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) |
 | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) |
 | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
+| [`tool-goal`](../packages/goal/tool-goal) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
 | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`home`](../packages/util/home), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
 | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
 | [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
@@ -542,7 +573,7 @@ flowchart TD
 | [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) |
 | [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools) |
 | [`agent-loop-testkit`](../packages/support/agent-loop-testkit) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
-| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) |
+| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`commands`](../packages/ui/commands), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) |
 | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
 | [`workspace-context`](../packages/context/workspace-context) | `context` | [`agent`](../packages/core/agent), [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
 | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) |
@@ -554,11 +585,11 @@ flowchart TD
 | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
 | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
 | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) |
-| [`tui`](../packages/ui/tui) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`session`](../packages/core/session), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
+| [`tui`](../packages/ui/tui) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`commands`](../packages/ui/commands), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`session`](../packages/core/session), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
 | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`home`](../packages/util/home), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) |
 | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
 | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
 | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
-| [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) |
+| [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`commands`](../packages/ui/commands), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) |
 | [`cli-demo`](../packages/examples/cli-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) |
-| [`tui-demo`](../packages/examples/tui-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) |
+| [`tui-demo`](../packages/examples/tui-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`commands`](../packages/ui/commands), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) |
diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md
index 3caf1415fa..15e75afa29 100644
--- a/docs/tool-catalog.md
+++ b/docs/tool-catalog.md
@@ -21,6 +21,7 @@ This table connects model-visible tool names to the plugin package and service s
 | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. |
 | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. |
 | `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. |
+| `@deepseek-ai/dsh-tool-goal` | `create_goal`, `get_goal`, `update_goal` | `ctx.tools`, `ctx.agents`, `ctx.goals`, `ctx.systemPrompt`, `a calling Agent in an authorized open turn` | `tool/call`, `context/message goal snapshot for mutations`, `tool/result` | - | create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds. |
 | `@deepseek-ai/dsh-tool-skill` | `skill` | `ctx.tools`, `ctx.skills` | `tool/call`, `tool/result` | - | - |
 | `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/tui-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. |
 | `@deepseek-ai/dsh-tool-tasks` | `task_kill`, `task_list`, `task_output` | `ctx.tools`, `ctx.tasks`, `ctx.systemPrompt` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The kind-agnostic background-task control surface: a background bash command and a background subagent are read, listed, and killed through the same three tools. Loading the plugin attaches the control surface that arms producers' `ctx.tasks.start()`. |
@@ -393,6 +394,98 @@ Source: [`packages/fs/tool-fs-search/src/index.ts`](../packages/fs/tool-fs-searc
 
 glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.
 
+## `@deepseek-ai/dsh-tool-goal`
+
+### `create_goal`
+
+Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say "create a goal". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "objective": {
+      "type": "string",
+      "description": "The concrete completion objective inferred from the direct human request."
+    },
+    "max_goal_rounds": {
+      "type": "number",
+      "description": "Optional positive safe-integer limit on automatic continuation rounds."
+    }
+  },
+  "required": [
+    "objective"
+  ]
+}
+```
+
+Source: [`packages/goal/tool-goal/src/index.ts`](../packages/goal/tool-goal/src/index.ts)
+
+### `get_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
+{
+  "type": "object",
+  "properties": {}
+}
+```
+
+Source: [`packages/goal/tool-goal/src/index.ts`](../packages/goal/tool-goal/src/index.ts)
+
+### `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 and must explain it in blocked_reason.
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "goal_id": {
+      "type": "string",
+      "description": "Exact id returned by get_goal."
+    },
+    "revision": {
+      "type": "number",
+      "description": "Exact positive revision returned by get_goal."
+    },
+    "action": {
+      "type": "string",
+      "description": "edit | pause | resume | complete | blocked",
+      "enum": [
+        "edit",
+        "pause",
+        "resume",
+        "complete",
+        "blocked"
+      ]
+    },
+    "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."
+    }
+  },
+  "required": [
+    "goal_id",
+    "revision",
+    "action"
+  ]
+}
+```
+
+Source: [`packages/goal/tool-goal/src/index.ts`](../packages/goal/tool-goal/src/index.ts)
+
+create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds.
+
 ## `@deepseek-ai/dsh-tool-skill`
 
 ### `skill`
diff --git a/examples/acp-agent/goal.cordis.snapshot.yml b/examples/acp-agent/goal.cordis.snapshot.yml
new file mode 100644
index 0000000000..89e1078117
--- /dev/null
+++ b/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
diff --git a/examples/acp-agent/goal.cordis.yml b/examples/acp-agent/goal.cordis.yml
new file mode 100644
index 0000000000..d077104bb8
--- /dev/null
+++ b/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'
diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/input.json b/examples/acp-agent/tests/goal-snapshots/goal-session/input.json
new file mode 100644
index 0000000000..93392c9e0f
--- /dev/null
+++ b/examples/acp-agent/tests/goal-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" }
+  ]
+}
diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/replay.override.json b/examples/acp-agent/tests/goal-snapshots/goal-session/replay.override.json
new file mode 100644
index 0000000000..b0c5c0f28f
--- /dev/null
+++ b/examples/acp-agent/tests/goal-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" }
+]
diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl
new file mode 100644
index 0000000000..3129ceead5
--- /dev/null
+++ b/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl
@@ -0,0 +1,53 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
+{"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},"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},"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"}}}
diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/session.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/session.jsonl
new file mode 100644
index 0000000000..c8da831f95
--- /dev/null
+++ b/examples/acp-agent/tests/goal-snapshots/goal-session/session.jsonl
@@ -0,0 +1 @@
+{"type":"session","version":0,"id":"goal-session-placeholder","createdAt":0,"cwd":"/tmp/goal-session-placeholder"}
diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl
new file mode 100644
index 0000000000..61602dc289
--- /dev/null
+++ b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl
@@ -0,0 +1,11 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_create","title":"Create goal","kind":"other","status":"in_progress","rawInput":"Finish the ACP goal-session snapshot proof"}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_create","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_get","title":"Read current goal","kind":"read","status":"in_progress"}}}
+{"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"}}}}
diff --git a/examples/acp-agent/tests/goal.snapshot.ts b/examples/acp-agent/tests/goal.snapshot.ts
new file mode 100644
index 0000000000..42e3041721
--- /dev/null
+++ b/examples/acp-agent/tests/goal.snapshot.ts
@@ -0,0 +1,114 @@
+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'
+
+// This lifecycle proof has goal-specific timestamp normalization and semantic
+// assertions, so it owns a separate snapshot root from the generic ACP suite.
+const scenarioDir = join(dirname(fileURLToPath(import.meta.url)), 'goal-snapshots/goal-session')
+const fixtureFile = join(scenarioDir, 'session.jsonl')
+const overrideFile = join(scenarioDir, 'replay.override.json')
+const stdoutExpected = join(scenarioDir, 'stdout.expected.jsonl')
+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'))
+  })
+})
diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl
index ce3fe8acef..6410d07df3 100644
--- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-code","title":"return await tools.cordis_inspect({ what: 'dynamic' })","kind":"execute","status":"in_progress","rawInput":"return await tools.cordis_inspect({ what: 'dynamic' })"}}}
diff --git a/examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl
index d9d2632bd0..739deae606 100644
--- a/examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_spill","title":"node -e \"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\"","kind":"execute","status":"in_progress","rawInput":"node -e \"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\"","content":[{"type":"content","content":{"type":"text","text":"Print large deterministic output"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_spill","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nSPILL_START-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-SPILL_END\n\n(Omitted 1417 bytes. Full formatted result stored at: {{spillLocator:bash.txt}}. Use read with offset/limit, or grep this path to search within it.)\n```"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl
index 4111ecc8de..d6964687d1 100644
--- a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl
index 11178b9bc7..4d770492c5 100644
--- a/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_wait","title":"node -e \"setInterval(() => {}, 1000)\"","kind":"execute","status":"in_progress","rawInput":"node -e \"setInterval(() => {}, 1000)\"","content":[{"type":"content","content":{"type":"text","text":"Wait until cancellation"}}]}}}
 {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_wait","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: command aborted\n```"}}]}}}
diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl
index 4146e8804d..c17327002f 100644
--- a/examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl
@@ -1,4 +1,5 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}}
 {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}}
diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl
index f3bd0b345c..003205b364 100644
--- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl
index 3d25d176ac..043607a926 100644
--- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/config-options/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/config-options/stdout.expected.jsonl
index 47dc73536f..eb9762f95a 100644
--- a/examples/acp-agent/tests/snapshots/config-options/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/config-options/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","id":3,"result":{"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":"workspace-write","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","id":4,"result":{"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","id":5,"error":{"code":-32602,"message":"Invalid params: unknown permission value \"plan\""}}
diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
index e5fd8608d6..5ff9ec5bdd 100644
--- a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"inspect-tools-api","title":"Inspect cordis runtime: api: tools","kind":"read","status":"in_progress"}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"inspect-tools-api","status":"completed","content":[{"type":"content","content":{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n    /**\n     * Register globally or in the calling agent scope. Scoped tools shadow\n     * globals; duplicates within one layer and the reserved `run_code` name fail.\n     * @param definition - the tool schema, execution, and optional presentation functions.\n     * @returns the exact disposer that unregisters the tool.\n     */\n    register(definition: ToolDefinition): () => void\n    /**\n     * Restrict global tools for the calling agent scope. Empty filters, unknown\n     * names, scope-local names, and reserved transport names fail. Restrictions\n     * intersect; scoped registrations remain visible.\n     * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n     * @returns the exact disposer that lifts this restriction.\n     */\n    restrict(filter: ToolRestriction): () => void\n    /**\n     * Register a monotonic guard after the extensible `tools/pre-execute`\n     * waterfall. A plain-context guard applies globally; one registered through\n     * `agent.ctx` applies only to that agent. Any matching guard may deny by\n     * returning a reason, while no guard can force-allow a call another guard\n     * denied. The exact effect disposer is returned for ordered ownership and\n     * HMR cleanup.\n     * @param guard - synchronous check; a returned string denies the execution.\n     * @returns the exact disposer that unregisters the guard.\n     */\n    guard(guard: ToolGuard): () => void\n    /**\n     * Look up a tool as one scope sees it (scoped\n     * shadows global; a restricted-away global reads as absent). Presenters pass\n     * the calling agent so the rendered card matches the definition that\n     * actually executed.\n     * @param name - the tool name as registered.\n     * @param scope - the viewing scope (the agent); omitted = the global view.\n     * @returns the definition the scope resolves, or undefined when none is visible.\n     */\n    get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n    /**\n     * Project visible definitions onto the allowlisted model-facing schema fields,\n     * excluding execution and presentation callbacks.\n     * @param scope - the viewing scope (the agent); omitted = the global view.\n     * @returns one deep-cloned schema per visible tool.\n     */\n    schemas(scope?: ScopeKey): ToolSchema[]\n    /**\n     * Classify a pending call through the caller's visible tool definition. Only\n     * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n     * throwing classifiers are exclusive.\n     * @param exec - call name, parsed arguments, and optional agent scope.\n     * @returns the fail-closed scheduling mode.\n     */\n    executionMode(exec: ToolExecutionInput): ToolExecutionMode\n    /**\n     * Execute through pre-policy, guards, around-dispatch, post-policy, and final\n     * notification. Tool and listener failures resolve as materialized error\n     * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is\n     * the same lossless, frozen snapshot final observers receive.\n     * @param exec - the typed same-process call input. The registry assigns its\n     *   correlation token before policy begins.\n     * @returns the materialized final result.\n     */\n    async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n    export interface Agent {\n        readonly id: SessionId;\n        readonly options: AgentOptions;\n        readonly session: Session;\n        readonly status: AgentStatus;\n        readonly ctx: Context;\n        send(content: ContentBlock[], options?: SendOptions): void;\n        steer(content: ContentBlock[], options?: SendOptions): void;\n        inject(content: ContentBlock[], options?: InjectOptions): void;\n        cancel(reason?: string): void;\n        whenIdle(): Promise<void>;\n    }\n    export interface AgentOptions {\n        provider?: string;\n        model?: string;\n    }\n    export type AgentStatus = 'idle' | 'running' | 'disposed';\n    export type Branded<B extends string> = string & {\n        readonly [BRAND]: B;\n    };\n    export type CallId = Branded<'CallId'>;\n    export interface DiffCallView {\n        card: 'diff';\n        title: string;\n        diffs: FileDiff[];\n        locations?: FileLocation[];\n    }\n    export interface DiffResultView {\n        card: 'diff';\n        title?: string;\n        diffs: FileDiff[];\n    }\n    export interface FileDiff {\n        path: string;\n        oldText: string | null;\n        newText: string;\n    }\n    export interface FileLocation {\n        path: string;\n        line?: number;\n    }\n    export interface GenericCallView {\n        card: 'generic';\n        title: string;\n        kind?: ToolCallKind;\n        rawInput?: unknown;\n        content?: ContentBlock[];\n        locations?: FileLocation[];\n    }\n    export interface GenericResultView {\n        card: 'generic';\n        title?: string;\n        content?: ContentBlock[];\n    }\n    export interface HookContext {\n        content: ContentBlock[];\n        source: MessageSource;\n        meta?: JsonValue;\n    }\n    export interface InjectOptions extends SendOptions {\n        meta?: JsonValue;\n    }\n    export type JsonValue = null | boolean | number | string | JsonValue[] | {\n        [key: string]: JsonValue;\n    };\n    export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n    export interface MessageSourceMap {\n        user: {\n            kind: 'user';\n        };\n        plugin: {\n            kind: 'plugin';\n            plugin: string;\n        };\n    }\n    export type ScopeKey = object;\n    export interface SendOptions {\n        source?: MessageSource;\n    }\n    export type SessionId = Branded<'SessionId'>;\n    export interface TerminalCallView {\n        card: 'terminal';\n        title: string;\n        description?: string;\n        cwd?: string;\n    }\n    export interface TerminalResultView {\n        card: 'terminal';\n        title?: string;\n        output?: string;\n        exitCode?: number;\n        signal?: string;\n    }\n    export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n    export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n    export interface ToolDefinition extends ToolSchema {\n        execute(args: unknown, exec: ToolRunContext): Promise<ToolExecuteReturn>;\n        timeoutMs?: number;\n        isConcurrencySafe?(args: unknown): boolean;\n        presentCall?(args: unknown): ToolCallView | undefined;\n        presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n    }\n    export interface ToolErrorInfo {\n        name: string;\n        code: string;\n    }\n    export type ToolExecuteReturn = ContentBlock[] | {\n        content: ContentBlock[];\n        meta?: unknown;\n    };\n    export interface ToolExecution extends ToolExecutionInput {\n        readonly token: ToolExecutionToken;\n    }\n    export interface ToolExecutionInput {\n        readonly callId: CallId;\n        readonly name: string;\n        readonly arguments: unknown;\n        readonly agent?: Agent;\n        readonly parent?: ToolExecutionToken;\n        signal?: AbortSignal;\n    }\n    export type ToolExecutionMode = {\n        kind: 'parallel';\n    } | {\n        kind: 'exclusive';\n    };\n    export interface ToolExecutionResult {\n        content: ContentBlock[];\n        isError: boolean;\n        error?: ToolErrorInfo;\n        additionalContexts?: HookContext[];\n        meta?: unknown;\n    }\n    export type ToolExecutionToken = symbol & {\n        readonly [toolExecutionTokenBrand]: true;\n    };\n    export type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined;\n    export interface ToolRestriction {\n        readonly allow?: readonly string[];\n        readonly deny?: readonly string[];\n    }\n    export interface ToolResult {\n        content: ContentBlock[];\n        isError: boolean;\n        meta?: unknown;\n    }\n    export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n    export interface ToolRunContext extends ToolExecution {\n        deferContext(context: HookContext): void;\n    }\n    export interface ToolSchema {\n        name: string;\n        description: string;\n        parameters: Record<string, unknown>;\n    }"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"inspect-tools-event","title":"Inspect cordis runtime: events: tools/pre-execute","kind":"read","status":"in_progress"}}}
diff --git a/examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl
index f941121f12..fa24d8140d 100644
--- a/examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl
@@ -1,4 +1,5 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\n\n[Model attempt failed; any partial output above is discarded: simulated provider error (HTTP 401)]\n\n"}}}}
 {"jsonrpc":"2.0","id":3,"error":{"code":-32603,"message":"Internal error: turn failed: simulated provider error (HTTP 401)"}}
diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.expected.jsonl
index 92743b8133..de4c76482c 100644
--- a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","id":3,"result":{"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":"workspace-write","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":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.expected.jsonl
index c8a9b320f0..e99bb3a5bb 100644
--- a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","id":3,"result":{"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":"workspace-write","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":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl
index fab47cc857..40223acda3 100644
--- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-escalation-approved/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-escalation-approved/stdout.expected.jsonl
index b8b2f245ee..c42d0d5d56 100644
--- a/examples/acp-agent/tests/snapshots/fs-escalation-approved/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-escalation-approved/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","id":3,"result":{"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":"workspace-write","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":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl
index d92ed5520b..635a185739 100644
--- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl
index 44ce1184e9..c2dcf2a731 100644
--- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl
index 712e8e5c3b..4ce2099ace 100644
--- a/examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl
index d06162a005..3244ee21c3 100644
--- a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl
index 270d1ace7c..f8c7edd015 100644
--- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl
index 1cac540a29..e2e3bef55d 100644
--- a/examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/handshake/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/handshake/stdout.expected.jsonl
index fb4f7cbbc5..dab4affa7e 100644
--- a/examples/acp-agent/tests/snapshots/handshake/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/handshake/stdout.expected.jsonl
@@ -1,2 +1,3 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl
index af42092168..653a7340f8 100644
--- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl
index bed3d3a03a..2aa177932e 100644
--- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl
index 48b5df1ac2..262ce3e2ea 100644
--- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl
index 74f4b9ea10..094e78be67 100644
--- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.expected.jsonl
index 29023a8d45..a6accd8f18 100644
--- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.expected.jsonl
@@ -1,3 +1,4 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}}
diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl
index 15bf48cb81..44a5da1302 100644
--- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'s"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl
index 2d92b5b3e7..1c39ec6502 100644
--- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl
index 7870b73dc2..05fc598709 100644
--- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl
index cece2795f7..bc4266cc04 100644
--- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl
index 1a0e83d191..73e123a566 100644
--- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.expected.jsonl
index 29023a8d45..a6accd8f18 100644
--- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.expected.jsonl
@@ -1,3 +1,4 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}}
diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl
index 15a91d1af3..2c602e4cc1 100644
--- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl
index a3e72075ed..0d727080d6 100644
--- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl
index 291525f825..e50144c03e 100644
--- a/examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl
index 9a55a86f02..a9da0b4a4f 100644
--- a/examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl
index 8680db3d30..946a91f75a 100644
--- a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_a","title":"Read a.txt","kind":"read","status":"in_progress","locations":[{"path":"a.txt","line":1}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_b","title":"Read b.txt","kind":"read","status":"in_progress","locations":[{"path":"b.txt","line":1}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_read_a","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/a.txt</path>\n<type>file</type>\n<content>\n1: alpha\n\n(End of file - total 1 lines)\n</content>"}}]}}}
diff --git a/examples/acp-agent/tests/snapshots/permission-switching/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.expected.jsonl
index 358e81f076..53197fe328 100644
--- a/examples/acp-agent/tests/snapshots/permission-switching/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/permission-switching/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","id":3,"result":{"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":"workspace-write","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":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl
index 8469933a94..f1c2fd0634 100644
--- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_1","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"watch the kettle boil","status":"in_progress"}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"watch the kettle boil","priority":"medium","status":"in_progress"}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_1","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}}]}}}
diff --git a/examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl
index a1b4b8c0cb..3e17783db5 100644
--- a/examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<skill_content name=\"snapshot-skill\">\n<skill_resources>\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n</skill_instructions>\n</skill_content>"}}]}}}
diff --git a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/stdout.expected.jsonl
index 7f629a2d71..496f7568b8 100644
--- a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_root_child","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Start depth one","prompt":"Call subagent once. Ask that child to attempt one further subagent call, then report the result."}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_root_child","status":"completed","content":[{"type":"content","content":{"type":"text","text":"DEPTH_ONE_DONE"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ROOT_DONE"}}}}
diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl
index e2941dd851..dd21b9674f 100644
--- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl
index e5cc8bfa90..7bfd214919 100644
--- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl
index bd4fb81d4a..4916b87bc8 100644
--- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl
index 2b77e856e6..22e034b251 100644
--- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl
index c717c3182a..6171c640e4 100644
--- a/examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl
index 8771e50182..ee40cae2fd 100644
--- a/examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl
index 2c19d8feb9..9183664a0f 100644
--- a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl
index 03f482bcc6..24333f95a0 100644
--- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl
index a55c6d6e01..3b233174fc 100644
--- a/examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_workspace_read","title":"Read nested/task.txt","kind":"read","status":"in_progress","locations":[{"path":"nested/task.txt","line":1}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_workspace_read","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl
index 4e8db74ba6..38c5dcdfc1 100644
--- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl
@@ -1,5 +1,6 @@
 {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
 {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
diff --git a/examples/headless-agent/goal.cordis.snapshot.yml b/examples/headless-agent/goal.cordis.snapshot.yml
new file mode 100644
index 0000000000..b853410ef0
--- /dev/null
+++ b/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'
diff --git a/examples/headless-agent/goal.cordis.yml b/examples/headless-agent/goal.cordis.yml
new file mode 100644
index 0000000000..8f8cdf9e0b
--- /dev/null
+++ b/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'
diff --git a/examples/headless-agent/tests/fixtures/goal-domain/cordis.yml b/examples/headless-agent/tests/fixtures/goal-domain/cordis.yml
new file mode 100644
index 0000000000..bc9b71685e
--- /dev/null
+++ b/examples/headless-agent/tests/fixtures/goal-domain/cordis.yml
@@ -0,0 +1,24 @@
+# Test-only composition: create one goal through a Loader-mounted step consumer.
+- id: cli-mock-llm
+  name: '../cli-mock-llm.ts'
+
+- id: bash
+  name: '@deepseek-ai/dsh-bash-local'
+
+- id: goal
+  name: '@deepseek-ai/dsh-goal'
+  config:
+    defaultMaxGoalRounds: 11
+
+- id: seed-goal
+  name: './seed-goal.ts'
+
+- id: cli-agent
+  name: '@deepseek-ai/dsh-cli-demo'
+  config:
+    provider: cli-mock
+    model: cli-mock
+    persona: 'Test the persisted goal domain.'
+    persistenceRoot: './.sessions'
+    persistenceCompression: none
+    workspaceContext: false
diff --git a/examples/headless-agent/tests/fixtures/goal-domain/seed-goal.ts b/examples/headless-agent/tests/fixtures/goal-domain/seed-goal.ts
new file mode 100644
index 0000000000..254870eca9
--- /dev/null
+++ b/examples/headless-agent/tests/fixtures/goal-domain/seed-goal.ts
@@ -0,0 +1,17 @@
+/** Test-only Loader plugin that creates a goal at the first real step edge. */
+
+import type { Context } from 'cordis'
+import type {} from '@deepseek-ai/dsh-goal'
+
+export const name = 'seed-goal'
+export const inject = ['goals']
+
+export function apply(ctx: Context): void {
+  ctx.on('agent/pre-step', (agent) => {
+    if (ctx.goals.get(agent) !== undefined) return
+    ctx.goals.create(agent, {
+      objective: 'Prove the composed goal survives in the session log',
+      maxGoalRounds: 7,
+    })
+  })
+}
diff --git a/examples/headless-agent/tests/headless.snapshot.ts b/examples/headless-agent/tests/headless.snapshot.ts
index dc448b9b23..d799c6250d 100644
--- a/examples/headless-agent/tests/headless.snapshot.ts
+++ b/examples/headless-agent/tests/headless.snapshot.ts
@@ -11,10 +11,12 @@ import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-l
 import { describe, expect, it } from 'vitest'
 
 const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
-const scenarioDir = join(snapshotsDir, 'advanced-toolchain')
-const sessionFixture = join(scenarioDir, 'session.jsonl')
-const streamExpected = join(scenarioDir, 'stream-json.expected.jsonl')
-const configPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url))
+const advancedScenarioDir = join(snapshotsDir, 'advanced-toolchain')
+const advancedSessionFixture = join(advancedScenarioDir, 'session.jsonl')
+const advancedStreamExpected = join(advancedScenarioDir, 'stream-json.expected.jsonl')
+const advancedConfigPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url))
+const goalScenarioDir = join(snapshotsDir, 'goal-tools')
+const goalConfigPath = fileURLToPath(new URL('../goal.cordis.snapshot.yml', import.meta.url))
 const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
 const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
 const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
@@ -70,12 +72,36 @@ function normalizeHeadlessStream(rawStdout: string, cwd: string): string {
   return normalizeStdout(`${normalizedRecords.map(record => JSON.stringify(record)).join('\n')}\n`, context)
 }
 
-async function advancedPrompt(): Promise<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)
diff --git a/examples/headless-agent/tests/snapshots/goal-tools/input.json b/examples/headless-agent/tests/snapshots/goal-tools/input.json
new file mode 100644
index 0000000000..5263ccd4e2
--- /dev/null
+++ b/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."
+    }
+  ]
+}
diff --git a/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json b/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json
new file mode 100644
index 0000000000..aec5204c7d
--- /dev/null
+++ b/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" } }
+    ]
+  }
+]
diff --git a/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl b/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl
new file mode 100644
index 0000000000..0721003577
--- /dev/null
+++ b/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl
@@ -0,0 +1,34 @@
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Create a durable goal to finish the snapshot proof, then inspect it."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"context/message","seq":12,"time":0,"data":{"content":[{"type":"text","text":"<goal_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},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":30,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":31,"time":0,"data":{"turn":1,"step":3}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":32,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
+{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":85,"outputTokens":14}}
diff --git a/examples/package.json b/examples/package.json
index f9956c498d..ed7b51680c 100644
--- a/examples/package.json
+++ b/examples/package.json
@@ -19,6 +19,8 @@
     "@deepseek-ai/dsh-fs-local": "workspace:*",
     "@deepseek-ai/dsh-fs-policy": "workspace:*",
     "@deepseek-ai/dsh-fs-sandbox": "workspace:^",
+    "@deepseek-ai/dsh-goal": "workspace:*",
+    "@deepseek-ai/dsh-goal-session": "workspace:*",
     "@deepseek-ai/dsh-hooks-claude": "workspace:*",
     "@deepseek-ai/dsh-hooks-codex": "workspace:*",
     "@deepseek-ai/dsh-jsonrpc": "workspace:*",
@@ -42,6 +44,7 @@
     "@deepseek-ai/dsh-tool-cordis": "workspace:*",
     "@deepseek-ai/dsh-tool-fs": "workspace:*",
     "@deepseek-ai/dsh-tool-fs-search": "workspace:*",
+    "@deepseek-ai/dsh-tool-goal": "workspace:*",
     "@deepseek-ai/dsh-tool-subagent": "workspace:*",
     "@deepseek-ai/dsh-tool-todo": "workspace:*",
     "@deepseek-ai/dsh-tool-workflow": "workspace:*",
diff --git a/examples/tui-agent/tests/tui.snapshot.ts b/examples/tui-agent/tests/tui.snapshot.ts
index 534207c875..2c62ba25e6 100644
--- a/examples/tui-agent/tests/tui.snapshot.ts
+++ b/examples/tui-agent/tests/tui.snapshot.ts
@@ -9,6 +9,7 @@ import type { Agent } from '@deepseek-ai/dsh-agent'
 import * as AgentCore from '@deepseek-ai/dsh-agent-spine-demo'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
 import WorkerCodeRuntime from '@deepseek-ai/dsh-code-runtime-worker'
+import CommandService from '@deepseek-ai/dsh-commands'
 import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
 import * as FsPolicy from '@deepseek-ai/dsh-fs-policy'
 import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
@@ -179,6 +180,7 @@ async function mountScenarioContext(
   await ctx.plugin(ToolSubagent, { provider: 'spawn', toolName: 'subagent', enableRunInBackground: false })
   await ctx.plugin(WorkerWorkflowEngine, { provider: 'spawn' })
   await ctx.plugin(ToolWorkflow)
+  await ctx.plugin(CommandService)
   if (scenario.composition === 'code' || scenario.composition === 'advanced') {
     await ctx.plugin(WorkerCodeRuntime, {})
   }
diff --git a/knip.json b/knip.json
index 6d0798031a..845d38a95d 100644
--- a/knip.json
+++ b/knip.json
@@ -10,6 +10,7 @@
     "examples": {
       "entry": [
         "headless-agent/tests/fixtures/cli-mock-llm.ts",
+        "headless-agent/tests/fixtures/goal-domain/seed-goal.ts",
         "headless-agent/tests/fixtures/time-context-driver.ts",
         "headless-agent/tests/fixtures/time-context-mock-llm.ts",
         "tui-agent/tests/fixtures/tui-scripted-llm.ts",
@@ -77,6 +78,18 @@
       "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
       "project": ["src/**/*.ts", "tests/**/*.ts"]
     },
+    "packages/goal/goal": {
+      "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
+      "project": ["src/**/*.ts", "tests/**/*.ts"]
+    },
+    "packages/goal/goal-session": {
+      "entry": ["tests/**/*.spec.ts"],
+      "project": ["src/**/*.ts", "tests/**/*.ts"]
+    },
+    "packages/goal/tool-goal": {
+      "entry": ["tests/**/*.spec.ts"],
+      "project": ["src/**/*.ts", "tests/**/*.ts"]
+    },
     "packages/code-runtime/code-runtime-worker": {
       "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
       "project": ["src/**/*.ts", "tests/**/*.ts"]
@@ -126,6 +139,10 @@
       "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
       "project": ["src/**/*.ts", "tests/**/*.ts"]
     },
+    "packages/ui/commands": {
+      "entry": ["tests/**/*.spec.ts"],
+      "project": ["src/**/*.ts", "tests/**/*.ts"]
+    },
     "packages/examples/tui-demo": {
       "entry": ["tests/**/*.spec.ts"],
       "project": ["src/**/*.ts", "tests/**/*.ts"]
diff --git a/packages/README.md b/packages/README.md
index d6f1b3355b..3976a0da09 100644
--- a/packages/README.md
+++ b/packages/README.md
@@ -9,6 +9,7 @@ Packages live at `packages/<group>/<pkg>/`; groups are containers, while names r
 | Group | Role | Release expectation |
 |---|---|---|
 | [`core/`](core/README.md) | Product API spine: sessions, prompts, tools, agent services, and the concrete loop | Product — stable surface |
+| [`goal/`](goal/README.md) | Persisted same-session goal state and lifecycle | Product — stable surface |
 | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface |
 | [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface |
 | [`code-runtime/`](code-runtime/README.md) | Code-execution capability family: the abstract runtime seam for model-written programs + a worker-thread backend | Product — stable surface |
diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts
index 1a80184d33..905306e362 100644
--- a/packages/cordis/tool-cordis/src/api-catalog.ts
+++ b/packages/cordis/tool-cordis/src/api-catalog.ts
@@ -198,6 +198,28 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
       },
     ],
   },
+  {
+    key: 'commands',
+    summary: 'Human-command registry.',
+    methods: [
+      {
+        signature: 'register(definition: CommandDefinition): () => void',
+        jsDoc: '/**\n * Register a global or calling-agent-scoped command.\n * @param definition - discovery metadata and direct UI handler.\n * @returns the exact effect disposer that unregisters this definition.\n */',
+      },
+      {
+        signature: 'list(agent: Agent): readonly CommandDescriptor[]',
+        jsDoc: '/**\n * List the effective immutable command descriptors for one agent.\n * @param agent - exact receiving agent and scoped-layer key.\n * @returns name-sorted descriptors after scoped shadowing.\n */',
+      },
+      {
+        signature: 'find(agent: Agent, name: string): CommandDefinition | undefined',
+        jsDoc: '/**\n * Resolve one effective command definition.\n * @param agent - exact receiving agent and scoped-layer key.\n * @param name - command name without a slash.\n * @returns the scoped shadow or global definition.\n */',
+      },
+      {
+        signature: 'async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise<CommandResult | undefined>',
+        jsDoc: '/**\n * Parse and execute a known command without sending it to the model.\n * @param agent - exact receiving agent.\n * @param line - complete slash-command line.\n * @param signal - cancellation signal owned by the UI request.\n * @returns a detached result, or `undefined` when syntax or name does not resolve.\n */',
+      },
+    ],
+  },
   {
     key: 'compact',
     summary: 'Abstract compaction service.',
@@ -250,6 +272,48 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
       },
     ],
   },
+  {
+    key: 'goals',
+    summary: 'Goal service (`ctx.goals`) backed exclusively by the owning session log.',
+    methods: [
+      {
+        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 */',
+      },
+      {
+        signature: 'disarm(agent: Agent): GoalView | undefined',
+        jsDoc: '/**\n * Remove process-local continuation authority without changing durable goal\n * phase or revision. Lifecycle owners use this before unloading a driver;\n * a later human-authorized {@link resume} records the new activation edge.\n * @param agent - owning live agent.\n * @returns a fresh disarmed view, or `undefined` when no goal is current.\n */',
+      },
+      {
+        signature: 'create(agent: Agent, request: CreateGoalRequest): GoalView',
+        jsDoc: '/**\n * Create and arm a goal. A completed goal may be replaced; every other\n * current phase must be cleared or resumed instead.\n * @param agent - owning live agent.\n * @param request - objective and optional round cap.\n * @returns the created live view.\n */',
+      },
+      {
+        signature: 'edit(agent: Agent, ref: GoalRef, request: EditGoalRequest): GoalView',
+        jsDoc: '/**\n * Edit objective and/or round cap without changing phase.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @param request - at least one replacement field.\n * @returns the edited view.\n */',
+      },
+      {
+        signature: 'pause(agent: Agent, ref: GoalRef): GoalView',
+        jsDoc: '/**\n * Pause an active goal and disarm automatic continuation.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @returns the paused view.\n */',
+      },
+      {
+        signature: 'resume(agent: Agent, ref: GoalRef): GoalView',
+        jsDoc: '/**\n * Resume and arm a stopped goal, or rearm an active goal after a\n * session-start edge, while its round budget still has capacity.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @returns the active view.\n */',
+      },
+      {
+        signature: 'complete(agent: Agent, ref: GoalRef): GoalView',
+        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, 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',
+        jsDoc: '/**\n * Clear the current goal while retaining a durable tombstone and history.\n * @param agent - owning live agent.\n * @param ref - expected current revision.\n * @returns the tombstone ref whose revision is one past the cleared snapshot.\n */',
+      },
+    ],
+  },
   {
     key: 'llm',
     summary: 'The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.',
@@ -641,6 +705,13 @@ export const EVENT_API: readonly EventApiEntry[] = [
     jsDoc: '/**\n * A declarative agent entry failed before it could publish a live agent.\n * Consumers that buffer work for the configured identity use this\n * transient signal to reject that work instead of waiting forever. Normal\n * factory teardown suppresses failures from the cancelled startup attempt.\n * @param sessionId - exact shared agent/session identity that failed startup.\n * @param error - persistence, setup, or publication failure.\n * @mode emit\n */',
     summary: 'A declarative agent entry failed before it could publish a live agent.',
   },
+  {
+    name: 'agent/cancel-requested',
+    mode: 'emit',
+    signature: '\'agent/cancel-requested\'(this: Scoped<Agent>, agent: Agent, reason: string): void',
+    jsDoc: '/**\n * Effective broad cancellation was requested, before queued/steering work\n * is cleared or the active step is aborted. This observe-only notification\n * cannot veto cancellation; listener failures are contained.\n * @param agent - the agent whose current work is being cancelled.\n * @param reason - resolved cancellation reason, including the default.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */',
+    summary: 'Effective broad cancellation was requested, before queued/steering work is cleared or the active step is aborted.',
+  },
   {
     name: 'agent/created',
     mode: 'emit',
@@ -753,6 +824,13 @@ export const EVENT_API: readonly EventApiEntry[] = [
     jsDoc: '/**\n * Ask composed answerers for one decision. Return an outcome to claim the\n * request or call `next()`; failure yields the fail-closed default.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @param req - the pending decision (agent, tool identity, reason, signal).\n * @mode waterfall\n */',
     summary: 'Ask composed answerers for one decision.',
   },
+  {
+    name: 'commands/change',
+    mode: 'emit',
+    signature: '\'commands/change\'(): void',
+    jsDoc: '/**\n * A command was registered or unregistered. This is an unfiltered registry\n * notification because a global or scoped change may affect any UI view.\n * Observer failures are contained and cannot veto the registry mutation.\n * @mode emit\n */',
+    summary: 'A command was registered or unregistered.',
+  },
   {
     name: 'fs/edit-intent',
     mode: 'waterfall',
@@ -774,6 +852,13 @@ export const EVENT_API: readonly EventApiEntry[] = [
     jsDoc: '/**\n * Single-slot decision for the next {@link FileSystem.writeText}. Calling\n * `next()` yields the bare provider\'s unconditional write; the first listener\n * that returns an intent owns the decision rather than composing with peers.\n * @param target - the resolved target about to be written.\n * @param actor - the opaque tool-execution context the decider keys off.\n * @mode waterfall\n */',
     summary: 'Single-slot decision for the next FileSystem.writeText.',
   },
+  {
+    name: 'goal/changed',
+    mode: 'emit',
+    signature: '\'goal/changed\'(this: import(\'@deepseek-ai/dsh-scope\').Scoped<Agent>, agent: Agent, change: GoalChanged): void',
+    jsDoc: '/**\n * Goal mutation accepted by one live agent. The matching context event is\n * already appended or queued in that agent\'s active tool-batch FIFO.\n * Listener failures are contained.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @param agent - agent whose session owns the goal.\n * @param change - fresh current projection or clear tombstone.\n * @mode emit\n */',
+    summary: 'Goal mutation accepted by one live agent.',
+  },
   {
     name: 'llm/stream',
     mode: 'waterfall',
@@ -1068,6 +1153,26 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'CollectedOutput',
     declaration: 'export interface CollectedOutput {\n    text: string;\n    truncated: boolean;\n    spillPath?: string;\n}',
   },
+  {
+    name: 'CommandDefinition',
+    declaration: 'export interface CommandDefinition {\n    readonly name: string;\n    readonly description: string;\n    readonly input?: CommandInputDescriptor;\n    readonly handler: (invocation: CommandInvocation) => CommandResult | Promise<CommandResult>;\n}',
+  },
+  {
+    name: 'CommandDescriptor',
+    declaration: 'export interface CommandDescriptor {\n    readonly name: string;\n    readonly description: string;\n    readonly input?: CommandInputDescriptor;\n}',
+  },
+  {
+    name: 'CommandInputDescriptor',
+    declaration: 'export interface CommandInputDescriptor {\n    readonly hint: string;\n}',
+  },
+  {
+    name: 'CommandInvocation',
+    declaration: 'export interface CommandInvocation {\n    readonly agent: Agent;\n    readonly rawInput: string;\n    readonly signal: AbortSignal;\n}',
+  },
+  {
+    name: 'CommandResult',
+    declaration: 'export type CommandResult = {\n    readonly kind: \'success\';\n    readonly text?: string;\n} | {\n    readonly kind: \'error\';\n    readonly text: string;\n};',
+  },
   {
     name: 'CompactAgentContext',
     declaration: 'export interface CompactAgentContext {\n    session: Session;\n    options: {\n        provider?: string;\n        model?: string;\n    };\n}',
@@ -1100,6 +1205,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'CreateAgentOptions',
     declaration: 'export interface CreateAgentOptions {\n    readonly sessionId: SessionId;\n    readonly meta?: {\n        readonly cwd?: string;\n        readonly parentSession?: SessionId;\n        readonly seedLength?: number;\n        readonly delegationDepth?: number;\n    };\n    readonly seed?: readonly SessionEvent[];\n    readonly agentOptions?: AgentOptions;\n    readonly signal?: AbortSignal;\n    readonly setup?: (agentCtx: Context) => Promise<void> | void;\n}',
   },
+  {
+    name: 'CreateGoalRequest',
+    declaration: 'export interface CreateGoalRequest {\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        readonly delegationDepth?: number;\n    };\n}',
@@ -1120,6 +1229,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'DshEnvironmentKey',
     declaration: 'export type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}`;',
   },
+  {
+    name: 'EditGoalRequest',
+    declaration: 'export interface EditGoalRequest {\n    readonly objective?: string;\n    readonly maxGoalRounds?: number;\n}',
+  },
   {
     name: 'EpochHeader',
     declaration: 'export interface EpochHeader {\n    config: LlmCallConfig;\n    system?: string;\n    tools?: ToolSchema[];\n    messagePrefix?: Message[];\n}',
@@ -1192,6 +1305,34 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'GenericResultView',
     declaration: 'export interface GenericResultView {\n    card: \'generic\';\n    title?: string;\n    content?: ContentBlock[];\n}',
   },
+  {
+    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\' | \'complete\';',
+  },
+  {
+    name: 'GoalRef',
+    declaration: 'export interface GoalRef {\n    readonly id: GoalId;\n    readonly revision: number;\n}',
+  },
+  {
+    name: 'GoalSnapshot',
+    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',
+    declaration: 'export interface GoalView extends GoalSnapshot {\n    readonly roundsStarted: number;\n    readonly createdAt: number;\n    readonly updatedAt: number;\n    readonly activation: GoalActivation;\n}',
+  },
   {
     name: 'HookContext',
     declaration: 'export interface HookContext {\n    content: ContentBlock[];\n    source: MessageSource;\n    meta?: JsonValue;\n}',
diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md
index 696b3a2cf7..f4193d44ad 100644
--- a/packages/core/agent-loop/README.md
+++ b/packages/core/agent-loop/README.md
@@ -56,7 +56,7 @@ The driver owns one agent for its lifetime and runs inside `ctx.agents.withIniti
 
 Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history.
 
-Plugin failure ends the current turn, not the loop. Only final adapter dispatch/iteration failures and terminal in-band error or aborted finishes enter `agent/request-error`; middleware, result processing, tools, and `agent/post-step` remain ordinary turn failures. Recovery receives the exact live error, immutable provider facts, and immutable prior failures after the failed step closes. A retry rebuilds from the durable log in a new numbered step, success clears the consecutive history, and exhaustion records the structured failure once on `turn/end`. Cancellation clears pending work and aborts the current step without leaking to the next prompt; undispatched model tool calls receive synthetic `tool/call` and aborted result pairs. Terminal continuation stops remain authoritative through turn close and durability flush.
+Plugin failure ends the current turn, not the loop. Only final adapter dispatch/iteration failures and terminal in-band error or aborted finishes enter `agent/request-error`; middleware, result processing, tools, and `agent/post-step` remain ordinary turn failures. Recovery receives the exact live error, immutable provider facts, and immutable prior failures after the failed step closes. A retry rebuilds from the durable log in a new numbered step, success clears the consecutive history, and exhaustion records the structured failure once on `turn/end`. Effective cancellation resolves its reason and emits `agent/cancel-requested` before clearing pending work or aborting the current step; notification failures are contained, queued work added by an observer is included in the same broad clear, and idle cancellation emits nothing. Undispatched model tool calls receive synthetic `tool/call` and aborted result pairs. Terminal continuation stops remain authoritative through turn close and durability flush.
 
 Within a step, exclusive calls form barriers; parallel-safe calls use a bounded rolling pool and are reclassified before start. Only dispatch/body overlaps. Policy, durable results, and result context remain model-ordered. Abort stops new calls, drains started results, then drains accepted batch context before the turn closes through the normal abort path.
 
diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts
index 8478ec1818..847a15d64f 100644
--- a/packages/core/agent-loop/src/agent.ts
+++ b/packages/core/agent-loop/src/agent.ts
@@ -331,13 +331,18 @@ export class ReactLoopAgent implements Agent {
   }
 
   cancel(reason?: string): void {
+    const resolvedReason = reason ?? 'cancelled'
     // Arm only for current work; an idle marker would cancel the next prompt.
     if (this._status === 'running' || this.currentAbort !== undefined || this.#inbox.hasQueued || this.#inbox.hasSteering) {
       this.cancelRequested = true
       // Capture the resolved reason for the marker-only windows (pre-step /
       // continuation). The mid-step path reads it from abort.signal.reason
       // below; the marker path reads it via the LoopHandle's cancelReason().
-      this.cancelReason = reason ?? 'cancelled'
+      this.cancelReason = resolvedReason
+      // Coordination consumers must update their own state before this call
+      // clears the inbox or aborts the step. Notification failures are
+      // contained by the fused dispatcher and cannot veto cancellation.
+      agentEvents(this.loopCtx, this).emit('agent/cancel-requested', resolvedReason)
     }
     // Drop all pending queued + steering work (un-started prompts never run; the
     // cancelled turn's steering is not re-enqueued). Cleared directly even when
@@ -347,7 +352,7 @@ export class ReactLoopAgent implements Agent {
     // Interrupt an in-flight step immediately (the running turn observes the
     // abort and ends `aborted`). The marker covers the windows where no step is
     // running (pre-step, continuation).
-    this.currentAbort?.abort(reason ?? 'cancelled')
+    this.currentAbort?.abort(resolvedReason)
   }
 
   /**
diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts
index 39289779be..f6df171365 100644
--- a/packages/core/agent-loop/tests/cancel.spec.ts
+++ b/packages/core/agent-loop/tests/cancel.spec.ts
@@ -7,7 +7,7 @@
  * @module dsh-agent-loop/tests/cancel
  */
 
-import { describe, expect, it } from 'vitest'
+import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import LlmService, { type Message } from '@deepseek-ai/dsh-llm'
 import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
@@ -55,6 +55,33 @@ function userTexts(agent: Agent): string[] {
 }
 
 describe('Agent.cancel()', () => {
+  it('notifies every observer before clearing work and contains listener failures', async () => {
+    const adapter = new MockAdapter([textResponse('must remain unused')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('cancel-event'), { provider: 'mock', model: 'mock' })
+    const warned = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {})
+    const seen: string[] = []
+    ctx.on('agent/cancel-requested', (subject, reason) => {
+      if (subject !== agent) return
+      seen.push(`first:${reason}`)
+      subject.send([{ type: 'text', text: 'queued by cancel observer' }])
+      throw new Error('observer failed')
+    })
+    ctx.on('agent/cancel-requested', (subject, reason) => {
+      if (subject === agent) seen.push(`second:${reason}`)
+    })
+
+    send(agent, 'drop me')
+    agent.cancel()
+    await new Promise(resolve => setTimeout(resolve, 30))
+    agent.cancel('idle no-op')
+
+    expect(seen).toEqual(['first:cancelled', 'second:cancelled'])
+    expect(userTexts(agent)).toEqual([])
+    expect(adapter.requests).toHaveLength(0)
+    expect(warned).toHaveBeenCalledWith(expect.stringContaining('agent/cancel-requested'))
+  })
+
   it('cancel() on an idle agent with nothing queued is a no-op; the next prompt runs (F2 leak guard)', async () => {
     const adapter = new MockAdapter([textResponse('reply')])
     const ctx = await harness(adapter)
diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md
index 2908569ade..72de35107b 100644
--- a/packages/core/agent/README.md
+++ b/packages/core/agent/README.md
@@ -44,7 +44,7 @@ Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-age
 
 The lifecycle edges have two important local caveats. `agent/created` runs after scoped setup and after both session and agent registry entries exist. Setup is trusted composition-only code; the immediately following non-vetoing `agent/session-start` notification is the first supported startup injection point. `agent/disposed` always means the exact agent has left the registry. AgentLoop emits it after its driver is quiescent, while ordered teardown may still be detaching the session and unwinding the scope; custom agents registered directly own any stronger driver-ordering contract themselves.
 
-Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: it receives the exact error, normalized failure facts, immutable prior-retried facts, and signal after the failed step closes; a retry opens a new numbered step. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design Agent Note](../../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way).
+Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: it receives the exact error, normalized failure facts, immutable prior-retried facts, and signal after the failed step closes; a retry opens a new numbered step. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. Effective broad cancellation first emits the observe-only `agent/cancel-requested` with its resolved reason, then clears queues and aborts; notification failures are contained and cannot veto the stop. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design Agent Note](../../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way).
 
 `PromptDecision.additionalContexts` is an array so every injected context keeps its own source and metadata. A `ContinuationDecision` reason is narrower: it becomes a `steering/message`, not a `context/message`, and therefore carries only content and source.
 
@@ -54,10 +54,10 @@ Turn and step boundaries and the model token stream are durable `session/event`
 
 The handle every plugin programs against:
 
-- `agent.send(content, options?)` — queue one independent FIFO item. If claimed, that item becomes the sole ordinary message in its turn; a claimed FIFO successor waits for that turn's checkpoint to settle. Broad cancellation, disposal, or a pre-start failure may instead drop it without a turn. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the rationale.
+- `agent.send(content, options?)` — queue one independent FIFO item. If claimed, that item becomes the sole ordinary message in its turn; a claimed FIFO successor waits for that turn's checkpoint to settle. Broad cancellation, disposal, or a pre-start failure may instead drop it without a turn. Omitting `options.source` attests direct human input as `{ kind: 'user' }` and may authorize policy consumers, so plugins, schedulers, and other non-human producers provide their own source. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the rationale.
 - `agent.steer(content, options?)` — submit steering while the agent is `running`. An open turn records it at the next steering checkpoint before a request or continuation decision; policy can still stop before another step. After turn close and its checkpoint, remaining steering becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. The method uses the same synchronous snapshot-and-validation boundary as `send` and delegates to `send` when idle
 - `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message` with `content` rendered verbatim as a user-role message. `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)).
-- `agent.cancel(reason?)` — cancel ALL pending work: clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window) so a queued-but-not-started prompt never runs. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op.
+- `agent.cancel(reason?)` — cancel ALL pending work: an effective call emits `agent/cancel-requested` before it clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window). Observers may synchronize their own state but cannot veto cancellation. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op with no notification.
 - `agent.whenIdle()` — resolve once the agent reaches quiescence after settling out of `running` (idle → immediately; disposed → awaits the loop exit). A non-owner's quiescence-observation hook: it observes the work settling WITHOUT tearing the agent down. Teardown is separate — a lifecycle owner stops and unregisters via `AgentHandle.dispose()`, which awaits the loop exit directly.
 - `agent.session`, `agent.status`, `agent.options`, `agent.id`
 
diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts
index ffeb92e3ba..e0ba54a60d 100644
--- a/packages/core/agent/src/types.ts
+++ b/packages/core/agent/src/types.ts
@@ -25,7 +25,10 @@ export interface AgentOptions {
   model?: string
 }
 
-/** Message options; an omitted source resolves to `{ kind: 'user' }`, so plugins must label their own content. */
+/**
+ * Message options. An omitted source attests direct human input as `{ kind: 'user' }`
+ * and may authorize policy consumers, so non-human producers must label their content.
+ */
 export interface SendOptions {
   source?: MessageSource
 }
@@ -122,10 +125,10 @@ export interface Agent {
 
   /**
    * Clear all queued and steering work, including items waiting to start, and
-   * abort the active step. The supplied reason is preserved across pre-step
-   * and active cancellation windows, and `whenIdle()` resolves after
-   * cancellation reaches quiescence. Idle cancellation is a no-op and does not
-   * arm a later cancel.
+   * abort the active step. An effective call first emits `agent/cancel-requested`
+   * with the resolved reason. That reason is preserved across pre-step and active
+   * cancellation windows, and `whenIdle()` resolves after cancellation reaches
+   * quiescence. Idle cancellation is a no-op and does not arm a later cancel.
    */
   cancel(reason?: string): void
 
@@ -176,6 +179,16 @@ declare module 'cordis' {
      * @mode emit
      */
     'agent/queued'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void
+    /**
+     * Effective broad cancellation was requested, before queued/steering work
+     * is cleared or the active step is aborted. This observe-only notification
+     * cannot veto cancellation; listener failures are contained.
+     * @param agent - the agent whose current work is being cancelled.
+     * @param reason - resolved cancellation reason, including the default.
+     * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
+     * @mode emit
+     */
+    'agent/cancel-requested'(this: Scoped<Agent>, agent: Agent, reason: string): void
 
     // ---- session lifecycle (emit) ----
     /**
diff --git a/packages/core/tools/tests/gen-tool-catalog.spec.ts b/packages/core/tools/tests/gen-tool-catalog.spec.ts
index 5aa4b6eb61..3bc5c46afc 100644
--- a/packages/core/tools/tests/gen-tool-catalog.spec.ts
+++ b/packages/core/tools/tests/gen-tool-catalog.spec.ts
@@ -23,7 +23,7 @@ describe('gen-tool-catalog collectToolCatalog', () => {
   it('boots every shipped tool package and harvests its model-facing schemas', async () => {
     const catalog = await collectToolCatalog()
     const names = catalog.flatMap(entry => entry.schemas.map(s => s.name)).sort()
-    expect(names).toEqual(['ask_user_question', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'edit', 'glob', 'grep', 'read', 'run_code', 'skill', 'subagent', 'task_kill', 'task_list', 'task_output', 'todo_write', 'web_fetch', 'web_search', 'workflow', 'write'])
+    expect(names).toEqual(['ask_user_question', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'create_goal', 'edit', 'get_goal', 'glob', 'grep', 'read', 'run_code', 'skill', 'subagent', 'task_kill', 'task_list', 'task_output', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write'])
     // Every tool carries a JSON-Schema `parameters` object (what the model sees).
     for (const entry of catalog) {
       for (const schema of entry.schemas) {
diff --git a/packages/examples/README.md b/packages/examples/README.md
index f13d15a8ea..46b5e7d923 100644
--- a/packages/examples/README.md
+++ b/packages/examples/README.md
@@ -5,9 +5,9 @@ Pre-composed plugin bundles a thin leaf `cordis.yml` loads instead of assembling
 | Package | npm name | Role |
 |---|---|---|
 | `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + system-prompt + tools + skills + agents + invariants + `tool-bash` + workspace-context + `tool-skill` + `agent-loop`) |
-| `tui-demo/` | `@deepseek-ai/dsh-tui-demo` | Full-screen terminal app: the spine + JSONL persistence + `dsh-tui` + a pre-created `main` agent, with a boot `bin` |
+| `tui-demo/` | `@deepseek-ai/dsh-tui-demo` | Full-screen terminal app: the spine + command registry + JSONL persistence + `dsh-tui` + a pre-created `main` agent, with a boot `bin` |
 | `cli-demo/` | `@deepseek-ai/dsh-cli-demo` | Headless one-shot app: the spine + JSONL persistence + a pre-created `main` agent, with text and DSH-native JSON output |
-| `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` |
+| `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + command registry + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` |
 | `jsonrpc-demo/` | `@deepseek-ai/dsh-jsonrpc-demo` | Bin-only runtime that boots an external `cordis.yml` for the stdio JSON-RPC SDK client |
 
 `agent-spine-demo` is the shared bundle; `tui-demo`, `cli-demo`, and `acp-demo` compose it with full-screen terminal, headless one-shot, and ACP front doors and own their boot bins. `jsonrpc-demo` mounts no composition of its own — it boots whatever tree the deployment's `cordis.yml` names, and is what the Python SDK runtime launches.
diff --git a/packages/examples/acp-demo/README.md b/packages/examples/acp-demo/README.md
index 92d75dec99..3526eef597 100644
--- a/packages/examples/acp-demo/README.md
+++ b/packages/examples/acp-demo/README.md
@@ -11,6 +11,7 @@ stdout is the ACP JSON-RPC channel, so the cluster is defined as much by what it
 | Plugin | Why |
 |---|---|
 | `@deepseek-ai/dsh-agent-spine-demo` | the spine, pre-creating **no** agents (ACP `session/new` creates them on demand) |
+| `@deepseek-ai/dsh-commands` | the human-command registry used for ACP discovery and direct slash dispatch |
 | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by clients that can complete ACP elicitation requests |
 | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log (the bridge advertises `loadSession`) |
 | `@deepseek-ai/dsh-acp` | the bridge that owns stdout for JSON-RPC and provides ACP-backed user answers when a leaf explicitly exposes a user-question tool |
diff --git a/packages/examples/acp-demo/package.json b/packages/examples/acp-demo/package.json
index 28d057c0a0..f74617f306 100644
--- a/packages/examples/acp-demo/package.json
+++ b/packages/examples/acp-demo/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@deepseek-ai/dsh-acp-demo",
-  "description": "ACP server app: the agent-spine-demo bundle + JSONL persistence + the ACP bridge (no stdout logger, no hmr, no pre-created agents), with a bin to boot a leaf cordis.yml over JSON-RPC stdio",
+  "description": "ACP server app: agent spine + human commands + JSONL persistence + ACP bridge (no stdout logger, hmr, or pre-created agents), with a JSON-RPC stdio bin",
   "version": "0.0.1",
   "private": true,
   "type": "module",
@@ -34,6 +34,7 @@
     "@cordisjs/plugin-loader": "^1.0.0-rc.5",
     "@deepseek-ai/dsh-app-boot": "^0.0.1",
     "@deepseek-ai/dsh-acp": "^0.0.1",
+    "@deepseek-ai/dsh-commands": "^0.0.1",
     "@deepseek-ai/dsh-agent-spine-demo": "^0.0.1",
     "@deepseek-ai/dsh-workspace-context": "^0.0.1",
     "@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1",
@@ -47,6 +48,7 @@
     "@cordisjs/plugin-loader": "workspace:^",
     "@deepseek-ai/dsh-app-boot": "workspace:^",
     "@deepseek-ai/dsh-acp": "workspace:^",
+    "@deepseek-ai/dsh-commands": "workspace:^",
     "@deepseek-ai/dsh-agent": "workspace:^",
     "@deepseek-ai/dsh-agent-spine-demo": "workspace:^",
     "@deepseek-ai/dsh-tools": "workspace:^",
diff --git a/packages/examples/acp-demo/src/index.ts b/packages/examples/acp-demo/src/index.ts
index 98ba012829..6e7e389a92 100644
--- a/packages/examples/acp-demo/src/index.ts
+++ b/packages/examples/acp-demo/src/index.ts
@@ -1,7 +1,7 @@
 /**
  * The ACP server app: the default agent spine ({@link @deepseek-ai/dsh-agent-spine-demo}),
- * JSONL session persistence, and the {@link @deepseek-ai/dsh-acp} bridge. It
- * writes nothing to stdout.
+ * human-command registry, JSONL session persistence, and the
+ * {@link @deepseek-ai/dsh-acp} bridge. It writes nothing to stdout.
  * It pre-creates no agents and leaves adapters, executors, and optional tools to
  * the leaf, which must likewise avoid stdout loggers. Named exports are
  * required so Loader retains this plugin's `Config` schema (see
@@ -12,6 +12,7 @@
 import type { Context } from 'cordis'
 import z from 'schemastery'
 import * as acp from '@deepseek-ai/dsh-acp'
+import CommandService from '@deepseek-ai/dsh-commands'
 import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo'
 import * as workspaceContext from '@deepseek-ai/dsh-workspace-context'
 import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools'
@@ -96,6 +97,7 @@ export const Config: z<Config> = z.object({
  * from the provider/model pair. No logger, no `hmr` — stdout stays pure.
  */
 export function apply(ctx: Context, config: Config): void {
+  ctx.plugin(CommandService)
   ctx.plugin(agentCore, agentCore.pickSpineConfig(config))
   ctx.plugin(UserInteractionService)
   ctx.plugin(SessionPersistenceJsonl, {
diff --git a/packages/examples/acp-demo/tsconfig.json b/packages/examples/acp-demo/tsconfig.json
index b0e537574a..78090f6273 100644
--- a/packages/examples/acp-demo/tsconfig.json
+++ b/packages/examples/acp-demo/tsconfig.json
@@ -23,6 +23,9 @@
     {
       "path": "../../ui/acp"
     },
+    {
+      "path": "../../ui/commands"
+    },
     {
       "path": "../../core/agent"
     },
diff --git a/packages/examples/tui-demo/README.md b/packages/examples/tui-demo/README.md
index b544e989fc..d944f9caed 100644
--- a/packages/examples/tui-demo/README.md
+++ b/packages/examples/tui-demo/README.md
@@ -1,6 +1,6 @@
 # @deepseek-ai/dsh-tui-demo
 
-The full-screen terminal app: a Cordis plugin that composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, keyboard-backed user interaction, a pre-created `main` agent, and [`@deepseek-ai/dsh-tui`](../../ui/tui/README.md). Its `bin` boots a leaf `cordis.yml`.
+The full-screen terminal app: a Cordis plugin that composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), the human-command registry, JSONL persistence, keyboard-backed user interaction, a pre-created `main` agent, and [`@deepseek-ai/dsh-tui`](../../ui/tui/README.md). Its `bin` boots a leaf `cordis.yml`.
 
 Use [`@deepseek-ai/dsh-cli-demo`](../cli-demo/README.md) for pipes, scripts, and other non-interactive runs. This package requires a TTY pair and has no line-oriented fallback.
 
@@ -9,6 +9,7 @@ Use [`@deepseek-ai/dsh-cli-demo`](../cli-demo/README.md) for pipes, scripts, and
 | Plugin | Why it is here |
 |---|---|
 | `@deepseek-ai/dsh-agent-spine-demo` | Shared services, model-facing tools, and one configured `main` agent |
+| `@deepseek-ai/dsh-commands` | Human-only discovery and dispatch consumed by the TUI and command plugins |
 | `@deepseek-ai/dsh-session-persistence-jsonl` | Durable session log under `persistenceRoot` |
 | `@deepseek-ai/dsh-user-interaction` | Provider-neutral human question service |
 | `@deepseek-ai/dsh-tui` | Full-screen transcript, editor, tool cards, plan, and question overlays |
@@ -70,7 +71,7 @@ Fresh runs mint a `main-session-<uuid>` session id and pass it to both the TUI a
 
 #### What the model sees
 
-Each non-empty editor submission becomes a user message; a submission during a running turn becomes steering. The shared spine contributes the configured persona, workspace instructions, skill catalog, and visible tool schemas. TUI rendering itself is not model-visible.
+Each non-empty non-command editor submission becomes a user message; a submission during a running turn becomes steering. Slash-command input and output remain human-only. The shared spine contributes the configured persona, workspace instructions, skill catalog, and visible tool schemas. TUI rendering itself is not model-visible.
 
 #### Token effect
 
diff --git a/packages/examples/tui-demo/package.json b/packages/examples/tui-demo/package.json
index 3bdc880023..7448858055 100644
--- a/packages/examples/tui-demo/package.json
+++ b/packages/examples/tui-demo/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@deepseek-ai/dsh-tui-demo",
-  "description": "Full-screen terminal app: agent spine + JSONL persistence + pi-tui front door + pre-created main agent",
+  "description": "Full-screen terminal app: agent spine + human commands + JSONL persistence + pi-tui front door + pre-created main agent",
   "version": "0.0.1",
   "private": true,
   "type": "module",
@@ -35,6 +35,7 @@
     "@deepseek-ai/dsh-app-boot": "^0.0.1",
     "@deepseek-ai/dsh-agent": "^0.0.1",
     "@deepseek-ai/dsh-agent-loop": "^0.0.1",
+    "@deepseek-ai/dsh-commands": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-agent-spine-demo": "^0.0.1",
     "@deepseek-ai/dsh-workspace-context": "^0.0.1",
@@ -53,6 +54,7 @@
     "@deepseek-ai/dsh-app-boot": "workspace:^",
     "@deepseek-ai/dsh-agent": "workspace:^",
     "@deepseek-ai/dsh-agent-loop": "workspace:^",
+    "@deepseek-ai/dsh-commands": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-agent-spine-demo": "workspace:^",
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
diff --git a/packages/examples/tui-demo/src/index.ts b/packages/examples/tui-demo/src/index.ts
index c4a13948e8..b4510ab5d6 100644
--- a/packages/examples/tui-demo/src/index.ts
+++ b/packages/examples/tui-demo/src/index.ts
@@ -1,7 +1,7 @@
 /**
  * Full-screen terminal app: the default agent spine ({@link @deepseek-ai/dsh-agent-spine-demo})
- * plus JSONL persistence, keyboard-backed user interaction, and one pre-created
- * agent whose exact session identity the TUI drives. Swappable adapters,
+ * plus human commands, JSONL persistence, keyboard-backed user interaction,
+ * and one pre-created agent whose exact session identity the TUI drives. Swappable adapters,
  * executors, optional tools, and HMR stay in the leaf. This Loader plugin
  * intentionally exposes named exports only; a default export would hide its
  * `Config` schema (see docs/postmortem/0001).
@@ -13,6 +13,7 @@ import { randomUUID } from 'node:crypto'
 import z from 'schemastery'
 import { SessionId } from '@deepseek-ai/dsh-session'
 import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools'
+import CommandService from '@deepseek-ai/dsh-commands'
 import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo'
 import * as workspaceContext from '@deepseek-ai/dsh-workspace-context'
 import SessionPersistenceJsonl, {
@@ -97,6 +98,7 @@ export const Config: z<Config> = z.object({
 export function composeTuiApp(ctx: Context, config: Config): void {
   const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId
   const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`)
+  ctx.plugin(CommandService)
   ctx.plugin(SessionPersistenceJsonl, {
     root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT,
     ...(config.persistenceCompression === undefined ? {} : { compression: config.persistenceCompression }),
diff --git a/packages/examples/tui-demo/tests/tui-agent.spec.ts b/packages/examples/tui-demo/tests/tui-agent.spec.ts
index 673f3e4f05..007120b4d5 100644
--- a/packages/examples/tui-demo/tests/tui-agent.spec.ts
+++ b/packages/examples/tui-demo/tests/tui-agent.spec.ts
@@ -41,17 +41,19 @@ describe('dsh-tui-demo app', () => {
     })
 
     expect(calls.map(call => call.name)).toEqual([
+      'CommandService',
       'SessionPersistenceJsonl',
       'UserInteractionService',
       'ui-tui',
       'agent-spine-demo',
       'tool-ask-user',
     ])
-    expect(calls[0]?.config).toEqual({ root: '/tmp/tui-sessions', compression: 'none' })
-    const tuiConfig = calls[2]?.config as { sessionId: string }
+    expect(calls[0]?.config).toBeUndefined()
+    expect(calls[1]?.config).toEqual({ root: '/tmp/tui-sessions', compression: 'none' })
+    const tuiConfig = calls[3]?.config as { sessionId: string }
     expect(tuiConfig).toMatchObject({ welcome: 'TUI ready', color: false, maxToolOutputLines: 3 })
     expect(tuiConfig.sessionId).toMatch(/^main-session-[0-9a-f-]{36}$/)
-    const spineConfig = calls[3]?.config as {
+    const spineConfig = calls[4]?.config as {
       readonly agents: Array<Record<string, unknown>>
       readonly maxParallelToolCalls: number
       readonly persona: string
@@ -82,9 +84,9 @@ describe('dsh-tui-demo app', () => {
       workspaceContext: false,
     })
 
-    expect(calls[0]?.config).toEqual({ root: './.sessions' })
-    expect(calls[2]?.config).toEqual({ welcome: 'ready.', sessionId: 'persisted-session' })
-    expect((calls[3]?.config as { agents: Array<Record<string, unknown>> }).agents[0]).toMatchObject({
+    expect(calls[1]?.config).toEqual({ root: './.sessions' })
+    expect(calls[3]?.config).toEqual({ welcome: 'ready.', sessionId: 'persisted-session' })
+    expect((calls[4]?.config as { agents: Array<Record<string, unknown>> }).agents[0]).toMatchObject({
       id: 'main',
       resumeSessionId: 'persisted-session',
     })
@@ -99,9 +101,9 @@ describe('dsh-tui-demo app', () => {
       workspaceContext: false,
     })
 
-    const tuiConfig = calls[2]?.config as { sessionId: string }
+    const tuiConfig = calls[3]?.config as { sessionId: string }
     expect(tuiConfig.sessionId).toMatch(/^main-session-[0-9a-f-]{36}$/)
-    expect((calls[3]?.config as { agents: Array<Record<string, unknown>> }).agents[0])
+    expect((calls[4]?.config as { agents: Array<Record<string, unknown>> }).agents[0])
       .toMatchObject({ sessionId: tuiConfig.sessionId })
   })
 
diff --git a/packages/examples/tui-demo/tsconfig.json b/packages/examples/tui-demo/tsconfig.json
index 2e92bb3b2b..cb3728904a 100644
--- a/packages/examples/tui-demo/tsconfig.json
+++ b/packages/examples/tui-demo/tsconfig.json
@@ -26,6 +26,9 @@
     {
       "path": "../../core/session"
     },
+    {
+      "path": "../../ui/commands"
+    },
     {
       "path": "../agent-spine-demo"
     },
diff --git a/packages/goal/README.md b/packages/goal/README.md
new file mode 100644
index 0000000000..fd0b94f321
--- /dev/null
+++ b/packages/goal/README.md
@@ -0,0 +1,11 @@
+# goal/ — persisted same-session goals
+
+The goal family owns durable objective state independently of the model-facing tools and continuation policy that consume it.
+
+| Package | Role | ctx key |
+|---|---|---|
+| `goal/` | Event-sourced goal lifecycle, replay fold, compare-and-set mutations, and process-local activation | `ctx.goals` |
+| `goal-session/` | Same-session goal-round admission, outcome mapping, and lifecycle race fencing | — |
+| `tool-goal/` | Model-facing read/create/update tools with execution-time authority checks | — |
+
+Goal state is part of the owning session log. Consumers depend on `dsh-goal`, not on the concrete agent loop; continuation behavior belongs in a separate plugin on the public agent seams.
diff --git a/packages/goal/goal-session/README.md b/packages/goal/goal-session/README.md
new file mode 100644
index 0000000000..2ad4b161a3
--- /dev/null
+++ b/packages/goal/goal-session/README.md
@@ -0,0 +1,71 @@
+# @deepseek-ai/dsh-goal-session
+
+Same-session continuation driver for [`ctx.goals`](../goal/README.md). It turns an active, armed goal into sequential [goal rounds](../../../docs/glossary.md#goal-round) through the public `Agent` and session seams; the [same-session driver Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.md) owns the race and lifecycle rationale.
+
+## Composition
+
+```yaml
+- 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'
+```
+
+The plugin has no tunable configuration. `maxGoalRounds` belongs to the goal definition, while the model-facing blocked threshold belongs to [`dsh-tool-goal`](../tool-goal/README.md); duplicating either value in the driver could produce divergent policy.
+
+## Round contract
+
+When an exact live agent is idle with an active, armed goal and remaining capacity, the driver first checkpoints pending goal mutations, then reserves `roundsStarted + 1` for the current `{ goalId, revision }`. It queues one `<goal_round>` prompt with `GoalMessageSource`. Admission through `agent/prompt-submit` verifies the complete queued record and current goal both before and after downstream prompt hooks; only the accepted `user/message` increments `roundsStarted`. A reservation rejected as stale does not consume the round number.
+
+One goal round owns one ordinary session turn, and that turn may contain several model/tool steps. Human messages remain ordinary turns and do not consume the goal cap. If human work enters the inbox before a reservation or joins its pending batch, automatic work yields until that work settles; a pending automatic prompt in a mixed batch is rejected and re-reserved only after the agent becomes idle.
+
+The retained prompt names the JSON-quoted objective and `round/maxGoalRounds`, treats the current workspace, tool results, and durable session state as authoritative, requires evidence before completion, and tells the model to leave the goal active when work remains. Quoting preserves multiline or tag-like objective text as data. Goal lifecycle mutations still require the independent authority checks in `dsh-tool-goal`.
+
+## Settlement policy
+
+| Durable turn outcome | Goal action | Automatic retry |
+|---|---|---|
+| `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` or `QUOTA` | `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.
+
+## Lifecycle and durability
+
+`goal/changed` creates a durability obligation. Before queuing work, the driver awaits `ctx.sessions.flush()` and rechecks both the goal revision and competing input after the await. A closing flush failure arrives through `agent/error`; the driver associates it with the exact closed turn even if a later one-shot injection has appended another turn, then disarms before another round can start.
+
+Activation is never inherited when this plugin loads over an existing agent. `GoalService.disarm()` removes process-local authority without changing durable phase, revision, or history; explicit human-authorized resume records the later reactivation. The same rule applies after session resume and fork through the goal domain's `agent/session-start` handling.
+
+Cancellation is observe-before-act: the concrete loop emits `agent/cancel-requested` before clearing queues or aborting a step. The plugin durably pauses an active goal only when the cancellation owns a reserved or admitted goal attempt; cancellation of unrelated human work merely disarms process-local continuation. If the pause mutation fails, the driver falls back to disarming. Plugin teardown closes admission, disarms every live goal, cancels an admitted round, and awaits the driver plus agent quiescence while its event fence remains installed.
+
+## Model Experience
+
+### Goal-round prompt
+
+#### What the model sees
+
+Each admitted round is one retained user-role `<goal_round>` block naming the full objective and positive round number. Earlier human messages, goal-state snapshots, assistant output, and tool records remain in the same session history.
+
+#### Token effect
+
+One fixed instruction block plus the objective is added per admitted round. Later requests resend retained rounds until compaction shadows them; no fresh agent or copied conversation prefix is created.
+
+#### KV Cache effect
+
+Append-only within an epoch: each admitted round extends the existing conversation after its reusable prefix. Compaction may replace the derived-history suffix and move the reusable boundary.
+
+## Known Limitations and Deferred Work
+
+- **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; observed `RATE_LIMIT` and `QUOTA` stops only map 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.
diff --git a/packages/goal/goal-session/package.json b/packages/goal/goal-session/package.json
new file mode 100644
index 0000000000..48a77019a3
--- /dev/null
+++ b/packages/goal/goal-session/package.json
@@ -0,0 +1,42 @@
+{
+  "name": "@deepseek-ai/dsh-goal-session",
+  "description": "Race-fenced same-session goal-round driver",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "@deepseek-ai/dsh-agent": "^0.0.1",
+    "@deepseek-ai/dsh-goal": "^0.0.1",
+    "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-session": "^0.0.1",
+    "cordis": "^4.0.0-rc.7"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-agent-loop": "workspace:^",
+    "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^",
+    "@deepseek-ai/dsh-goal": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "@deepseek-ai/dsh-system-prompt": "workspace:^",
+    "@deepseek-ai/dsh-tools": "workspace:^",
+    "cordis": "^4.0.0-rc.7"
+  }
+}
diff --git a/packages/goal/goal-session/src/index.ts b/packages/goal/goal-session/src/index.ts
new file mode 100644
index 0000000000..24364a4983
--- /dev/null
+++ b/packages/goal/goal-session/src/index.ts
@@ -0,0 +1,456 @@
+/**
+ * Same-session goal-round driver over public agent, session, and goal seams.
+ * @module @deepseek-ai/dsh-goal-session
+ */
+
+import { isDeepStrictEqual } from 'node:util'
+import { FiberState } from 'cordis'
+import type { Context } from 'cordis'
+import type { Agent, PromptDecision } from '@deepseek-ai/dsh-agent'
+import type { GoalMessageSource, GoalRef, GoalView } from '@deepseek-ai/dsh-goal'
+import { assertNever } from '@deepseek-ai/dsh-llm'
+import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
+import type { Session, SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session'
+import { classifyGoalRound } from './outcome.ts'
+import type { GoalRoundOutcome } from './outcome.ts'
+import { renderGoalRoundPrompt } from './prompt.ts'
+
+export { classifyGoalRound } from './outcome.ts'
+export type { GoalRoundOutcome } from './outcome.ts'
+export { renderGoalRoundPrompt } from './prompt.ts'
+
+export const name = 'goal-session'
+export const inject = ['agents', 'goals', 'sessions']
+
+const STALE_ROUND_REASON = 'stale goal-round reservation'
+
+/** Identity reserved before a goal continuation enters the agent inbox. */
+interface RoundIdentity {
+  readonly goalId: GoalRef['id']
+  readonly revision: number
+  readonly round: number
+}
+
+/** One queued or admitted attempt, retained until its physical turn settles. */
+interface RoundAttempt extends RoundIdentity {
+  readonly content: ContentBlock[]
+  phase: 'queued' | 'admitted'
+  turn: number | undefined
+  reason: TurnEndReason | undefined
+  rejectedReason: string | undefined
+  stale: boolean
+}
+
+/** Serialized process-local scheduling state for one exact Agent lifecycle. */
+interface DriverState {
+  readonly agent: Agent
+  attempt: RoundAttempt | undefined
+  openTurn: number | undefined
+  competingQueued: boolean
+  needsCheckpoint: boolean
+  requested: boolean
+  run: Promise<void> | undefined
+  stopping: boolean
+  readonly flushFailedTurns: Set<number>
+}
+
+/** Whether a source identifies an automatic, positive-numbered goal round. */
+function isGoalRoundSource(source: MessageSource): source is GoalMessageSource {
+  return source.kind === 'goal' && source.round > 0
+}
+
+/** Compare a source to one reserved identity. */
+function sameRound(source: GoalMessageSource, round: RoundIdentity): boolean {
+  return source.goalId === round.goalId
+    && source.revision === round.revision
+    && source.round === round.round
+}
+
+/** Compare the complete queued record to the driver's reservation. */
+function sameQueued(content: ContentBlock[], source: MessageSource, attempt: RoundAttempt): boolean {
+  return isGoalRoundSource(source) && sameRound(source, attempt) && isDeepStrictEqual(content, attempt.content)
+}
+
+/** Exact current ref for a view. */
+function goalRef(goal: GoalView): GoalRef {
+  return { id: goal.id, revision: goal.revision }
+}
+
+/** Human-readable unexpected values for logs. */
+function renderThrown(value: unknown): string {
+  return value instanceof Error ? value.message : String(value)
+}
+
+/** Install automatic same-session continuation and its race fences. */
+export function apply(ctx: Context): void {
+  const states = new Map<Agent, DriverState>()
+
+  /** Create state for an exact currently live agent. */
+  function stateFor(agent: Agent): DriverState {
+    const existing = states.get(agent)
+    if (existing !== undefined) return existing
+    const state: DriverState = {
+      agent,
+      attempt: undefined,
+      openTurn: undefined,
+      competingQueued: false,
+      needsCheckpoint: false,
+      requested: false,
+      run: undefined,
+      stopping: false,
+      flushFailedTurns: new Set(),
+    }
+    states.set(agent, state)
+    return state
+  }
+
+  /** Read only when the exact Agent remains live. */
+  function currentGoal(state: DriverState): GoalView | undefined {
+    if (ctx.agents.get(state.agent.id) !== state.agent || state.agent.status === 'disposed') return undefined
+    return ctx.goals.get(state.agent)
+  }
+
+  /** Whether this exact lifecycle is quiescent with no competing prompt. */
+  function readyToDrive(state: DriverState): boolean {
+    return ctx.fiber.state === FiberState.ACTIVE
+      && !state.stopping
+      && ctx.agents.get(state.agent.id) === state.agent
+      && state.agent.status === 'idle'
+      && !state.competingQueued
+  }
+
+  /** Recheck every condition that an awaited checkpoint may have changed. */
+  function readyAfterCheckpoint(state: DriverState): boolean {
+    return readyToDrive(state) && !state.needsCheckpoint
+  }
+
+  /** Remove automatic authority while preserving the durable phase. */
+  function disarm(state: DriverState): void {
+    try {
+      const goal = currentGoal(state)
+      if (goal?.activation === 'armed') ctx.goals.disarm(state.agent)
+    } catch (error: unknown) {
+      ctx.logger.warn(`goal-session: could not disarm agent "${state.agent.id}": ${renderThrown(error)}`)
+    }
+  }
+
+  /** Apply one closed-round outcome only to the exact still-current revision. */
+  function applyOutcome(state: DriverState, goal: GoalView, outcome: GoalRoundOutcome): void {
+    const ref = goalRef(goal)
+    switch (outcome.kind) {
+      case 'continue':
+        return
+      case 'pause':
+        ctx.goals.pause(state.agent, ref)
+        return
+      case 'blocked':
+        ctx.goals.block(state.agent, ref, { code: outcome.code, message: outcome.message })
+        return
+      case 'disarm':
+        ctx.goals.disarm(state.agent)
+        return
+      /* v8 ignore next 2 -- GoalRoundOutcome is closed and every member is handled above */
+      default:
+        assertNever(outcome, 'goal round outcome')
+    }
+  }
+
+  /** Process a settled attempt, then reserve at most one next round. */
+  async function drive(state: DriverState): Promise<void> {
+    const { agent } = state
+    if (!readyToDrive(state)) return
+
+    if (state.needsCheckpoint) {
+      state.needsCheckpoint = false
+      try {
+        await ctx.sessions.flush(agent.session)
+      } catch (error: unknown) {
+        ctx.logger.warn(`goal-session: durability checkpoint failed for agent "${agent.id}": ${renderThrown(error)}`)
+        const goal = currentGoal(state)
+        if (goal !== undefined) applyOutcome(state, goal, { kind: 'disarm', reason: 'durability-failed' })
+        return
+      }
+      // A mutation or ordinary prompt may have arrived while the checkpoint
+      // was settling. Give it its own checkpoint / turn before reserving.
+      if (!readyAfterCheckpoint(state)) return
+    }
+
+    const attempt = state.attempt
+    if (attempt !== undefined) {
+      if (attempt.reason === undefined) return
+      state.attempt = undefined
+      const turn = attempt.turn
+      /* v8 ignore next -- a closed attempt acquired its turn at turn/start */
+      if (turn === undefined) throw new Error('settled goal-round attempt lacks a turn')
+      const durable = !state.flushFailedTurns.delete(turn)
+      const goal = currentGoal(state)
+      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', code: 'prompt-rejected', message: attempt.rejectedReason } as const
+          : classifyGoalRound(attempt.reason, durable)
+        if (!attempt.stale) applyOutcome(state, goal, outcome)
+      }
+      if (!readyToDrive(state)) return
+    }
+
+    const goal = currentGoal(state)
+    if (goal === undefined || goal.phase !== 'active' || goal.activation !== 'armed') return
+    if (goal.roundsStarted >= goal.maxGoalRounds) {
+      ctx.goals.block(agent, goalRef(goal), {
+        code: 'round-limit',
+        message: `Goal reached its configured limit of ${goal.maxGoalRounds} rounds.`,
+      })
+      return
+    }
+
+    const round = goal.roundsStarted + 1
+    const content = renderGoalRoundPrompt(goal, round)
+    const reservation: RoundAttempt = {
+      goalId: goal.id,
+      revision: goal.revision,
+      round,
+      content,
+      phase: 'queued',
+      turn: undefined,
+      reason: undefined,
+      rejectedReason: undefined,
+      stale: false,
+    }
+    state.attempt = reservation
+    try {
+      agent.send(content, {
+        source: { kind: 'goal', goalId: goal.id, revision: goal.revision, round },
+      })
+    } catch (error: unknown) {
+      state.attempt = undefined
+      ctx.logger.warn(`goal-session: could not queue round ${round} for agent "${agent.id}": ${renderThrown(error)}`)
+      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), {
+          code: 'queue-failed',
+          message: `Could not queue goal round ${round}: ${renderThrown(error)}`,
+        })
+      }
+    }
+  }
+
+  /** Coalesce triggers onto one agent-local serialized driver. */
+  function requestDrive(state: DriverState): void {
+    /* v8 ignore next -- teardown may race a final trigger after synchronously closing admission */
+    if (state.stopping) return
+    state.requested = true
+    if (state.run !== undefined) return
+    let run: Promise<void>
+    try {
+      run = ctx.agents.withoutInitiator(async () => {
+        while (state.requested && !state.stopping) {
+          state.requested = false
+          try {
+            await drive(state)
+          } catch (error: unknown) {
+            ctx.logger.warn(`goal-session: driver failed for agent "${state.agent.id}": ${renderThrown(error)}`)
+            disarm(state)
+          }
+        }
+      })
+    } catch (error: unknown) {
+      ctx.logger.warn(`goal-session: could not start driver for agent "${state.agent.id}": ${renderThrown(error)}`)
+      disarm(state)
+      return
+    }
+    state.run = run
+    const retire = (): void => {
+      state.run = undefined
+      if (state.requested && !state.stopping) requestDrive(state)
+    }
+    void run.then(retire, (error: unknown) => {
+      ctx.logger.warn(`goal-session: driver task rejected for agent "${state.agent.id}": ${renderThrown(error)}`)
+      disarm(state)
+      retire()
+    })
+  }
+
+  // One composite effect owns every listener and the quiescent close. Cordis
+  // unloads sibling effects concurrently; nesting makes the close run first
+  // and keeps the admission fence installed until its drain settles.
+  ctx.effect(function* () {
+    /** Mark a post-turn persistence failure before idle scheduling can run. */
+    ctx.on('agent/error', (agent, turn) => {
+      const state = stateFor(agent)
+      const closed = agent.session.events.some(event => event.type === 'turn/end' && event.data.turn === turn)
+      if (!closed) return
+      if (state.attempt?.turn === turn) state.flushFailedTurns.add(turn)
+      disarm(state)
+    })
+
+    ctx.on('agent/created', (agent) => { stateFor(agent) })
+    ctx.on('agent/disposed', (agent) => { states.delete(agent) })
+    ctx.on('agent/session-start', (agent) => {
+      const state = stateFor(agent)
+      state.attempt = undefined
+      state.openTurn = undefined
+      state.competingQueued = false
+      state.needsCheckpoint = false
+      state.flushFailedTurns.clear()
+    })
+    ctx.on('agent/status', (agent, status) => {
+      const state = stateFor(agent)
+      if (status === 'disposed') {
+        state.stopping = true
+        return
+      }
+      if (status === 'idle') {
+        state.competingQueued = false
+        requestDrive(state)
+      }
+    })
+    ctx.on('agent/queued', (agent, content, info) => {
+      const state = stateFor(agent)
+      const attempt = state.attempt
+      if (attempt !== undefined && sameQueued(content, info.source, attempt)) return
+      state.competingQueued = true
+      if (attempt?.phase === 'queued') attempt.stale = true
+    })
+    ctx.on('agent/cancel-requested', (agent, reason) => {
+      const state = stateFor(agent)
+      const attempt = state.attempt
+      state.attempt = undefined
+      state.competingQueued = false
+      const goal = currentGoal(state)
+      if (goal?.phase === 'active' && goal.activation === 'armed') {
+        if (attempt === undefined) {
+          disarm(state)
+          return
+        }
+        try {
+          applyOutcome(state, goal, { kind: 'pause', reason })
+        } catch (error: unknown) {
+          ctx.logger.warn(`goal-session: could not pause cancelled goal for agent "${agent.id}": ${renderThrown(error)}`)
+          disarm(state)
+        }
+      }
+    })
+    ctx.on('goal/changed', (agent) => {
+      const state = stateFor(agent)
+      state.needsCheckpoint = true
+      requestDrive(state)
+    })
+
+    ctx.on('session/event', (session: Session, event: SessionEvent) => {
+      const agent = ctx.agents.get(session.id)
+      if (agent === undefined || agent.session !== session) return
+      const state = stateFor(agent)
+      switch (event.type) {
+        case 'turn/start':
+          state.openTurn = event.data.turn
+          if (state.attempt !== undefined && isGoalRoundSource(event.data.trigger.source)
+          && sameRound(event.data.trigger.source, state.attempt)) {
+            state.attempt.turn = event.data.turn
+          }
+          return
+        case 'user/message':
+          if (state.attempt !== undefined && isGoalRoundSource(event.data.source)
+          && sameRound(event.data.source, state.attempt)) {
+            state.attempt.phase = 'admitted'
+            /* v8 ignore next -- this driver's admitted message always follows its observed turn/start */
+            if (state.openTurn !== undefined) state.attempt.turn = state.openTurn
+          }
+          return
+        case 'prompt/blocked':
+          if (state.attempt !== undefined && state.attempt.phase === 'queued'
+          && isGoalRoundSource(event.data.source) && sameRound(event.data.source, state.attempt)) {
+          /* v8 ignore next -- this driver's rejected message always follows its observed turn/start */
+            if (state.openTurn !== undefined) state.attempt.turn = state.openTurn
+            state.attempt.rejectedReason = event.data.reason
+            if (event.data.reason === STALE_ROUND_REASON) state.attempt.stale = true
+          }
+          return
+        case 'turn/end':
+          if (state.attempt?.turn === event.data.turn) state.attempt.reason = event.data.reason
+          /* v8 ignore next -- balanced live turns close the open turn just observed by this listener */
+          if (state.openTurn === event.data.turn) state.openTurn = undefined
+          return
+        default:
+          return
+      }
+    })
+
+    /** Fail closed unless the queued prompt still owns the exact live revision. */
+    function validReservation(
+      state: DriverState,
+      content: ContentBlock[],
+      source: GoalMessageSource,
+    ): boolean {
+      const attempt = state.attempt
+      const goal = currentGoal(state)
+      return ctx.fiber.state === FiberState.ACTIVE
+        && !state.stopping && attempt !== undefined && attempt.phase === 'queued'
+      && !attempt.stale && sameQueued(content, source, attempt)
+      && goal !== undefined && goal.id === source.goalId && goal.revision === source.revision
+      && goal.phase === 'active' && goal.activation === 'armed'
+      && source.round === goal.roundsStarted + 1
+    }
+
+    ctx.on('agent/prompt-submit', async (agent, content, source, next): Promise<PromptDecision> => {
+      if (!isGoalRoundSource(source)) return next()
+      const state = stateFor(agent)
+      let valid = false
+      try {
+        valid = validReservation(state, content, source)
+      } catch (error: unknown) {
+        ctx.logger.warn(`goal-session: admission check failed for agent "${agent.id}": ${renderThrown(error)}`)
+        disarm(state)
+      }
+      if (!valid) {
+        const attempt = state.attempt
+        if (attempt !== undefined && sameRound(source, attempt)) attempt.stale = true
+        return { kind: 'block', reason: STALE_ROUND_REASON }
+      }
+      const decision = await next()
+      if (decision.kind === 'block') return decision
+      try {
+        valid = validReservation(state, content, source)
+      } catch (error: unknown) {
+        ctx.logger.warn(`goal-session: post-admission check failed for agent "${agent.id}": ${renderThrown(error)}`)
+        disarm(state)
+        valid = false
+      }
+      if (!valid) {
+        const attempt = state.attempt
+        if (attempt !== undefined && sameRound(source, attempt)) attempt.stale = true
+        return { kind: 'block', reason: STALE_ROUND_REASON }
+      }
+      return decision
+    })
+
+    // Loading a lifecycle driver over existing agents never inherits hidden
+    // automatic authority from an earlier producer instance.
+    for (const agent of ctx.agents.list()) {
+      const state = stateFor(agent)
+      disarm(state)
+    }
+
+    // Yielded after listener registration, so this close runs first and the
+    // composite effect removes listeners only after its promise settles.
+    yield async () => {
+      const waits: Promise<void>[] = []
+      for (const state of states.values()) {
+        state.stopping = true
+        disarm(state)
+        const attempt = state.attempt
+        if (attempt !== undefined) {
+          attempt.stale = true
+          if (attempt.phase === 'admitted' && state.agent.status === 'running') {
+            state.agent.cancel('goal-session driver disposed')
+          }
+          waits.push(state.agent.whenIdle())
+        }
+        if (state.run !== undefined) waits.push(state.run)
+      }
+      await Promise.allSettled(waits)
+      states.clear()
+    }
+  }, 'goal-session lifecycle')
+}
diff --git a/packages/goal/goal-session/src/outcome.ts b/packages/goal/goal-session/src/outcome.ts
new file mode 100644
index 0000000000..e69f53eeec
--- /dev/null
+++ b/packages/goal/goal-session/src/outcome.ts
@@ -0,0 +1,53 @@
+/** Typed settlement policy for one admitted same-session goal round. */
+
+import type { TurnEndReason } from '@deepseek-ai/dsh-session'
+
+/** Driver action derived from one closed goal-owned turn. */
+export type GoalRoundOutcome =
+  | { readonly kind: 'continue' }
+  | { readonly kind: 'pause'; readonly reason: string }
+  | {
+    readonly kind: 'blocked'
+    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' }
+
+/**
+ * Classify one closed goal round without mutating goal state.
+ * @param reason - durable reason from the round's `turn/end`.
+ * @param durable - whether the closing flush reached its durability checkpoint.
+ * @returns the single driver action; no abnormal outcome requests an automatic retry.
+ */
+export function classifyGoalRound(reason: TurnEndReason, durable: boolean): GoalRoundOutcome {
+  if (!durable) return { kind: 'disarm', reason: 'durability-failed' }
+  const extensibleReason: { readonly kind: string } = reason
+  switch (reason.kind) {
+    case 'completed':
+      return { kind: 'continue' }
+    case 'aborted':
+      return { kind: 'pause', reason: reason.reason ?? 'cancelled' }
+    case 'error': {
+      const { code, message } = reason.failure ?? reason
+      return code === 'RATE_LIMIT' || code === 'QUOTA'
+        ? { kind: 'blocked', code: 'usage-limited', message }
+        : { kind: 'blocked', code: 'turn-error', message }
+    }
+    case 'max-tokens':
+      return { kind: 'blocked', code: 'max-tokens', message: 'model output reached max tokens' }
+    case 'rejected':
+      return { kind: 'blocked', code: 'prompt-rejected', message: reason.reason }
+    case 'disposed':
+      return { kind: 'disarm', reason: 'disposed' }
+    case 'interrupted':
+      return { kind: 'disarm', reason: 'interrupted' }
+    // 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',
+        code: 'unknown-turn-outcome',
+        message: `unknown turn outcome: ${extensibleReason.kind}`,
+      }
+  }
+}
diff --git a/packages/goal/goal-session/src/prompt.ts b/packages/goal/goal-session/src/prompt.ts
new file mode 100644
index 0000000000..9a2f69fcd8
--- /dev/null
+++ b/packages/goal/goal-session/src/prompt.ts
@@ -0,0 +1,26 @@
+/** Model-visible continuation prompt for one same-session goal round. */
+
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import type { GoalView } from '@deepseek-ai/dsh-goal'
+
+/**
+ * Render the complete goal-round instruction retained in session history.
+ * @param goal - exact active goal revision being admitted.
+ * @param round - next positive round number.
+ * @returns a fresh one-block prompt for `Agent.send()`.
+ */
+export function renderGoalRoundPrompt(goal: GoalView, round: number): ContentBlock[] {
+  return [{
+    type: 'text',
+    text: '<goal_round>\n'
+      + `Objective: ${JSON.stringify(goal.objective)}\n`
+      + `Round: ${round}/${goal.maxGoalRounds}\n\n`
+      + 'Continue 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>',
+  }]
+}
diff --git a/packages/goal/goal-session/tests/goal-session.spec.ts b/packages/goal/goal-session/tests/goal-session.spec.ts
new file mode 100644
index 0000000000..8495b73ecc
--- /dev/null
+++ b/packages/goal/goal-session/tests/goal-session.spec.ts
@@ -0,0 +1,707 @@
+import { afterEach, describe, expect, it, vi } from 'vitest'
+import { Context } from 'cordis'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+import { agentEvents } from '@deepseek-ai/dsh-agent'
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
+import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
+import GoalService, { GoalId } from '@deepseek-ai/dsh-goal'
+import type { GoalView } from '@deepseek-ai/dsh-goal'
+import { LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
+import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import type { TurnEndReason } from '@deepseek-ai/dsh-session'
+import * as goalSession from '../src/index.ts'
+
+type ScriptEntry = StreamChunk[] | Error | 'hang' | ((options: GenerateOptions) => StreamChunk[])
+
+/** Small request-recording adapter with controllable failure and cancellation. */
+class ScriptedAdapter extends LlmAdapter {
+  readonly requests: GenerateOptions[] = []
+
+  constructor(private readonly script: ScriptEntry[]) {
+    super()
+  }
+
+  override async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
+    this.requests.push(options)
+    const entry = this.script.shift()
+    if (entry === undefined) throw new Error('ScriptedAdapter: script exhausted')
+    if (entry instanceof Error) throw entry
+    if (entry === 'hang') {
+      yield { type: 'block-start', index: 0, blockType: 'text' }
+      yield { type: 'text-delta', index: 0, text: 'partial' }
+      await new Promise<void>((_resolve, reject) => {
+        if (options.signal?.aborted) {
+          reject(new Error('aborted'))
+          return
+        }
+        options.signal?.addEventListener('abort', () => { reject(new Error('aborted')) }, { once: true })
+      })
+      return
+    }
+    const chunks = typeof entry === 'function' ? entry(options) : entry
+    for (const chunk of chunks) yield chunk
+  }
+}
+
+/** One successful text response. */
+function textResponse(text: string): StreamChunk[] {
+  return [
+    { type: 'block-start', index: 0, blockType: 'text' },
+    { type: 'block-end', index: 0, block: { type: 'text', text } },
+    { type: 'finish', reason: { kind: 'stop' } },
+  ]
+}
+
+/** One successful response cut off at the model output limit. */
+function maxTokensResponse(text: string): StreamChunk[] {
+  return [
+    { type: 'block-start', index: 0, blockType: 'text' },
+    { type: 'block-end', index: 0, block: { type: 'text', text } },
+    { type: 'finish', reason: { kind: 'max-tokens' } },
+  ]
+}
+
+/** Complete request history as a single string for ordering assertions. */
+function requestText(request: GenerateOptions): string {
+  return request.messages
+    .flatMap(message => message.content)
+    .filter(block => block.type === 'text')
+    .map(block => block.text)
+    .join('\n')
+}
+
+interface Harness {
+  readonly ctx: Context
+  readonly adapter: ScriptedAdapter
+  readonly agent: Agent
+  readonly driver: Awaited<ReturnType<Context['plugin']>>
+}
+
+const contexts: Context[] = []
+
+afterEach(async () => {
+  await Promise.allSettled(contexts.splice(0).map(context => context.fiber.dispose()))
+})
+
+/** Mount a real loop with only its model scripted. */
+async function harness(script: ScriptEntry[]): Promise<Harness> {
+  const ctx = new Context()
+  contexts.push(ctx)
+  await mountAgentLoopTestDependencies(ctx)
+  await ctx.plugin(GoalService)
+  const driver = await ctx.plugin(goalSession)
+  await ctx.plugin(AgentLoop, { agents: [] })
+  const adapter = new ScriptedAdapter(script)
+  ctx.llm.registerAdapter(['mock'], adapter)
+  const agent = ctx.agentLoop.create(SessionId(`goal-session-${Math.random()}`), {
+    provider: 'mock',
+    model: 'mock',
+  })
+  return { ctx, adapter, agent, driver }
+}
+
+/** Await a stable goal projection selected by the caller. */
+async function waitForGoal(
+  ctx: Context,
+  agent: Agent,
+  predicate: (goal: GoalView | undefined) => boolean,
+): Promise<GoalView | undefined> {
+  await vi.waitFor(() => {
+    expect(predicate(ctx.goals.get(agent))).toBe(true)
+  })
+  return ctx.goals.get(agent)
+}
+
+/** Await a specific number of dispatched model requests. */
+async function waitForRequests(adapter: ScriptedAdapter, count: number): Promise<void> {
+  await vi.waitFor(() => {
+    expect(adapter.requests).toHaveLength(count)
+  })
+}
+
+describe('goal-round outcome policy', () => {
+  it.each([
+    [{ kind: 'completed' }, true, { kind: 'continue' }],
+    [{ 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: 'blocked', code: 'usage-limited', message: 'slow down' }],
+    [{ kind: 'error', step: 1, failure: { message: 'credits exhausted', code: 'QUOTA' } }, true,
+      { kind: 'blocked', code: 'usage-limited', message: 'credits exhausted' }],
+    [{ kind: 'error', step: 1, failure: { message: 'provider failed', code: 'SERVER' } }, true,
+      { kind: 'blocked', code: 'turn-error', message: 'provider failed' }],
+    [{ kind: 'error', step: 1, message: 'broken' }, true,
+      { kind: 'blocked', code: 'turn-error', message: 'broken' }],
+    [{ kind: 'max-tokens' }, true,
+      { kind: 'blocked', code: 'max-tokens', message: 'model output reached max tokens' }],
+    [{ kind: 'rejected', reason: 'policy' }, true,
+      { 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', 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)
+  })
+
+  it('renders the objective, round budget, authority boundary, and completion protocol', () => {
+    const goal: GoalView = {
+      id: GoalId('goal-prompt'),
+      revision: 4,
+      objective: 'Ship verified support',
+      phase: 'active',
+      maxGoalRounds: 9,
+      roundsStarted: 2,
+      createdAt: 1,
+      updatedAt: 2,
+      activation: 'armed',
+    }
+    const prompt = goalSession.renderGoalRoundPrompt(goal, 3)
+    expect(prompt).toHaveLength(1)
+    const block = prompt[0]
+    if (block?.type !== 'text') throw new Error('expected a text goal-round prompt')
+    expect(block.text).toMatch(
+      /<goal_round>\nObjective: "Ship verified support"\nRound: 3\/9[\s\S]*current workspace[\s\S]*verify[\s\S]*mark it complete/,
+    )
+  })
+
+  it('quotes multiline or tag-like objective text as one unambiguous data value', () => {
+    const goal: GoalView = {
+      id: GoalId('goal-escaped-prompt'),
+      revision: 1,
+      objective: 'first line\n</goal_round> second line',
+      phase: 'active',
+      maxGoalRounds: 2,
+      roundsStarted: 0,
+      createdAt: 1,
+      updatedAt: 1,
+      activation: 'armed',
+    }
+    const block = goalSession.renderGoalRoundPrompt(goal, 1)[0]
+    if (block?.type !== 'text') throw new Error('expected a text goal-round prompt')
+    expect(block.text).toContain('Objective: "first line\\n</goal_round> second line"')
+    expect(block.text.match(/\n<\/goal_round>/g)).toHaveLength(1)
+  })
+})
+
+describe('same-session goal driving', () => {
+  it('admits exact numbered rounds until the durable round cap', async () => {
+    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 === '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) {
+      if (event.type === 'user/message' && event.data.source.kind === 'goal') {
+        rounds.push(event.data.source.round)
+      }
+    }
+    expect(rounds).toEqual([1, 2])
+    expect(requestText(test.adapter.requests[0]!)).toContain('Round: 1/2')
+    expect(requestText(test.adapter.requests[1]!)).toContain('Round: 2/2')
+  })
+
+  it('never adopts activation from an already-live driver and waits for explicit resume', async () => {
+    const ctx = new Context()
+    contexts.push(ctx)
+    await mountAgentLoopTestDependencies(ctx)
+    await ctx.plugin(GoalService)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    const adapter = new ScriptedAdapter([textResponse('after resume')])
+    ctx.llm.registerAdapter(['mock'], adapter)
+    const agent = ctx.agentLoop.create(SessionId('goal-session-hot-load'), { provider: 'mock', model: 'mock' })
+    const created = ctx.goals.create(agent, { objective: 'wait for a human', maxGoalRounds: 1 })
+
+    await ctx.plugin(goalSession)
+    await Promise.resolve()
+    expect(ctx.goals.get(agent)).toMatchObject({ phase: 'active', activation: 'disarmed', revision: 1 })
+    expect(adapter.requests).toHaveLength(0)
+
+    ctx.goals.resume(agent, created)
+    await waitForGoal(ctx, agent, goal => goal?.phase === 'blocked')
+    expect(adapter.requests).toHaveLength(1)
+  })
+
+  it.each([
+    ['rate limit', new LlmError('slow down', 'RATE_LIMIT'), 'usage-limited'],
+    ['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 === 'blocked')
+
+    expect(goal).toMatchObject({ roundsStarted: 1, activation: 'disarmed' })
+    expect(goal?.blockedReason?.code).toBe(code)
+    expect(test.adapter.requests).toHaveLength(1)
+  })
+
+  it('maps a downstream prompt veto to blocked without admitting the round', async () => {
+    const test = await harness([])
+    test.ctx.on('agent/prompt-submit', (_agent, _content, source, next) => source.kind === 'goal'
+      ? Promise.resolve({ kind: 'block', reason: 'deployment policy' })
+      : next())
+    test.ctx.goals.create(test.agent, { objective: 'respect policy' })
+
+    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)
+  })
+
+  it('does not reserve again when a stopped-goal observer queues ordinary work', async () => {
+    const test = await harness([textResponse('human follow-up')])
+    test.ctx.on('agent/prompt-submit', (_agent, _content, source, next) => source.kind === 'goal'
+      ? Promise.resolve({ kind: 'block', reason: 'stop this round' })
+      : next())
+    test.ctx.on('goal/changed', (agent, change) => {
+      if (change.operation === 'block') agent.send([{ type: 'text', text: 'inspect the blocker' }])
+    })
+    test.ctx.goals.create(test.agent, { objective: 'stop and inspect' })
+
+    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'blocked')
+    await waitForRequests(test.adapter, 1)
+    await test.agent.whenIdle()
+
+    expect(requestText(test.adapter.requests[0]!)).toContain('inspect the blocker')
+  })
+
+  it('pauses and drops a reserved round when cancellation lands before admission', async () => {
+    const test = await harness([])
+    const cancel = test.ctx.on('agent/queued', (agent, _content, info) => {
+      if (agent === test.agent && info.source.kind === 'goal') {
+        cancel()
+        agent.cancel('operator cancelled pending goal')
+      }
+    })
+    test.ctx.goals.create(test.agent, { objective: 'do not start yet' })
+
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'paused')
+
+    expect(goal).toMatchObject({ roundsStarted: 0, activation: 'disarmed' })
+    expect(test.adapter.requests).toHaveLength(0)
+    expect(test.agent.session.events.some(event => event.type === 'user/message'
+      && event.data.source.kind === 'goal')).toBe(false)
+  })
+
+  it('pauses an admitted round when cancellation aborts an active step', async () => {
+    const test = await harness(['hang'])
+    test.ctx.goals.create(test.agent, { objective: 'stop in flight' })
+    await waitForRequests(test.adapter, 1)
+
+    test.agent.cancel('operator stopped active goal')
+    await test.agent.whenIdle()
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'paused')
+
+    expect(goal).toMatchObject({ roundsStarted: 1, activation: 'disarmed' })
+    expect(test.adapter.requests).toHaveLength(1)
+  })
+
+  it('lets already-queued human work finish before reserving the next round', async () => {
+    const test = await harness([textResponse('human answer'), textResponse('goal answer')])
+    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 === 'blocked')
+
+    expect(test.adapter.requests).toHaveLength(2)
+    expect(requestText(test.adapter.requests[0]!)).toContain('human goes first')
+    expect(requestText(test.adapter.requests[0]!)).not.toContain('<goal_round>')
+    expect(requestText(test.adapter.requests[1]!)).toContain('<goal_round>')
+  })
+
+  it('makes a reserved round stale when a listener queues human work behind it', async () => {
+    const test = await harness([textResponse('human batch'), textResponse('later goal')])
+    let inserted = false
+    test.ctx.on('agent/queued', (agent, _content, info) => {
+      if (agent !== test.agent || info.source.kind !== 'goal' || inserted) return
+      inserted = true
+      agent.send([{ type: 'text', text: 'human joined the pending batch' }])
+    })
+    test.ctx.goals.create(test.agent, { objective: 'yield to nested human input', maxGoalRounds: 1 })
+
+    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')
+    expect(requestText(test.adapter.requests[0]!)).not.toContain('<goal_round>')
+    expect(requestText(test.adapter.requests[1]!)).toContain('<goal_round>')
+  })
+
+  it('blocks a queued reservation made stale by a goal edit and continues the new revision', async () => {
+    const test = await harness([textResponse('new revision')])
+    let edited = false
+    test.ctx.on('agent/queued', (agent, _content, info) => {
+      if (agent !== test.agent || info.source.kind !== 'goal' || edited) return
+      edited = true
+      const current = test.ctx.goals.get(agent)
+      if (current === undefined) throw new Error('missing goal during queued edit')
+      test.ctx.goals.edit(agent, current, { objective: 'new objective' })
+    })
+    test.ctx.goals.create(test.agent, { objective: 'old objective', maxGoalRounds: 1 })
+
+    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')
+    expect(blocked?.type === 'prompt/blocked' ? blocked.data.reason : undefined)
+      .toBe('stale goal-round reservation')
+    const admitted = test.agent.session.events.find(event => event.type === 'user/message'
+      && event.data.source.kind === 'goal')
+    expect(admitted?.type === 'user/message' && admitted.data.source.kind === 'goal'
+      ? admitted.data.source.revision
+      : undefined).toBe(2)
+  })
+
+  it('rechecks revision after downstream prompt hooks before admitting', async () => {
+    const test = await harness([textResponse('new revision')])
+    let edited = false
+    test.ctx.on('agent/prompt-submit', (agent, _content, source, next) => {
+      if (source.kind === 'goal' && !edited) {
+        edited = true
+        const current = test.ctx.goals.get(agent)
+        if (current === undefined) throw new Error('missing goal during prompt edit')
+        test.ctx.goals.edit(agent, current, { objective: 'edited downstream' })
+      }
+      return next()
+    })
+    test.ctx.goals.create(test.agent, { objective: 'edit during admission', maxGoalRounds: 1 })
+
+    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)
+    expect(test.agent.session.events.some(event => event.type === 'prompt/blocked'
+      && event.data.reason === 'stale goal-round reservation')).toBe(true)
+  })
+
+  it('disarms without dispatch when a durability checkpoint fails', async () => {
+    const test = await harness([])
+    test.ctx.on('session/flush', () => Promise.reject(new Error('disk unavailable')))
+    test.ctx.goals.create(test.agent, { objective: 'do not outrun storage' })
+
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.activation === 'disarmed')
+
+    expect(goal).toMatchObject({ phase: 'active', roundsStarted: 0 })
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('contains a checkpoint failure after a clear notification leaves no current goal', async () => {
+    const test = await harness([])
+    test.ctx.on('session/flush', () => Promise.reject(new Error('clear checkpoint failed')))
+    agentEvents(test.ctx, test.agent).emit('goal/changed', {
+      operation: 'clear',
+      ref: { id: GoalId('cleared-goal'), revision: 2 },
+    })
+    await new Promise<void>((resolve) => { setImmediate(resolve) })
+
+    expect(test.ctx.goals.get(test.agent)).toBeUndefined()
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('disarms an admitted round when a later injection hides its failed closing checkpoint', async () => {
+    const test = await harness([textResponse('not durable')])
+    let injected = false
+    test.ctx.on('session/flush', (session) => {
+      const lastStart = session.events.findLast(event => event.type === 'turn/start')
+      if (lastStart?.type === 'turn/start' && lastStart.data.trigger.kind === 'message'
+        && lastStart.data.trigger.source.kind === 'goal' && !injected) {
+        injected = true
+        test.agent.inject([{ type: 'text', text: 'concurrent completion notice' }], {
+          source: { kind: 'plugin', plugin: 'test' },
+        })
+        return Promise.reject(new Error('round flush failed'))
+      }
+    })
+    test.ctx.goals.create(test.agent, { objective: 'checkpoint the result' })
+
+    const goal = await waitForGoal(
+      test.ctx,
+      test.agent,
+      current => current?.roundsStarted === 1 && current.activation === 'disarmed',
+    )
+
+    expect(goal?.phase).toBe('active')
+    expect(test.adapter.requests).toHaveLength(1)
+    const turns = test.agent.session.events.filter(event => event.type === 'turn/start')
+    const goalTurn = turns.findIndex(event => event.data.trigger.source.kind === 'goal')
+    const injectedTurn = turns.findIndex(event => event.data.trigger.source.kind === 'plugin')
+    expect(injectedTurn).toBeGreaterThan(goalTurn)
+  })
+
+  it('blocks the goal when a custom agent rejects the otherwise valid send', async () => {
+    const test = await harness([])
+    vi.spyOn(test.agent, 'send').mockImplementationOnce(() => {
+      throw new Error('queue rejected')
+    })
+    test.ctx.goals.create(test.agent, { objective: 'handle queue failure' })
+
+    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)
+  })
+
+  it('preserves a custom agent side effect when send disarms before throwing', async () => {
+    const test = await harness([])
+    vi.spyOn(test.agent, 'send').mockImplementationOnce(() => {
+      test.ctx.goals.disarm(test.agent)
+      throw new Error('queue rejected after disarm')
+    })
+    test.ctx.goals.create(test.agent, { objective: 'preserve the newer activation state' })
+
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.activation === 'disarmed')
+
+    expect(goal).toMatchObject({ phase: 'active', roundsStarted: 0 })
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('contains a driver read failure and removes continuation authority', async () => {
+    const test = await harness([])
+    let flushes = 0
+    test.ctx.on('session/flush', () => {
+      flushes += 1
+      if (flushes !== 2) return
+      vi.spyOn(test.ctx.goals, 'get').mockImplementationOnce(() => {
+        throw new Error('corrupt projection')
+      })
+    })
+    test.ctx.goals.create(test.agent, { objective: 'fail the driver closed' })
+    await new Promise<void>((resolve) => { setImmediate(resolve) })
+
+    const goal = test.ctx.goals.get(test.agent)
+
+    expect(goal?.phase).toBe('active')
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('contains synchronous scheduler startup failure', async () => {
+    const test = await harness([])
+    vi.spyOn(test.ctx.agents, 'withoutInitiator').mockImplementationOnce(() => {
+      throw 'scheduler closed'
+    })
+    test.ctx.goals.create(test.agent, { objective: 'fail startup closed' })
+
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.activation === 'disarmed')
+
+    expect(goal?.phase).toBe('active')
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('contains an asynchronously rejected scheduler task', async () => {
+    const test = await harness([])
+    vi.spyOn(test.ctx.agents, 'withoutInitiator').mockImplementationOnce(
+      () => Promise.reject(new Error('scheduler task rejected')),
+    )
+    test.ctx.goals.create(test.agent, { objective: 'fail task closed' })
+
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.activation === 'disarmed')
+
+    expect(goal?.phase).toBe('active')
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('fails a pre-admission read closed even when the first disarm attempt throws', async () => {
+    const test = await harness([textResponse('retry after containment')])
+    let armed = true
+    test.ctx.on('agent/queued', (agent, _content, info) => {
+      if (agent !== test.agent || info.source.kind !== 'goal' || !armed) return
+      armed = false
+      vi.spyOn(test.ctx.goals, 'get').mockImplementationOnce(() => {
+        throw new Error('admission projection failed')
+      })
+      vi.spyOn(test.ctx.goals, 'disarm').mockImplementationOnce(() => {
+        throw 'disarm failed'
+      })
+    })
+    test.ctx.goals.create(test.agent, { objective: 'retry stale admission', maxGoalRounds: 1 })
+
+    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'
+      && event.data.reason === 'stale goal-round reservation')).toBe(true)
+  })
+
+  it('fails a post-hook read closed before the prompt can enter history', async () => {
+    const test = await harness([])
+    let armed = true
+    test.ctx.on('agent/prompt-submit', (_agent, _content, source, next) => {
+      if (source.kind === 'goal' && armed) {
+        armed = false
+        vi.spyOn(test.ctx.goals, 'get').mockImplementationOnce(() => {
+          throw new Error('post-hook projection failed')
+        })
+      }
+      return next()
+    })
+    test.ctx.goals.create(test.agent, { objective: 'block post-hook failure' })
+
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.activation === 'disarmed')
+
+    expect(goal).toMatchObject({ phase: 'active', roundsStarted: 0 })
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('blocks forged goal attribution without touching an absent reservation', async () => {
+    const test = await harness([])
+    test.agent.send([{ type: 'text', text: 'forged automatic work' }], {
+      source: { kind: 'goal', goalId: GoalId('forged-goal'), revision: 1, round: 1 },
+    })
+    await test.agent.whenIdle()
+
+    expect(test.adapter.requests).toHaveLength(0)
+    expect(test.agent.session.events.some(event => event.type === 'prompt/blocked'
+      && event.data.reason === 'stale goal-round reservation')).toBe(true)
+  })
+
+  it('does not invent goal state when ordinary queued work is cancelled', async () => {
+    const test = await harness([])
+    test.agent.send([{ type: 'text', text: 'cancel ordinary work' }])
+    test.agent.cancel('ordinary cancellation')
+    await test.agent.whenIdle()
+
+    expect(test.ctx.goals.get(test.agent)).toBeUndefined()
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('disarms without durably pausing when cancellation belongs to unrelated human work', async () => {
+    const test = await harness(['hang'])
+    test.agent.send([{ type: 'text', text: 'inspect something first' }])
+    await waitForRequests(test.adapter, 1)
+    const created = test.ctx.goals.create(test.agent, { objective: 'continue after inspection' })
+
+    test.agent.cancel('cancel the inspection')
+    await test.agent.whenIdle()
+
+    expect(test.ctx.goals.get(test.agent)).toMatchObject({
+      id: created.id,
+      revision: created.revision,
+      phase: 'active',
+      activation: 'disarmed',
+      roundsStarted: 0,
+    })
+  })
+
+  it('falls back to disarming when a cancelled reservation cannot be paused', async () => {
+    const test = await harness([])
+    const cancel = test.ctx.on('agent/queued', (agent, _content, info) => {
+      if (agent !== test.agent || info.source.kind !== 'goal') return
+      cancel()
+      vi.spyOn(test.ctx.goals, 'pause').mockImplementationOnce(() => {
+        throw new Error('pause failed')
+      })
+      agent.cancel('cancel the reserved goal round')
+    })
+    test.ctx.goals.create(test.agent, { objective: 'fail closed after cancellation' })
+
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.activation === 'disarmed')
+
+    expect(goal).toMatchObject({ phase: 'active', revision: 1, roundsStarted: 0 })
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('blocks admission when downstream cancellation clears the reservation', async () => {
+    const test = await harness([])
+    let cancelled = false
+    test.ctx.on('agent/prompt-submit', (agent, _content, source, next) => {
+      if (source.kind === 'goal' && !cancelled) {
+        cancelled = true
+        agent.cancel('cancel from downstream admission policy')
+      }
+      return next()
+    })
+    test.ctx.goals.create(test.agent, { objective: 'cancel during admission' })
+
+    const goal = await waitForGoal(test.ctx, test.agent, current => current?.phase === 'paused')
+    await test.agent.whenIdle()
+
+    expect(goal?.roundsStarted).toBe(0)
+    expect(test.adapter.requests).toHaveLength(0)
+  })
+
+  it('disarms and cancels an admitted round before driver teardown completes', async () => {
+    const test = await harness(['hang'])
+    test.ctx.goals.create(test.agent, { objective: 'survive plugin unload' })
+    await waitForRequests(test.adapter, 1)
+
+    await test.driver.dispose()
+
+    expect(test.ctx.goals.get(test.agent)).toMatchObject({
+      phase: 'active',
+      activation: 'disarmed',
+      roundsStarted: 1,
+    })
+    await test.agent.whenIdle()
+    expect(test.adapter.requests).toHaveLength(1)
+  })
+
+  it('cancels an accepted queued round and awaits its driver task during teardown', async () => {
+    const test = await harness([])
+    let unloading: Promise<void> | undefined
+    test.ctx.on('agent/queued', (agent, _content, info) => {
+      if (agent === test.agent && info.source.kind === 'goal' && unloading === undefined) {
+        unloading = Promise.resolve(test.driver.dispose())
+      }
+    })
+    test.ctx.goals.create(test.agent, { objective: 'unload while queued' })
+    await vi.waitFor(() => { expect(unloading).toBeDefined() })
+    await unloading
+
+    expect(test.ctx.goals.get(test.agent)).toMatchObject({
+      phase: 'active',
+      activation: 'disarmed',
+      roundsStarted: 1,
+    })
+    expect(test.adapter.requests).toHaveLength(1)
+  })
+
+  it('resets process-local scheduling state at a session-start edge', async () => {
+    const test = await harness([textResponse('after explicit resume')])
+    const created = test.ctx.goals.create(test.agent, { objective: 'restart safely', maxGoalRounds: 1 })
+    agentEvents(test.ctx, test.agent).emit('agent/session-start', 'resume')
+    await Promise.resolve()
+
+    expect(test.ctx.goals.get(test.agent)).toMatchObject({ activation: 'disarmed', roundsStarted: 0 })
+    expect(test.adapter.requests).toHaveLength(0)
+
+    test.ctx.goals.resume(test.agent, created)
+    await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'blocked')
+    expect(test.adapter.requests).toHaveLength(1)
+  })
+
+  it('ignores session events without an exact owning agent and retires disposed agent state', async () => {
+    const test = await harness([])
+    const orphan = test.ctx.sessions.create(SessionId('goal-session-orphan'))
+    orphan.append('turn/start', {
+      turn: 1,
+      trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'test' } },
+    })
+    orphan.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
+
+    const handle = await test.ctx.agents.create({
+      sessionId: SessionId('goal-session-disposed'),
+      agentOptions: { provider: 'mock', model: 'mock' },
+    })
+    await handle.dispose()
+
+    expect(test.ctx.agents.get(handle.agent.id)).toBeUndefined()
+  })
+})
diff --git a/packages/goal/goal-session/tsconfig.json b/packages/goal/goal-session/tsconfig.json
new file mode 100644
index 0000000000..d3cf5d5294
--- /dev/null
+++ b/packages/goal/goal-session/tsconfig.json
@@ -0,0 +1,30 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../core/agent"
+    },
+    {
+      "path": "../goal"
+    },
+    {
+      "path": "../../llm/llm"
+    },
+    {
+      "path": "../../core/session"
+    }
+  ]
+}
diff --git a/packages/goal/goal/README.md b/packages/goal/goal/README.md
new file mode 100644
index 0000000000..a71308d5f2
--- /dev/null
+++ b/packages/goal/goal/README.md
@@ -0,0 +1,54 @@
+# @deepseek-ai/dsh-goal
+
+Event-sourced same-session goal state. The service retains one current completion objective in an agent's existing session while keeping permission to continue as process-local activation. The [goal-domain Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md) owns the design rationale; the [goal type catalog](../../../docs/core-data-structures/goal.md) records the literal data shapes.
+
+## Config
+
+```yaml
+- id: goal
+  name: '@deepseek-ai/dsh-goal'
+  config:
+    defaultMaxGoalRounds: 256
+```
+
+`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, 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, 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 `context/message` content projected verbatim to the model, 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.
+
+Injection may append immediately or wait in an active tool-batch FIFO. The service overlays accepted pending changes in memory and reconciles each exact payload when it enters the log, so consecutive model-tool mutations see their own latest revisions without treating an unlogged cache as durable state. Reentrant append observers see each accepted mutation exactly once, and incremental replay retains its cursor at the first corrupt event. `goal/changed` fires after the append or enqueue succeeds; listener failures are contained.
+
+Activation is never persisted. A fresh cache and every `agent/session-start` edge disarm it even when replay finds an active durable phase. A continuation driver also calls `disarm()` before unload or after durability uncertainty. Session resume, fork, and driver replacement therefore retain the objective, phase, revisions, and admitted-round count without initiating work; a later explicit resume mutation must arm continuation.
+
+## Extension points
+
+Policy plugins call the service verbs and react to the scoped `goal/changed` event. A continuation consumer admits rounds as `user/message` events with `GoalMessageSource`; ordinary human turns never increment `roundsStarted`. Consumers use the `Agent` interface and events rather than importing `dsh-agent-loop`.
+
+## Model Experience
+
+### Goal-state mutation
+
+#### 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. 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
+
+Every retained mutation adds one full snapshot to derived history until compaction shadows it. Full snapshots make each record independently inspectable but repeat the objective and lifecycle fields.
+
+#### KV Cache effect
+
+Append-only within an epoch: each mutation follows the reusable request prefix and preceding history. Compaction may replace the derived-history suffix and move the reusable boundary.
+
+## Known Limitations and Deferred Work
+
+- **State, not scheduling** — this package does not decide when an armed goal continues, retry abnormal failures, or cancel an active turn; those policies belong to agent-seam consumers.
+- **Round-count budget only** — `maxGoalRounds` does not meter tokens, currency, wall time, or provider quotas.
+- **No independent evaluator** — the caller that records completion or blocking is authoritative; evaluator-backed certification is deferred to a separate policy layer.
+- **One current goal** — parallel objectives and a separate goal database are intentionally absent; history remains available in the session log after replacement or clear.
+- **Trusted in-process producers** — a plugin with direct `Session` access can append counterfeit goal metadata. Strict replay detects malformed or inconsistent records and leaves goal access failed at that record until the log is repaired; this is integrity detection, not plugin isolation.
diff --git a/packages/goal/goal/package.json b/packages/goal/goal/package.json
new file mode 100644
index 0000000000..534c258c6b
--- /dev/null
+++ b/packages/goal/goal/package.json
@@ -0,0 +1,44 @@
+{
+  "name": "@deepseek-ai/dsh-goal",
+  "description": "Event-sourced same-session goal state and lifecycle service for the DeepSeek Harness",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "@deepseek-ai/dsh-agent": "^0.0.1",
+    "@deepseek-ai/dsh-brand": "^0.0.1",
+    "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-scope": "^0.0.1",
+    "@deepseek-ai/dsh-session": "^0.0.1",
+    "cordis": "^4.0.0-rc.7"
+  },
+  "dependencies": {
+    "schemastery": "^3.17.2"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-brand": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-loader-smoke": "workspace:^",
+    "@deepseek-ai/dsh-scope": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "cordis": "^4.0.0-rc.7"
+  }
+}
diff --git a/packages/goal/goal/src/fold.ts b/packages/goal/goal/src/fold.ts
new file mode 100644
index 0000000000..fe88ebcdba
--- /dev/null
+++ b/packages/goal/goal/src/fold.ts
@@ -0,0 +1,377 @@
+/** Pure replay fold and strict decoder for durable goal changes. */
+
+import type { MessageSource } from '@deepseek-ai/dsh-llm'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import { renderGoalChange } from './render.ts'
+import { GOAL_CHANGE_VERSION, GoalId } from './runtime.ts'
+import type {
+  FoldedGoal,
+  GoalBlockReason,
+  GoalChangeMeta,
+  GoalClearChangeMeta,
+  GoalMessageSource,
+  GoalOperation,
+  GoalPhase,
+  GoalRef,
+  GoalSnapshot,
+  GoalSnapshotChangeMeta,
+} from './types.ts'
+
+type ContextMessageEvent = Extract<SessionEvent, { type: 'context/message' }>
+
+const SNAPSHOT_OPERATIONS: ReadonlySet<Exclude<GoalOperation, 'clear'>> = new Set([
+  'create',
+  'edit',
+  'pause',
+  'resume',
+  'complete',
+  'block',
+])
+const PHASES: ReadonlySet<GoalPhase> = new Set(['active', 'paused', 'blocked', 'complete'])
+
+/** Mutable accumulator kept private to the pure fold. */
+export interface GoalFoldState {
+  goal: GoalSnapshot | undefined
+  roundsStarted: number
+  createdAt: number | undefined
+  updatedAt: number | undefined
+  lastRef: GoalRef | undefined
+  seenGoalIds: Set<GoalSnapshot['id']>
+}
+
+/**
+ * Build an empty replay accumulator.
+ * @returns mutable state with no current goal or prior ref.
+ */
+export function emptyGoalFoldState(): GoalFoldState {
+  return {
+    goal: undefined,
+    roundsStarted: 0,
+    createdAt: undefined,
+    updatedAt: undefined,
+    lastRef: undefined,
+    seenGoalIds: new Set(),
+  }
+}
+
+/** Whether a value is a JSON record rather than an array. */
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === 'object' && value !== null && !Array.isArray(value)
+}
+
+/** Require one positive safe integer. */
+function positiveInteger(value: unknown, field: string): number {
+  if (typeof value !== 'number' || !Number.isSafeInteger(value) || value < 1) {
+    throw new Error(`goal change ${field} must be a positive safe integer`)
+  }
+  return value
+}
+
+/** Require one non-negative safe integer. */
+function nonNegativeInteger(value: unknown, field: string): number {
+  if (typeof value !== 'number' || !Number.isSafeInteger(value) || value < 0) {
+    throw new Error(`goal change ${field} must be a non-negative safe integer`)
+  }
+  return value
+}
+
+/** Decode one canonical blocker explanation. */
+function decodeBlockReason(value: unknown): GoalBlockReason {
+  if (!isRecord(value) || Object.keys(value).sort().join(',') !== 'code,message') {
+    throw new Error('goal change goal.blockedReason has an invalid shape')
+  }
+  if (typeof value['code'] !== 'string' || !/^[a-z][a-z0-9]*(?:-[a-z0-9]+)*$/.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')
+  if (typeof value['id'] !== 'string' || value['id'].length === 0) {
+    throw new Error('goal change goal.id must be a non-empty string')
+  }
+  if (typeof value['objective'] !== 'string' || value['objective'].trim().length === 0
+    || value['objective'] !== value['objective'].trim()) {
+    throw new Error('goal change goal.objective must be non-empty and normalized')
+  }
+  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,
+    maxGoalRounds: positiveInteger(value['maxGoalRounds'], 'goal.maxGoalRounds'),
+    ...phase === 'blocked' ? { blockedReason: decodeBlockReason(value['blockedReason']) } : {},
+  }
+}
+
+/** Decode and validate one ref. */
+function decodeRef(value: unknown): GoalRef {
+  if (!isRecord(value) || Object.keys(value).sort().join(',') !== 'id,revision') {
+    throw new Error('goal clear tombstone has an invalid shape')
+  }
+  if (typeof value['id'] !== 'string' || value['id'].length === 0) {
+    throw new Error('goal clear tombstone id must be a non-empty string')
+  }
+  return { id: GoalId(value['id']), revision: positiveInteger(value['revision'], 'cleared.revision') }
+}
+
+/**
+ * Decode metadata that declares itself as a goal change. Unrelated metadata
+ * returns `undefined`; malformed goal metadata fails replay loudly.
+ * @param value - context-message metadata.
+ * @returns validated goal change or `undefined` for another metadata kind.
+ */
+export function decodeGoalChange(value: unknown): GoalChangeMeta | undefined {
+  if (!isRecord(value) || value['kind'] !== 'goal/change') return undefined
+  if (value['version'] !== GOAL_CHANGE_VERSION) {
+    throw new Error(`unsupported goal change version ${String(value['version'])}`)
+  }
+  if (value['operation'] === 'clear') {
+    const allowed = ['cleared', 'clearedAt', 'kind', 'operation', 'version']
+    if (Object.keys(value).sort().join(',') !== allowed.sort().join(',')) {
+      throw new Error('goal clear change has an invalid shape')
+    }
+    return {
+      kind: 'goal/change',
+      version: GOAL_CHANGE_VERSION,
+      operation: 'clear',
+      cleared: decodeRef(value['cleared']),
+      clearedAt: nonNegativeInteger(value['clearedAt'], 'clearedAt'),
+    } satisfies GoalClearChangeMeta
+  }
+  if (typeof value['operation'] !== 'string'
+    || !SNAPSHOT_OPERATIONS.has(value['operation'] as Exclude<GoalOperation, 'clear'>)) {
+    throw new Error('goal change operation is invalid')
+  }
+  const allowed = ['createdAt', 'goal', 'kind', 'operation', 'roundsStarted', 'updatedAt', 'version']
+  if (Object.keys(value).sort().join(',') !== allowed.sort().join(',')) {
+    throw new Error('goal snapshot change has an invalid shape')
+  }
+  const createdAt = nonNegativeInteger(value['createdAt'], 'createdAt')
+  const updatedAt = nonNegativeInteger(value['updatedAt'], 'updatedAt')
+  if (updatedAt < createdAt) throw new Error('goal change updatedAt cannot precede createdAt')
+  return {
+    kind: 'goal/change',
+    version: GOAL_CHANGE_VERSION,
+    operation: value['operation'] as Exclude<GoalOperation, 'clear'>,
+    goal: decodeSnapshot(value['goal']),
+    roundsStarted: nonNegativeInteger(value['roundsStarted'], 'roundsStarted'),
+    createdAt,
+    updatedAt,
+  } satisfies GoalSnapshotChangeMeta
+}
+
+/** Narrow model attribution to a valid goal source. */
+function goalSource(source: MessageSource): GoalMessageSource | undefined {
+  if (source.kind !== 'goal') return undefined
+  if (typeof source.goalId !== 'string' || source.goalId.length === 0
+    || !Number.isSafeInteger(source.revision) || source.revision < 1
+    || !Number.isSafeInteger(source.round) || source.round < 0) {
+    throw new Error('goal message source is invalid')
+  }
+  return source
+}
+
+/** Require two snapshots to retain fields that only `edit` may replace. */
+function requireSameDefinition(current: GoalSnapshot, next: GoalSnapshot, operation: GoalOperation): void {
+  if (next.objective !== current.objective || next.maxGoalRounds !== current.maxGoalRounds) {
+    throw new Error(`goal ${operation} cannot change objective or maxGoalRounds`)
+  }
+}
+
+/** Require one exact next revision of the current goal. */
+function requireNextRevision(current: GoalSnapshot, next: GoalRef, operation: GoalOperation): void {
+  if (next.id !== current.id || next.revision !== current.revision + 1) {
+    throw new Error(`goal ${operation} must advance the current goal by one revision`)
+  }
+}
+
+/** Validate one non-create snapshot operation against the preceding projection. */
+function validateSnapshotTransition(
+  state: GoalFoldState,
+  change: GoalSnapshotChangeMeta,
+  current: GoalSnapshot,
+): void {
+  const next = change.goal
+  requireNextRevision(current, next, change.operation)
+  /* v8 ignore next -- a current goal established by this fold always has an updatedAt */
+  if (state.updatedAt === undefined) throw new Error('current goal fold lacks updatedAt')
+  if (change.createdAt !== state.createdAt
+    || change.updatedAt < state.updatedAt
+    || change.roundsStarted !== state.roundsStarted) {
+    throw new Error(`goal ${change.operation} does not preserve the current counters and timestamps`)
+  }
+  switch (change.operation) {
+    case 'edit':
+      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)
+      if (current.phase !== 'active' || next.phase !== 'paused') throw new Error('goal pause has an invalid phase transition')
+      break
+    case 'resume': {
+      requireSameDefinition(current, next, change.operation)
+      const resumable: ReadonlySet<GoalPhase> = new Set([
+        'active',
+        'paused',
+        'blocked',
+      ])
+      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')
+      }
+      break
+    }
+    case 'complete':
+      requireSameDefinition(current, next, change.operation)
+      if (current.phase === 'complete' || next.phase !== 'complete') throw new Error('goal complete has an invalid phase transition')
+      break
+    case 'block':
+      requireSameDefinition(current, next, change.operation)
+      if (current.phase !== 'active' || next.phase !== 'blocked') throw new Error('goal block has an invalid phase transition')
+      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')
+    default:
+      change.operation satisfies never
+      throw new Error('unknown goal snapshot operation')
+    /* v8 ignore stop */
+  }
+}
+
+/**
+ * Return the revision identity carried by a snapshot or tombstone.
+ * @param change - decoded goal mutation.
+ * @returns stable identity used to reconcile a deferred change with its log event.
+ */
+export function goalChangeRef(change: GoalChangeMeta): GoalRef {
+  return change.operation === 'clear' ? change.cleared : change.goal
+}
+
+/**
+ * Validate and apply one decoded change to a mutable accumulator.
+ * @param state - preceding durable goal projection.
+ * @param change - decoded full snapshot or clear tombstone.
+ */
+export function applyGoalChange(state: GoalFoldState, change: GoalChangeMeta): void {
+  const ref = goalChangeRef(change)
+  if (change.operation === 'clear') {
+    const current = state.goal
+    if (current === undefined) throw new Error('goal clear requires a current goal')
+    requireNextRevision(current, change.cleared, change.operation)
+    /* v8 ignore next -- a current goal established by this fold always has an updatedAt */
+    if (state.updatedAt === undefined) throw new Error('current goal fold lacks updatedAt')
+    if (change.clearedAt < state.updatedAt) {
+      throw new Error('goal clear timestamp cannot precede the current goal update')
+    }
+    state.goal = undefined
+    state.roundsStarted = 0
+    state.createdAt = undefined
+    state.updatedAt = undefined
+    state.lastRef = ref
+    return
+  }
+  if (change.operation === 'create') {
+    if (change.goal.revision !== 1 || change.goal.phase !== 'active' || change.roundsStarted !== 0
+      || (state.goal !== undefined && state.goal.phase !== 'complete')
+      || state.seenGoalIds.has(change.goal.id)) {
+      throw new Error('goal create requires a fresh active revision-one goal with zero rounds')
+    }
+    state.seenGoalIds.add(change.goal.id)
+  } else {
+    const current = state.goal
+    if (current === undefined) throw new Error(`goal ${change.operation} requires a current goal`)
+    validateSnapshotTransition(state, change, current)
+  }
+  state.goal = change.goal
+  state.roundsStarted = change.roundsStarted
+  state.createdAt = change.createdAt
+  state.updatedAt = change.updatedAt
+  state.lastRef = ref
+}
+
+/**
+ * Decode and verify one model-visible goal context event without folding it.
+ * @param event - context event whose metadata and rendered content must agree.
+ * @returns validated change or `undefined` for an unrelated context event.
+ */
+export function decodeGoalEvent(event: ContextMessageEvent): GoalChangeMeta | undefined {
+  const change = decodeGoalChange(event.data.meta)
+  const source = goalSource(event.data.source)
+  if (change === undefined) {
+    if (source !== undefined) throw new Error(`goal source at session event ${event.seq} lacks goal change metadata`)
+    return undefined
+  }
+  const ref = goalChangeRef(change)
+  if (source === undefined || source.goalId !== ref.id || source.revision !== ref.revision || source.round !== 0) {
+    throw new Error(`goal change at session event ${event.seq} has mismatched source attribution`)
+  }
+  if (JSON.stringify(event.data.content) !== JSON.stringify(renderGoalChange(change))) {
+    throw new Error(`goal change at session event ${event.seq} has mismatched model-visible content`)
+  }
+  return change
+}
+
+/**
+ * Apply one session event and return its goal change, when present.
+ * @param state - mutable fold accumulator.
+ * @param event - next event in sequence order.
+ * @returns decoded change for pending-overlay reconciliation.
+ */
+export function applyGoalEvent(state: GoalFoldState, event: SessionEvent): GoalChangeMeta | undefined {
+  if (event.type === 'context/message') {
+    const change = decodeGoalEvent(event)
+    if (change === undefined) return undefined
+    applyGoalChange(state, change)
+    return change
+  }
+  if (event.type === 'user/message') {
+    const source = goalSource(event.data.source)
+    if (source !== undefined) {
+      const current = state.goal
+      if (current === undefined || current.phase !== 'active' || source.goalId !== current.id
+        || source.revision !== current.revision || source.round !== state.roundsStarted + 1
+        || source.round > current.maxGoalRounds) {
+        throw new Error(`goal round at session event ${event.seq} is not the next admitted round of the active goal`)
+      }
+      state.roundsStarted = source.round
+    }
+  }
+  return undefined
+}
+
+/**
+ * Fold current goal state from a contiguous session event log.
+ * @param events - session events in sequence order.
+ * @returns a fresh durable projection; activation is deliberately absent.
+ */
+export function foldGoal(events: readonly SessionEvent[]): FoldedGoal {
+  const state = emptyGoalFoldState()
+  for (const event of events) applyGoalEvent(state, event)
+  return {
+    ...state.goal === undefined ? {} : { goal: { ...state.goal } },
+    roundsStarted: state.roundsStarted,
+    ...state.createdAt === undefined ? {} : { createdAt: state.createdAt },
+    ...state.updatedAt === undefined ? {} : { updatedAt: state.updatedAt },
+    ...state.lastRef === undefined ? {} : { lastRef: { ...state.lastRef } },
+  }
+}
diff --git a/packages/goal/goal/src/index.ts b/packages/goal/goal/src/index.ts
new file mode 100644
index 0000000000..7391c69e93
--- /dev/null
+++ b/packages/goal/goal/src/index.ts
@@ -0,0 +1,544 @@
+/**
+ * Same-session goal domain: event-sourced state, compare-and-set mutations,
+ * and process-local continuation activation.
+ * @module @deepseek-ai/dsh-goal
+ */
+
+import { randomUUID } from 'node:crypto'
+import { Context, Service } from 'cordis'
+import z from 'schemastery'
+import { agentEvents } from '@deepseek-ai/dsh-agent'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+import { snapshotJsonValue } from '@deepseek-ai/dsh-session'
+import type { JsonValue, Session } from '@deepseek-ai/dsh-session'
+import {
+  applyGoalChange,
+  applyGoalEvent,
+  decodeGoalEvent,
+  emptyGoalFoldState,
+  goalChangeRef,
+} from './fold.ts'
+import type { GoalFoldState } from './fold.ts'
+import { renderGoalChange } from './render.ts'
+import {
+  GOAL_CHANGE_VERSION,
+  GoalError,
+  GoalId,
+} from './runtime.ts'
+import type {
+  CreateGoalRequest,
+  EditGoalRequest,
+  GoalActivation,
+  GoalBlockReason,
+  GoalChangeMeta,
+  GoalChanged,
+  GoalClearChangeMeta,
+  GoalOperation,
+  GoalPhase,
+  GoalRef,
+  GoalSnapshot,
+  GoalSnapshotChangeMeta,
+  GoalView,
+} from './types.ts'
+
+export * from './types.ts'
+export { GOAL_CHANGE_VERSION, GoalError, GoalId } from './runtime.ts'
+export { decodeGoalChange, foldGoal, goalChangeRef } from './fold.ts'
+export { renderGoalChange } from './render.ts'
+
+declare module 'cordis' {
+  interface Context {
+    goals: GoalService
+  }
+}
+
+/** Deployment defaults for goal creation. */
+export interface Config {
+  /** Total rounds used when a create request omits its own cap. */
+  defaultMaxGoalRounds?: number
+}
+
+/** Resolved defaults. */
+export interface ResolvedConfig {
+  /** Validated positive safe-integer default round cap. */
+  defaultMaxGoalRounds: number
+}
+
+/** One accepted mutation waiting to enter or be observed in the session log. */
+interface PendingGoalChange {
+  readonly change: GoalChangeMeta
+  readonly activation: GoalActivation
+  applied: boolean
+}
+
+/** Process-local cache plus mutations waiting in the active tool-batch FIFO. */
+interface GoalCache {
+  readonly state: GoalFoldState
+  activation: GoalActivation
+  observedSeq: number
+  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) {
+    throw new GoalError('maxGoalRounds must be a positive safe integer', 'GOAL_INVALID_MAX_ROUNDS')
+  }
+  return value
+}
+
+/** Validate and normalize an objective at the domain boundary. */
+function resolveObjective(value: string): string {
+  if (typeof value !== 'string' || value.trim().length === 0) {
+    throw new GoalError('goal objective must be a non-empty string', 'GOAL_INVALID_OBJECTIVE')
+  }
+  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)
+}
+
+/** Goal service (`ctx.goals`) backed exclusively by the owning session log. */
+export class GoalService extends Service {
+  static inject = ['agents']
+
+  static Config: z<Config> = z.object({
+    defaultMaxGoalRounds: z.number().default(256),
+  })
+
+  private readonly resolved: ResolvedConfig
+  private readonly caches = new WeakMap<Session, GoalCache>()
+
+  constructor(ctx: Context, config: Config = {}) {
+    super(ctx, 'goals')
+    this.resolved = {
+      defaultMaxGoalRounds: resolveMaxGoalRounds(config.defaultMaxGoalRounds ?? 256),
+    }
+    ctx.on('agent/session-start', (agent) => {
+      this.cache(agent.session).activation = 'disarmed'
+    })
+  }
+
+  /**
+   * Read the current goal for one exact live agent.
+   * @param agent - owning live agent.
+   * @returns a fresh view or `undefined` when no goal is current.
+   * @throws {@link GoalError} when the agent is not the registry's live instance.
+   */
+  get(agent: Agent): GoalView | undefined {
+    this.assertLive(agent)
+    const cache = this.cache(agent.session)
+    this.sync(agent.session, cache)
+    return this.view(cache)
+  }
+
+  /**
+   * Remove process-local continuation authority without changing durable goal
+   * phase or revision. Lifecycle owners use this before unloading a driver;
+   * a later human-authorized {@link resume} records the new activation edge.
+   * @param agent - owning live agent.
+   * @returns a fresh disarmed view, or `undefined` when no goal is current.
+   */
+  disarm(agent: Agent): GoalView | undefined {
+    this.assertLive(agent)
+    const cache = this.cache(agent.session)
+    this.sync(agent.session, cache)
+    cache.activation = 'disarmed'
+    return this.view(cache)
+  }
+
+  /**
+   * Create and arm a goal. A completed goal may be replaced; every other
+   * current phase must be cleared or resumed instead.
+   * @param agent - owning live agent.
+   * @param request - objective and optional round cap.
+   * @returns the created live view.
+   */
+  create(agent: Agent, request: CreateGoalRequest): GoalView {
+    const spec = resolveCreateGoal(request, this.resolved.defaultMaxGoalRounds)
+    const cache = this.prepareMutation(agent)
+    const current = cache.state.goal
+    if (current !== undefined && current.phase !== 'complete') {
+      throw new GoalError(`goal "${current.id}" already exists with phase "${current.phase}"`, 'GOAL_ALREADY_EXISTS')
+    }
+    const now = Date.now()
+    const goal: GoalSnapshot = {
+      id: GoalId(`goal-${randomUUID()}`),
+      revision: 1,
+      objective: spec.objective,
+      phase: 'active',
+      maxGoalRounds: spec.maxGoalRounds,
+    }
+    return this.commitSnapshot(agent, cache, 'create', goal, 0, now, now, 'armed')
+  }
+
+  /**
+   * Edit objective and/or round cap without changing phase.
+   * @param agent - owning live agent.
+   * @param ref - expected current revision.
+   * @param request - at least one replacement field.
+   * @returns the edited view.
+   */
+  edit(agent: Agent, ref: GoalRef, request: EditGoalRequest): GoalView {
+    const cache = this.prepareMutation(agent)
+    const current = this.expectCurrent(cache, ref)
+    if (request.objective === undefined && request.maxGoalRounds === undefined) {
+      throw new GoalError('goal edit requires objective and/or maxGoalRounds', 'GOAL_INVALID_EDIT')
+    }
+    const goal: GoalSnapshot = {
+      ...current,
+      revision: current.revision + 1,
+      ...request.objective === undefined ? {} : { objective: resolveObjective(request.objective) },
+      ...request.maxGoalRounds === undefined ? {} : { maxGoalRounds: resolveMaxGoalRounds(request.maxGoalRounds) },
+    }
+    return this.commitCurrent(agent, cache, 'edit', goal, cache.activation)
+  }
+
+  /**
+   * Pause an active goal and disarm automatic continuation.
+   * @param agent - owning live agent.
+   * @param ref - expected current revision.
+   * @returns the paused view.
+   */
+  pause(agent: Agent, ref: GoalRef): GoalView {
+    return this.transition(agent, ref, 'pause', ['active'], 'paused', 'disarmed')
+  }
+
+  /**
+   * Resume and arm a stopped goal, or rearm an active goal after a
+   * session-start edge, while its round budget still has capacity.
+   * @param agent - owning live agent.
+   * @param ref - expected current revision.
+   * @returns the active view.
+   */
+  resume(agent: Agent, ref: GoalRef): GoalView {
+    const cache = this.prepareMutation(agent)
+    const current = this.expectCurrent(cache, ref)
+    const resumable: readonly GoalPhase[] = ['active', 'paused', 'blocked']
+    if (!resumable.includes(current.phase)) {
+      throw this.transitionError(current, 'resume', resumable)
+    }
+    if (current.phase === 'active' && cache.activation === 'armed') {
+      throw new GoalError(`goal "${current.id}" is already active and armed`, 'GOAL_INVALID_TRANSITION')
+    }
+    if (cache.state.roundsStarted >= current.maxGoalRounds) {
+      throw new GoalError(
+        `goal "${current.id}" exhausted ${current.maxGoalRounds} goal rounds; increase maxGoalRounds before resuming`,
+        'GOAL_INVALID_TRANSITION',
+      )
+    }
+    return this.commitCurrent(agent, cache, 'resume', this.withPhase(current, 'active'), 'armed')
+  }
+
+  /**
+   * Mark a current non-complete goal complete and disarm it.
+   * @param agent - owning live agent.
+   * @param ref - expected current revision.
+   * @returns the completed view.
+   */
+  complete(agent: Agent, ref: GoalRef): GoalView {
+    return this.transition(
+      agent,
+      ref,
+      'complete',
+      ['active', 'paused', 'blocked'],
+      'complete',
+      'disarmed',
+    )
+  }
+
+  /**
+   * Mark an active goal blocked and disarm it.
+   * @param agent - owning live agent.
+   * @param ref - expected current revision.
+   * @param reason - policy-owned stable code and human-readable explanation.
+   * @returns the blocked view with its durable reason.
+   */
+  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, 'block', ['active'])
+    }
+    return this.commitCurrent(
+      agent,
+      cache,
+      'block',
+      { ...this.withPhase(current, 'blocked'), blockedReason: resolveBlockReason(reason) },
+      'disarmed',
+    )
+  }
+
+  /**
+   * Clear the current goal while retaining a durable tombstone and history.
+   * @param agent - owning live agent.
+   * @param ref - expected current revision.
+   * @returns the tombstone ref whose revision is one past the cleared snapshot.
+   */
+  clear(agent: Agent, ref: GoalRef): GoalRef {
+    const cache = this.prepareMutation(agent)
+    const current = this.expectCurrent(cache, ref)
+    const tombstone: GoalRef = { id: current.id, revision: current.revision + 1 }
+    const change: GoalClearChangeMeta = {
+      kind: 'goal/change',
+      version: GOAL_CHANGE_VERSION,
+      operation: 'clear',
+      cleared: tombstone,
+      clearedAt: this.nextMutationTime(cache),
+    }
+    this.commit(agent, cache, change, 'disarmed')
+    return { ...tombstone }
+  }
+
+  /** Resolve and validate the cache used by a mutation. */
+  private prepareMutation(agent: Agent): GoalCache {
+    this.assertLive(agent)
+    const cache = this.cache(agent.session)
+    this.sync(agent.session, cache)
+    return cache
+  }
+
+  /** Reject stale or missing current-state refs. */
+  private expectCurrent(cache: GoalCache, ref: GoalRef): GoalSnapshot {
+    const current = cache.state.goal
+    if (current === undefined) throw new GoalError('no current goal', 'GOAL_NOT_FOUND')
+    if (ref.id !== current.id || ref.revision !== current.revision) {
+      throw new GoalError(
+        `stale goal ref "${ref.id}" revision ${ref.revision}; current is "${current.id}" revision ${current.revision}`,
+        'GOAL_STALE_REVISION',
+      )
+    }
+    return current
+  }
+
+  /** Enforce exact live-agent identity rather than trusting a matching id. */
+  private assertLive(agent: Agent): void {
+    if (this.ctx.agents.get(agent.id) !== agent || agent.status === 'disposed') {
+      throw new GoalError(`agent "${agent.id}" is not live in this registry`, 'GOAL_AGENT_NOT_LIVE')
+    }
+  }
+
+  /** Return the per-session cache, folding a seed once with activation disarmed. */
+  private cache(session: Session): GoalCache {
+    let cache = this.caches.get(session)
+    if (cache !== undefined) return cache
+    const state = emptyGoalFoldState()
+    for (const event of session.events) applyGoalEvent(state, event)
+    cache = {
+      state,
+      activation: 'disarmed',
+      observedSeq: session.seq,
+      pending: [],
+    }
+    this.caches.set(session, cache)
+    return cache
+  }
+
+  /** Incrementally observe durable events without losing deferred mutations. */
+  private sync(session: Session, cache: GoalCache): void {
+    for (const event of session.events.slice(cache.observedSeq)) {
+      if (event.type === 'context/message') {
+        const change = decodeGoalEvent(event)
+        if (change !== undefined) {
+          const pending = cache.pending[0]
+          if (pending !== undefined && sameChange(pending.change, change)) {
+            if (!pending.applied) {
+              applyGoalChange(cache.state, change)
+              cache.activation = pending.activation
+              pending.applied = true
+            }
+            cache.pending.shift()
+            cache.observedSeq += 1
+            continue
+          }
+        }
+      }
+      applyGoalEvent(cache.state, event)
+      cache.observedSeq += 1
+    }
+  }
+
+  /** Build a new revision with one replacement phase. */
+  private withPhase(current: GoalSnapshot, phase: GoalPhase): GoalSnapshot {
+    return {
+      id: current.id,
+      revision: current.revision + 1,
+      objective: current.objective,
+      phase,
+      maxGoalRounds: current.maxGoalRounds,
+    }
+  }
+
+  /** Shared validated phase transition. */
+  private transition(
+    agent: Agent,
+    ref: GoalRef,
+    operation: Exclude<GoalOperation, 'create' | 'edit' | 'clear'>,
+    allowed: readonly GoalPhase[],
+    phase: GoalPhase,
+    activation: GoalActivation,
+  ): GoalView {
+    const cache = this.prepareMutation(agent)
+    const current = this.expectCurrent(cache, ref)
+    if (!allowed.includes(current.phase)) throw this.transitionError(current, operation, allowed)
+    return this.commitCurrent(agent, cache, operation, this.withPhase(current, phase), activation)
+  }
+
+  /** Render a stable invalid-transition error. */
+  private transitionError(current: GoalSnapshot, operation: GoalOperation, allowed: readonly GoalPhase[]): GoalError {
+    return new GoalError(
+      `cannot ${operation} goal "${current.id}" from phase "${current.phase}"; expected ${allowed.join(' or ')}`,
+      'GOAL_INVALID_TRANSITION',
+    )
+  }
+
+  /** Commit a mutation that retains the current goal's derived counters/times. */
+  private commitCurrent(
+    agent: Agent,
+    cache: GoalCache,
+    operation: Exclude<GoalOperation, 'create' | 'clear'>,
+    goal: GoalSnapshot,
+    activation: GoalActivation,
+  ): GoalView {
+    const createdAt = cache.state.createdAt
+    /* v8 ignore next -- strict replay and every snapshot commit set createdAt whenever a current goal exists */
+    if (createdAt === undefined) throw new Error('current goal cache lacks createdAt')
+    return this.commitSnapshot(
+      agent,
+      cache,
+      operation,
+      goal,
+      cache.state.roundsStarted,
+      createdAt,
+      this.nextMutationTime(cache),
+      activation,
+    )
+  }
+
+  /** Clamp a current goal's next timestamp across backward wall-clock movement. */
+  private nextMutationTime(cache: GoalCache): number {
+    const updatedAt = cache.state.updatedAt
+    /* v8 ignore next -- strict replay and every snapshot commit set updatedAt whenever a current goal exists */
+    if (updatedAt === undefined) throw new Error('current goal cache lacks updatedAt')
+    return Math.max(Date.now(), updatedAt)
+  }
+
+  /** Build and commit one full-snapshot mutation. */
+  private commitSnapshot(
+    agent: Agent,
+    cache: GoalCache,
+    operation: Exclude<GoalOperation, 'clear'>,
+    goal: GoalSnapshot,
+    roundsStarted: number,
+    createdAt: number,
+    updatedAt: number,
+    activation: GoalActivation,
+  ): GoalView {
+    const change: GoalSnapshotChangeMeta = {
+      kind: 'goal/change',
+      version: GOAL_CHANGE_VERSION,
+      operation,
+      goal,
+      roundsStarted,
+      createdAt,
+      updatedAt,
+    }
+    this.commit(agent, cache, change, activation)
+    const view = this.view(cache)
+    /* v8 ignore next -- applyGoalChange installs the snapshot immediately before this read */
+    if (view === undefined) throw new Error('snapshot commit cleared the goal unexpectedly')
+    return view
+  }
+
+  /** Accept one mutation into the agent log/FIFO, cache, and live event stream. */
+  private commit(agent: Agent, cache: GoalCache, change: GoalChangeMeta, activation: GoalActivation): void {
+    const ref = goalChangeRef(change)
+    // snapshotJsonValue preserves its input type for callers that already have
+    // a JsonValue; this interface is structurally JSON but intentionally has no
+    // index signature, so narrow the validated output at this boundary.
+    const meta = snapshotJsonValue(change) as JsonValue | undefined
+    /* v8 ignore next -- validated goal changes contain only finite JSON primitives and records */
+    if (meta === undefined) throw new Error('goal change is not losslessly JSON-serializable')
+    const pending: PendingGoalChange = { change, activation, applied: false }
+    cache.pending.push(pending)
+    try {
+      agent.inject(renderGoalChange(change), {
+        source: { kind: 'goal', goalId: ref.id, revision: ref.revision, round: 0 },
+        meta,
+      })
+    } catch (error: unknown) {
+      const index = cache.pending.indexOf(pending)
+      /* v8 ignore next -- a committed goal append cannot reject after its contained observers run */
+      if (index < 0) throw new Error('goal injection failed after its pending mutation was reconciled', { cause: error })
+      cache.pending.splice(index, 1)
+      throw error
+    }
+    if (!pending.applied) {
+      applyGoalChange(cache.state, change)
+      cache.activation = activation
+      pending.applied = true
+    }
+    this.sync(agent.session, cache)
+    const goal = this.view(cache)
+    const notification: GoalChanged = {
+      operation: change.operation,
+      ref: { ...ref },
+      ...goal === undefined ? {} : { goal },
+    }
+    agentEvents(this.ctx, agent).emit('goal/changed', notification)
+  }
+
+  /** Build a detached current view. */
+  private view(cache: GoalCache): GoalView | undefined {
+    const goal = cache.state.goal
+    const createdAt = cache.state.createdAt
+    const updatedAt = cache.state.updatedAt
+    if (goal === undefined) return undefined
+    /* v8 ignore next 3 -- strict replay and snapshot commits establish both timestamps with every current goal */
+    if (createdAt === undefined || updatedAt === undefined) {
+      throw new Error(`goal "${goal.id}" cache lacks timestamps`)
+    }
+    return {
+      ...goal,
+      roundsStarted: cache.state.roundsStarted,
+      createdAt,
+      updatedAt,
+      activation: cache.activation,
+    }
+  }
+}
+
+export default GoalService
diff --git a/packages/goal/goal/src/render.ts b/packages/goal/goal/src/render.ts
new file mode 100644
index 0000000000..955c9a070c
--- /dev/null
+++ b/packages/goal/goal/src/render.ts
@@ -0,0 +1,21 @@
+/** Model-visible rendering for durable goal mutations. */
+
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import type { GoalChangeMeta } from './types.ts'
+
+/**
+ * Render a complete goal snapshot or clear tombstone without hidden prose.
+ * @param change - durable goal change metadata.
+ * @returns the single context block logged and projected verbatim for model reconstruction.
+ */
+export function renderGoalChange(change: GoalChangeMeta): ContentBlock[] {
+  const payload = change.operation === 'clear'
+    ? { cleared: change.cleared, clearedAt: change.clearedAt }
+    : {
+      goal: change.goal,
+      roundsStarted: change.roundsStarted,
+      createdAt: change.createdAt,
+      updatedAt: change.updatedAt,
+    }
+  return [{ type: 'text', text: `<goal_state>${JSON.stringify(payload)}</goal_state>` }]
+}
diff --git a/packages/goal/goal/src/runtime.ts b/packages/goal/goal/src/runtime.ts
new file mode 100644
index 0000000000..49184faa8c
--- /dev/null
+++ b/packages/goal/goal/src/runtime.ts
@@ -0,0 +1,29 @@
+/** Runtime constructors and protocol constants for the goal domain. */
+
+import { HarnessError } from '@deepseek-ai/dsh-llm'
+import type { GoalErrorCode, GoalId as GoalIdType } from './types.ts'
+
+/** Version of the goal change metadata embedded in `context/message`. */
+export const GOAL_CHANGE_VERSION = 1
+
+/**
+ * Brand a string as a goal id.
+ * @param id - raw goal identifier.
+ * @returns the same string with the compile-time brand.
+ */
+export function GoalId(id: string): GoalIdType {
+  return id as GoalIdType
+}
+
+/** Error returned by the goal domain boundary. */
+export class GoalError extends HarnessError {
+  /**
+   * @param message - human-readable rejection reason.
+   * @param code - stable machine-routable classification.
+   */
+  // Keep the constructor to narrow HarnessError's string code at this boundary.
+  // eslint-disable-next-line @typescript-eslint/no-useless-constructor -- type-only narrowing
+  constructor(message: string, code: GoalErrorCode) {
+    super(message, code)
+  }
+}
diff --git a/packages/goal/goal/src/types.ts b/packages/goal/goal/src/types.ts
new file mode 100644
index 0000000000..2c6798718d
--- /dev/null
+++ b/packages/goal/goal/src/types.ts
@@ -0,0 +1,169 @@
+/**
+ * Durable and live vocabulary for one same-session goal.
+ * @module @deepseek-ai/dsh-goal/types
+ */
+
+import type { Branded } from '@deepseek-ai/dsh-brand'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+
+/** Identifies one goal across its durable revisions. */
+export type GoalId = Branded<'GoalId'>
+
+/** Compare-and-set identity for one exact goal revision. */
+export interface GoalRef {
+  /** Stable goal identity. */
+  readonly id: GoalId
+  /** Positive revision; every durable mutation increments it. */
+  readonly revision: number
+}
+
+/** Durable continuation phase. Activation is process-local and separate. */
+export type GoalPhase =
+  | 'active'
+  | 'paused'
+  | 'blocked'
+  | '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
+}
+
+/** Whether this live process may automatically continue an active goal. */
+export type GoalActivation = 'armed' | 'disarmed'
+
+/** Current goal projection, including values derived from the session log. */
+export interface GoalView extends GoalSnapshot {
+  /** Highest admitted round number for this goal. */
+  readonly roundsStarted: number
+  /** Epoch milliseconds of the create mutation. */
+  readonly createdAt: number
+  /** Epoch milliseconds of the latest mutation. */
+  readonly updatedAt: number
+  /** Process-local continuation eligibility; never persisted. */
+  readonly activation: GoalActivation
+}
+
+/** Goal state-changing verbs recorded in the durable change metadata. */
+export type GoalOperation =
+  | 'create'
+  | 'edit'
+  | 'pause'
+  | 'resume'
+  | 'complete'
+  | 'block'
+  | 'clear'
+
+/** Full-snapshot goal mutation retained in a model-visible context event. */
+export interface GoalSnapshotChangeMeta {
+  readonly kind: 'goal/change'
+  readonly version: 1
+  readonly operation: Exclude<GoalOperation, 'clear'>
+  readonly goal: GoalSnapshot
+  readonly roundsStarted: number
+  readonly createdAt: number
+  readonly updatedAt: number
+}
+
+/** Tombstone retained when the current goal is cleared. */
+export interface GoalClearChangeMeta {
+  readonly kind: 'goal/change'
+  readonly version: 1
+  readonly operation: 'clear'
+  readonly cleared: GoalRef
+  readonly clearedAt: number
+}
+
+/** Durable metadata union carried by a goal-owned `context/message`. */
+export type GoalChangeMeta = GoalSnapshotChangeMeta | GoalClearChangeMeta
+
+/** Message attribution for durable goal state and continuation rounds. */
+export interface GoalMessageSource {
+  readonly kind: 'goal'
+  readonly goalId: GoalId
+  readonly revision: number
+  /** Zero for state changes; positive for admitted continuation rounds. */
+  readonly round: number
+}
+
+declare module '@deepseek-ai/dsh-llm' {
+  interface MessageSourceMap {
+    goal: GoalMessageSource
+  }
+}
+
+/** Pure replay fold of durable goal facts. */
+export interface FoldedGoal {
+  /** Current goal, absent after a clear or before the first create. */
+  readonly goal?: GoalSnapshot
+  /** Highest admitted round for the current goal. */
+  readonly roundsStarted: number
+  /** Current goal creation time, absent without a current goal. */
+  readonly createdAt?: number
+  /** Current goal mutation time, absent without a current goal. */
+  readonly updatedAt?: number
+  /** Latest mutation ref, including a clear tombstone. */
+  readonly lastRef?: GoalRef
+}
+
+/** Input whose omitted round cap is resolved by the service configuration. */
+export interface CreateGoalRequest {
+  readonly objective: string
+  readonly maxGoalRounds?: number
+}
+
+/** Fields changed by an edit; at least one must be present. */
+export interface EditGoalRequest {
+  readonly objective?: string
+  readonly maxGoalRounds?: number
+}
+
+/** Live notification after one goal mutation has been accepted for logging. */
+export interface GoalChanged {
+  readonly operation: GoalOperation
+  readonly ref: GoalRef
+  /** Absent for a clear tombstone. */
+  readonly goal?: GoalView
+}
+
+/** Stable error codes for rejected goal reads and mutations. */
+export type GoalErrorCode =
+  | 'GOAL_AGENT_NOT_LIVE'
+  | 'GOAL_NOT_FOUND'
+  | 'GOAL_ALREADY_EXISTS'
+  | 'GOAL_STALE_REVISION'
+  | 'GOAL_INVALID_OBJECTIVE'
+  | 'GOAL_INVALID_MAX_ROUNDS'
+  | 'GOAL_INVALID_BLOCK_REASON'
+  | 'GOAL_INVALID_EDIT'
+  | 'GOAL_INVALID_TRANSITION'
+
+declare module 'cordis' {
+  interface Events {
+    /**
+     * Goal mutation accepted by one live agent. The matching context event is
+     * already appended or queued in that agent's active tool-batch FIFO.
+     * Listener failures are contained.
+     * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
+     * @param agent - agent whose session owns the goal.
+     * @param change - fresh current projection or clear tombstone.
+     * @mode emit
+     */
+    'goal/changed'(this: import('@deepseek-ai/dsh-scope').Scoped<Agent>, agent: Agent, change: GoalChanged): void
+  }
+}
diff --git a/packages/goal/goal/tests/goal.e2e.ts b/packages/goal/goal/tests/goal.e2e.ts
new file mode 100644
index 0000000000..0c582645bc
--- /dev/null
+++ b/packages/goal/goal/tests/goal.e2e.ts
@@ -0,0 +1,75 @@
+import { readFile, readdir } from 'node:fs/promises'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { describe, expect, it } from 'vitest'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import { decodeGoalChange, renderGoalChange } from '@deepseek-ai/dsh-goal'
+import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
+
+const binScript = fileURLToPath(new URL('../../../examples/cli-demo/src/bin.ts', import.meta.url))
+const configPath = fileURLToPath(new URL(
+  '../../../../examples/headless-agent/tests/fixtures/goal-domain/cordis.yml',
+  import.meta.url,
+))
+const repoTsconfig = fileURLToPath(new URL('../../../../tsconfig.json', import.meta.url))
+
+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()
+}
+
+describe('goal domain through a real cordis.yml and headless process', () => {
+  it('persists the Loader-mounted snapshot without starting a goal round', async () => {
+    let events: SessionEvent[] = []
+    const { stdout, stderr } = await runLoaderSmoke({
+      label: 'goal-domain',
+      tempDirPrefix: 'goal-domain-e2e-',
+      binScript,
+      configPath,
+      binArgs: ['--config', configPath, '--output-format', 'json', 'prove the persisted goal domain'],
+      tsconfigPath: repoTsconfig,
+      inspect: async (cwd) => {
+        const logs = await jsonlFiles(join(cwd, '.sessions'))
+        expect(logs).toHaveLength(1)
+        const lines = (await readFile(logs[0] as string, 'utf8')).trimEnd().split('\n')
+        events = lines.slice(1).map(line => JSON.parse(line) as SessionEvent)
+      },
+    })
+    expect(stderr).toBe('')
+    const result = JSON.parse(stdout) as Record<string, unknown>
+    expect(result).toMatchObject({
+      type: 'result',
+      success: true,
+    })
+    expect(result['result']).toBeTypeOf('string')
+    expect(result['result']).toContain('CLI tool round trip complete')
+    expect(events.filter(event => event.type === 'turn/end')).toHaveLength(1)
+
+    const contexts = events.filter(event => event.type === 'context/message'
+      && event.data.source.kind === 'goal')
+    expect(contexts).toHaveLength(1)
+    const context = contexts[0]
+    if (context?.type !== 'context/message') throw new Error('expected goal context event')
+    const change = decodeGoalChange(context.data.meta)
+    if (change === undefined) throw new Error('expected durable goal change')
+    expect(change).toMatchObject({
+      operation: 'create',
+      roundsStarted: 0,
+      goal: {
+        revision: 1,
+        objective: 'Prove the composed goal survives in the session log',
+        phase: 'active',
+        maxGoalRounds: 7,
+      },
+    })
+    expect(context.data.content).toEqual(renderGoalChange(change))
+    expect(JSON.stringify(context)).not.toContain('activation')
+    expect(events.filter(event => event.type === 'user/message'
+      && event.data.source.kind === 'goal')).toHaveLength(0)
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+})
diff --git a/packages/goal/goal/tests/goal.spec.ts b/packages/goal/goal/tests/goal.spec.ts
new file mode 100644
index 0000000000..ad2011fc62
--- /dev/null
+++ b/packages/goal/goal/tests/goal.spec.ts
@@ -0,0 +1,865 @@
+import { describe, expect, it, vi } from 'vitest'
+import { Context } from 'cordis'
+import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent'
+import type { Agent, AgentStatus, InjectOptions } from '@deepseek-ai/dsh-agent'
+import { HarnessError, type ContentBlock, type MessageSource } from '@deepseek-ai/dsh-llm'
+import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session'
+import GoalService, {
+  GoalError,
+  GoalId,
+  decodeGoalChange,
+  foldGoal,
+  renderGoalChange,
+} from '@deepseek-ai/dsh-goal'
+import type { GoalChangeMeta, GoalRef, GoalSnapshotChangeMeta } from '@deepseek-ai/dsh-goal'
+
+interface DeferredInjection {
+  content: ContentBlock[]
+  options: InjectOptions | undefined
+}
+
+interface StubAgent {
+  agent: Agent
+  session: Session
+  deferred: DeferredInjection[]
+  setDeferred(value: boolean): void
+  setStatus(value: AgentStatus): void
+  drain(): void
+}
+
+/** Number the next balanced one-shot injection turn. */
+function nextTurn(session: Session): number {
+  return session.events.reduce((max, event) => event.type === 'turn/start' ? Math.max(max, event.data.turn) : max, 0) + 1
+}
+
+/** Mirror the public Agent.inject idle/open-turn contract for domain tests. */
+function appendInjection(session: Session, content: ContentBlock[], options?: InjectOptions): void {
+  const source: MessageSource = options?.source ?? { kind: 'user' }
+  const context = {
+    content,
+    source,
+    ...options?.meta === undefined ? {} : { meta: options.meta },
+  }
+  const last = session.events.at(-1)
+  const open = last !== undefined && last.type !== 'turn/end'
+  if (open) {
+    session.append('context/message', context, { surfaceOp: 'append' })
+    return
+  }
+  const turn = nextTurn(session)
+  session.append('turn/start', { turn, trigger: { kind: 'injection', source } })
+  session.append('context/message', context, { surfaceOp: 'append' })
+  session.append('turn/end', { turn, reason: { kind: 'completed' } })
+}
+
+/** Build a registry-compatible agent around one concrete session. */
+function stubAgentForSession(session: Session): StubAgent {
+  const id = session.id
+  const deferred: DeferredInjection[] = []
+  let shouldDefer = false
+  let status: AgentStatus = 'idle'
+  const agent: Agent = {
+    id,
+    options: {},
+    session,
+    ctx: new Context(),
+    get status() { return status },
+    send() {},
+    steer() {},
+    inject(content, options) {
+      if (shouldDefer) deferred.push({ content, options })
+      else appendInjection(session, content, options)
+    },
+    cancel() {},
+    whenIdle() { return Promise.resolve() },
+  }
+  return {
+    agent,
+    session,
+    deferred,
+    setDeferred(value) { shouldDefer = value },
+    setStatus(value) { status = value },
+    drain() {
+      shouldDefer = false
+      for (const injection of deferred.splice(0)) appendInjection(session, injection.content, injection.options)
+    },
+  }
+}
+
+/** Build a registry-compatible agent with controllable context deferral. */
+function stubAgent(rawId: string, seed?: readonly import('@deepseek-ai/dsh-session').SessionEvent[]): StubAgent {
+  return stubAgentForSession(new Session(SessionId(rawId), seed))
+}
+
+async function harness(config: { defaultMaxGoalRounds?: number } = {}) {
+  const ctx = new Context()
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(GoalService, config)
+  const stub = stubAgent(`goal-test-${Math.random()}`)
+  ctx.agents.register(stub.agent)
+  return { ctx, ...stub }
+}
+
+/** Append one admitted goal round as a balanced user-message turn. */
+function appendRound(session: Session, ref: GoalRef, round: number): void {
+  const source = { kind: 'goal', goalId: ref.id, revision: ref.revision, round } as const
+  const turn = nextTurn(session)
+  session.append('turn/start', { turn, trigger: { kind: 'message', source } })
+  session.append('user/message', { content: [{ type: 'text', text: `round ${round}` }], source }, { surfaceOp: 'append' })
+  session.append('turn/end', { turn, reason: { kind: 'completed' } })
+}
+
+describe('GoalService creation and replay', () => {
+  it('applies the configured default and writes one balanced verbatim 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) })
+
+    const goal = ctx.goals.create(agent, { objective: '  finish the feature  ' })
+
+    expect(goal).toMatchObject({
+      objective: 'finish the feature',
+      phase: 'active',
+      revision: 1,
+      maxGoalRounds: 17,
+      roundsStarted: 0,
+      createdAt: 1_700_000_000_000,
+      updatedAt: 1_700_000_000_000,
+      activation: 'armed',
+    })
+    expect(goal.id).toMatch(/^goal-/)
+    expect(seen).toEqual(['create'])
+    expect(session.events.map(event => event.type)).toEqual(['turn/start', 'context/message', 'turn/end'])
+    const context = session.events[1]
+    expect(context?.type).toBe('context/message')
+    if (context?.type !== 'context/message') throw new Error('expected goal context')
+    expect(context.data.source).toEqual({ kind: 'goal', goalId: goal.id, revision: 1, round: 0 })
+    const change = decodeGoalChange(context.data.meta)
+    if (change === undefined) throw new Error('expected decoded goal change')
+    expect(change).toMatchObject({ operation: 'create', goal: { id: goal.id } })
+    expect(context.data.content).toEqual(renderGoalChange(change))
+    expect(session.deriveMessages()).toEqual([{ role: 'user', content: context.data.content }])
+    expect(foldGoal(session.events)).toMatchObject({ goal: { id: goal.id }, roundsStarted: 0 })
+    vi.useRealTimers()
+  })
+
+  it('uses 256 rounds by default and validates create input inside create', async () => {
+    const { ctx, agent } = await harness()
+    expect(() => ctx.goals.create(agent, { objective: '   ' })).toThrow(expect.objectContaining({
+      code: 'GOAL_INVALID_OBJECTIVE',
+    }))
+    expect(() => ctx.goals.create(agent, { objective: 'x', maxGoalRounds: 0 })).toThrow(expect.objectContaining({
+      code: 'GOAL_INVALID_MAX_ROUNDS',
+    }))
+    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)
+  })
+
+  it('also resolves the default when constructed directly without Cordis config normalization', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    const goals = new GoalService(ctx)
+    const stub = stubAgent('goal-direct-construction')
+    ctx.agents.register(stub.agent)
+    expect(goals.create(stub.agent, { objective: 'direct' })).toMatchObject({
+      objective: 'direct', maxGoalRounds: 256,
+    })
+  })
+
+  it('rejects invalid direct configuration', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    await expect(ctx.plugin(GoalService, { defaultMaxGoalRounds: -1 })).rejects.toThrow(expect.objectContaining({
+      code: 'GOAL_INVALID_MAX_ROUNDS',
+    }))
+  })
+
+  it('restores a seeded goal and rounds with activation disarmed', async () => {
+    const first = await harness()
+    const created = first.ctx.goals.create(first.agent, { objective: 'seed me', maxGoalRounds: 9 })
+    appendRound(first.session, created, 1)
+    appendRound(first.session, created, 2)
+
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(GoalService)
+    const resumed = stubAgent('seeded-goal', first.session.events)
+    ctx.agents.register(resumed.agent)
+    expect(ctx.goals.get(resumed.agent)).toMatchObject({
+      id: created.id,
+      roundsStarted: 2,
+      activation: 'disarmed',
+    })
+  })
+
+  it('inherits the completed-turn goal prefix through SessionStore.fork with child activation disarmed', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(GoalService)
+    const parent = stubAgentForSession(ctx.sessions.create(SessionId('goal-fork-parent')))
+    ctx.agents.register(parent.agent)
+    const goal = ctx.goals.create(parent.agent, { objective: 'inherit through fork', maxGoalRounds: 5 })
+    appendRound(parent.session, goal, 1)
+
+    const child = stubAgentForSession(ctx.sessions.fork(parent.session))
+    ctx.agents.register(child.agent)
+    expect(ctx.goals.get(child.agent)).toMatchObject({
+      id: goal.id,
+      objective: goal.objective,
+      roundsStarted: 1,
+      activation: 'disarmed',
+    })
+    expect(child.session.header.parentSession).toBe(parent.session.id)
+    expect(child.session.header.seedLength).toBe(parent.session.seq)
+  })
+
+  it('disarms live activation on every session-start edge', async () => {
+    const { ctx, agent, session } = await harness()
+    let goal = ctx.goals.create(agent, { objective: 'stay stopped after resume' })
+    expect(goal.activation).toBe('armed')
+    agentEvents(ctx, agent).emit('agent/session-start', 'resume')
+    expect(ctx.goals.get(agent)?.activation).toBe('disarmed')
+    goal = ctx.goals.resume(agent, goal)
+    expect(goal).toMatchObject({ phase: 'active', activation: 'armed', revision: 2 })
+    expect(() => foldGoal(session.events)).not.toThrow()
+  })
+
+  it('lets a lifecycle owner disarm without writing a durable revision', async () => {
+    const { ctx, agent, session } = await harness()
+    const goal = ctx.goals.create(agent, { objective: 'survive driver reload' })
+    const before = session.events.length
+    expect(ctx.goals.disarm(agent)).toMatchObject({
+      id: goal.id,
+      revision: goal.revision,
+      phase: 'active',
+      activation: 'disarmed',
+    })
+    expect(session.events).toHaveLength(before)
+    expect(ctx.goals.resume(agent, goal)).toMatchObject({ revision: 2, activation: 'armed' })
+  })
+
+  it('removes the service and its session-start listener with the providing fiber', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    const fiber = await ctx.plugin(GoalService)
+    const first = ctx.goals
+    const stub = stubAgent('goal-hmr')
+    ctx.agents.register(stub.agent)
+    const goal = first.create(stub.agent, { objective: 'survive service reload' })
+
+    await fiber.dispose()
+    expect(ctx.get('goals')).toBeUndefined()
+    agentEvents(ctx, stub.agent).emit('agent/session-start', 'resume')
+    expect(first.get(stub.agent)).toMatchObject({ id: goal.id, activation: 'armed' })
+
+    await ctx.plugin(GoalService)
+    expect(ctx.goals).not.toBe(first)
+    expect(ctx.goals.get(stub.agent)).toMatchObject({ id: goal.id, activation: 'disarmed' })
+  })
+
+  it('requires the exact live registry instance for reads and mutations', async () => {
+    const { ctx, agent } = await harness()
+    const impostor = { ...agent, session: new Session(agent.id) }
+    expect(() => ctx.goals.get(impostor)).toThrow(expect.objectContaining({ code: 'GOAL_AGENT_NOT_LIVE' }))
+    expect(() => ctx.goals.create(impostor, { objective: 'no' })).toThrow(expect.objectContaining({
+      code: 'GOAL_AGENT_NOT_LIVE',
+    }))
+  })
+
+  it('rejects a disposed live object even before registry teardown', async () => {
+    const test = await harness()
+    test.setStatus('disposed')
+    expect(() => test.ctx.goals.get(test.agent)).toThrow(expect.objectContaining({ code: 'GOAL_AGENT_NOT_LIVE' }))
+  })
+})
+
+describe('GoalService mutations', () => {
+  it('edits with compare-and-set revisions and rejects empty edits', async () => {
+    const { ctx, agent } = await harness()
+    const created = ctx.goals.create(agent, { objective: 'old', maxGoalRounds: 4 })
+    expect(() => ctx.goals.edit(agent, created, {})).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_EDIT' }))
+    const objective = ctx.goals.edit(agent, created, { objective: ' new ' })
+    expect(objective).toMatchObject({ objective: 'new', maxGoalRounds: 4, revision: 2, activation: 'armed' })
+    expect(() => ctx.goals.edit(agent, created, { maxGoalRounds: 8 })).toThrow(expect.objectContaining({
+      code: 'GOAL_STALE_REVISION',
+    }))
+    const cap = ctx.goals.edit(agent, objective, { maxGoalRounds: 8 })
+    expect(cap).toMatchObject({ objective: 'new', maxGoalRounds: 8, revision: 3 })
+    expect(() => ctx.goals.edit(agent, cap, { objective: ' ' })).toThrow(expect.objectContaining({
+      code: 'GOAL_INVALID_OBJECTIVE',
+    }))
+  })
+
+  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, { 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)
+    expect(goal).toMatchObject({ phase: 'complete', activation: 'disarmed' })
+    expect(() => ctx.goals.resume(agent, goal)).toThrow(expect.objectContaining({ code: 'GOAL_INVALID_TRANSITION' }))
+  })
+
+  it('allows completion from every stopped phase and replacement only after completion', async () => {
+    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)
+        : 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')
+      expect(replacement.id).not.toBe(complete.id)
+      expect(replacement.revision).toBe(1)
+    }
+  })
+
+  it('rejects replacement and invalid phase transitions while a resumable goal exists', async () => {
+    const { ctx, agent } = await harness()
+    const goal = ctx.goals.create(agent, { objective: 'still active' })
+    expect(() => ctx.goals.create(agent, { objective: 'replacement' })).toThrow(expect.objectContaining({
+      code: 'GOAL_ALREADY_EXISTS',
+    }))
+    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, {
+      code: 'test-blocker', message: 'Blocked for the test.',
+    })).toThrow(expect.objectContaining({
+      code: 'GOAL_INVALID_TRANSITION',
+    }))
+  })
+
+  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)
+    appendRound(session, goal, 2)
+    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.block(agent, goal, { code: 'round-limit', message: 'Goal round limit reached.' })
+    expect(ctx.goals.complete(agent, goal).phase).toBe('complete')
+  })
+
+  it('clears through a revisioned tombstone and permits a fresh goal', async () => {
+    const { ctx, agent, session } = await harness()
+    const goal = ctx.goals.create(agent, { objective: 'temporary' })
+    const tombstone = ctx.goals.clear(agent, goal)
+    expect(tombstone).toEqual({ id: goal.id, revision: 2 })
+    expect(ctx.goals.get(agent)).toBeUndefined()
+    expect(foldGoal(session.events)).toEqual({ roundsStarted: 0, lastRef: tombstone })
+    expect(() => ctx.goals.clear(agent, goal)).toThrow(expect.objectContaining({ code: 'GOAL_NOT_FOUND' }))
+    const next = ctx.goals.create(agent, { objective: 'fresh' })
+    expect(next.id).not.toBe(goal.id)
+  })
+
+  it('keeps per-goal mutation timestamps monotonic when the wall clock moves backward', async () => {
+    vi.useFakeTimers()
+    vi.setSystemTime(100)
+    const { ctx, agent, session } = await harness()
+    let goal = ctx.goals.create(agent, { objective: 'monotonic time' })
+    vi.setSystemTime(90)
+    goal = ctx.goals.pause(agent, goal)
+    expect(goal.updatedAt).toBe(100)
+    vi.setSystemTime(80)
+    ctx.goals.clear(agent, goal)
+    const clear = session.events
+      .filter(event => event.type === 'context/message')
+      .map(event => decodeGoalChange(event.data.meta))
+      .at(-1)
+    expect(clear).toMatchObject({ operation: 'clear', clearedAt: 100 })
+    expect(() => foldGoal(session.events)).not.toThrow()
+    vi.useRealTimers()
+  })
+
+  it('contains goal notification failures and preserves later listeners', async () => {
+    const { ctx, agent } = await harness()
+    const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {})
+    const seen: string[] = []
+    ctx.on('goal/changed', () => { throw new Error('broken observer') })
+    ctx.on('goal/changed', (_subject, change) => { seen.push(change.operation) })
+    expect(ctx.goals.create(agent, { objective: 'notify' }).phase).toBe('active')
+    expect(seen).toEqual(['create'])
+    expect(warn).toHaveBeenCalledWith(expect.stringContaining('broken observer'))
+  })
+
+  it('preserves multiple pending revisions until deferred injections enter the log', async () => {
+    const test = await harness()
+    const { ctx, agent, session, deferred } = test
+    test.setDeferred(true)
+    let goal = ctx.goals.create(agent, { objective: 'deferred', maxGoalRounds: 5 })
+    goal = ctx.goals.edit(agent, goal, { objective: 'deferred edit' })
+    goal = ctx.goals.pause(agent, goal)
+    expect(goal).toMatchObject({ revision: 3, phase: 'paused', activation: 'disarmed' })
+    expect(deferred).toHaveLength(3)
+    expect(session.events).toHaveLength(0)
+
+    appendInjection(session, [{ type: 'text', text: 'unrelated' }], { source: { kind: 'plugin', plugin: 'test' } })
+    expect(ctx.goals.get(agent)).toMatchObject({ revision: 3, phase: 'paused' })
+    test.drain()
+    expect(deferred).toHaveLength(0)
+    expect(ctx.goals.get(agent)).toMatchObject({ revision: 3, phase: 'paused' })
+    expect(foldGoal(session.events)).toMatchObject({ goal: { revision: 3, phase: 'paused' } })
+  })
+
+  it('publishes a mutation consistently to a reentrant session observer', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(GoalService)
+    const stub = stubAgentForSession(ctx.sessions.create(SessionId('goal-reentrant-observer')))
+    ctx.agents.register(stub.agent)
+    let observed: ReturnType<GoalService['get']>
+    ctx.on('session/event', (session, event) => {
+      if (session === stub.session && event.type === 'context/message') observed = ctx.goals.get(stub.agent)
+    })
+
+    const created = ctx.goals.create(stub.agent, { objective: 'publish once' })
+
+    expect(observed).toEqual(created)
+    expect(ctx.goals.get(stub.agent)).toEqual(created)
+    expect(foldGoal(stub.session.events)).toMatchObject({ goal: { id: created.id, revision: 1 } })
+  })
+
+  it('rolls back a pending mutation when injection rejects before append', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(GoalService)
+    const stub = stubAgent('goal-rejected-injection')
+    const append = stub.agent.inject.bind(stub.agent)
+    let reject = true
+    stub.agent.inject = (content, options) => {
+      if (reject) throw new Error('injection rejected')
+      append(content, options)
+    }
+    ctx.agents.register(stub.agent)
+
+    expect(() => ctx.goals.create(stub.agent, { objective: 'first attempt' })).toThrow('injection rejected')
+    reject = false
+    expect(ctx.goals.create(stub.agent, { objective: 'second attempt' })).toMatchObject({
+      objective: 'second attempt',
+      revision: 1,
+    })
+  })
+
+  it('rejects deferred goal mutations that enter the log out of FIFO order', async () => {
+    const test = await harness()
+    test.setDeferred(true)
+    const created = test.ctx.goals.create(test.agent, { objective: 'ordered' })
+    test.ctx.goals.edit(test.agent, created, { objective: 'ordered edit' })
+    const second = test.deferred[1]
+    if (second === undefined) throw new Error('expected a second deferred goal mutation')
+    appendInjection(test.session, second.content, second.options)
+    expect(() => test.ctx.goals.get(test.agent)).toThrow('advance the current goal')
+  })
+
+  it('observes a valid goal snapshot appended after an empty cache was established', async () => {
+    const { ctx, agent, session } = await harness()
+    expect(ctx.goals.get(agent)).toBeUndefined()
+    const change: GoalSnapshotChangeMeta = {
+      kind: 'goal/change',
+      version: 1,
+      operation: 'create',
+      goal: {
+        id: GoalId('goal-external'),
+        revision: 1,
+        objective: 'observe external append',
+        phase: 'active',
+        maxGoalRounds: 4,
+      },
+      roundsStarted: 0,
+      createdAt: 12,
+      updatedAt: 12,
+    }
+    const source = { kind: 'goal', goalId: change.goal.id, revision: 1, round: 0 } as const
+    const turn = nextTurn(session)
+    session.append('turn/start', { turn, trigger: { kind: 'injection', source } })
+    session.append('context/message', {
+      content: renderGoalChange(change), source, meta: change as never,
+    }, { surfaceOp: 'append' })
+    session.append('turn/end', { turn, reason: { kind: 'completed' } })
+
+    expect(ctx.goals.get(agent)).toMatchObject({
+      id: change.goal.id,
+      objective: change.goal.objective,
+      activation: 'disarmed',
+    })
+  })
+
+  it('reports the same corrupt unseen event after committing its valid prefix', async () => {
+    const { ctx, agent, session } = await harness()
+    expect(ctx.goals.get(agent)).toBeUndefined()
+    const change: GoalSnapshotChangeMeta = {
+      kind: 'goal/change',
+      version: 1,
+      operation: 'create',
+      goal: {
+        id: GoalId('goal-valid-prefix'),
+        revision: 1,
+        objective: 'valid prefix',
+        phase: 'active',
+        maxGoalRounds: 4,
+      },
+      roundsStarted: 0,
+      createdAt: 12,
+      updatedAt: 12,
+    }
+    appendInjection(session, renderGoalChange(change), {
+      source: { kind: 'goal', goalId: change.goal.id, revision: 1, round: 0 },
+      meta: change as never,
+    })
+    appendInjection(session, [{ type: 'text', text: 'corrupt' }], {
+      source: { kind: 'goal', goalId: change.goal.id, revision: 2, round: 0 },
+      meta: { ...change, operation: 'edit', extra: true } as never,
+    })
+
+    expect(() => ctx.goals.get(agent)).toThrow('invalid shape')
+    expect(() => ctx.goals.get(agent)).toThrow('invalid shape')
+  })
+})
+
+describe('goal replay validation', () => {
+  function snapshotChange(overrides: Partial<GoalSnapshotChangeMeta> = {}): GoalSnapshotChangeMeta {
+    return {
+      kind: 'goal/change',
+      version: 1,
+      operation: 'create',
+      goal: {
+        id: GoalId('goal-validation'),
+        revision: 1,
+        objective: 'validate',
+        phase: 'active',
+        maxGoalRounds: 2,
+      },
+      roundsStarted: 0,
+      createdAt: 10,
+      updatedAt: 10,
+      ...overrides,
+    }
+  }
+
+  function appendChange(
+    session: Session,
+    change: GoalChangeMeta,
+    overrides: { content?: ContentBlock[]; source?: MessageSource } = {},
+  ): void {
+    const source = overrides.source ?? {
+      kind: 'goal',
+      goalId: change.operation === 'clear' ? change.cleared.id : change.goal.id,
+      revision: change.operation === 'clear' ? change.cleared.revision : change.goal.revision,
+      round: 0,
+    }
+    const turn = nextTurn(session)
+    session.append('turn/start', { turn, trigger: { kind: 'injection', source } })
+    session.append('context/message', {
+      content: overrides.content ?? renderGoalChange(change),
+      source,
+      meta: change as never,
+    }, { surfaceOp: 'append' })
+    session.append('turn/end', { turn, reason: { kind: 'completed' } })
+  }
+
+  function oneChange(change: GoalChangeMeta, overrides: { content?: ContentBlock[]; source?: MessageSource } = {}) {
+    const session = new Session(SessionId(`validation-${Math.random()}`))
+    appendChange(session, change, overrides)
+    return session.events
+  }
+
+  function mutation(
+    current: GoalSnapshotChangeMeta,
+    operation: Exclude<GoalSnapshotChangeMeta['operation'], 'create'>,
+    phase: GoalSnapshotChangeMeta['goal']['phase'],
+    overrides: Partial<GoalSnapshotChangeMeta> = {},
+  ): GoalSnapshotChangeMeta {
+    return {
+      ...current,
+      operation,
+      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,
+    }
+  }
+
+  function foldPair(first: GoalSnapshotChangeMeta, second: GoalChangeMeta): ReturnType<typeof foldGoal> {
+    const session = new Session(SessionId(`validation-pair-${Math.random()}`))
+    appendChange(session, first)
+    appendChange(session, second)
+    return foldGoal(session.events)
+  }
+
+  it('ignores unrelated metadata and non-goal round sources', () => {
+    expect(decodeGoalChange(undefined)).toBeUndefined()
+    expect(decodeGoalChange({ kind: 'other' })).toBeUndefined()
+    const session = new Session(SessionId('unrelated'))
+    appendInjection(session, [{ type: 'text', text: 'other' }], {
+      source: { kind: 'plugin', plugin: 'test' },
+      meta: { kind: 'other' },
+    })
+    expect(foldGoal(session.events)).toEqual({ roundsStarted: 0 })
+    const source = { kind: 'plugin', plugin: 'ordinary-user-message' } as const
+    const turn = nextTurn(session)
+    session.append('turn/start', { turn, trigger: { kind: 'message', source } })
+    session.append('user/message', { content: [{ type: 'text', text: 'ordinary' }], source }, { surfaceOp: 'append' })
+    session.append('turn/end', { turn, reason: { kind: 'completed' } })
+    expect(foldGoal(session.events)).toEqual({ roundsStarted: 0 })
+  })
+
+  it('rejects rounds attributed to another goal', () => {
+    const change = snapshotChange()
+    const session = new Session(SessionId('other-goal-round'), oneChange(change))
+    appendRound(session, { id: GoalId('goal-other'), revision: 1 }, 1)
+    expect(() => foldGoal(session.events)).toThrow('not the next admitted round')
+  })
+
+  it('rejects unsupported versions, operations, and top-level shapes', () => {
+    expect(() => decodeGoalChange({ ...snapshotChange(), version: 2 })).toThrow('unsupported goal change version')
+    expect(() => decodeGoalChange({ ...snapshotChange(), operation: 'explode' })).toThrow('operation is invalid')
+    expect(() => decodeGoalChange({ ...snapshotChange(), extra: true })).toThrow('snapshot change has an invalid shape')
+    expect(() => decodeGoalChange({
+      kind: 'goal/change', version: 1, operation: 'clear', cleared: { id: 'x', revision: 2 }, clearedAt: 1, extra: true,
+    })).toThrow('clear change has an invalid shape')
+  })
+
+  it('rejects invalid create and missing-current mutation sequences', () => {
+    const base = snapshotChange()
+    const invalidCreates: GoalSnapshotChangeMeta[] = [
+      { ...base, goal: { ...base.goal, revision: 2 } },
+      { ...base, goal: { ...base.goal, phase: 'paused' } },
+      { ...base, roundsStarted: 1 },
+    ]
+    for (const change of invalidCreates) expect(() => foldGoal(oneChange(change))).toThrow('goal create requires')
+
+    const edit = mutation(base, 'edit', 'active')
+    expect(() => foldGoal(oneChange(edit))).toThrow('requires a current goal')
+    const clear: GoalChangeMeta = {
+      kind: 'goal/change', version: 1, operation: 'clear', cleared: { id: base.goal.id, revision: 2 }, clearedAt: 12,
+    }
+    expect(() => foldGoal(oneChange(clear))).toThrow('clear requires a current goal')
+
+    const secondCreate = snapshotChange({
+      goal: { ...base.goal, id: GoalId('goal-second') },
+      createdAt: 20,
+      updatedAt: 20,
+    })
+    expect(() => foldPair(base, secondCreate)).toThrow('goal create requires')
+  })
+
+  it('rejects stale identity, counters, timestamps, and definition changes', () => {
+    const base = snapshotChange()
+    const invalid: GoalSnapshotChangeMeta[] = [
+      mutation(base, 'edit', 'active', { goal: { ...base.goal, id: GoalId('goal-wrong'), revision: 2 } }),
+      mutation(base, 'edit', 'active', { goal: { ...base.goal, revision: 3 } }),
+      mutation(base, 'edit', 'active', { createdAt: 11 }),
+      mutation(base, 'edit', 'active', { updatedAt: 9 }),
+      mutation(base, 'edit', 'active', { roundsStarted: 1 }),
+      mutation(base, 'pause', 'paused', {
+        goal: { ...base.goal, revision: 2, phase: 'paused', objective: 'changed illegally' },
+      }),
+      mutation(base, 'pause', 'paused', {
+        goal: { ...base.goal, revision: 2, phase: 'paused', maxGoalRounds: 3 },
+      }),
+    ]
+    for (const change of invalid) expect(() => foldPair(base, change)).toThrow()
+  })
+
+  it('rejects invalid replayed lifecycle phase transitions', () => {
+    const base = snapshotChange()
+    const invalid: GoalSnapshotChangeMeta[] = [
+      mutation(base, 'edit', 'paused'),
+      mutation(base, 'pause', 'active'),
+      mutation(base, 'resume', 'paused'),
+      mutation(base, 'complete', 'active'),
+      mutation(base, 'block', 'active'),
+    ]
+    for (const change of invalid) expect(() => foldPair(base, change)).toThrow()
+
+    const paused = mutation(base, 'pause', 'paused')
+    const exhausted = mutation(paused, 'resume', 'active', {
+      roundsStarted: 2,
+      goal: { ...paused.goal, revision: 3, phase: 'active', maxGoalRounds: 2 },
+    })
+    const session = new Session(SessionId('exhausted-resume'))
+    appendChange(session, base)
+    appendRound(session, base.goal, 1)
+    appendRound(session, base.goal, 2)
+    appendChange(session, { ...paused, roundsStarted: 2 })
+    appendChange(session, exhausted)
+    expect(() => foldGoal(session.events)).toThrow('exhausted round budget')
+  })
+
+  it('rejects invalid clear continuity and goal id reuse', () => {
+    const base = snapshotChange()
+    const staleClear: GoalChangeMeta = {
+      kind: 'goal/change', version: 1, operation: 'clear', cleared: { id: base.goal.id, revision: 3 }, clearedAt: 11,
+    }
+    expect(() => foldPair(base, staleClear)).toThrow('advance the current goal')
+    const earlyClear: GoalChangeMeta = {
+      kind: 'goal/change', version: 1, operation: 'clear', cleared: { id: base.goal.id, revision: 2 }, clearedAt: 9,
+    }
+    expect(() => foldPair(base, earlyClear)).toThrow('timestamp cannot precede')
+
+    const complete = mutation(base, 'complete', 'complete')
+    const sameCurrentId = snapshotChange({
+      goal: { ...base.goal, revision: 1 },
+      createdAt: 20,
+      updatedAt: 20,
+    })
+    const completedSession = new Session(SessionId('reuse-complete'))
+    appendChange(completedSession, base)
+    appendChange(completedSession, complete)
+    appendChange(completedSession, sameCurrentId)
+    expect(() => foldGoal(completedSession.events)).toThrow('fresh active revision-one')
+
+    const second = snapshotChange({
+      goal: { ...base.goal, id: GoalId('goal-second') },
+      createdAt: 20,
+      updatedAt: 20,
+    })
+    const secondComplete = mutation(second, 'complete', 'complete')
+    const nonAdjacentReuse = new Session(SessionId('reuse-non-adjacent'))
+    appendChange(nonAdjacentReuse, base)
+    appendChange(nonAdjacentReuse, complete)
+    appendChange(nonAdjacentReuse, second)
+    appendChange(nonAdjacentReuse, secondComplete)
+    appendChange(nonAdjacentReuse, { ...sameCurrentId, createdAt: 30, updatedAt: 30 })
+    expect(() => foldGoal(nonAdjacentReuse.events)).toThrow('fresh active revision-one')
+
+    const clear: GoalChangeMeta = {
+      kind: 'goal/change', version: 1, operation: 'clear', cleared: { id: base.goal.id, revision: 2 }, clearedAt: 11,
+    }
+    const clearedSession = new Session(SessionId('reuse-clear'))
+    appendChange(clearedSession, base)
+    appendChange(clearedSession, clear)
+    appendChange(clearedSession, sameCurrentId)
+    expect(() => foldGoal(clearedSession.events)).toThrow('fresh active revision-one')
+  })
+
+  it('rejects goal-source context without matching durable metadata', () => {
+    const session = new Session(SessionId('goal-source-without-meta'))
+    const source = { kind: 'goal', goalId: GoalId('goal-missing-meta'), revision: 1, round: 0 } as const
+    const turn = nextTurn(session)
+    session.append('turn/start', { turn, trigger: { kind: 'injection', source } })
+    session.append('context/message', {
+      content: [{ type: 'text', text: 'missing' }], source,
+    }, { surfaceOp: 'append' })
+    session.append('turn/end', { turn, reason: { kind: 'completed' } })
+    expect(() => foldGoal(session.events)).toThrow('lacks goal change metadata')
+  })
+
+  it('rejects malformed snapshots, refs, counters, and timestamps', () => {
+    const base = snapshotChange()
+    const badSnapshots: unknown[] = [
+      null,
+      { ...base.goal, extra: true },
+      { ...base.goal, id: '' },
+      { ...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 },
+    ]
+    for (const goal of badSnapshots) expect(() => decodeGoalChange({ ...base, goal })).toThrow()
+    expect(() => decodeGoalChange({ ...base, roundsStarted: -1 })).toThrow('roundsStarted')
+    expect(() => decodeGoalChange({ ...base, createdAt: -1 })).toThrow('createdAt')
+    expect(() => decodeGoalChange({ ...base, updatedAt: 9 })).toThrow('cannot precede')
+    expect(() => decodeGoalChange({
+      kind: 'goal/change', version: 1, operation: 'clear', cleared: null, clearedAt: 1,
+    })).toThrow('tombstone')
+    expect(() => decodeGoalChange({
+      kind: 'goal/change', version: 1, operation: 'clear', cleared: { id: '', revision: 1 }, clearedAt: 1,
+    })).toThrow('non-empty')
+    expect(() => decodeGoalChange({
+      kind: 'goal/change', version: 1, operation: 'clear', cleared: { id: 'x', revision: 0 }, clearedAt: 1,
+    })).toThrow('positive safe integer')
+  })
+
+  it('rejects source and content drift from the durable metadata', () => {
+    const change = snapshotChange()
+    expect(() => foldGoal(oneChange(change, { source: { kind: 'plugin', plugin: 'wrong' } }))).toThrow('mismatched source')
+    expect(() => foldGoal(oneChange(change, {
+      source: { kind: 'goal', goalId: change.goal.id, revision: 1, round: -1 },
+    }))).toThrow('source is invalid')
+    expect(() => foldGoal(oneChange(change, { content: [{ type: 'text', text: 'wrong' }] }))).toThrow('model-visible content')
+  })
+
+  it('folds a clear tombstone after a snapshot', () => {
+    const change = snapshotChange()
+    const session = new Session(SessionId('fold-clear'), oneChange(change))
+    const clear: GoalChangeMeta = {
+      kind: 'goal/change',
+      version: 1,
+      operation: 'clear',
+      cleared: { id: change.goal.id, revision: 2 },
+      clearedAt: 20,
+    }
+    const source = { kind: 'goal', goalId: change.goal.id, revision: 2, round: 0 } as const
+    const turn = nextTurn(session)
+    session.append('turn/start', { turn, trigger: { kind: 'injection', source } })
+    session.append('context/message', {
+      content: renderGoalChange(clear), source, meta: clear as never,
+    }, { surfaceOp: 'append' })
+    session.append('turn/end', { turn, reason: { kind: 'completed' } })
+    expect(foldGoal(session.events)).toEqual({
+      roundsStarted: 0,
+      lastRef: { id: change.goal.id, revision: 2 },
+    })
+  })
+})
diff --git a/packages/goal/goal/tsconfig.json b/packages/goal/goal/tsconfig.json
new file mode 100644
index 0000000000..8a97b2a5e0
--- /dev/null
+++ b/packages/goal/goal/tsconfig.json
@@ -0,0 +1,36 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/schemastery"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../util/brand"
+    },
+    {
+      "path": "../../llm/llm"
+    },
+    {
+      "path": "../../core/session"
+    },
+    {
+      "path": "../../core/scope"
+    },
+    {
+      "path": "../../core/agent"
+    }
+  ]
+}
diff --git a/packages/goal/tool-goal/README.md b/packages/goal/tool-goal/README.md
new file mode 100644
index 0000000000..3b97d7aa82
--- /dev/null
+++ b/packages/goal/tool-goal/README.md
@@ -0,0 +1,76 @@
+# @deepseek-ai/dsh-tool-goal
+
+The model-facing control surface for [`ctx.goals`](../goal/README.md): `get_goal`, `create_goal`, and `update_goal`. The [goal-tool Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md) owns the authority split and Codex-shaped UX.
+
+## Tools
+
+- `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?, 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.
+
+An autonomous goal round that successfully reports `complete` or `blocked` contributes the existing terminal `agent/turn-stop` decision for that physical turn. Direct-human mutations never contribute this stop: the assistant may acknowledge the change and concurrent human steering remains available to the loop.
+
+## Authority
+
+Execution requires the exact live `exec.agent`, its inherited `AgentRegistry` initiator, running status, and an open turn. Create, edit, pause, and resume additionally require an accepted `{ kind: 'user' }` message or steering event in a runtime-root agent's current turn. Durable fork lineage does not demote a resumed root; live subagent ownership does.
+
+`{ 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 and must describe it in `blocked_reason`. Direct human authority may stop a goal immediately.
+
+## Config
+
+```yaml
+- id: tool-goal
+  name: '@deepseek-ai/dsh-tool-goal'
+  config:
+    blockedAfterConsecutiveRounds: 3
+```
+
+The value must be a positive safe integer. It supplies both the hard lower bound on model self-blocking and the number named in model guidance.
+
+## Model Experience
+
+### System prompt
+
+#### What the model sees
+
+A fixed goal policy says when semantic human intent warrants creation, requires exact read-before-update refs, explains rearming after resume/fork, and limits completion/blocking claims. The configured threshold is interpolated into that guidance.
+
+##### 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, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
+```
+
+#### Token effect
+
+Small fixed input cost on every request where this plugin's prompt registration is in scope.
+
+#### KV Cache effect
+
+Prefix-stable while the plugin scope, configured threshold, and guidance text are unchanged. Activation, disposal, or configuration changes may invalidate reuse from this prompt section.
+
+### Tool schemas and results
+
+#### What the model sees
+
+The generated [`get_goal`, `create_goal`, and `update_goal` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-goal). Successful results are compact JSON. Mutation results are followed by the goal domain's raw `<goal_state>` snapshot after the tool batch. `activation` in a result is a live observation and never becomes replay authority.
+
+#### Token effect
+
+Fixed schema cost plus one compact result per call. Mutations also retain the domain snapshot until compaction.
+
+#### KV Cache effect
+
+Schemas are prefix-stable while their definitions and visibility are unchanged. Calls, results, and resulting goal snapshots append after the reusable request prefix without invalidating earlier entries.
+
+## Known Limitations and Deferred Work
+
+- **Semantic intent remains model judgment** — execution can prove direct human provenance, not whether a request is substantial enough to merit a goal.
+- **Same-condition blocking remains model judgment** — the runtime enforces distinct admitted-round count, not semantic equivalence of obstacles; an independent evaluator is deferred.
+- **No scheduling or UI commands** — these tools mutate state only; the same-session driver and human command surfaces are separate stack layers.
+- **Goal-round authority requires a driver** — the autonomous `complete`/`blocked` path is dormant unless a continuation driver admits goal-sourced user turns; mounting this tool package alone does not create them.
+- **Prompt registration is independent of filtering** — a scope may hide the tools while retaining their guidance unless the deployment scopes both registrations together.
diff --git a/packages/goal/tool-goal/package.json b/packages/goal/tool-goal/package.json
new file mode 100644
index 0000000000..b9b4912cf4
--- /dev/null
+++ b/packages/goal/tool-goal/package.json
@@ -0,0 +1,46 @@
+{
+  "name": "@deepseek-ai/dsh-tool-goal",
+  "description": "Model-facing same-session goal tools with execution-time authority checks",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "@deepseek-ai/dsh-agent": "^0.0.1",
+    "@deepseek-ai/dsh-goal": "^0.0.1",
+    "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-session": "^0.0.1",
+    "@deepseek-ai/dsh-system-prompt": "^0.0.1",
+    "@deepseek-ai/dsh-tools": "^0.0.1",
+    "cordis": "^4.0.0-rc.7"
+  },
+  "dependencies": {
+    "schemastery": "^3.18.0"
+  },
+  "devDependencies": {
+    "@cordisjs/plugin-loader": "workspace:^",
+    "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-goal": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "@deepseek-ai/dsh-system-prompt": "workspace:^",
+    "@deepseek-ai/dsh-tools": "workspace:^",
+    "cordis": "^4.0.0-rc.7"
+  }
+}
diff --git a/packages/goal/tool-goal/src/authority.ts b/packages/goal/tool-goal/src/authority.ts
new file mode 100644
index 0000000000..41fe713dc6
--- /dev/null
+++ b/packages/goal/tool-goal/src/authority.ts
@@ -0,0 +1,109 @@
+/** Execution-time authority checks for the model-facing goal tools. */
+
+import type { Context } from 'cordis'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+import type { GoalView } from '@deepseek-ai/dsh-goal'
+import { HarnessError } from '@deepseek-ai/dsh-llm'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import type { ToolRunContext } from '@deepseek-ai/dsh-tools'
+
+type TurnStartEvent = Extract<SessionEvent, { type: 'turn/start' }>
+
+/** Current open turn plus the events accepted after its start boundary. */
+export interface GoalToolExecution {
+  readonly agent: Agent
+  readonly start: TurnStartEvent
+  readonly events: readonly SessionEvent[]
+}
+
+/** Hard authority granted to one state-changing call. */
+export type GoalToolAuthority =
+  | { readonly kind: 'direct-human' }
+  | { readonly kind: 'goal-round'; readonly goal: GoalView }
+
+/** Throw one structured tool-policy failure. */
+function reject(message: string, code = 'GOAL_TOOL_AUTHORITY_REQUIRED'): never {
+  throw new HarnessError(message, code)
+}
+
+/** Locate the open turn enclosing a model tool call. */
+function openTurn(agent: Agent): { start: TurnStartEvent; events: readonly SessionEvent[] } {
+  const events = agent.session.events
+  for (let index = events.length - 1; index >= 0; index -= 1) {
+    const boundary = events[index]
+    if (boundary?.type === 'turn/end') {
+      reject('goal tools require an open model turn', 'GOAL_TOOL_DRIVER_REQUIRED')
+    }
+    if (boundary?.type === 'turn/start') {
+      return { start: boundary, events: events.slice(index + 1) }
+    }
+  }
+  return reject('goal tools require an open model turn', 'GOAL_TOOL_DRIVER_REQUIRED')
+}
+
+/**
+ * Resolve and authenticate the calling agent and its driver boundary.
+ * @param ctx - Context carrying the live agent registry.
+ * @param exec - Tool execution metadata supplied by the registry.
+ * @returns The authenticated agent and its current turn window.
+ */
+export function goalToolExecution(ctx: Context, exec: ToolRunContext): GoalToolExecution {
+  const agent = exec.agent
+  if (agent === undefined) {
+    return reject('goal tools require a calling agent', 'GOAL_TOOL_AGENT_REQUIRED')
+  }
+  if (ctx.agents.get(agent.id) !== agent || agent.status !== 'running'
+    || ctx.agents.currentInitiator() !== agent) {
+    return reject(
+      'goal tools require the exact live calling agent inside its active driver',
+      'GOAL_TOOL_DRIVER_REQUIRED',
+    )
+  }
+  return { agent, ...openTurn(agent) }
+}
+
+/**
+ * Whether host-attested human input appears in the current root-agent turn.
+ * An omitted `Agent.send()` / `steer()` source resolves to `user`, so non-human
+ * producers must supply their own source rather than inheriting this authority.
+ */
+function hasDirectHumanInput(ctx: Context, execution: GoalToolExecution): boolean {
+  if (!ctx.agents.roots().includes(execution.agent)) return false
+  return execution.events.some(event =>
+    (event.type === 'user/message' || event.type === 'steering/message')
+    && event.data.source.kind === 'user')
+}
+
+/** Whether this turn is the current goal's exact admitted round. */
+function isMatchingGoalRound(execution: GoalToolExecution, goal: GoalView): boolean {
+  return execution.events.some(event => event.type === 'user/message'
+    && event.data.source.kind === 'goal'
+    && event.data.source.goalId === goal.id
+    && event.data.source.revision === goal.revision
+    && event.data.source.round === goal.roundsStarted)
+}
+
+/**
+ * Require authority originating in a human message accepted by a runtime root.
+ * @param ctx - Context carrying the live agent graph.
+ * @param execution - Authenticated current tool execution.
+ */
+export function requireDirectHuman(ctx: Context, execution: GoalToolExecution): void {
+  if (hasDirectHumanInput(ctx, execution)) return
+  reject('this goal operation requires a direct human turn on a top-level agent')
+}
+
+/**
+ * Resolve completion authority from either direct human input or the exact goal round.
+ * @param ctx - Context carrying live agents and goal state.
+ * @param execution - Authenticated current tool execution.
+ * @returns The direct-human or exact-goal-round authority grant.
+ */
+export function completionAuthority(ctx: Context, execution: GoalToolExecution): GoalToolAuthority {
+  if (hasDirectHumanInput(ctx, execution)) return { kind: 'direct-human' }
+  const goal = ctx.goals.get(execution.agent)
+  if (goal !== undefined && isMatchingGoalRound(execution, goal)) {
+    return { kind: 'goal-round', goal }
+  }
+  return reject('complete and blocked require a direct human turn or the current goal round')
+}
diff --git a/packages/goal/tool-goal/src/index.ts b/packages/goal/tool-goal/src/index.ts
new file mode 100644
index 0000000000..075264f93e
--- /dev/null
+++ b/packages/goal/tool-goal/src/index.ts
@@ -0,0 +1,276 @@
+/**
+ * Model-facing `get_goal`, `create_goal`, and `update_goal` tools over the
+ * persisted same-session goal domain.
+ * @module @deepseek-ai/dsh-tool-goal
+ */
+
+import type { Context } from 'cordis'
+import z from 'schemastery'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+import { GoalId } from '@deepseek-ai/dsh-goal'
+import type { GoalRef, GoalView } from '@deepseek-ai/dsh-goal'
+import { HarnessError } from '@deepseek-ai/dsh-llm'
+import { defineTool } from '@deepseek-ai/dsh-tools'
+import type { GenericCallView } from '@deepseek-ai/dsh-tools'
+import type {} from '@deepseek-ai/dsh-system-prompt'
+import {
+  completionAuthority,
+  goalToolExecution,
+  requireDirectHuman,
+} from './authority.ts'
+import type { GoalToolExecution } from './authority.ts'
+
+export const name = 'tool-goal'
+export const inject = ['agents', 'goals', 'tools', 'systemPrompt']
+
+/** Model policy and hard lower bounds for goal-state updates. */
+export interface Config {
+  /** Minimum admitted goal rounds before the model may self-report `blocked`. */
+  blockedAfterConsecutiveRounds?: number
+}
+
+/** Schemastery config for the goal-tool policy. */
+export const Config: z<Config> = z.object({
+  blockedAfterConsecutiveRounds: z.number().step(1).min(1).default(3),
+})
+
+/** Fully materialized tool policy. */
+interface ResolvedConfig {
+  readonly blockedAfterConsecutiveRounds: number
+}
+
+type UpdateAction = 'edit' | 'pause' | 'resume' | 'complete' | 'blocked'
+
+const UPDATE_ACTIONS: UpdateAction[] = ['edit', 'pause', 'resume', 'complete', 'blocked']
+
+const CREATE_DESCRIPTION =
+  'Create one persisted same-session completion goal when the current direct human request '
+  + 'is a long-running objective that should continue across autonomous goal rounds. You may '
+  + 'infer that intent without requiring the user to say "create a goal". Do not use this for '
+  + 'trivial single-turn work. Execution rejects non-human and subagent authority.'
+
+const GET_DESCRIPTION =
+  'Read the current same-session goal, including its exact id/revision, objective, phase, completed '
+  + 'continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. '
+  + 'Call this before updating a goal.'
+
+/** Render policy guidance with its deployment-selected blocked threshold. */
+function guidance(blockedAfter: number): string {
+  return '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 ${blockedAfter} `
+    + '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. */
+function resolveConfig(config: Config): ResolvedConfig {
+  const blockedAfter = config.blockedAfterConsecutiveRounds ?? 3
+  if (!Number.isSafeInteger(blockedAfter) || blockedAfter < 1) {
+    throw new TypeError('blockedAfterConsecutiveRounds must be a positive safe integer')
+  }
+  return { blockedAfterConsecutiveRounds: blockedAfter }
+}
+
+/** Build the exact compare-and-set ref from model arguments. */
+function goalRef(goalId: string, revision: number): GoalRef {
+  if (goalId.length === 0 || goalId !== goalId.trim()
+    || !Number.isSafeInteger(revision) || revision < 1) {
+    throw new HarnessError(
+      'goal_id must be non-empty and revision must be a positive safe integer',
+      'GOAL_TOOL_INVALID_UPDATE',
+    )
+  }
+  return { id: GoalId(goalId), revision }
+}
+
+/** Stable compact model result; activation is an observation, not replay state. */
+function renderGoal(goal: GoalView | undefined): string {
+  if (goal === undefined) return JSON.stringify({ goal: null })
+  return JSON.stringify({
+    goal: {
+      id: goal.id,
+      revision: goal.revision,
+      objective: goal.objective,
+      phase: goal.phase,
+      roundsStarted: goal.roundsStarted,
+      maxGoalRounds: goal.maxGoalRounds,
+      ...goal.blockedReason === undefined ? {} : { blockedReason: goal.blockedReason },
+    },
+    activation: goal.activation,
+  })
+}
+
+/** Generic, args-only pending presentation shared by the goal tools. */
+function present(title: string, kind: 'read' | 'other', rawInput?: unknown): GenericCallView {
+  return { card: 'generic', title, kind, ...rawInput === undefined ? {} : { rawInput } }
+}
+
+/** Remember whether one autonomous terminal report should stop this turn. */
+function observeMutation(
+  terminalTurns: WeakMap<Agent, number>,
+  execution: GoalToolExecution,
+  autonomousTerminal: boolean,
+): void {
+  if (!autonomousTerminal) {
+    terminalTurns.delete(execution.agent)
+    return
+  }
+  terminalTurns.set(execution.agent, execution.start.data.turn)
+}
+
+/** Register the three Codex-shaped goal tools and their shared policy section. */
+export function apply(ctx: Context, config: Config): void {
+  const resolved = resolveConfig(config)
+  // A stale entry cannot match a later loop turn because turn numbers increase
+  // monotonically within the agent's fixed session.
+  const terminalTurns = new WeakMap<Agent, number>()
+  ctx.on('agent/turn-stop', (agent, turn) => {
+    if (terminalTurns.get(agent) !== turn) return undefined
+    terminalTurns.delete(agent)
+    return { action: 'stop' }
+  })
+  ctx.systemPrompt.section({
+    name: 'tool:goal',
+    order: 114,
+    text: guidance(resolved.blockedAfterConsecutiveRounds),
+  })
+
+  ctx.tools.register(defineTool({
+    name: 'get_goal',
+    description: GET_DESCRIPTION,
+    parameters: {},
+    execute(_args, exec) {
+      const execution = goalToolExecution(ctx, exec)
+      return Promise.resolve([{
+        type: 'text',
+        text: renderGoal(ctx.goals.get(execution.agent)),
+      }])
+    },
+    presentCall: () => present('Read current goal', 'read'),
+  }))
+
+  ctx.tools.register(defineTool({
+    name: 'create_goal',
+    description: CREATE_DESCRIPTION,
+    parameters: {
+      objective: {
+        type: 'string',
+        required: true,
+        description: 'The concrete completion objective inferred from the direct human request.',
+      },
+      max_goal_rounds: {
+        type: 'number',
+        description: 'Optional positive safe-integer limit on automatic continuation rounds.',
+      },
+    },
+    execute(args, exec) {
+      const execution = goalToolExecution(ctx, exec)
+      requireDirectHuman(ctx, execution)
+      const goal = ctx.goals.create(execution.agent, {
+        objective: args.objective,
+        ...args.max_goal_rounds === undefined ? {} : { maxGoalRounds: args.max_goal_rounds },
+      })
+      observeMutation(terminalTurns, execution, false)
+      return Promise.resolve([{ type: 'text', text: renderGoal(goal) }])
+    },
+    presentCall: args => present('Create goal', 'other', args.objective),
+  }))
+
+  ctx.tools.register(defineTool({
+    name: 'update_goal',
+    description: 'Update the exact current goal revision. edit, pause, and resume require a direct '
+      + 'top-level human request. During an automatic continuation of the current goal, complete '
+      + 'and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains '
+      + 'responsible for judging that the same condition persisted across those rounds 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.' },
+      action: {
+        type: 'string',
+        required: true,
+        enum: UPDATE_ACTIONS,
+        description: 'edit | pause | resume | complete | blocked',
+      },
+      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)
+      const ref = goalRef(args.goal_id, args.revision)
+      const replacements = {
+        ...args.objective === undefined ? {} : { objective: args.objective },
+        ...args.max_goal_rounds === undefined ? {} : { maxGoalRounds: args.max_goal_rounds },
+      }
+      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([{
+          type: 'text',
+          text: renderGoal(goal),
+        }])
+      }
+      if (args.action === 'pause' || args.action === 'resume') {
+        requireDirectHuman(ctx, execution)
+        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; blocked_reason is valid only with action blocked',
+            'GOAL_TOOL_INVALID_UPDATE',
+          )
+        }
+        const goal = args.action === 'pause'
+          ? ctx.goals.pause(execution.agent, ref)
+          : ctx.goals.resume(execution.agent, ref)
+        observeMutation(terminalTurns, execution, false)
+        return Promise.resolve([{ type: 'text', text: renderGoal(goal) }])
+      }
+      const authority = completionAuthority(ctx, execution)
+      if (args.objective !== undefined || args.max_goal_rounds !== undefined) {
+        throw new HarnessError(
+          'objective and max_goal_rounds are valid only with action edit',
+          '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(
+          `blocked requires at least ${resolved.blockedAfterConsecutiveRounds} consecutive goal rounds; `
+          + `current round is ${authority.goal.roundsStarted}`,
+          'GOAL_TOOL_BLOCK_THRESHOLD',
+        )
+      }
+      const goal = args.action === 'complete'
+        ? ctx.goals.complete(execution.agent, ref)
+        : ctx.goals.block(execution.agent, ref, {
+          code: 'model-reported',
+          message: args.blocked_reason as string,
+        })
+      observeMutation(terminalTurns, execution, authority.kind === 'goal-round')
+      return Promise.resolve([{ type: 'text', text: renderGoal(goal) }])
+    },
+    presentCall: args => present(
+      `${args.action === 'blocked' ? 'Mark' : args.action.charAt(0).toUpperCase() + args.action.slice(1)} goal`,
+      'other',
+      args.blocked_reason ?? args.objective ?? args.goal_id,
+    ),
+  }))
+}
diff --git a/packages/goal/tool-goal/tests/tool-goal.spec.ts b/packages/goal/tool-goal/tests/tool-goal.spec.ts
new file mode 100644
index 0000000000..2065bac23e
--- /dev/null
+++ b/packages/goal/tool-goal/tests/tool-goal.spec.ts
@@ -0,0 +1,486 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import Loader from '@cordisjs/plugin-loader'
+import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent'
+import type { Agent, AgentStatus, InjectOptions } from '@deepseek-ai/dsh-agent'
+import GoalService, { GoalId } from '@deepseek-ai/dsh-goal'
+import type { GoalRef } from '@deepseek-ai/dsh-goal'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
+import { SESSION_FORMAT_VERSION, Session, SessionId } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry from '@deepseek-ai/dsh-tools'
+import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools'
+import * as toolGoal from '@deepseek-ai/dsh-tool-goal'
+
+interface StubAgent {
+  readonly agent: Agent
+  readonly session: Session
+  setStatus(status: AgentStatus): void
+}
+
+/** Build one registry-compatible live agent whose injections append in place. */
+function stubAgent(rawId: string, supplied?: Session): StubAgent {
+  const session = supplied ?? new Session(SessionId(rawId))
+  let status: AgentStatus = 'running'
+  const agent: Agent = {
+    id: session.id,
+    options: {},
+    session,
+    get status() { return status },
+    ctx: new Context(),
+    send() {},
+    steer() {},
+    inject(content: ContentBlock[], options?: InjectOptions) {
+      const source = options?.source ?? { kind: 'user' }
+      session.append('context/message', {
+        content,
+        source,
+        ...options?.meta === undefined ? {} : { meta: options.meta },
+      }, { surfaceOp: 'append' })
+    },
+    cancel() {},
+    whenIdle() { return Promise.resolve() },
+  }
+  return { agent, session, setStatus(value) { status = value } }
+}
+
+/** Open one message-triggered turn with its accepted model-visible input. */
+function openTurn(stub: StubAgent, source: MessageSource, text = 'prompt'): number {
+  const turn = stub.session.events
+    .filter(event => event.type === 'turn/start')
+    .reduce((max, event) => Math.max(max, event.data.turn), 0) + 1
+  stub.session.append('turn/start', { turn, trigger: { kind: 'message', source } })
+  stub.session.append('user/message', {
+    content: [{ type: 'text', text }],
+    source,
+  }, { surfaceOp: 'append' })
+  return turn
+}
+
+/** Close the currently open test turn. */
+function closeTurn(stub: StubAgent, turn: number): void {
+  stub.session.append('turn/end', { turn, reason: { kind: 'completed' } })
+}
+
+async function harness(config: toolGoal.Config = {}) {
+  const ctx = new Context()
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(GoalService)
+  const fiber = await ctx.plugin(toolGoal, config)
+  const root = stubAgent(`goal-tool-root-${Math.random()}`)
+  ctx.agents.register(root.agent)
+  return { ctx, fiber, root }
+}
+
+/** Execute one registered tool under an optional driver initiator. */
+async function execute(
+  ctx: Context,
+  name: string,
+  args: unknown,
+  agent?: Agent,
+  initiator: Agent | undefined = agent,
+): Promise<ToolExecutionResult> {
+  const run = () => ctx.tools.execute({
+    callId: CallId(`call-${Math.random()}`),
+    name,
+    arguments: args,
+    ...agent === undefined ? {} : { agent },
+  })
+  return initiator === undefined ? run() : ctx.agents.withInitiator(initiator, run)
+}
+
+/** Parse the compact JSON returned by a successful goal tool. */
+function resultJson(result: ToolExecutionResult): Record<string, unknown> {
+  expect(result.isError).toBe(false)
+  const block = result.content[0]
+  if (block?.type !== 'text') throw new Error('expected text tool result')
+  return JSON.parse(block.text) as Record<string, unknown>
+}
+
+/** Read the returned goal sub-object. */
+function resultGoal(result: ToolExecutionResult): Record<string, unknown> {
+  const goal = resultJson(result)['goal']
+  if (typeof goal !== 'object' || goal === null) throw new Error('expected returned goal')
+  return goal as Record<string, unknown>
+}
+
+describe('goal tool registration and presentation', () => {
+  it('registers three exclusive tools plus configured guidance and disposes all contributions', async () => {
+    const { ctx, fiber } = await harness({ blockedAfterConsecutiveRounds: 5 })
+    expect(['create_goal', 'get_goal', 'update_goal'].map(name => ctx.tools.get(name)?.name))
+      .toEqual(['create_goal', 'get_goal', 'update_goal'])
+    for (const name of ['create_goal', 'get_goal', 'update_goal']) {
+      expect(ctx.tools.executionMode({ callId: CallId(name), name, arguments: {} }))
+        .toEqual({ kind: 'exclusive' })
+    }
+    const section = (await ctx.systemPrompt.assemble()).sections.find(item => item.name === 'tool:goal')
+    expect(section?.text).toContain('infer goal intent')
+    expect(section?.text).toContain('at least 5 consecutive goal rounds')
+
+    await fiber.dispose()
+    expect(ctx.tools.get('get_goal')).toBeUndefined()
+    expect((await ctx.systemPrompt.assemble()).sections.some(item => item.name === 'tool:goal')).toBe(false)
+  })
+
+  it('uses args-only generic render intent and soft-fails malformed replay args', async () => {
+    const { ctx } = await harness()
+    expect(ctx.tools.get('get_goal')?.presentCall?.({})).toEqual({
+      card: 'generic', title: 'Read current goal', kind: 'read',
+    })
+    expect(ctx.tools.get('create_goal')?.presentCall?.({ objective: 'ship' })).toEqual({
+      card: 'generic', title: 'Create goal', kind: 'other', rawInput: 'ship',
+    })
+    expect(ctx.tools.get('update_goal')?.presentCall?.({
+      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' })
+    expect(ctx.tools.get('update_goal')?.presentCall?.({ wrong: true })).toBeUndefined()
+  })
+
+  it('has the Loader-safe namespace export shape', () => {
+    expect('default' in toolGoal).toBe(false)
+    expect(toolGoal.name).toBe('tool-goal')
+    expect(toolGoal.inject).toEqual(['agents', 'goals', 'tools', 'systemPrompt'])
+    const loader = Object.create(Loader.prototype) as Loader
+    expect(loader.unwrapExports(toolGoal)).toBe(toolGoal)
+  })
+
+  it('fails invalid direct config before registering anything', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(GoalService)
+    expect(() => {
+      toolGoal.apply(ctx, { blockedAfterConsecutiveRounds: 1.5 })
+    }).toThrow(
+      'blockedAfterConsecutiveRounds must be a positive safe integer',
+    )
+    expect(ctx.tools.get('get_goal')).toBeUndefined()
+  })
+
+  it('resolves the direct-apply default before registration', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(GoalService)
+    toolGoal.apply(ctx, {})
+    const section = (await ctx.systemPrompt.assemble()).sections.find(item => item.name === 'tool:goal')
+    expect(section?.text).toContain('at least 3 consecutive goal rounds')
+  })
+})
+
+describe('goal tool execution authority', () => {
+  it('lets a root model infer create intent from its accepted human turn', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'user' }, '请持续工作直到这个功能完成')
+    const result = await execute(ctx, 'create_goal', {
+      objective: 'Finish the feature', max_goal_rounds: 9,
+    }, root.agent)
+    expect(resultGoal(result)).toMatchObject({
+      objective: 'Finish the feature', revision: 1, phase: 'active', maxGoalRounds: 9,
+    })
+    expect(resultJson(result)['activation']).toBe('armed')
+    expect(ctx.goals.get(root.agent)?.objective).toBe('Finish the feature')
+  })
+
+  it('rejects agentless, driverless, non-human, and live-child creation', async () => {
+    const { ctx, root } = await harness()
+    const agentless = await execute(ctx, 'get_goal', {})
+    expect(agentless.error?.code).toBe('GOAL_TOOL_AGENT_REQUIRED')
+
+    openTurn(root, { kind: 'user' })
+    const driverless = await ctx.tools.execute({
+      callId: CallId('call-driverless'),
+      name: 'get_goal',
+      arguments: {},
+      agent: root.agent,
+    })
+    expect(driverless.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+    closeTurn(root, 1)
+
+    openTurn(root, { kind: 'plugin', plugin: 'test' })
+    const nonHuman = await execute(ctx, 'create_goal', { objective: 'forged' }, root.agent)
+    expect(nonHuman.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+    closeTurn(root, 2)
+
+    const child = stubAgent('goal-tool-child')
+    ctx.agents.enter(child.agent, root.agent)
+    ctx.agents.announce(child.agent)
+    openTurn(child, { kind: 'user' })
+    const childResult = await execute(ctx, 'create_goal', { objective: 'child goal' }, child.agent)
+    expect(childResult.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+  })
+
+  it('rejects stale agent objects and agents outside running status through the executor', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'user' })
+    const stale = { ...root.agent }
+    const staleResult = await execute(ctx, 'get_goal', {}, stale, stale)
+    expect(staleResult.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+
+    root.setStatus('idle')
+    const idleResult = await execute(ctx, 'get_goal', {}, root.agent)
+    expect(idleResult.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+  })
+
+  it('treats a fork resumed as a runtime root as direct-human authority', async () => {
+    const { ctx, root } = await harness()
+    const originalTurn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'resume the fork' })
+    closeTurn(root, originalTurn)
+    const forkId = SessionId('goal-tool-resumed-fork')
+    const forkSession = new Session(forkId, root.session.events, {
+      version: SESSION_FORMAT_VERSION,
+      id: forkId,
+      createdAt: Date.now(),
+      parentSession: root.session.id,
+      seedLength: root.session.seq,
+    })
+    const fork = stubAgent(forkId, forkSession)
+    ctx.agents.register(fork.agent)
+    expect(ctx.goals.get(fork.agent)).toMatchObject({ id: created.id, activation: 'disarmed' })
+
+    openTurn(fork, { kind: 'user' }, '继续这个目标')
+    const resumed = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'resume',
+    }, fork.agent)
+    expect(resultGoal(resumed)).toMatchObject({ id: created.id, revision: 2, phase: 'active' })
+  })
+
+  it('rejects calls before a turn and after its end boundary', async () => {
+    const { ctx, root } = await harness()
+    const before = await execute(ctx, 'get_goal', {}, root.agent)
+    expect(before.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+
+    const turn = openTurn(root, { kind: 'user' })
+    closeTurn(root, turn)
+    const after = await execute(ctx, 'get_goal', {}, root.agent)
+    expect(after.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+  })
+
+  it('rejects terminal reporting without human input or a current goal round', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'plugin', plugin: 'test' })
+    const result = await execute(ctx, 'update_goal', {
+      goal_id: 'goal-missing', revision: 1, action: 'complete',
+    }, root.agent)
+    expect(result.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+    const malformed = await execute(ctx, 'update_goal', {
+      goal_id: 'goal-missing', revision: 1, action: 'pause', objective: 'probe',
+    }, root.agent)
+    expect(malformed.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+  })
+
+  it('accepts direct human steering in a goal-sourced root turn', async () => {
+    const { ctx, root } = await harness()
+    const humanTurn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'steer me' })
+    closeTurn(root, humanTurn)
+    const round = openTurn(root, {
+      kind: 'goal', goalId: created.id, revision: created.revision, round: 1,
+    })
+    root.session.append('steering/message', {
+      turn: round,
+      content: [{ type: 'text', text: 'pause now' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    const paused = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'pause',
+    }, root.agent)
+    expect(resultGoal(paused)).toMatchObject({ phase: 'paused', revision: 2 })
+  })
+
+  it('rejects an initiator different from exec.agent', async () => {
+    const { ctx, root } = await harness()
+    const other = stubAgent('goal-tool-other')
+    ctx.agents.register(other.agent)
+    openTurn(other, { kind: 'user' })
+    const result = await execute(ctx, 'get_goal', {}, other.agent, root.agent)
+    expect(result.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+  })
+})
+
+describe('goal tool state transitions', () => {
+  it('reads null, then edits, pauses, and resumes by exact revision in one human turn', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'user' })
+    expect(resultJson(await execute(ctx, 'get_goal', {}, root.agent))).toEqual({ goal: null })
+    let goal = resultGoal(await execute(ctx, 'create_goal', { objective: 'old' }, root.agent))
+    goal = resultGoal(await execute(ctx, 'update_goal', {
+      goal_id: goal['id'], revision: goal['revision'], action: 'edit',
+      objective: 'new', max_goal_rounds: 8,
+    }, root.agent))
+    expect(goal).toMatchObject({ objective: 'new', revision: 2, maxGoalRounds: 8 })
+    goal = resultGoal(await execute(ctx, 'update_goal', {
+      goal_id: goal['id'], revision: goal['revision'], action: 'pause',
+    }, root.agent))
+    expect(goal).toMatchObject({ phase: 'paused', revision: 3 })
+    goal = resultGoal(await execute(ctx, 'update_goal', {
+      goal_id: goal['id'], revision: goal['revision'], action: 'resume',
+    }, root.agent))
+    expect(goal).toMatchObject({ phase: 'active', revision: 4 })
+    expect(await agentEvents(ctx, root.agent).serial('agent/turn-stop', 1)).toBeUndefined()
+  })
+
+  it('terminal-stops an autonomous completion but leaves a human pause interactive', async () => {
+    const { ctx, root } = await harness()
+    const humanTurn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'pause cleanly' })
+    const paused = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'pause',
+    }, root.agent)
+    expect(resultGoal(paused)).toMatchObject({ phase: 'paused' })
+    expect(await agentEvents(ctx, root.agent).serial('agent/turn-stop', humanTurn)).toBeUndefined()
+    const resumed = resultGoal(await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: 2, action: 'resume',
+    }, root.agent))
+    closeTurn(root, humanTurn)
+
+    const roundTurn = openTurn(root, {
+      kind: 'goal', goalId: created.id, revision: resumed['revision'] as number, round: 1,
+    })
+    const complete = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: resumed['revision'], action: 'complete',
+    }, root.agent)
+    expect(resultGoal(complete)).toMatchObject({ phase: 'complete' })
+    expect(await agentEvents(ctx, root.agent).serial('agent/turn-stop', roundTurn)).toEqual({ action: 'stop' })
+    expect(await agentEvents(ctx, root.agent).serial('agent/turn-stop', roundTurn)).toBeUndefined()
+  })
+
+  it('rearms a restored active goal only after a new direct human prompt', async () => {
+    const { ctx, root } = await harness()
+    let turn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'continue later' })
+    closeTurn(root, turn)
+    agentEvents(ctx, root.agent).emit('agent/session-start', 'resume')
+    expect(ctx.goals.get(root.agent)?.activation).toBe('disarmed')
+    turn = openTurn(root, { kind: 'user' }, '继续')
+    const resumed = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'resume',
+    }, root.agent)
+    expect(resultGoal(resumed)).toMatchObject({ phase: 'active', revision: 2 })
+    expect(resultJson(resumed)['activation']).toBe('armed')
+    closeTurn(root, turn)
+  })
+
+  it('returns structured domain and conditional-argument failures', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'user' })
+    const invalidCreate = await execute(ctx, 'create_goal', { objective: ' ' }, root.agent)
+    expect(invalidCreate.error?.code).toBe('GOAL_INVALID_OBJECTIVE')
+    const created = ctx.goals.create(root.agent, { objective: 'valid' })
+    const replacement = await execute(ctx, 'update_goal', {
+      goal_id: created.id,
+      revision: created.revision,
+      action: 'pause',
+      objective: 'not valid for pause',
+    }, root.agent)
+    expect(replacement.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE')
+    const terminalUpdate = await execute(ctx, 'update_goal', {
+      goal_id: created.id,
+      revision: created.revision,
+      action: 'complete',
+      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)
+    expect(malformedRef.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE')
+  })
+
+  it('allows exact goal rounds to complete but not edit or pause', async () => {
+    const { ctx, root } = await harness()
+    const humanTurn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'round-owned' })
+    closeTurn(root, humanTurn)
+    openTurn(root, { kind: 'goal', goalId: created.id, revision: created.revision, round: 1 })
+    const edit = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'edit', objective: 'forbidden',
+    }, root.agent)
+    expect(edit.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+    const complete = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'complete',
+    }, root.agent)
+    expect(resultGoal(complete)).toMatchObject({ phase: 'complete', revision: 2, roundsStarted: 1 })
+  })
+
+  it('enforces the configured model self-block lower bound across admitted rounds', async () => {
+    const { ctx, root } = await harness({ blockedAfterConsecutiveRounds: 3 })
+    let turn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'blocked eventually' })
+    closeTurn(root, turn)
+    const ref: GoalRef = { id: GoalId(created.id), revision: created.revision }
+
+    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',
+        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',
+      blocked_reason: 'The required credential is still unavailable.',
+    }, root.agent)
+    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 () => {
+    const { ctx, root } = await harness({ blockedAfterConsecutiveRounds: 9 })
+    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',
+      blocked_reason: 'The user asked to stop until a prerequisite is available.',
+    }, root.agent)
+    expect(resultGoal(blocked)).toMatchObject({
+      phase: 'blocked',
+      blockedReason: {
+        code: 'model-reported',
+        message: 'The user asked to stop until a prerequisite is available.',
+      },
+      roundsStarted: 0,
+    })
+  })
+})
diff --git a/packages/goal/tool-goal/tsconfig.json b/packages/goal/tool-goal/tsconfig.json
new file mode 100644
index 0000000000..d5c34d4e29
--- /dev/null
+++ b/packages/goal/tool-goal/tsconfig.json
@@ -0,0 +1,39 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/schemastery"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../llm/llm"
+    },
+    {
+      "path": "../../core/session"
+    },
+    {
+      "path": "../../core/agent"
+    },
+    {
+      "path": "../../core/tools"
+    },
+    {
+      "path": "../../core/system-prompt"
+    },
+    {
+      "path": "../goal"
+    }
+  ]
+}
diff --git a/packages/sdk/helper/README.md b/packages/sdk/helper/README.md
index 45ad545458..89ca897d31 100644
--- a/packages/sdk/helper/README.md
+++ b/packages/sdk/helper/README.md
@@ -6,7 +6,7 @@ The package owns the builtin typed-spec catalog, provider/app behavior entities,
 
 All business and document validation completes before commit writes any affected file. Commit detects external edits made after the session opened, but deliberately provides no cross-file rollback after writing starts.
 
-Builtin features are provider, bash, app, persistence, HMR, filesystem, todo, skill, web, subagent, workflow, compaction, hooks, repeat-tool guard, timeout policy, and ask-user. The catalog owns feature options, required and non-default Cordis plugin config, feature requirements, resource contribution, and round-trip markers; create and config use the same registry and configurator.
+Builtin features are provider, bash, app, persistence, HMR, filesystem, todo, skill, web, subagent, workflow, compaction, hooks, repeat-tool guard, timeout policy, and ask-user. The catalog owns feature options, required and non-default Cordis plugin config, feature requirements, resource contribution, and round-trip markers; create and config use the same registry and configurator. The ACP app option contributes the human-command and user-interaction services before the bridge.
 
 `SdkProject.open()` requires only readable root `package.json` and `cordis.yml`. A Cordis config entry anchors feature installation; a package present only through a linked NPM dependency closure leaves the feature absent. Once an owned Cordis config entry exists, an incomplete resource shape is `inconsistent` and cannot be modified automatically.
 
diff --git a/packages/sdk/helper/src/features/builtin/app.ts b/packages/sdk/helper/src/features/builtin/app.ts
index 8e7793ab8f..835a9a8710 100644
--- a/packages/sdk/helper/src/features/builtin/app.ts
+++ b/packages/sdk/helper/src/features/builtin/app.ts
@@ -73,6 +73,10 @@ class AppOption extends FeatureOption {
       case 'acp':
         return new ProjectContribution([
           ...appProjectResources(profile, this.id),
+          ...npmCordisConfigEntry(ID, {
+            id: 'commands',
+            name: '@deepseek-ai/dsh-commands',
+          }),
           ...npmCordisConfigEntry(ID, {
             id: 'user-interaction',
             name: '@deepseek-ai/dsh-user-interaction',
diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts
index 18540d4e67..4df8c5d3f2 100644
--- a/packages/sdk/helper/tests/project.spec.ts
+++ b/packages/sdk/helper/tests/project.spec.ts
@@ -283,6 +283,7 @@ describe('SdkProject and ProjectEditSession', () => {
     edit.configureFeature(registry.get(featureId('app')), selection('app', ['acp']))
     const acp = (await edit.commit()).project
     expect(acp.profile.runInterface).toBe('acp')
+    expect(acp.cordis.entry('commands')).toMatchObject({ name: '@deepseek-ai/dsh-commands' })
     expect(acp.packageManifest().scripts).toMatchObject({
       dev: 'dsh-sdk dev index.ts',
       start: 'dsh-sdk start index.js',
diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts
index 0735338d9a..36744026b8 100644
--- a/packages/support/acp-snapshot/src/harness.ts
+++ b/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')
diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts
index 3d174b3c3e..1f69388968 100644
--- a/packages/support/acp-snapshot/tests/harness.spec.ts
+++ b/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',
@@ -443,6 +458,7 @@ describe('runScenario', () => {
 
   it.each([
     [{ op: 'prompt', text: 'x' }, /prompt before newSession/],
+    [{ op: 'promptAndWaitForAgentMessage', text: 'x', waitForText: 'later' }, /promptAndWaitForAgentMessage before newSession/],
     [{ op: 'promptExpectError', text: 'x' }, /promptExpectError before newSession/],
     [{ op: 'promptAndCancel', text: 'x' }, /promptAndCancel before newSession/],
     [{ op: 'cancel' }, /cancel before newSession/],
diff --git a/packages/support/invariants/package.json b/packages/support/invariants/package.json
index 59a425387b..9ca1e0aab1 100644
--- a/packages/support/invariants/package.json
+++ b/packages/support/invariants/package.json
@@ -30,6 +30,7 @@
   },
   "devDependencies": {
     "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-goal": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-scope": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
diff --git a/packages/support/invariants/src/scoped-events.generated.ts b/packages/support/invariants/src/scoped-events.generated.ts
index 36d1721945..a007ab4174 100644
--- a/packages/support/invariants/src/scoped-events.generated.ts
+++ b/packages/support/invariants/src/scoped-events.generated.ts
@@ -8,6 +8,7 @@
 import type { Events } from 'cordis'
 import type { Scoped } from '@deepseek-ai/dsh-scope'
 import type {} from '@deepseek-ai/dsh-agent'
+import type {} from '@deepseek-ai/dsh-goal'
 import type {} from '@deepseek-ai/dsh-session'
 import type {} from '@deepseek-ai/dsh-subagent'
 import type {} from '@deepseek-ai/dsh-system-prompt'
@@ -27,6 +28,7 @@ function adapt<K extends ScopedEventName>(
 }
 
 const scopedSubjectResolvers = Object.freeze({
+  'agent/cancel-requested': adapt<'agent/cancel-requested'>(args => args[0]),
   'agent/created': adapt<'agent/created'>(args => args[0]),
   'agent/disposed': adapt<'agent/disposed'>(args => args[0]),
   'agent/error': adapt<'agent/error'>(args => args[0]),
@@ -43,6 +45,7 @@ const scopedSubjectResolvers = Object.freeze({
   'agent/turn-continuation': adapt<'agent/turn-continuation'>(args => args[0]),
   'agent/turn-stop': adapt<'agent/turn-stop'>(args => args[0]),
   'approval/request': adapt<'approval/request'>(args => args[0].agent),
+  'goal/changed': adapt<'goal/changed'>(args => args[0]),
   'session/created': null,
   'session/disposed': null,
   'session/event': null,
diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts
index d2c21fe020..4f066eff8c 100644
--- a/packages/support/invariants/tests/invariants.spec.ts
+++ b/packages/support/invariants/tests/invariants.spec.ts
@@ -936,6 +936,7 @@ describe('scoped-dispatch invariants', () => {
       ['agent/turn-stop', [agent, 1]],
       ['agent/error', [agent, 1, 0, new Error('x')]],
       ['approval/request', [{ agent, toolName: 'echo' }, () => Promise.resolve('unavailable')]],
+      ['goal/changed', [agent, { operation: 'create', ref: { id: 'goal-a', revision: 1 } }]],
       ['tools/pre-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ kind: 'allow' })]],
       ['tools/execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ content: [], isError: false })]],
       ['tools/post-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, { content: [], isError: false }, () => Promise.resolve({ kind: 'accept' })]],
diff --git a/packages/support/invariants/tsconfig.json b/packages/support/invariants/tsconfig.json
index 6c5bc479b5..8fefb2d7eb 100644
--- a/packages/support/invariants/tsconfig.json
+++ b/packages/support/invariants/tsconfig.json
@@ -23,6 +23,9 @@
     {
       "path": "../../core/agent"
     },
+    {
+      "path": "../../goal/goal"
+    },
     {
       "path": "../../core/scope"
     },
diff --git a/packages/ui/README.md b/packages/ui/README.md
index bd6b6c9406..aad4a9b628 100644
--- a/packages/ui/README.md
+++ b/packages/ui/README.md
@@ -5,6 +5,7 @@ Integrations that expose the agent to an external editor or client. These are **
 | Package | Role | ctx key |
 |---|---|---|
 | `acp/` | Agent Client Protocol bridge: serves the agent to an ACP editor (Zed) over JSON-RPC stdio | (drives `ctx.agents`/`ctx.sessions`) |
+| `commands/` | Human-command registry: shared discovery metadata, scoped shadowing, cancellation, and direct UI dispatch | `ctx.commands` |
 | `user-approval/` | One-shot user-approval mechanism, closed outcome vocabulary, audit events, and per-session approval policy | `ctx.approval` |
 | `permission/` | User-facing permission presets (`workspace-write`/`danger-full-access`): one product-level select bundling the sandbox-mode and approval-policy knobs, written through to their session events | `ctx.permission` |
 | `user-interaction/` | Abstract human question/answer seam used by UI-backed confirmation tools | `ctx.userInteraction` |
@@ -13,7 +14,7 @@ Integrations that expose the agent to an external editor or client. These are **
 | `jsonrpc/` | Stdio JSON-RPC server for out-of-process SDK clients | (drives `ctx.agents`) |
 | `app-boot/` | Shared boot glue for the app bins: `.env` loading, fail-loud Loader guards, snapshot-aware config resolution, the settle-the-tree boot sequence | (library for the bins) |
 
-A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The `jsonrpc` plugin is the SDK-client sibling of the `acp` bridge (a JSON-RPC server over `ctx.agents` for out-of-process SDK clients rather than editors). [`tui`](tui/README.md) is the interactive terminal front door; non-interactive tasks use the headless `cli-demo` app instead of a UI channel.
+A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The `jsonrpc` plugin is the SDK-client sibling of the `acp` bridge (a JSON-RPC server over `ctx.agents` for out-of-process SDK clients rather than editors). [`tui`](tui/README.md) is the interactive terminal front door; non-interactive tasks use the headless `cli-demo` app instead of a UI channel. [`commands`](commands/README.md) is the human-only discovery and dispatch plane shared by TUI and ACP; command input and output do not become model messages.
 
 `user-approval`, `user-interaction`, and `tool-ask-user` live here because asking a human is a UI-backed product affordance, not part of the providerless core spine. `user-approval` owns the one-shot `ctx.approval` decision mechanism and its policy tier; answerers remain with their UI channel owners. `user-interaction` remains provider-neutral (`ctx.userInteraction`), while `tool-ask-user` is its model-facing consumer and the app/bridge packages provide concrete providers.
 
diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md
index 7a1a9fb00e..32b523cccd 100644
--- a/packages/ui/acp/README.md
+++ b/packages/ui/acp/README.md
@@ -8,7 +8,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the terminal `
 
 `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface.
 
-The plugin injects `agents`, `sessionPersistence`, `tools`, `userInteraction`, `llm`, and `systemPrompt`, never the concrete loop. Persistence backs `session/load`; the LLM catalog backs model selection; prompt assembly keeps model variables aligned with routing; tool definitions own presentation; user interaction maps agent questions to ACP forms.
+The plugin injects `agents`, [`commands`](../commands/README.md), `sessionPersistence`, `tools`, `userInteraction`, `llm`, and `systemPrompt`, never the concrete loop. Persistence backs `session/load`; the command registry backs slash discovery and direct dispatch; the LLM catalog backs model selection; prompt assembly keeps model variables aligned with routing; tool definitions own presentation; user interaction maps agent questions to ACP forms.
 
 ### Config
 
@@ -26,10 +26,10 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name:
 | ACP method | Harness seam | Notes |
 |---|---|---|
 | `initialize` | static | negotiate `protocolVersion`; advertise baseline prompt capabilities (`text`, plus `resource_link` rendered as text) and `loadSession: true` |
-| `session/new` | `ctx.agents.create({ sessionId, meta:{cwd} })` | creates a new session/agent; N concurrent sessions are allowed, keyed by id; `cwd` must be absolute (it becomes the session's workspace — see Per-session cwd); non-empty `additionalDirectories` and `mcpServers` rejected |
-| `session/load` | `ctx.agents.resume(...)` | reserves the id, verifies the persisted cwd, resumes, and replays user, assistant, and tool events |
-| `session/prompt` | `agent.send()` | supports ACP `text` and `resource_link` blocks; rejects image/audio/embedded resource and empty prompts; one in-flight prompt PER session (independent); settles on the OWNING turn's end (a turn that ends in `error` rejects the RPC) |
-| `session/cancel` | `agent.cancel()` | the queue-aware cancel: aborts a running step, clears queued + steering work, and drops a turn about to start, then settles the prompt `cancelled` — for ONLY that session (a cancel never touches another session's stream or prompt) |
+| `session/new` | `ctx.agents.create({ sessionId, meta:{cwd} })` | creates a new session/agent; N concurrent sessions are allowed, keyed by id; advertises the effective command snapshot; `cwd` must be absolute (it becomes the session's workspace — see Per-session cwd); non-empty `additionalDirectories` and `mcpServers` rejected |
+| `session/load` | `ctx.agents.resume(...)` | reserves the id, verifies the persisted cwd, resumes, replays user, assistant, and tool events, and re-advertises commands |
+| `session/prompt` | `ctx.commands.execute()` or `agent.send()` | a flattened prompt beginning with `/` stays in the direct command plane; ordinary prompts support ACP `text` and `resource_link`; unsupported content and empty prompts are rejected; one request is in flight per session and settles on the owning turn's end, with an error turn rejecting the RPC |
+| `session/cancel` | command `AbortSignal` or `agent.cancel()` | aborts the exact direct command, or applies the queue-aware agent cancel and settles its prompt `cancelled`; one session never cancels another |
 | `session/update` | `session/event` | streams user replay, assistant text/reasoning, retry/failure attempt markers, and tool render intents |
 | `elicitation/create` | `ctx.userInteraction.ask()` | maps `ask_user_question` questions to ACP form elicitations; option descriptions are shown in enum titles, `multi_select` uses ACP array enums, optionless requests use a required `custom` field, and a non-empty custom answer overrides any selected choice |
 | `session/request_permission` | `approval/request` listener | answers one-shot allow/reject requests for bridge-owned calls; foreign or call-less requests delegate and fail closed if unanswered — see "Permission prompts" |
@@ -39,6 +39,12 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name:
 
 One id-keyed record map plus exact agent-object checks route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session Agent Note](../../../.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md).
 
+## Human commands
+
+After `session/new` and `session/load`, the bridge emits ACP's full `available_commands_update` snapshot for that exact agent. A new session's server-generated id is introduced by the RPC response before its snapshot enters the connection write queue. A global or scoped registry change refreshes every live session from its independently resolved view, so clients replace rather than merge cached catalogs. Names omit the slash; descriptions and optional unstructured-input hints map directly to ACP `AvailableCommand`.
+
+ACP v1 permits a command prompt to carry additional content blocks. The bridge applies its ordinary lossless flattening for supported `text` and `resource_link` blocks, then dispatches when the result begins with `/`. Known commands execute without a model request. Unknown or malformed slash input returns a direct error instead of falling back to the model; prefix whitespace when literal slash-leading text must reach the model. Expected handler errors, thrown failures, and successful text stream as UI-only `agent_message_chunk` output and end the request; cancellation returns `cancelled`. See the [command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md) and the [ACP v1 slash-command contract](https://agentclientprotocol.com/protocol/v1/slash-commands).
+
 ## Session config options
 
 The bridge advertises a `model`-category select in `session/new` and `session/load` when the session has a complete target whose provider is registered. Values encode the complete provider/model pair, are grouped by provider when more than one group is available, and come from `ctx.llm.listProviders()` / `listModels()`. The configured or last-requested model is added when absent because catalogs are advisory and private adapters may accept unlisted ids. A selection changes only that ACP session. Agent-scoped prompt assembly snapshots the selected pair for one step, supplies matching `{{provider}}` / `{{model}}` variables, and the `agent/request` waterfall applies the same pair; a concurrent selection therefore takes effect on the next step instead of splitting prompt text from routing. The resulting request header is the durable record restored by `session/load`; a selection never used by a request remains in-memory only.
@@ -108,6 +114,20 @@ Prompt tokens are data-dependent and remain in that session's history until comp
 
 Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries.
 
+### Human commands
+
+#### What the model sees
+
+Nothing from command discovery, slash input, or command output. A command handler may separately mutate a durable domain whose later state affects model requests.
+
+#### Token effect
+
+Direct dispatch adds no model tokens and no session message. The mutated domain owns any later prompt or history cost.
+
+#### KV Cache effect
+
+Command discovery, dispatch, and direct output never enter a model request and do not affect its cache. A mutated domain owns any later cache effect.
+
 ### Human answers and permission decisions
 
 #### What the model sees
@@ -170,3 +190,4 @@ Loading does not rewrite the stored log, but the next request is reconstructed u
 - **Prompt content is `text` + `resource_link` only** — image, audio, and embedded-resource blocks are rejected, as is a non-empty `mcpServers` list at `session/new`.
 - **Terminal cards render completed output** — live incremental streaming and command classification are named follow-ups of [the terminal-rendering Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md).
 - **Permission answers are one-shot only** — the bridge offers `allow_once` / `reject_once`; durable `allow_always` grants and their storage/revocation policy remain deferred to the approval seam.
+- **Command output is live-only** — discovery is refreshed after load, but direct command results are not persisted or replayed into a reconnected editor.
diff --git a/packages/ui/acp/acp-feature-support.md b/packages/ui/acp/acp-feature-support.md
index 497973731e..60c7b19adf 100644
--- a/packages/ui/acp/acp-feature-support.md
+++ b/packages/ui/acp/acp-feature-support.md
@@ -10,7 +10,7 @@ Legend: ✅ supported · ⚠️ partial / fallback · ❌ not yet · — n/a. Th
 
 ## At a glance
 
-The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), resumable session replay, one-shot permission prompts, per-session model selection, and permission presets. The largest **unbuilt** areas are **MCP passthrough**, **slash commands**, and **agent plans**, plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary).
+The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), resumable session replay, slash commands, one-shot permission prompts, per-session model selection, and permission presets. The largest **unbuilt** areas are **MCP passthrough** and **agent plans**, plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary).
 
 ## 1. Agent methods (client → agent)
 
@@ -23,8 +23,8 @@ The bridge implements the **core prompt-turn loop** for N concurrent sessions: i
 | `session/load` | S | ✅ | ✅ | ✅ | Maps to `agents.resume` + full event-log replay; validates persisted `cwd` before constructing the agent. |
 | `session/resume` | S | ❌ | ✅ | ✅ | Reconnect WITHOUT replay; gated by `sessionCapabilities.resume`. Not advertised. |
 | `session/close` | S | ❌ | ✅ | ✅ | No `session/close` handler — the SDK dispatch returns `method_not_found`. The bridge tears sessions down on client disconnect / Cordis disposal (cross-cutting, see [§8](#8-cross-cutting)), but that is not the on-demand per-session method. |
-| `session/prompt` | S | ✅ | ✅ | ✅ | Maps to `agent.send`; one in-flight prompt per session; settles on the owning turn's end. |
-| `session/cancel` | S | ✅ | ✅ | ✅ | Queue-aware `agent.cancel`; settles the in-flight prompt `cancelled`, scoped to the one session. |
+| `session/prompt` | S | ✅ | ✅ | ✅ | A flattened prompt beginning with `/` dispatches through `ctx.commands` without a model request; ordinary input maps to `agent.send`. One request is in flight per session. |
+| `session/cancel` | S | ✅ | ✅ | ✅ | Aborts the exact direct command, or applies queue-aware `agent.cancel` and settles its prompt `cancelled`, scoped to one session. |
 | `session/set_mode` | S | ❌ | ✅ | ✅ | Session modes deliberately skipped: config options are the spec's replacement and modes are slated for removal in ACP v2 (see [§6](#6-session-modes--config-options--models)). |
 | `session/set_config_option` | S | ✅ | ✅ | ✅ | A provider/model select is present for a complete registered target; one `permission` select is added when `ctx.permission` is composed. Every response carries the complete refreshed state. |
 | model selection | S | ✅ | ✅ | ✅ | No distinct stable `session/set_model` — model is the `model`-category `session/set_config_option`. Values preserve the provider/model pair, catalogs come from `ctx.llm`, selection is per session, and `session/load` restores the last requested pair. Codex also supports the legacy `unstable_setSessionModel` ext method. |
@@ -84,7 +84,7 @@ These are capabilities the bridge would *drive* on the editor. The harness runs
 | `tool_call` | S | ✅ | ✅ | ✅ | Tool-owned presentation (`presentCall`); see [§5](#5-tool-call-rendering). |
 | `tool_call_update` | S | ✅ | ✅ | ✅ | From appended `tool/result` via `presentResult`; replacement results rewrite model context and do not duplicate or overwrite execution presentation. |
 | `plan` | S | ❌ | ✅ | ✅ | No agent plan emitted. Both adapters emit real plan entries (Codex's `CodexEventHandler.updatePlan` maps `turn/plan/updated` → `{ sessionUpdate: 'plan', entries }`). |
-| `available_commands_update` | S | ❌ | ✅ | ✅ | No slash commands advertised. |
+| `available_commands_update` | S | ✅ | ✅ | ✅ | Full effective snapshot after create/load and registry changes; names, descriptions, and unstructured-input hints come from `ctx.commands`. |
 | `current_mode_update` | S | ❌ | ✅ | ✅ | No session modes. |
 | `config_option_update` | S | ❌ | ✅ | ✅ | Config options exist (advertised in `session/new`/`session/load`, switched via `session/set_config_option`), but the bridge never pushes agent-initiated changes — an operator default drift is narrated to the MODEL, not echoed to the editor. Future work in the [sandbox Agent Note § Per-session mode switching](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md). |
 | `usage_update` | S | ❌ | ✅ | ✅ | Token/cost reporting not surfaced (the harness records token usage internally on `assistant/message`). |
@@ -142,11 +142,10 @@ Ranked by how commonly the reference adapters ship them and how much UX they unl
 
 1. **Session lifecycle** — `session/list` + `session/delete` (the persistence layer already lists), then `session/resume` / `session/close`.
 2. **Agent plan** (`sessionUpdate: 'plan'`) — surface the loop's plan as structured entries.
-3. **Slash commands** (`available_commands_update`).
-4. **MCP passthrough** (`mcpServers` on `session/new` + `mcpCapabilities`).
-5. **Richer prompt content** — image / embedded `resource` blocks (needs a multimodal model path).
-6. **Usage reporting** (`usage_update`) — the harness already records token usage internally (on `assistant/message`).
-7. **Editor filesystem delegation** (`fs/read_text_file` / `fs/write_text_file`) — lets the agent see unsaved buffers; lower priority since the harness has direct disk access.
+3. **MCP passthrough** (`mcpServers` on `session/new` + `mcpCapabilities`).
+4. **Richer prompt content** — image / embedded `resource` blocks (needs a multimodal model path).
+5. **Usage reporting** (`usage_update`) — the harness already records token usage internally (on `assistant/message`).
+6. **Editor filesystem delegation** (`fs/read_text_file` / `fs/write_text_file`) — lets the agent see unsaved buffers; lower priority since the harness has direct disk access.
 
 ## Out of scope
 
diff --git a/packages/ui/acp/package.json b/packages/ui/acp/package.json
index 94cdd10743..9c4fefaa01 100644
--- a/packages/ui/acp/package.json
+++ b/packages/ui/acp/package.json
@@ -29,6 +29,7 @@
   "peerDependencies": {
     "@deepseek-ai/dsh-agent": "^0.0.1",
     "@deepseek-ai/dsh-bash": "^0.0.1",
+    "@deepseek-ai/dsh-commands": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-llm-retry": "^0.0.1",
     "@deepseek-ai/dsh-permission": "^0.0.1",
@@ -47,6 +48,7 @@
     "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^",
     "@deepseek-ai/dsh-bash": "workspace:^",
     "@deepseek-ai/dsh-bash-local": "workspace:^",
+    "@deepseek-ai/dsh-commands": "workspace:^",
     "@deepseek-ai/dsh-fs-local": "workspace:^",
     "@deepseek-ai/dsh-fs-policy": "workspace:^",
     "@deepseek-ai/dsh-invariants": "workspace:^",
diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts
index 38eeb3f914..62455223a4 100644
--- a/packages/ui/acp/src/index.ts
+++ b/packages/ui/acp/src/index.ts
@@ -17,7 +17,9 @@ import {
   PROTOCOL_VERSION,
   RequestError,
   type Agent as AcpAgent,
+  type AnyMessage,
   type AuthenticateRequest,
+  type AvailableCommand,
   type CancelNotification,
   type ContentBlock as AcpContentBlock,
   type CreateElicitationRequest,
@@ -46,6 +48,7 @@ import type { ContentBlock, LlmCallConfig, LlmModelInfo, LlmProviderInfo } from
 import { assertNever, CallId } from '@deepseek-ai/dsh-llm'
 import type {} from '@deepseek-ai/dsh-llm-retry'
 import type { Agent } from '@deepseek-ai/dsh-agent'
+import type {} from '@deepseek-ai/dsh-commands'
 import { SessionId } from '@deepseek-ai/dsh-session'
 // Side-effect type import: resolves `ctx.get('permission')` to the service.
 import type {} from '@deepseek-ai/dsh-permission'
@@ -77,13 +80,50 @@ import {
 
 export const name = 'acp'
 // Interface services back loading, presentation, interaction, and prompt assembly.
-export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction', 'llm', 'systemPrompt']
+export const inject = ['agents', 'commands', 'sessionPersistence', 'tools', 'userInteraction', 'llm', 'systemPrompt']
 
 /** Preserve invalid-parameter detail in the SDK wire error message. */
 function invalidParams(detail: string): RequestError {
   return RequestError.invalidParams(undefined, detail)
 }
 
+/** Render arbitrary thrown values without trusting their string coercion. */
+function renderThrown(value: unknown): string {
+  try {
+    return String(value)
+  } catch {
+    return '<unrenderable thrown value>'
+  }
+}
+
+/** Return a server-created session id carried by an outbound success response. */
+function responseSessionId(message: AnyMessage): SessionId | undefined {
+  if (!('result' in message) || typeof message.result !== 'object' || message.result === null
+    || !('sessionId' in message.result) || typeof message.result.sessionId !== 'string') {
+    return undefined
+  }
+  return SessionId(message.result.sessionId)
+}
+
+/** Observe messages only after the wrapped ACP transport has written them. */
+function observeOutbound(stream: Stream, onWritten: (message: AnyMessage) => void): Stream {
+  const writer = stream.writable.getWriter()
+  return {
+    readable: stream.readable,
+    writable: new WritableStream<AnyMessage>({
+      async write(message) {
+        await writer.write(message)
+        onWritten(message)
+      },
+      /* v8 ignore start -- the ACP SDK never closes or aborts its outbound stream;
+         preserve the wrapped Stream contract for other consumers nonetheless */
+      close: () => writer.close(),
+      abort: (reason: unknown) => writer.abort(reason),
+      /* v8 ignore stop */
+    }),
+  }
+}
+
 /** Preserve failed-turn detail; plain handler errors become a generic wire internal error. */
 function internalError(detail: string): RequestError {
   return RequestError.internalError(undefined, detail)
@@ -260,6 +300,8 @@ interface SessionRecord {
     reject: (error: Error) => void
     turn: number | undefined
   } | undefined
+  /** Abort owner for a direct slash-command request, mutually exclusive with `inflight`. */
+  commandAbort: AbortController | undefined
   /** Last idle switch per knob, anchored before the next prompt assembles. */
   pendingSwitches: { preset?: string }
 }
@@ -274,6 +316,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
   // ACP handlers execute outside this plugin's injection scope, so capture
   // injected services during apply(); lazy service reads in a handler fail.
   const agents = ctx.agents
+  const commands = ctx.commands
   const llm = ctx.llm
   const sessionPersistence = ctx.sessionPersistence
   const logger = ctx.logger
@@ -380,6 +423,9 @@ export function apply(ctx: Context, config: AcpConfig): void {
   const sessions = new Map<SessionId, SessionRecord>()
   // Reserve an id before resume so pipelined load/new requests cannot duplicate it.
   const loadingIds = new Set<SessionId>()
+  // A new-session response introduces its server-generated id to the client;
+  // keep its initial command snapshot pending until that response is written.
+  const pendingCommandSnapshots = new Map<SessionId, SessionRecord>()
   // Async creation checks this after awaits to avoid publishing after teardown.
   let closed = false
   // Each new or loaded session snapshots the latest connection capability.
@@ -468,6 +514,43 @@ export function apply(ctx: Context, config: AcpConfig): void {
     })
   }
 
+  /** Project the effective registry view onto ACP discovery metadata. */
+  const availableCommands = (agent: Agent): AvailableCommand[] => commands.list(agent).map(command => ({
+    name: command.name,
+    description: command.description,
+    ...command.input === undefined ? {} : { input: { hint: command.input.hint } },
+  }))
+
+  /** Push the protocol's full-snapshot command catalog for one live session. */
+  const notifyCommands = (rec: SessionRecord): void => {
+    notify({
+      sessionId: rec.agent.session.id,
+      update: {
+        sessionUpdate: 'available_commands_update',
+        availableCommands: availableCommands(rec.agent),
+      },
+    })
+  }
+
+  /** Enqueue a new session's first command snapshot behind its written RPC response. */
+  const announceInitialCommands = (message: AnyMessage): void => {
+    const sessionId = responseSessionId(message)
+    if (sessionId === undefined) return
+    const rec = pendingCommandSnapshots.get(sessionId)
+    if (rec === undefined) return
+    pendingCommandSnapshots.delete(sessionId)
+    notifyCommands(rec)
+  }
+
+  // Registration and HMR removal can affect global or one scoped view; refresh
+  // every announced bridge-owned session and let the registry resolve each
+  // exact agent. A pending new-session snapshot will read the latest registry.
+  ctx.on('commands/change', () => {
+    for (const rec of sessions.values()) {
+      if (!pendingCommandSnapshots.has(rec.agent.session.id)) notifyCommands(rec)
+    }
+  })
+
   /** Settle the in-flight prompt with a stop reason, exactly once (no-op if none pending). */
   const settlePrompt = (rec: SessionRecord, reason: StopReason): void => {
     const inflight = rec.inflight
@@ -674,15 +757,18 @@ export function apply(ctx: Context, config: AcpConfig): void {
           await handle.dispose()
           throw internalError('connection closed during session/new')
         }
-        sessions.set(sessionId, {
+        const record: SessionRecord = {
           agent: handle.agent,
           dispose: () => handle.dispose(),
           presenter: makePresenter(handle.agent),
           terminalEnabled: terminalOutputCap,
           target,
           inflight: undefined,
+          commandAbort: undefined,
           pendingSwitches: {},
-        })
+        }
+        sessions.set(sessionId, record)
+        pendingCommandSnapshots.set(sessionId, record)
         const configOptions = configOptionsFor(handle.agent, directory)
         return { sessionId, ...configOptions.length > 0 ? { configOptions } : {} }
       },
@@ -763,6 +849,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
             terminalEnabled,
             target,
             inflight: undefined,
+            commandAbort: undefined,
             pendingSwitches: {},
           }
           sessions.set(sessionId, record)
@@ -787,6 +874,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
           for (const event of agent.session.events) {
             streamSessionEventUpdate(sessionId, event, notify, replayPresenter, replayTerminal)
           }
+          notifyCommands(record)
           const configOptions = configOptionsFor(agent, directory)
           return configOptions.length > 0 ? { configOptions } : {}
         } finally {
@@ -797,7 +885,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
       async prompt(params: PromptRequest): Promise<PromptResponse> {
         assertOpen()
         const rec = requireSession(SessionId(params.sessionId))
-        if (rec.inflight !== undefined) {
+        if (rec.inflight !== undefined || rec.commandAbort !== undefined) {
           throw invalidParams('a prompt is already in flight for this session')
         }
         if (promptHasUnsupportedContent(params.prompt)) {
@@ -810,6 +898,52 @@ export function apply(ctx: Context, config: AcpConfig): void {
           // waiting for a settle that never comes.
           throw invalidParams('empty prompt')
         }
+        // ACP command prompts may carry additional supported content blocks.
+        // The same lossless flattening used for model prompts supplies their
+        // unstructured command input; unsupported kinds were rejected above.
+        const commandLine = text.startsWith('/') ? text : undefined
+        if (commandLine !== undefined) {
+          const controller = new AbortController()
+          rec.commandAbort = controller
+          try {
+            const result = await commands.execute(rec.agent, commandLine, controller.signal)
+            if (result !== undefined && result.text !== undefined && result.text !== '') {
+              notify({
+                sessionId: rec.agent.session.id,
+                update: {
+                  sessionUpdate: 'agent_message_chunk',
+                  content: {
+                    type: 'text',
+                    text: result.kind === 'error' ? `Error: ${result.text}` : result.text,
+                  },
+                },
+              })
+            } else if (result === undefined) {
+              notify({
+                sessionId: rec.agent.session.id,
+                update: {
+                  sessionUpdate: 'agent_message_chunk',
+                  content: { type: 'text', text: `Error: unknown command: ${commandLine}` },
+                },
+              })
+            }
+            return { stopReason: 'end_turn' }
+          } catch (error: unknown) {
+            if (controller.signal.aborted) return { stopReason: 'cancelled' }
+            const rendered = renderThrown(error)
+            logger.warn(`acp: command failed: ${rendered}`)
+            notify({
+              sessionId: rec.agent.session.id,
+              update: {
+                sessionUpdate: 'agent_message_chunk',
+                content: { type: 'text', text: `Error: command failed: ${rendered}` },
+              },
+            })
+            return { stopReason: 'end_turn' }
+          } finally {
+            rec.commandAbort = undefined
+          }
+        }
         // Install the in-flight slot BEFORE send() (send does not synchronously
         // flip status to running; the session/event listener records the turn
         // number and settle/rejects it). Capture the log length now as the
@@ -837,8 +971,12 @@ export function apply(ctx: Context, config: AcpConfig): void {
         // settle it, because cancel() may drop the turn before any turn/end is
         // emitted, and removing this direct settle would move the RPC's
         // resolution onto a later observer path, changing its timing.
-        rec.agent.cancel('session/cancel')
-        settlePrompt(rec, 'cancelled')
+        if (rec.commandAbort !== undefined) {
+          rec.commandAbort.abort(new Error('session/cancel'))
+        } else {
+          rec.agent.cancel('session/cancel')
+          settlePrompt(rec, 'cancelled')
+        }
         return Promise.resolve()
       },
 
@@ -908,7 +1046,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
     Writable.toWeb(process.stdout) as WritableStream<Uint8Array>,
     Readable.toWeb(process.stdin) as ReadableStream<Uint8Array>,
   )
-  conn = new AgentSideConnection(makeAgent, stream)
+  conn = new AgentSideConnection(makeAgent, observeOutbound(stream, announceInitialCommands))
 
   /**
    * Tear ALL live sessions down to quiescence (docs/defensive-patterns.md "dispose must reach
@@ -946,12 +1084,14 @@ export function apply(ctx: Context, config: AcpConfig): void {
     // installed yet) must observe this after its await and refuse to install a
     // post-teardown record. Set even when there are no live sessions.
     closed = true
+    pendingCommandSnapshots.clear()
     const recs = [...sessions.values()]
     sessions.clear()
     if (recs.length === 0) return Promise.resolve()
     quiescing = (async () => {
       await Promise.all(recs.map(async (rec) => {
         settlePrompt(rec, 'cancelled')
+        rec.commandAbort?.abort(new Error('ACP connection closed'))
         // Per-agent dispose (the AgentHandle disposer): unregister this agent,
         // stop its loop (sets disposed + aborts the in-flight step), await
         // quiescence (the loop exit + final flush), and remove its session — so
diff --git a/packages/ui/acp/tests/commands.spec.ts b/packages/ui/acp/tests/commands.spec.ts
new file mode 100644
index 0000000000..71aae1ea64
--- /dev/null
+++ b/packages/ui/acp/tests/commands.spec.ts
@@ -0,0 +1,276 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
+import { mkdtemp, rm } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import { makeBridgeHarness, textResponse, type BridgeHarness } from './harness.ts'
+
+function commandUpdates(harness: BridgeHarness, sessionId: string) {
+  return harness.sessionUpdates.filter(update => update.sessionId === sessionId
+    && update.update.sessionUpdate === 'available_commands_update')
+}
+
+function messageText(harness: BridgeHarness, sessionId: string): string {
+  return harness.sessionUpdates
+    .filter(update => update.sessionId === sessionId && update.update.sessionUpdate === 'agent_message_chunk')
+    .map(({ update }) => update.sessionUpdate === 'agent_message_chunk' && update.content.type === 'text'
+      ? update.content.text : '')
+    .join('')
+}
+
+describe('ACP plugin commands', () => {
+  let storageDir: string
+  let harness: BridgeHarness | undefined
+
+  beforeEach(async () => { storageDir = await mkdtemp(join(tmpdir(), 'acp-command-')) })
+  afterEach(async () => {
+    if (harness !== undefined) await harness.dispose()
+    harness = undefined
+    await rm(storageDir, { recursive: true, force: true })
+  })
+
+  it('publishes a full command snapshot after session creation and refreshes it dynamically', async () => {
+    harness = await makeBridgeHarness({ storageDir })
+    harness.ctx.commands.register({
+      name: 'inspect',
+      description: 'Inspect the session',
+      input: { hint: '<target>' },
+      handler: () => ({ kind: 'success' }),
+    })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+
+    await vi.waitFor(() => {
+      expect(commandUpdates(harness!, sessionId).at(-1)?.update).toEqual({
+        sessionUpdate: 'available_commands_update',
+        availableCommands: [{
+          name: 'inspect',
+          description: 'Inspect the session',
+          input: { hint: '<target>' },
+        }],
+      })
+    })
+
+    const dispose = harness.ctx.commands.register({
+      name: 'alpha',
+      description: 'Alpha command',
+      handler: () => ({ kind: 'success' }),
+    })
+    await vi.waitFor(() => {
+      expect(commandUpdates(harness!, sessionId).at(-1)?.update).toMatchObject({
+        availableCommands: [{ name: 'alpha' }, { name: 'inspect' }],
+      })
+    })
+    dispose()
+    await vi.waitFor(() => {
+      expect(commandUpdates(harness!, sessionId).at(-1)?.update).toMatchObject({
+        availableCommands: [{ name: 'inspect' }],
+      })
+    })
+  })
+
+  it('re-advertises commands after loading a persisted session', async () => {
+    const live = await makeBridgeHarness({ storageDir, script: [textResponse('persisted')] })
+    await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+    await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'persist this session' }] })
+    await live.dispose()
+
+    harness = await makeBridgeHarness({ storageDir })
+    harness.ctx.commands.register({
+      name: 'loaded', description: 'Loaded command', handler: () => ({ kind: 'success' }),
+    })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    await harness.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] })
+
+    expect(commandUpdates(harness, sessionId).at(-1)?.update).toMatchObject({
+      availableCommands: [{ name: 'loaded', description: 'Loaded command' }],
+    })
+  })
+
+  it('coalesces registry changes before a new session command snapshot is announced', async () => {
+    harness = await makeBridgeHarness({ storageDir })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+
+    harness.ctx.commands.register({
+      name: 'raced', description: 'Registered after the response', handler: () => ({ kind: 'success' }),
+    })
+
+    await vi.waitFor(() => {
+      expect(commandUpdates(harness!, sessionId)).toHaveLength(1)
+      expect(commandUpdates(harness!, sessionId)[0]?.update).toMatchObject({
+        availableCommands: [{ name: 'raced' }],
+      })
+    })
+  })
+
+  it('executes a known single-text command directly and never sends it to the model', async () => {
+    harness = await makeBridgeHarness({ storageDir })
+    const seen = vi.fn(() => ({ kind: 'success' as const, text: 'DIRECT RESULT' }))
+    harness.ctx.commands.register({ name: 'direct', description: 'Run directly', handler: seen })
+    harness.ctx.commands.register({
+      name: 'silent', description: 'Return no text', handler: () => ({ kind: 'success' }),
+    })
+    harness.ctx.commands.register({
+      name: 'empty', description: 'Return empty text', handler: () => ({ kind: 'success', text: '' }),
+    })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+
+    const response = await harness.client.prompt({
+      sessionId,
+      prompt: [{ type: 'text', text: '/direct  raw args ' }],
+    })
+
+    expect(response.stopReason).toBe('end_turn')
+    expect(seen).toHaveBeenCalledWith(expect.objectContaining({ rawInput: '  raw args ' }))
+    expect(messageText(harness, sessionId)).toContain('DIRECT RESULT')
+    const updatesAfterText = harness.sessionUpdates.length
+    await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: '/silent' }] })
+    await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: '/empty' }] })
+    expect(harness.sessionUpdates).toHaveLength(updatesAfterText)
+    expect(harness.adapter.requests).toHaveLength(0)
+    expect(harness.ctx.agents.get(SessionId(sessionId))?.session.events).toHaveLength(0)
+  })
+
+  it('renders expected command errors and rejects unknown slash commands without model fallback', async () => {
+    harness = await makeBridgeHarness({ storageDir })
+    harness.ctx.commands.register({
+      name: 'denied',
+      description: 'Deny directly',
+      handler: () => ({ kind: 'error', text: 'not allowed now' }),
+    })
+    harness.ctx.commands.register({
+      name: 'throws',
+      description: 'Throw an ordinary error',
+      handler: () => { throw new Error('handler exploded') },
+    })
+    harness.ctx.commands.register({
+      name: 'hostile',
+      description: 'Throw a hostile value',
+      handler: () => {
+        throw { toString(): string { throw new Error('coercion exploded') } }
+      },
+    })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+
+    await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: '/denied' }] }))
+      .resolves.toEqual({ stopReason: 'end_turn' })
+    await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: '/missing input' }] }))
+      .resolves.toEqual({ stopReason: 'end_turn' })
+    await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: '/throws' }] }))
+      .resolves.toEqual({ stopReason: 'end_turn' })
+    await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: '/hostile' }] }))
+      .resolves.toEqual({ stopReason: 'end_turn' })
+
+    expect(messageText(harness, sessionId)).toContain('Error: not allowed now')
+    expect(messageText(harness, sessionId)).toContain('Error: unknown command: /missing input')
+    expect(messageText(harness, sessionId)).toContain('Error: command failed: Error: handler exploded')
+    expect(messageText(harness, sessionId)).toContain('Error: command failed: <unrenderable thrown value>')
+    expect(harness.adapter.requests).toHaveLength(0)
+  })
+
+  it('flattens supported command prompt blocks without invoking the model', async () => {
+    harness = await makeBridgeHarness({ storageDir })
+    const command = vi.fn(() => ({ kind: 'success' as const, text: 'combined' }))
+    harness.ctx.commands.register({ name: 'direct', description: 'Direct', handler: command })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+
+    await expect(harness.client.prompt({
+      sessionId,
+      prompt: [
+        { type: 'text', text: '/direct' },
+        { type: 'text', text: ' extra' },
+        { type: 'resource_link', name: 'input', uri: 'file:///workspace/input.txt' },
+      ],
+    })).resolves.toEqual({ stopReason: 'end_turn' })
+    expect(command).toHaveBeenCalledWith(expect.objectContaining({
+      rawInput: ' extra\n[resource_link name="input" uri="file:///workspace/input.txt"]\n',
+    }))
+    expect(messageText(harness, sessionId)).toContain('combined')
+    expect(harness.adapter.requests).toHaveLength(0)
+  })
+
+  it('maps session cancellation to the in-flight command signal and isolates other sessions', async () => {
+    harness = await makeBridgeHarness({ storageDir })
+    let started!: () => void
+    const ready = new Promise<void>((resolve) => { started = resolve })
+    harness.ctx.commands.register({
+      name: 'wait',
+      description: 'Wait for cancellation',
+      handler: ({ signal }) => {
+        started()
+        return new Promise((resolve) => {
+          signal.addEventListener('abort', () => { resolve({ kind: 'error', text: 'late abort result' }) }, { once: true })
+        })
+      },
+    })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const a = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+    const b = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+
+    const waiting = harness.client.prompt({ sessionId: a.sessionId, prompt: [{ type: 'text', text: '/wait' }] })
+    await ready
+    await expect(harness.client.prompt({ sessionId: a.sessionId, prompt: [{ type: 'text', text: '/wait' }] }))
+      .rejects.toThrow(/already in flight/)
+    await harness.client.cancel({ sessionId: a.sessionId })
+
+    await expect(waiting).resolves.toEqual({ stopReason: 'cancelled' })
+    await expect(harness.client.prompt({ sessionId: b.sessionId, prompt: [{ type: 'text', text: '/missing' }] }))
+      .resolves.toEqual({ stopReason: 'end_turn' })
+    expect(messageText(harness, a.sessionId)).not.toContain('late abort result')
+  })
+
+  it('aborts an in-flight command when the ACP bridge is disposed', async () => {
+    harness = await makeBridgeHarness({ storageDir })
+    let started!: () => void
+    const ready = new Promise<void>((resolve) => { started = resolve })
+    let commandSignal: AbortSignal | undefined
+    harness.ctx.commands.register({
+      name: 'wait-dispose',
+      description: 'Wait for bridge disposal',
+      handler: ({ signal }) => {
+        commandSignal = signal
+        started()
+        return new Promise<never>(() => {})
+      },
+    })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+
+    const waiting = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: '/wait-dispose' }] })
+    await ready
+    await harness.acpFiber.dispose()
+
+    expect(commandSignal?.aborted).toBe(true)
+    await expect(waiting).resolves.toEqual({ stopReason: 'cancelled' })
+  })
+
+  it('resolves scoped command catalogs and execution independently per session', async () => {
+    harness = await makeBridgeHarness({ storageDir })
+    await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const a = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+    const b = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+    const agentA = harness.ctx.agents.get(SessionId(a.sessionId))
+    if (agentA === undefined) throw new Error('session A has no agent')
+    await agentA.ctx.inject(['commands'], (commandCtx) => {
+      commandCtx.commands.register({
+        name: 'private', description: 'Only session A',
+        handler: () => ({ kind: 'success', text: 'A ONLY' }),
+      })
+    })
+
+    await vi.waitFor(() => {
+      expect(commandUpdates(harness!, a.sessionId).at(-1)?.update).toMatchObject({ availableCommands: [{ name: 'private' }] })
+    })
+    expect(commandUpdates(harness, b.sessionId).at(-1)?.update).toMatchObject({ availableCommands: [] })
+    await harness.client.prompt({ sessionId: a.sessionId, prompt: [{ type: 'text', text: '/private' }] })
+    await harness.client.prompt({ sessionId: b.sessionId, prompt: [{ type: 'text', text: '/private' }] })
+    expect(messageText(harness, a.sessionId)).toContain('A ONLY')
+    expect(messageText(harness, b.sessionId)).toContain('unknown command')
+  })
+})
diff --git a/packages/ui/acp/tests/edges.spec.ts b/packages/ui/acp/tests/edges.spec.ts
index 35dd54a634..fdbaf241e6 100644
--- a/packages/ui/acp/tests/edges.spec.ts
+++ b/packages/ui/acp/tests/edges.spec.ts
@@ -1,4 +1,4 @@
-import { afterEach, beforeEach, describe, expect, it } from 'vitest'
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
 import { mkdtemp, rm } from 'node:fs/promises'
 import { tmpdir } from 'node:os'
 import { join } from 'node:path'
@@ -24,6 +24,9 @@ describe('acp bridge — demux & config edges', () => {
     harness = await makeBridgeHarness({ storageDir, script: [textResponse('foreign')] })
     await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
     await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+    await vi.waitFor(() => {
+      expect(harness!.updates.some(update => update.sessionUpdate === 'available_commands_update')).toBe(true)
+    })
     const before = harness.updates.length
 
     const { agent: foreign } = await harness.ctx.agents.create({ sessionId: SessionId('foreign-session'), agentOptions: { provider: 'mock', model: 'mock' } })
diff --git a/packages/ui/acp/tests/harness.ts b/packages/ui/acp/tests/harness.ts
index b8b47b80d5..b728ee5bfc 100644
--- a/packages/ui/acp/tests/harness.ts
+++ b/packages/ui/acp/tests/harness.ts
@@ -9,6 +9,7 @@ import { CallId, type GenerateOptions, type LlmModelInfo, type LlmProviderInfo,
 import { LlmAdapter } from '@deepseek-ai/dsh-llm'
 import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
+import CommandService from '@deepseek-ai/dsh-commands'
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
 import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
@@ -210,6 +211,7 @@ export async function makeBridgeHarness(options: {
   await mountAgentLoopTestDependencies(ctx, {
     systemPrompt: { persona: options.persona ?? '' },
   })
+  await ctx.plugin(CommandService)
   await ctx.plugin(AgentLoop, { agents: [] })
   await ctx.plugin(SessionPersistenceJsonl, { root: options.storageDir })
   await ctx.plugin(UserInteractionService)
diff --git a/packages/ui/acp/tsconfig.json b/packages/ui/acp/tsconfig.json
index de4ccd3650..91e1272212 100644
--- a/packages/ui/acp/tsconfig.json
+++ b/packages/ui/acp/tsconfig.json
@@ -32,6 +32,9 @@
     {
       "path": "../../core/tools"
     },
+    {
+      "path": "../commands"
+    },
     {
       "path": "../user-interaction"
     },
diff --git a/packages/ui/commands/README.md b/packages/ui/commands/README.md
new file mode 100644
index 0000000000..6e0efa458b
--- /dev/null
+++ b/packages/ui/commands/README.md
@@ -0,0 +1,39 @@
+# @deepseek-ai/dsh-commands
+
+Plugin-owned human-command registry shared by the TUI and ACP adapters. The [plugin command registration Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md) owns the boundary and protocol mapping.
+
+## Service contract
+
+`ctx.commands.register(definition)` registers one lowercase command name, description, optional ACP-compatible unstructured-input hint, and abortable handler. A registered command is available to every composed command adapter; a plugin that is incompatible with a deployment does not register there. A plain-context registration is global. A command-producing plugin mounted beneath `agent.ctx` declares its own `commands` injection and creates an exact agent-scoped definition; it shadows a global definition with the same name. This child-injection shape preserves the agent scope without making the core agent loop depend on a UI service. Duplicate names within one layer fail during registration. Every disposer is the exact Cordis effect disposer, and registration or removal notifies every `commands/change` observer so live adapters can refresh discovery; observer failures are logged and cannot veto the registry mutation or starve later observers.
+
+`list(agent)` returns immutable, name-sorted descriptors after scoped shadowing. `find(agent, name)` returns the corresponding definition. `execute(agent, line, signal)` uses `parseCommand()` and runs only a known command, returning `undefined` for invalid syntax or unknown names.
+
+`parseCommand()` recognizes a slash at byte zero, a lowercase name containing letters, digits, `_`, or `-`, and either end-of-input or whitespace. It returns every byte after the name as `rawInput`, including separator whitespace; consumers own their command-specific grammar and may normalize only what that grammar permits.
+
+Handlers return `success` or `error` plus optional UI text. Results are rendered directly by the adapter and never enter model history. The registry races handler completion against the supplied abort signal, but an uncooperative handler may continue its own external side effects after the caller stops awaiting it.
+
+## Composition
+
+The terminal and ACP app bundles mount this service with their consuming front door; the UI-less agent spine does not. Custom compositions that use `dsh-tui`, `dsh-acp`, or a command producer mount `@deepseek-ai/dsh-commands` explicitly.
+
+## Model Experience
+
+### Direct human commands
+
+#### What the model sees
+
+Nothing. Known slash commands execute in the UI command plane, and their `CommandResult` text is not submitted as a user message. Unknown slash-command input is rejected by shipped adapters instead of becoming a model prompt.
+
+#### Token effect
+
+Command discovery, execution, and UI output add no model tokens. A command plugin may separately mutate a model-visible domain through that domain's durable APIs.
+
+#### KV Cache effect
+
+Registry metadata, command input, and direct output never enter a model request and do not affect its cache. A mutated domain owns any later cache effect.
+
+## Known Limitations and Deferred Work
+
+- **Only unstructured text input** — the descriptor intentionally matches ACP's current unstructured command input; forms, completion schemas, and typed arguments remain command-owned parsing concerns.
+- **No persisted command output** — adapters display results live, but the generic registry does not add them to the session log or reconstruct them after reconnect.
+- **Cooperative side-effect cancellation** — dispatch stops awaiting on abort; handlers must honor the signal to stop work that has already escaped into external systems.
diff --git a/packages/ui/commands/package.json b/packages/ui/commands/package.json
new file mode 100644
index 0000000000..ef7e54e1c1
--- /dev/null
+++ b/packages/ui/commands/package.json
@@ -0,0 +1,35 @@
+{
+  "name": "@deepseek-ai/dsh-commands",
+  "description": "Plugin-owned human command registry for DeepSeek Harness UI surfaces",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "@deepseek-ai/dsh-agent": "^0.0.1",
+    "@deepseek-ai/dsh-scope": "^0.0.1",
+    "cordis": "^4.0.0-rc.7"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-scope": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "cordis": "^4.0.0-rc.7"
+  }
+}
diff --git a/packages/ui/commands/src/index.ts b/packages/ui/commands/src/index.ts
new file mode 100644
index 0000000000..16e665e71f
--- /dev/null
+++ b/packages/ui/commands/src/index.ts
@@ -0,0 +1,321 @@
+/**
+ * Plugin-owned human-command registry shared by interactive UI adapters.
+ * @module @deepseek-ai/dsh-commands
+ */
+
+import { Context, Service } from 'cordis'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+import { scopeOf } from '@deepseek-ai/dsh-scope'
+import type { ScopeKey } from '@deepseek-ai/dsh-scope'
+
+export const name = 'commands'
+
+const COMMAND_NAME = /^[a-z][a-z0-9_-]*$/u
+
+/** Immutable command input metadata compatible with ACP unstructured input. */
+export interface CommandInputDescriptor {
+  /** Placeholder shown before the user supplies free-form input. */
+  readonly hint: string
+}
+
+/** Invocation passed to one registered command handler. */
+export interface CommandInvocation {
+  /** Exact agent whose human-facing surface received the command. */
+  readonly agent: Agent
+  /** Exact text following the registered command name, including separator whitespace. */
+  readonly rawInput: string
+  /** Cancellation signal owned by the dispatching UI request. */
+  readonly signal: AbortSignal
+}
+
+/** Expected command outcome rendered directly by the dispatching UI. */
+export type CommandResult =
+  | { readonly kind: 'success'; readonly text?: string }
+  | { readonly kind: 'error'; readonly text: string }
+
+/** Plugin-owned command registration. */
+export interface CommandDefinition {
+  /** Lowercase command name without the leading slash. */
+  readonly name: string
+  /** Human-readable summary used in discovery UI. */
+  readonly description: string
+  /** Optional free-form input hint advertised to capable clients. */
+  readonly input?: CommandInputDescriptor
+  /** Execute against the receiving agent without sending the command to the model. */
+  readonly handler: (invocation: CommandInvocation) => CommandResult | Promise<CommandResult>
+}
+
+/** Handler-free immutable command view returned to UI adapters. */
+export interface CommandDescriptor {
+  /** Lowercase command name without the leading slash. */
+  readonly name: string
+  /** Human-readable summary used in discovery UI. */
+  readonly description: string
+  /** Optional free-form input hint advertised to capable clients. */
+  readonly input?: CommandInputDescriptor
+}
+
+/** Syntactically valid slash command before registry resolution. */
+export interface ParsedCommand {
+  /** Lowercase command name without the leading slash. */
+  readonly name: string
+  /** Exact text following the command name. */
+  readonly rawInput: string
+}
+
+interface RegisteredCommand {
+  readonly definition: CommandDefinition
+  readonly descriptor: CommandDescriptor
+}
+
+declare module 'cordis' {
+  interface Context {
+    commands: CommandService
+  }
+
+  interface Events {
+    /**
+     * A command was registered or unregistered. This is an unfiltered registry
+     * notification because a global or scoped change may affect any UI view.
+     * Observer failures are contained and cannot veto the registry mutation.
+     * @mode emit
+     */
+    'commands/change'(): void
+  }
+}
+
+/**
+ * Parse an exact slash command without normalizing its trailing input.
+ *
+ * @param line - Complete candidate command line.
+ * @returns The parsed command, or `undefined` when the line is not a command.
+ */
+export function parseCommand(line: string): ParsedCommand | undefined {
+  const match = /^\/([a-z][a-z0-9_-]*)(?=$|[\t\n\r ])/u.exec(line)
+  if (match === null) return undefined
+  const name = match[1]
+  /* v8 ignore next -- the first capture is required whenever the regular expression matches */
+  if (name === undefined) return undefined
+  return Object.freeze({ name, rawInput: line.slice(match[0].length) })
+}
+
+/** Convert arbitrary abort reasons to one stable rejected Error. */
+function abortError(signal: AbortSignal): Error {
+  if (signal.reason instanceof Error) return signal.reason
+  return new Error(typeof signal.reason === 'string' ? signal.reason : 'command aborted')
+}
+
+/** Render arbitrary thrown values without trusting their string coercion. */
+function renderThrown(value: unknown): string {
+  try {
+    return String(value)
+  } catch {
+    return '<unrenderable thrown value>'
+  }
+}
+
+/** Stop awaiting an uncooperative handler once its owning UI request aborts. */
+function withAbort<T>(promise: Promise<T>, signal: AbortSignal): Promise<T> {
+  if (signal.aborted) return Promise.reject(abortError(signal))
+  return new Promise<T>((resolve, reject) => {
+    const onAbort = (): void => {
+      signal.removeEventListener('abort', onAbort)
+      reject(abortError(signal))
+    }
+    signal.addEventListener('abort', onAbort, { once: true })
+    promise.then(
+      (value) => {
+        signal.removeEventListener('abort', onAbort)
+        resolve(value)
+      },
+      (error: unknown) => {
+        signal.removeEventListener('abort', onAbort)
+        reject(error instanceof Error
+          ? error
+          : new Error(`command handler rejected with a non-Error value: ${renderThrown(error)}`, { cause: error }))
+      },
+    )
+  })
+}
+
+/** Reject invalid command metadata before it can reach a UI protocol. */
+function normalizeDefinition(definition: CommandDefinition): RegisteredCommand {
+  if (!COMMAND_NAME.test(definition.name)) {
+    throw new TypeError(`command name "${definition.name}" must match ${String(COMMAND_NAME)}`)
+  }
+  if (typeof definition.description !== 'string') {
+    throw new TypeError(`command "${definition.name}" description must be a string`)
+  }
+  if (definition.description.trim().length === 0) {
+    throw new TypeError(`command "${definition.name}" description must not be empty`)
+  }
+  if (typeof definition.handler !== 'function') {
+    throw new TypeError(`command "${definition.name}" handler must be a function`)
+  }
+  const rawInput: unknown = definition.input
+  let input: CommandInputDescriptor | undefined
+  if (rawInput !== undefined) {
+    if (typeof rawInput !== 'object' || rawInput === null || !('hint' in rawInput)
+      || typeof rawInput.hint !== 'string') {
+      throw new TypeError(`command "${definition.name}" input hint must be a string`)
+    }
+    if (rawInput.hint.trim().length === 0) {
+      throw new TypeError(`command "${definition.name}" input hint must not be empty`)
+    }
+    input = Object.freeze({ hint: rawInput.hint })
+  }
+  const normalized = Object.freeze({
+    name: definition.name,
+    description: definition.description,
+    ...input === undefined ? {} : { input },
+    handler: definition.handler,
+  })
+  const descriptor = Object.freeze({
+    name: normalized.name,
+    description: normalized.description,
+    ...normalized.input === undefined ? {} : { input: normalized.input },
+  })
+  return { definition: normalized, descriptor }
+}
+
+/** Validate and detach an untrusted handler result at the registry boundary. */
+function normalizeResult(command: string, value: unknown): CommandResult {
+  if (typeof value !== 'object' || value === null || !('kind' in value)) {
+    throw new TypeError(`command "${command}" handler must return a CommandResult`)
+  }
+  const result = value as { kind?: unknown; text?: unknown }
+  if (result.kind === 'success') {
+    if (result.text !== undefined && typeof result.text !== 'string') {
+      throw new TypeError(`command "${command}" success text must be a string when supplied`)
+    }
+    return Object.freeze(result.text === undefined ? { kind: 'success' } : { kind: 'success', text: result.text })
+  }
+  if (result.kind === 'error') {
+    if (typeof result.text !== 'string' || result.text.trim().length === 0) {
+      throw new TypeError(`command "${command}" error text must be a non-empty string`)
+    }
+    return Object.freeze({ kind: 'error', text: result.text })
+  }
+  throw new TypeError(`command "${command}" returned unknown result kind "${String(result.kind)}"`)
+}
+
+/**
+ * Human-command registry. Plain-context definitions are global; definitions
+ * registered through a command-injected child of an agent context shadow
+ * globals for that agent.
+ */
+export class CommandService extends Service {
+  private readonly global = new Map<string, RegisteredCommand>()
+  private readonly scoped = new Map<ScopeKey, Map<string, RegisteredCommand>>()
+
+  constructor(ctx: Context) {
+    super(ctx, 'commands')
+  }
+
+  /**
+   * Register a global or calling-agent-scoped command.
+   * @param definition - discovery metadata and direct UI handler.
+   * @returns the exact effect disposer that unregisters this definition.
+   */
+  register(definition: CommandDefinition): () => void {
+    const scope = scopeOf(this.ctx)
+    const registered = normalizeDefinition(definition)
+    const dispose = this.ctx.effect(function* (this: CommandService) {
+      const layer = scope === undefined ? this.global : this.layerFor(scope)
+      if (layer.has(registered.definition.name)) {
+        throw new Error(scope === undefined
+          ? `command "${registered.definition.name}" is already registered (for a per-agent variant, mount a command-injected plugin under that agent's \`agent.ctx\`)`
+          : `command "${registered.definition.name}" is already registered in this scope`)
+      }
+      layer.set(registered.definition.name, registered)
+      yield () => {
+        layer.delete(registered.definition.name)
+        if (scope !== undefined && layer.size === 0) this.scoped.delete(scope)
+        this.notifyChange()
+      }
+      this.notifyChange()
+    }.bind(this), 'commands.register()')
+    // eslint-disable-next-line @typescript-eslint/no-misused-promises -- exact synchronous disposer preserves composite teardown order
+    return dispose
+  }
+
+  /**
+   * List the effective immutable command descriptors for one agent.
+   * @param agent - exact receiving agent and scoped-layer key.
+   * @returns name-sorted descriptors after scoped shadowing.
+   */
+  list(agent: Agent): readonly CommandDescriptor[] {
+    return Object.freeze([...this.view(agent).values()]
+      .map(command => command.descriptor)
+      // Names are unique in the effective view, so equality is impossible.
+      .sort((left, right) => left.name < right.name ? -1 : 1))
+  }
+
+  /**
+   * Resolve one effective command definition.
+   * @param agent - exact receiving agent and scoped-layer key.
+   * @param name - command name without a slash.
+   * @returns the scoped shadow or global definition.
+   */
+  find(agent: Agent, name: string): CommandDefinition | undefined {
+    return this.view(agent).get(name)?.definition
+  }
+
+  /**
+   * Parse and execute a known command without sending it to the model.
+   * @param agent - exact receiving agent.
+   * @param line - complete slash-command line.
+   * @param signal - cancellation signal owned by the UI request.
+   * @returns a detached result, or `undefined` when syntax or name does not resolve.
+   */
+  async execute(
+    agent: Agent,
+    line: string,
+    signal: AbortSignal,
+  ): Promise<CommandResult | undefined> {
+    const parsed = parseCommand(line)
+    if (parsed === undefined) return undefined
+    const command = this.view(agent).get(parsed.name)
+    if (command === undefined) return undefined
+    if (signal.aborted) throw abortError(signal)
+    const invocation = Object.freeze({ agent, rawInput: parsed.rawInput, signal })
+    const output = command.definition.handler(invocation)
+    return normalizeResult(parsed.name, await withAbort(Promise.resolve(output), signal))
+  }
+
+  /** Resolve global definitions followed by exact scoped shadows. */
+  private view(agent: Agent): Map<string, RegisteredCommand> {
+    const visible = new Map(this.global)
+    for (const [name, command] of this.scoped.get(agent) ?? []) visible.set(name, command)
+    return visible
+  }
+
+  /** Create the registration layer for one agent scope on demand. */
+  private layerFor(scope: ScopeKey): Map<string, RegisteredCommand> {
+    let layer = this.scoped.get(scope)
+    if (layer === undefined) {
+      layer = new Map()
+      this.scoped.set(scope, layer)
+    }
+    return layer
+  }
+
+  /** Notify every registry observer without making UI refresh load-bearing. */
+  private notifyChange(): void {
+    // Cordis emit uses Array.map: one synchronous throw starves later listeners,
+    // and returned promises are discarded. Registry notifications are
+    // non-vetoing, so contain each callback independently.
+    for (const callback of this.ctx.events.dispatch('emit', ['commands/change'])) {
+      try {
+        const returned: unknown = callback()
+        void Promise.resolve(returned).catch((error: unknown) => {
+          this.ctx.logger.warn(`commands/change listener rejected: ${renderThrown(error)}`)
+        })
+      } catch (error: unknown) {
+        this.ctx.logger.warn(`commands/change listener threw: ${renderThrown(error)}`)
+      }
+    }
+  }
+}
+
+export default CommandService
diff --git a/packages/ui/commands/tests/commands.spec.ts b/packages/ui/commands/tests/commands.spec.ts
new file mode 100644
index 0000000000..839ccb0297
--- /dev/null
+++ b/packages/ui/commands/tests/commands.spec.ts
@@ -0,0 +1,294 @@
+import { describe, expect, it, vi } from 'vitest'
+import { Context } from 'cordis'
+import { createScope } from '@deepseek-ai/dsh-scope'
+import type { Scope } from '@deepseek-ai/dsh-scope'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+import type { SessionId } from '@deepseek-ai/dsh-session'
+import CommandService, { parseCommand, type CommandDefinition } from '@deepseek-ai/dsh-commands'
+
+function command(name: string, text = `ran:${name}`): CommandDefinition {
+  return {
+    name,
+    description: `command ${name}`,
+    handler: () => ({ kind: 'success', text }),
+  }
+}
+
+async function mount(): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(CommandService)
+  return ctx
+}
+
+/** Mint a scope whose key is sufficient for registry lookup and invocation. */
+async function mintAgentScope(ctx: Context, name: string): Promise<{ scope: Scope; agent: Agent }> {
+  const agent = { id: name as SessionId } as Agent
+  let scope!: Scope
+  await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, agent) }, { inject: ['commands'] }))
+  return { scope, agent }
+}
+
+describe('parseCommand()', () => {
+  it.each([
+    ['/goal', { name: 'goal', rawInput: '' }],
+    ['/goal create the thing', { name: 'goal', rawInput: ' create the thing' }],
+    ['/goal\ncreate the thing', { name: 'goal', rawInput: '\ncreate the thing' }],
+    ['/goal_name-2\t x ', { name: 'goal_name-2', rawInput: '\t x ' }],
+  ] as const)('parses %j without normalizing trailing input', (line, expected) => {
+    expect(parseCommand(line)).toEqual(expected)
+  })
+
+  it.each(['goal', ' /goal', '/', '/Goal', '/goal/path', '/goal🔥'])('rejects non-command boundary %j', (line) => {
+    expect(parseCommand(line)).toBeUndefined()
+  })
+})
+
+describe('CommandService', () => {
+  it('lists immutable global descriptors with input metadata', async () => {
+    const ctx = await mount()
+    const { agent } = await mintAgentScope(ctx, 'a')
+    const definition: CommandDefinition = {
+      name: 'inspect',
+      description: 'Inspect state',
+      input: { hint: '<target>' },
+      handler: () => ({ kind: 'success' }),
+    }
+    ctx.commands.register(definition)
+
+    const listed = ctx.commands.list(agent)
+    expect(listed).toEqual([{
+      name: 'inspect',
+      description: 'Inspect state',
+      input: { hint: '<target>' },
+    }])
+    expect(Object.isFrozen(listed)).toBe(true)
+    expect(Object.isFrozen(listed[0])).toBe(true)
+    expect(Object.isFrozen(listed[0]?.input)).toBe(true)
+    expect(ctx.commands.find(agent, 'inspect')).toMatchObject({ name: 'inspect' })
+    expect(ctx.commands.find(agent, 'missing')).toBeUndefined()
+  })
+
+  it('sorts distinct effective command names', async () => {
+    const ctx = await mount()
+    const { agent } = await mintAgentScope(ctx, 'a')
+    ctx.commands.register(command('zeta'))
+    ctx.commands.register(command('alpha'))
+    ctx.commands.register(command('middle'))
+    expect(ctx.commands.list(agent).map(item => item.name)).toEqual(['alpha', 'middle', 'zeta'])
+  })
+
+  it('uses agent-scoped shadows and removes them with their scope', async () => {
+    const ctx = await mount()
+    const { scope, agent } = await mintAgentScope(ctx, 'a')
+    const other = { id: 'other' as SessionId } as Agent
+    ctx.commands.register(command('shared', 'global'))
+    scope.ctx.commands.register(command('shared', 'scoped'))
+
+    expect(ctx.commands.list(agent).map(item => item.name)).toEqual(['shared'])
+    expect(ctx.commands.find(agent, 'shared')?.handler).toBeDefined()
+    expect(ctx.commands.list(other).map(item => item.name)).toEqual(['shared'])
+    expect(await ctx.commands.execute(agent, '/shared', new AbortController().signal))
+      .toEqual({ kind: 'success', text: 'scoped' })
+
+    await scope.dispose()
+    expect((await ctx.commands.execute(agent, '/shared', new AbortController().signal))?.text).toBe('global')
+  })
+
+  it('rejects duplicates within one layer while allowing a scoped shadow', async () => {
+    const ctx = await mount()
+    const { scope } = await mintAgentScope(ctx, 'a')
+    ctx.commands.register(command('same'))
+    expect(() => ctx.commands.register(command('same'))).toThrow(/agent\.ctx/)
+    scope.ctx.commands.register(command('same'))
+    expect(() => scope.ctx.commands.register(command('same'))).toThrow(/already registered in this scope/)
+  })
+
+  it('notifies on registration and disposal while containing broken observers', async () => {
+    const ctx = await mount()
+    const changed = vi.fn()
+    ctx.on('commands/change', changed)
+    const dispose = ctx.commands.register(command('live'))
+    dispose()
+    dispose()
+    expect(changed).toHaveBeenCalledTimes(2)
+
+    const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
+    ctx.on('commands/change', () => { throw new Error('observer threw') })
+    // eslint-disable-next-line @typescript-eslint/no-misused-promises -- exercises rejected-listener containment
+    ctx.on('commands/change', () => Promise.reject(new Error('observer rejected')))
+    const afterFailures = vi.fn()
+    ctx.on('commands/change', afterFailures)
+    const removeContained = ctx.commands.register(command('contained'))
+    const { agent } = await mintAgentScope(ctx, 'a')
+    expect(ctx.commands.find(agent, 'contained')).toBeDefined()
+    expect(afterFailures).toHaveBeenCalledTimes(1)
+    await vi.waitFor(() => {
+      expect(warn).toHaveBeenCalledWith('commands/change listener threw: Error: observer threw')
+      expect(warn).toHaveBeenCalledWith('commands/change listener rejected: Error: observer rejected')
+    })
+    removeContained()
+    expect(ctx.commands.find(agent, 'contained')).toBeUndefined()
+    expect(afterFailures).toHaveBeenCalledTimes(2)
+  })
+
+  it('rejects non-string descriptions and input hints with boundary diagnostics', async () => {
+    const ctx = await mount()
+    expect(() => ctx.commands.register({
+      ...command('description-type'),
+      description: undefined,
+    } as unknown as CommandDefinition)).toThrow('command "description-type" description must be a string')
+    expect(() => ctx.commands.register({
+      ...command('hint-type'),
+      input: { hint: 42 },
+    } as unknown as CommandDefinition)).toThrow('command "hint-type" input hint must be a string')
+    expect(() => ctx.commands.register({
+      ...command('input-type'),
+      input: null,
+    } as unknown as CommandDefinition)).toThrow('command "input-type" input hint must be a string')
+  })
+
+  it('passes exact invocation context and detaches valid handler results', async () => {
+    const ctx = await mount()
+    const { agent } = await mintAgentScope(ctx, 'a')
+    const seen = vi.fn(() => ({ kind: 'success' as const, text: 'ok' }))
+    ctx.commands.register({ name: 'run', description: 'Run it', handler: seen })
+    const controller = new AbortController()
+
+    const result = await ctx.commands.execute(agent, '/run  untouched ', controller.signal)
+
+    expect(result).toEqual({ kind: 'success', text: 'ok' })
+    expect(Object.isFrozen(result)).toBe(true)
+    expect(seen).toHaveBeenCalledWith(expect.objectContaining({
+      agent,
+      rawInput: '  untouched ',
+      signal: controller.signal,
+    }))
+    await expect(ctx.commands.execute(agent, 'run', controller.signal)).resolves.toBeUndefined()
+    await expect(ctx.commands.execute(agent, '/missing', controller.signal)).resolves.toBeUndefined()
+  })
+
+  it('stops awaiting an aborted handler and handles an already-aborted signal', async () => {
+    const ctx = await mount()
+    const { agent } = await mintAgentScope(ctx, 'a')
+    let release!: (result: { kind: 'success'; text: string }) => void
+    ctx.commands.register({
+      name: 'wait',
+      description: 'Wait',
+      handler: () => new Promise((resolve) => { release = resolve }),
+    })
+    const running = new AbortController()
+    const promise = ctx.commands.execute(agent, '/wait', running.signal)
+    running.abort('operator cancelled command')
+    await expect(promise).rejects.toThrow('operator cancelled command')
+    release({ kind: 'success', text: 'late' })
+
+    const already = new AbortController()
+    already.abort(new Error('already gone'))
+    await expect(ctx.commands.execute(agent, '/wait', already.signal)).rejects.toThrow('already gone')
+
+    const defaultReason = new AbortController()
+    defaultReason.abort({ source: 'test' })
+    await expect(ctx.commands.execute(agent, '/wait', defaultReason.signal)).rejects.toThrow('command aborted')
+  })
+
+  it('propagates an asynchronously rejected handler', async () => {
+    const ctx = await mount()
+    const { agent } = await mintAgentScope(ctx, 'a')
+    ctx.commands.register({
+      name: 'reject',
+      description: 'Reject',
+      handler: () => Promise.reject(new Error('handler rejected')),
+    })
+    await expect(ctx.commands.execute(agent, '/reject', new AbortController().signal))
+      .rejects.toThrow('handler rejected')
+
+    ctx.commands.register({
+      name: 'reject-value',
+      description: 'Reject a non-Error value',
+      // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors -- exercise untyped plugin normalization
+      handler: () => Promise.reject('not an Error'),
+    })
+    await expect(ctx.commands.execute(agent, '/reject-value', new AbortController().signal))
+      .rejects.toThrow('command handler rejected with a non-Error value: not an Error')
+
+    const hostile = { toString(): string { throw new Error('cannot render') } }
+    ctx.commands.register({
+      name: 'reject-hostile',
+      description: 'Reject an unrenderable value',
+      // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors -- exercise hostile plugin normalization
+      handler: () => Promise.reject(hostile),
+    })
+    await expect(ctx.commands.execute(agent, '/reject-hostile', new AbortController().signal))
+      .rejects.toMatchObject({
+        message: 'command handler rejected with a non-Error value: <unrenderable thrown value>',
+        cause: hostile,
+      })
+  })
+
+  it('observes an abort triggered synchronously inside the handler', async () => {
+    const ctx = await mount()
+    const { agent } = await mintAgentScope(ctx, 'a')
+    const controller = new AbortController()
+    ctx.commands.register({
+      name: 'self-abort',
+      description: 'Abort before returning',
+      handler: () => {
+        controller.abort('aborted in handler')
+        return { kind: 'success' }
+      },
+    })
+    await expect(ctx.commands.execute(agent, '/self-abort', controller.signal))
+      .rejects.toThrow('aborted in handler')
+  })
+
+  it('returns a detached expected-error result', async () => {
+    const ctx = await mount()
+    const { agent } = await mintAgentScope(ctx, 'a')
+    ctx.commands.register({
+      name: 'denied',
+      description: 'Denied',
+      handler: () => ({ kind: 'error', text: 'not now' }),
+    })
+    const result = await ctx.commands.execute(agent, '/denied', new AbortController().signal)
+    expect(result).toEqual({ kind: 'error', text: 'not now' })
+    expect(Object.isFrozen(result)).toBe(true)
+
+    ctx.commands.register({
+      name: 'silent',
+      description: 'No output',
+      handler: () => ({ kind: 'success' }),
+    })
+    const silent = await ctx.commands.execute(agent, '/silent', new AbortController().signal)
+    expect(silent).toEqual({ kind: 'success' })
+    expect(Object.isFrozen(silent)).toBe(true)
+  })
+
+  it.each([
+    [{ ...command('Bad') }, /command name/],
+    [{ ...command('empty-description'), description: ' ' }, /description/],
+    [{ ...command('empty-hint'), input: { hint: '' } }, /input hint/],
+    [{ ...command('bad-handler'), handler: undefined }, /handler/],
+  ] as const)('rejects invalid definition %#', async (definition, expected) => {
+    const ctx = await mount()
+    expect(() => ctx.commands.register(definition as unknown as CommandDefinition)).toThrow(expected)
+  })
+
+  it.each([
+    [undefined, /CommandResult/],
+    [null, /CommandResult/],
+    [{}, /CommandResult/],
+    [{ kind: 'success', text: 1 }, /success text/],
+    [{ kind: 'error', text: '' }, /error text/],
+    [{ kind: 'error', text: 1 }, /error text/],
+    [{ kind: 'future', text: 'x' }, /unknown result kind/],
+  ] as const)('rejects malformed handler result %j', async (output, expected) => {
+    const ctx = await mount()
+    const { agent } = await mintAgentScope(ctx, 'a')
+    ctx.commands.register({
+      name: 'broken',
+      description: 'Broken',
+      handler: () => output as never,
+    })
+    await expect(ctx.commands.execute(agent, '/broken', new AbortController().signal)).rejects.toThrow(expected)
+  })
+})
diff --git a/packages/ui/commands/tsconfig.json b/packages/ui/commands/tsconfig.json
new file mode 100644
index 0000000000..478cc26479
--- /dev/null
+++ b/packages/ui/commands/tsconfig.json
@@ -0,0 +1,24 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../core/agent"
+    },
+    {
+      "path": "../../core/scope"
+    }
+  ]
+}
diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md
index dd6553d09f..550652c22d 100644
--- a/packages/ui/tui/README.md
+++ b/packages/ui/tui/README.md
@@ -6,13 +6,13 @@ The implemented [TUI feature Agent Note](../../../.agents/notes/implemented/feat
 
 Interactive terminals on macOS, Linux, and Windows are supported. Windows uses pi-tui's native console VT-input handling, and the [Windows support Agent Note](../../../.agents/notes/implemented/feature/2026-07-20-windows-tui-support.md) owns the platform decision and ConPTY process verification.
 
-This package owns interactive terminal presentation and input only. It injects `agents`, `tools`, and `userInteraction`, then drives an agent created or resumed by app or developer code. Agent lifecycle, persistence, and the model-facing [`ask_user_question`](../tool-ask-user/README.md) tool remain separate composition entries.
+This package owns interactive terminal presentation and input only. It injects `agents`, [`commands`](../commands/README.md), `tools`, and `userInteraction`, then drives an agent created or resumed by app or developer code. Agent lifecycle, persistence, and the model-facing [`ask_user_question`](../tool-ask-user/README.md) tool remain separate composition entries.
 
 The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions as keyboard-driven overlays. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Surface replacement events rebuild the transcript so compacted history does not reappear.
 
 Before model output, session events, tool presenters, questions, configuration, or diagnostics reach pi-tui's ANSI-aware renderers or the terminal title, the TUI renders C0 and C1 controls other than line feeds as visible `\xNN` text. Those sources cannot add terminal control sequences; the TUI and pi-tui retain ownership of terminal rendering and styling.
 
-While the agent is running, editor submissions call `agent.steer()`; otherwise they call `agent.send()`. Ctrl+C or Escape cancels a running turn. Ctrl+O expands tool cards, Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle. `/help`, `/clear`, `/cancel`, `/reasoning`, `/tools`, `/redraw`, and `/exit` provide the same actions without key chords.
+While the agent is running, ordinary editor submissions call `agent.steer()`; otherwise they call `agent.send()`. A slash at the start of the submitted line enters `ctx.commands` instead: known commands execute directly, unknown commands produce a warning, and neither path reaches the model. The TUI registers `/help`, `/clear`, `/cancel`, `/reasoning`, `/tools`, `/redraw`, and `/exit` as agent-scoped definitions; every other effective command joins autocomplete and `/help` dynamically. Ctrl+C or Escape cancels a running turn. Ctrl+O expands tool cards, Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle.
 
 ## Config
 
@@ -39,7 +39,7 @@ While the agent is running, editor submissions call `agent.steer()`; otherwise t
     maxToolOutputLines: 12
 ```
 
-Startup fails before mounting when either process stream is not a TTY. The composing app must mount the TUI before its config-created agent so the front door can observe `agent-loop/config-start-failed`; a matching exact-session failure is written before fullscreen mode starts and exits with status 1 instead of leaving a blank terminal. Disposal stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR.
+Startup fails before mounting when either process stream is not a TTY. The composing app must mount the TUI before its config-created agent so the front door can observe `agent-loop/config-start-failed`; a matching exact-session failure is written before fullscreen mode starts and exits with status 1 instead of leaving a blank terminal. Disposal aborts running commands, removes the TUI definitions, stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR.
 
 ## Color
 
@@ -51,7 +51,7 @@ The palette uses the standard 16-color ANSI foregrounds and SGR attributes, whic
 
 #### What the model sees
 
-Each non-empty editor submission becomes one text block, sent with `agent.send()` while the target agent is idle and `agent.steer()` while it is running. Slash commands and keybindings are TUI-only.
+Each non-empty ordinary editor submission becomes one text block, sent with `agent.send()` while the target agent is idle and `agent.steer()` while it is running. Slash commands and keybindings are TUI-only; command results remain terminal notices.
 
 #### Token effect
 
diff --git a/packages/ui/tui/package.json b/packages/ui/tui/package.json
index 5e7c8d060c..136acde7bc 100644
--- a/packages/ui/tui/package.json
+++ b/packages/ui/tui/package.json
@@ -24,6 +24,7 @@
   "peerDependencies": {
     "@deepseek-ai/dsh-agent": "^0.0.1",
     "@deepseek-ai/dsh-agent-loop": "^0.0.1",
+    "@deepseek-ai/dsh-commands": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-llm-retry": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
@@ -39,6 +40,7 @@
     "@cordisjs/plugin-loader": "workspace:^",
     "@deepseek-ai/dsh-agent": "workspace:^",
     "@deepseek-ai/dsh-agent-loop": "workspace:^",
+    "@deepseek-ai/dsh-commands": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-llm-retry": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
diff --git a/packages/ui/tui/src/index.ts b/packages/ui/tui/src/index.ts
index db696dde2a..cbb3593209 100644
--- a/packages/ui/tui/src/index.ts
+++ b/packages/ui/tui/src/index.ts
@@ -35,6 +35,7 @@ import type { Context } from 'cordis'
 import z from 'schemastery'
 import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent'
 import type {} from '@deepseek-ai/dsh-agent-loop'
+import type {} from '@deepseek-ai/dsh-commands'
 import { errorChain } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm'
 import type {} from '@deepseek-ai/dsh-llm-retry'
@@ -55,7 +56,7 @@ import {
 } from '@deepseek-ai/dsh-user-interaction'
 
 export const name = 'ui-tui'
-export const inject = ['agents', 'userInteraction', 'tools']
+export const inject = ['agents', 'commands', 'userInteraction', 'tools']
 
 /** Presentation settings for the pi-tui terminal mode. */
 export interface TuiConfig {
@@ -855,6 +856,7 @@ export function createTuiChat(
   const allToolCards = new Set<ToolCardComponent>()
   const liveErrors = new Set<string>()
   const questionQueue: PendingQuestion[] = []
+  const commandControllers = new Set<AbortController>()
   let activeQuestion: PendingQuestion | undefined
 
   const welcome = config.welcome ?? 'ready.'
@@ -1129,6 +1131,8 @@ export function createTuiChat(
     shuttingDown ??= (async () => {
       disposed = true
       clearStatus()
+      for (const controller of commandControllers) controller.abort(new Error('TUI disposed'))
+      commandControllers.clear()
       if (activeQuestion !== undefined) {
         const pending = activeQuestion
         activeQuestion = undefined
@@ -1153,16 +1157,6 @@ export function createTuiChat(
     void shutdown(true)
   }
 
-  editor.setAutocompleteProvider(new CombinedAutocompleteProvider([
-    { name: 'help', description: 'Show keyboard shortcuts and commands' },
-    { name: 'clear', description: 'Clear the transcript view (session history is unchanged)' },
-    { name: 'cancel', description: 'Cancel the active turn' },
-    { name: 'reasoning', description: 'Toggle reasoning blocks' },
-    { name: 'tools', description: 'Expand or collapse all tool cards' },
-    { name: 'redraw', description: 'Invalidate components and redraw the terminal' },
-    { name: 'exit', description: 'Exit after the active turn reaches idle' },
-  ], agent.session.header.cwd ?? process.cwd()))
-
   const toggleTools = (): void => {
     toolsExpanded = !toolsExpanded
     for (const card of allToolCards) card.setExpanded(toolsExpanded)
@@ -1182,52 +1176,107 @@ export function createTuiChat(
   }
 
   const showHelp = (): void => {
+    const commandLines = ctx.commands.list(agent).map((command) => {
+      const input = command.input === undefined ? '' : ` ${command.input.hint}`
+      return `/${command.name}${input} — ${command.description}`
+    })
     chat.addChild(new Spacer(1))
     chat.addChild(new Text(palette.bold(palette.accent('Keyboard shortcuts')), 1, 0))
     chat.addChild(new Text([
       'Enter send • Shift/Alt+Enter newline • Up/Down prompt history',
       'Esc cancel active turn • Ctrl+O expand tool cards • Ctrl+R toggle reasoning',
       'Ctrl+C cancel while running; clear input or exit while idle • Ctrl+D exit',
-      '/help /clear /cancel /reasoning /tools /redraw /exit',
+      '',
+      ...commandLines,
     ].map(line => palette.muted(line)).join('\n'), 1, 0))
     requestRender()
   }
 
+  const refreshCommandAutocomplete = (): void => {
+    editor.setAutocompleteProvider(new CombinedAutocompleteProvider(
+      ctx.commands.list(agent).map(command => ({
+        name: command.name,
+        description: command.description,
+      })),
+      agent.session.header.cwd ?? process.cwd(),
+    ))
+  }
+  const disposeCommandChanges = ctx.on('commands/change', refreshCommandAutocomplete)
+  refreshCommandAutocomplete()
+
+  // The agent scope is minted by agent-loop and intentionally inherits only
+  // that core plugin's dependencies. A child command producer declares its own
+  // UI-service dependency while retaining the parent agent scope and lifetime.
+  const commandFiber = agent.ctx.inject(['commands'], (commandCtx) => {
+    commandCtx.commands.register({
+      name: 'help',
+      description: 'Show keyboard shortcuts and commands',
+      handler: () => { showHelp(); return { kind: 'success' } },
+    })
+    commandCtx.commands.register({
+      name: 'clear',
+      description: 'Clear the transcript view (session history is unchanged)',
+      handler: () => { chat.clear(); requestRender(); return { kind: 'success' } },
+    })
+    commandCtx.commands.register({
+      name: 'cancel',
+      description: 'Cancel the active turn',
+      handler: () => {
+        if (agent.status !== 'running') return { kind: 'error', text: 'The agent is already idle.' }
+        agent.cancel('cancelled from terminal')
+        return { kind: 'success', text: 'Cancellation requested.' }
+      },
+    })
+    commandCtx.commands.register({
+      name: 'reasoning',
+      description: 'Toggle reasoning blocks',
+      handler: () => { toggleReasoning(); return { kind: 'success' } },
+    })
+    commandCtx.commands.register({
+      name: 'tools',
+      description: 'Expand or collapse all tool cards',
+      handler: () => { toggleTools(); return { kind: 'success' } },
+    })
+    commandCtx.commands.register({
+      name: 'redraw',
+      description: 'Invalidate components and redraw the terminal',
+      handler: () => { ui.invalidate(); ui.requestRender(true); return { kind: 'success' } },
+    })
+    commandCtx.commands.register({
+      name: 'exit',
+      description: 'Exit after the active turn reaches idle',
+      handler: () => { requestExit(); return { kind: 'success' } },
+    })
+  })
+
+  const runCommand = (text: string): void => {
+    const controller = new AbortController()
+    commandControllers.add(controller)
+    void ctx.commands.execute(agent, text, controller.signal).then(
+      (result) => {
+        if (disposed) return
+        if (result === undefined) {
+          appendNotice(`Unknown command: ${text}`, 'warning')
+        } else if (result.text !== undefined && result.text !== '') {
+          appendNotice(result.text, result.kind === 'error' ? 'error' : 'info')
+        }
+      },
+      (error: unknown) => {
+        if (!disposed) {
+          appendNotice(`Command failed: ${errorChain(error)}`, 'error')
+        }
+      },
+    ).finally(() => { commandControllers.delete(controller) })
+  }
+
   editor.onSubmit = (value: string) => {
     const text = value.trim()
     if (text === '') return
     editor.addToHistory(text)
     editor.setText('')
-    switch (text) {
-      case '/help':
-        showHelp()
-        return
-      case '/clear':
-        chat.clear()
-        requestRender()
-        return
-      case '/cancel':
-        if (agent.status === 'running') agent.cancel('cancelled from terminal')
-        else appendNotice('The agent is already idle.')
-        return
-      case '/reasoning':
-        toggleReasoning()
-        return
-      case '/tools':
-        toggleTools()
-        return
-      case '/redraw':
-        ui.invalidate()
-        ui.requestRender(true)
-        return
-      case '/exit':
-        requestExit()
-        return
-      default:
-        if (text.startsWith('/')) {
-          appendNotice(`Unknown command: ${text}`, 'warning')
-          return
-        }
+    if (value.startsWith('/')) {
+      runCommand(value)
+      return
     }
     if (agent.status === 'disposed') {
       appendNotice(`Agent "${agent.id}" is disposed.`, 'error')
@@ -1304,6 +1353,7 @@ export function createTuiChat(
 
   const detachListeners = (): void => {
     removeInputListener()
+    disposeCommandChanges()
     disposeSessionEvents()
     disposeStatus()
     disposeError()
@@ -1317,6 +1367,12 @@ export function createTuiChat(
   } catch (error: unknown) {
     disposed = true
     detachListeners()
+    void commandFiber.dispose().catch(
+      /* v8 ignore next 2 -- command registration cleanup is non-throwing; this guards a future disposer regression */
+      (cleanupError: unknown) => {
+        ctx.logger.warn(`ui-tui: command cleanup after startup failure failed: ${errorChain(cleanupError)}`)
+      },
+    )
     clearStatus()
     disposeUserInteraction()
     ui.stop()
@@ -1327,6 +1383,7 @@ export function createTuiChat(
     async dispose(): Promise<void> {
       detachListeners()
       await shutdown(false)
+      await commandFiber.dispose()
     },
   }
 }
diff --git a/packages/ui/tui/tests/harness.ts b/packages/ui/tui/tests/harness.ts
index 96d0570921..c24577b7fd 100644
--- a/packages/ui/tui/tests/harness.ts
+++ b/packages/ui/tui/tests/harness.ts
@@ -1,6 +1,7 @@
 import { Context } from 'cordis'
 import type { Terminal } from '@earendil-works/pi-tui'
 import AgentRegistry, { type Agent, type AgentStatus } from '@deepseek-ai/dsh-agent'
+import CommandService from '@deepseek-ai/dsh-commands'
 import type { ContentBlock } from '@deepseek-ai/dsh-llm'
 import SessionStore, { SessionId, type Session } from '@deepseek-ai/dsh-session'
 import type { ToolDefinition } from '@deepseek-ai/dsh-tools'
@@ -47,6 +48,7 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
   const ctx = new Context()
   await ctx.plugin(SessionStore)
   await ctx.plugin(AgentRegistry)
+  await ctx.plugin(CommandService)
   await ctx.plugin(UserInteractionService)
   if (options.configureContext === undefined) {
     const tools = options.tools ?? {}
diff --git a/packages/ui/tui/tests/plugin-shape.spec.ts b/packages/ui/tui/tests/plugin-shape.spec.ts
index d1e4b92f3d..a5312156ed 100644
--- a/packages/ui/tui/tests/plugin-shape.spec.ts
+++ b/packages/ui/tui/tests/plugin-shape.spec.ts
@@ -12,7 +12,7 @@ describe('dsh-tui plugin export shape', () => {
     const unwrapped = loader.unwrapExports(tui) as Record<string, unknown>
     expect(unwrapped).toBe(tui)
     expect(unwrapped.name).toBe('ui-tui')
-    expect(unwrapped.inject).toEqual(['agents', 'userInteraction', 'tools'])
+    expect(unwrapped.inject).toEqual(['agents', 'commands', 'userInteraction', 'tools'])
     expect(unwrapped.Config).toBeDefined()
     expect(typeof unwrapped.apply).toBe('function')
   })
diff --git a/packages/ui/tui/tests/snapshots/disposed-terminal.expected.txt b/packages/ui/tui/tests/snapshots/disposed-terminal.expected.txt
index 05809dea0c..5006083358 100644
--- a/packages/ui/tui/tests/snapshots/disposed-terminal.expected.txt
+++ b/packages/ui/tui/tests/snapshots/disposed-terminal.expected.txt
@@ -1,7 +1,7 @@
 terminal 92x32 buffer=normal length=32 base=0 viewport=0
 lifecycle started=1 stopped=1 progress=inactive
 title "DSH snapshot"
-cursor visible column=0 viewportRow=22 bufferRow=22
+cursor visible column=0 viewportRow=29 bufferRow=29
 buffer
 0| "╭──────────────────────────────────────────────────────────────────────────────────────────╮"
   style 0-91 fg=bright-blue
@@ -29,24 +29,37 @@ buffer
   style 1-75 fg=bright-black
 9| " Ctrl+C cancel while running; clear input or exit while idle • Ctrl+D exit                  "
   style 1-73 fg=bright-black
-10| " /help /clear /cancel /reasoning /tools /redraw /exit                                       "
-  style 1-52 fg=bright-black
-11| <blank>
-12| " Unknown command: /unknown-advanced-command                                                 "
-  style 1-42 fg=yellow
-13| <blank>
-14| " provider stream failed after partial output                                                "
+10| "                                                                                            "
+11| " /cancel — Cancel the active turn                                                           "
+  style 1-32 fg=bright-black
+12| " /clear — Clear the transcript view (session history is unchanged)                          "
+  style 1-65 fg=bright-black
+13| " /exit — Exit after the active turn reaches idle                                            "
+  style 1-47 fg=bright-black
+14| " /help — Show keyboard shortcuts and commands                                               "
+  style 1-44 fg=bright-black
+15| " /reasoning — Toggle reasoning blocks                                                       "
+  style 1-36 fg=bright-black
+16| " /redraw — Invalidate components and redraw the terminal                                    "
+  style 1-55 fg=bright-black
+17| " /tools — Expand or collapse all tool cards                                                 "
+  style 1-42 fg=bright-black
+18| <blank>
+19| " provider stream failed after partial output                                                "
   style 1-43 fg=red
-15| <blank>
-16| " The previous process ended during this turn.                                               "
+20| <blank>
+21| " The previous process ended during this turn.                                               "
   style 1-44 fg=yellow
-17| "────────────────────────────────────────────────────────────────────────────────────────────"
+22| <blank>
+23| " Unknown command: /unknown-advanced-command                                                 "
+  style 1-42 fg=yellow
+24| "────────────────────────────────────────────────────────────────────────────────────────────"
   style 0-91 dim
-18| "                                                                                            "
+25| "                                                                                            "
   style 1-1 inverse
-19| "────────────────────────────────────────────────────────────────────────────────────────────"
+26| "────────────────────────────────────────────────────────────────────────────────────────────"
   style 0-91 dim
-20| "/workspace/project  ↑0 ↓0                                  idle  reasoning:on  tools:compact"
+27| "/workspace/project  ↑0 ↓0                                  idle  reasoning:on  tools:compact"
   style 0-24 dim
   style 59-91 dim
-21-31| <blank>
+28-31| <blank>
diff --git a/packages/ui/tui/tests/snapshots/errors-and-help.expected.txt b/packages/ui/tui/tests/snapshots/errors-and-help.expected.txt
index fccfca604b..4a99d7e9e7 100644
--- a/packages/ui/tui/tests/snapshots/errors-and-help.expected.txt
+++ b/packages/ui/tui/tests/snapshots/errors-and-help.expected.txt
@@ -1,7 +1,7 @@
 terminal 92x32 buffer=normal length=32 base=0 viewport=0
 lifecycle started=1 stopped=0 progress=inactive
 title "DSH snapshot"
-cursor hidden column=1 viewportRow=18 bufferRow=18
+cursor hidden column=1 viewportRow=25 bufferRow=25
 buffer
 0| "╭──────────────────────────────────────────────────────────────────────────────────────────╮"
   style 0-91 fg=bright-blue
@@ -29,24 +29,37 @@ buffer
   style 1-75 fg=bright-black
 9| " Ctrl+C cancel while running; clear input or exit while idle • Ctrl+D exit                  "
   style 1-73 fg=bright-black
-10| " /help /clear /cancel /reasoning /tools /redraw /exit                                       "
-  style 1-52 fg=bright-black
-11| <blank>
-12| " Unknown command: /unknown-advanced-command                                                 "
-  style 1-42 fg=yellow
-13| <blank>
-14| " provider stream failed after partial output                                                "
+10| "                                                                                            "
+11| " /cancel — Cancel the active turn                                                           "
+  style 1-32 fg=bright-black
+12| " /clear — Clear the transcript view (session history is unchanged)                          "
+  style 1-65 fg=bright-black
+13| " /exit — Exit after the active turn reaches idle                                            "
+  style 1-47 fg=bright-black
+14| " /help — Show keyboard shortcuts and commands                                               "
+  style 1-44 fg=bright-black
+15| " /reasoning — Toggle reasoning blocks                                                       "
+  style 1-36 fg=bright-black
+16| " /redraw — Invalidate components and redraw the terminal                                    "
+  style 1-55 fg=bright-black
+17| " /tools — Expand or collapse all tool cards                                                 "
+  style 1-42 fg=bright-black
+18| <blank>
+19| " provider stream failed after partial output                                                "
   style 1-43 fg=red
-15| <blank>
-16| " The previous process ended during this turn.                                               "
+20| <blank>
+21| " The previous process ended during this turn.                                               "
   style 1-44 fg=yellow
-17| "────────────────────────────────────────────────────────────────────────────────────────────"
+22| <blank>
+23| " Unknown command: /unknown-advanced-command                                                 "
+  style 1-42 fg=yellow
+24| "────────────────────────────────────────────────────────────────────────────────────────────"
   style 0-91 dim
-18| "                                                                                            "
+25| "                                                                                            "
   style 1-1 inverse
-19| "────────────────────────────────────────────────────────────────────────────────────────────"
+26| "────────────────────────────────────────────────────────────────────────────────────────────"
   style 0-91 dim
-20| "/workspace/project  ↑0 ↓0                                  idle  reasoning:on  tools:compact"
+27| "/workspace/project  ↑0 ↓0                                  idle  reasoning:on  tools:compact"
   style 0-24 dim
   style 59-91 dim
-21-31| <blank>
+28-31| <blank>
diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts
index c0a916e4f0..aa2ff5510e 100644
--- a/packages/ui/tui/tests/tui.spec.ts
+++ b/packages/ui/tui/tests/tui.spec.ts
@@ -4,6 +4,7 @@ import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import type { Terminal } from '@earendil-works/pi-tui'
 import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+import CommandService, { type CommandInvocation } from '@deepseek-ai/dsh-commands'
 import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
 import type { ToolDefinition } from '@deepseek-ai/dsh-tools'
 import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
@@ -499,6 +500,108 @@ describe('pi-tui chat lifecycle and transcript', () => {
     await dispose(disposedAgent)
   })
 
+  it('discovers and executes plugin commands, then removes TUI-local commands on disposal', async () => {
+    const result = await setup()
+    const handler = vi.fn(({ rawInput }: CommandInvocation) => ({
+      kind: 'success' as const,
+      text: `PLUGIN:${rawInput}`,
+    }))
+    result.ctx.commands.register({
+      name: 'plugin-check',
+      description: 'Run a plugin command',
+      input: { hint: '<value>' },
+      handler,
+    })
+    result.ctx.commands.register({
+      name: 'plugin-fail',
+      description: 'Fail a plugin command',
+      handler: () => { throw new Error('plugin command exploded') },
+    })
+
+    result.terminal.send('/plugin-check  value  ')
+    result.terminal.send('\r')
+    await tick()
+
+    expect(handler).toHaveBeenCalledTimes(1)
+    const invocation = handler.mock.calls[0]?.[0]
+    expect(invocation?.agent).toBe(result.agent)
+    // pi-tui's Editor owns terminal-line normalization and removes trailing
+    // spaces before onSubmit; the registry preserves the adapter-delivered line.
+    expect(invocation?.rawInput).toBe('  value')
+    expect(result.terminal.output).toContain('PLUGIN:  value')
+    result.terminal.send('/plugin-fail')
+    result.terminal.send('\r')
+    await tick()
+    expect(result.terminal.output).toContain('Command failed: plugin command exploded')
+    result.terminal.send('/help')
+    result.terminal.send('\r')
+    await tick()
+    expect(result.terminal.output).toContain('/plugin-check <value> — Run a plugin command')
+    expect(result.ctx.commands.list(result.agent).map(command => command.name)).toContain('help')
+
+    await result.controller.dispose()
+    expect(result.ctx.commands.list(result.agent).map(command => command.name)).toEqual([
+      'plugin-check',
+      'plugin-fail',
+    ])
+    await result.ctx.fiber.dispose()
+  })
+
+  it('aborts an in-flight plugin command during TUI disposal', async () => {
+    const result = await setup()
+    let started!: () => void
+    const ready = new Promise<void>((resolve) => { started = resolve })
+    let commandSignal: AbortSignal | undefined
+    result.ctx.commands.register({
+      name: 'wait-plugin',
+      description: 'Wait until disposal',
+      handler: ({ signal }) => {
+        commandSignal = signal
+        started()
+        return new Promise((resolve) => {
+          signal.addEventListener('abort', () => { resolve({ kind: 'error', text: 'late result' }) }, { once: true })
+        })
+      },
+    })
+
+    result.terminal.send('/wait-plugin')
+    result.terminal.send('\r')
+    await ready
+    await result.controller.dispose()
+
+    expect(commandSignal?.aborted).toBe(true)
+    expect(result.terminal.output).not.toContain('late result')
+    await result.ctx.fiber.dispose()
+  })
+
+  it('suppresses a successful plugin result that settles as TUI disposal starts', async () => {
+    const result = await setup()
+    let started!: () => void
+    const ready = new Promise<void>((resolve) => { started = resolve })
+    let resolveCommand!: (result: { kind: 'success'; text: string }) => void
+    result.ctx.commands.register({
+      name: 'late-success',
+      description: 'Resolve while the TUI closes',
+      handler: () => new Promise((resolve) => {
+        resolveCommand = resolve
+        started()
+      }),
+    })
+
+    result.terminal.send('/late-success')
+    result.terminal.send('\r')
+    await ready
+    resolveCommand({ kind: 'success', text: 'must not render after disposal' })
+    // Let the command boundary accept the result before disposal, but leave the
+    // TUI continuation queued so the success-side disposal guard owns the race.
+    await Promise.resolve()
+    await result.controller.dispose()
+    await tick()
+
+    expect(result.terminal.output).not.toContain('must not render after disposal')
+    await result.ctx.fiber.dispose()
+  })
+
   it('cancels before /exit while running and handles agent errors/disposal', async () => {
     const result = await setup({ status: 'running' })
     result.terminal.send('/exit')
@@ -881,6 +984,7 @@ describe('terminal mounting', () => {
     const ctx = new Context()
     await ctx.plugin(SessionStore)
     await ctx.plugin(AgentRegistry)
+    await ctx.plugin(CommandService)
     await ctx.plugin(UserInteractionService)
     ctx.provide('tools', { get: () => undefined } as never)
     const session = ctx.sessions.create(SessionId('main'))
@@ -899,6 +1003,7 @@ describe('terminal mounting', () => {
     const ctx = new Context()
     await ctx.plugin(SessionStore)
     await ctx.plugin(AgentRegistry)
+    await ctx.plugin(CommandService)
     await ctx.plugin(UserInteractionService)
     ctx.provide('tools', { get: () => undefined } as never)
     const terminal = new FakeTerminal()
@@ -927,6 +1032,7 @@ describe('terminal mounting', () => {
     const ctx = new Context()
     await ctx.plugin(SessionStore)
     await ctx.plugin(AgentRegistry)
+    await ctx.plugin(CommandService)
     await ctx.plugin(UserInteractionService)
     ctx.provide('tools', { get: () => undefined } as never)
     const terminal = new FakeTerminal()
@@ -954,6 +1060,7 @@ describe('terminal mounting', () => {
     const ctx = new Context()
     await ctx.plugin(SessionStore)
     await ctx.plugin(AgentRegistry)
+    await ctx.plugin(CommandService)
     await ctx.plugin(UserInteractionService)
     ctx.provide('tools', { get: () => undefined } as never)
     const terminal = new FakeTerminal()
@@ -974,6 +1081,7 @@ describe('terminal mounting', () => {
     const ctx = new Context()
     await ctx.plugin(SessionStore)
     await ctx.plugin(AgentRegistry)
+    await ctx.plugin(CommandService)
     await ctx.plugin(UserInteractionService)
     ctx.provide('tools', { get: () => undefined } as never)
     const session = ctx.sessions.create(SessionId('failed-start-session'))
@@ -986,6 +1094,8 @@ describe('terminal mounting', () => {
 
     expect(() => createTuiChat(ctx, { sessionId: 'failed-start-session', color: false }, { terminal, exit: vi.fn() }))
       .toThrow('terminal startup failed')
+    await tick()
+    expect(ctx.commands.list(ctx.agents.get(SessionId('failed-start-session'))!)).toEqual([])
     expect(terminal.stopped).toBe(1)
     expect(terminal.progress).toEqual([false, true, false])
     await expect(ctx.userInteraction.ask({ questions: [{ id: 'late', question: 'Late?' }] }))
@@ -1003,6 +1113,7 @@ describe('terminal mounting', () => {
   it('throws when createTuiChat is called without the configured agent', async () => {
     const ctx = new Context()
     await ctx.plugin(AgentRegistry)
+    await ctx.plugin(CommandService)
     await ctx.plugin(UserInteractionService)
     ctx.provide('tools', { get: () => undefined } as never)
     const runtime: TuiRuntime = { terminal: new FakeTerminal(), exit: vi.fn() }
diff --git a/packages/ui/tui/tsconfig.json b/packages/ui/tui/tsconfig.json
index 0c9e89e9e5..62cfef1a14 100644
--- a/packages/ui/tui/tsconfig.json
+++ b/packages/ui/tui/tsconfig.json
@@ -32,6 +32,9 @@
     {
       "path": "../../core/tools"
     },
+    {
+      "path": "../commands"
+    },
     {
       "path": "../user-interaction"
     }
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 5c8c1f97cd..39b74d6747 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -134,6 +134,12 @@ importers:
       '@deepseek-ai/dsh-fs-sandbox':
         specifier: workspace:^
         version: link:../packages/fs/fs-sandbox
+      '@deepseek-ai/dsh-goal':
+        specifier: workspace:*
+        version: link:../packages/goal/goal
+      '@deepseek-ai/dsh-goal-session':
+        specifier: workspace:*
+        version: link:../packages/goal/goal-session
       '@deepseek-ai/dsh-hooks-claude':
         specifier: workspace:*
         version: link:../packages/hooks/hooks-claude
@@ -200,6 +206,9 @@ importers:
       '@deepseek-ai/dsh-tool-fs-search':
         specifier: workspace:*
         version: link:../packages/fs/tool-fs-search
+      '@deepseek-ai/dsh-tool-goal':
+        specifier: workspace:*
+        version: link:../packages/goal/tool-goal
       '@deepseek-ai/dsh-tool-subagent':
         specifier: workspace:*
         version: link:../packages/subagent/tool-subagent
@@ -713,6 +722,9 @@ importers:
       '@deepseek-ai/dsh-app-boot':
         specifier: workspace:^
         version: link:../../ui/app-boot
+      '@deepseek-ai/dsh-commands':
+        specifier: workspace:^
+        version: link:../../ui/commands
       '@deepseek-ai/dsh-session-persistence-jsonl':
         specifier: workspace:^
         version: link:../../session-persistence/session-persistence-jsonl
@@ -892,6 +904,9 @@ importers:
       '@deepseek-ai/dsh-app-boot':
         specifier: workspace:^
         version: link:../../ui/app-boot
+      '@deepseek-ai/dsh-commands':
+        specifier: workspace:^
+        version: link:../../ui/commands
       '@deepseek-ai/dsh-llm':
         specifier: workspace:^
         version: link:../../llm/llm
@@ -1079,6 +1094,95 @@ importers:
         specifier: ^4.0.0-rc.6
         version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5)
 
+  packages/goal/goal:
+    dependencies:
+      schemastery:
+        specifier: ^3.17.2
+        version: 3.18.0
+    devDependencies:
+      '@deepseek-ai/dsh-agent':
+        specifier: workspace:^
+        version: link:../../core/agent
+      '@deepseek-ai/dsh-brand':
+        specifier: workspace:^
+        version: link:../../util/brand
+      '@deepseek-ai/dsh-llm':
+        specifier: workspace:^
+        version: link:../../llm/llm
+      '@deepseek-ai/dsh-loader-smoke':
+        specifier: workspace:^
+        version: link:../../support/loader-smoke
+      '@deepseek-ai/dsh-scope':
+        specifier: workspace:^
+        version: link:../../core/scope
+      '@deepseek-ai/dsh-session':
+        specifier: workspace:^
+        version: link:../../core/session
+      cordis:
+        specifier: ^4.0.0-rc.7
+        version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5)
+
+  packages/goal/goal-session:
+    devDependencies:
+      '@deepseek-ai/dsh-agent':
+        specifier: workspace:^
+        version: link:../../core/agent
+      '@deepseek-ai/dsh-agent-loop':
+        specifier: workspace:^
+        version: link:../../core/agent-loop
+      '@deepseek-ai/dsh-agent-loop-testkit':
+        specifier: workspace:^
+        version: link:../../support/agent-loop-testkit
+      '@deepseek-ai/dsh-goal':
+        specifier: workspace:^
+        version: link:../goal
+      '@deepseek-ai/dsh-llm':
+        specifier: workspace:^
+        version: link:../../llm/llm
+      '@deepseek-ai/dsh-session':
+        specifier: workspace:^
+        version: link:../../core/session
+      '@deepseek-ai/dsh-system-prompt':
+        specifier: workspace:^
+        version: link:../../core/system-prompt
+      '@deepseek-ai/dsh-tools':
+        specifier: workspace:^
+        version: link:../../core/tools
+      cordis:
+        specifier: ^4.0.0-rc.7
+        version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5)
+
+  packages/goal/tool-goal:
+    dependencies:
+      schemastery:
+        specifier: ^3.18.0
+        version: 3.18.0
+    devDependencies:
+      '@cordisjs/plugin-loader':
+        specifier: workspace:^
+        version: link:../../../vendor/loader
+      '@deepseek-ai/dsh-agent':
+        specifier: workspace:^
+        version: link:../../core/agent
+      '@deepseek-ai/dsh-goal':
+        specifier: workspace:^
+        version: link:../goal
+      '@deepseek-ai/dsh-llm':
+        specifier: workspace:^
+        version: link:../../llm/llm
+      '@deepseek-ai/dsh-session':
+        specifier: workspace:^
+        version: link:../../core/session
+      '@deepseek-ai/dsh-system-prompt':
+        specifier: workspace:^
+        version: link:../../core/system-prompt
+      '@deepseek-ai/dsh-tools':
+        specifier: workspace:^
+        version: link:../../core/tools
+      cordis:
+        specifier: ^4.0.0-rc.7
+        version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@vendor+loader)
+
   packages/guard/repeat-tool-guard:
     dependencies:
       schemastery:
@@ -1933,6 +2037,9 @@ importers:
       '@deepseek-ai/dsh-agent':
         specifier: workspace:^
         version: link:../../core/agent
+      '@deepseek-ai/dsh-goal':
+        specifier: workspace:^
+        version: link:../../goal/goal
       '@deepseek-ai/dsh-llm':
         specifier: workspace:^
         version: link:../../llm/llm
@@ -2095,6 +2202,9 @@ importers:
       '@deepseek-ai/dsh-bash-local':
         specifier: workspace:^
         version: link:../../bash/bash-local
+      '@deepseek-ai/dsh-commands':
+        specifier: workspace:^
+        version: link:../commands
       '@deepseek-ai/dsh-fs-local':
         specifier: workspace:^
         version: link:../../fs/fs-local
@@ -2165,6 +2275,21 @@ importers:
         specifier: ^4.0.0-rc.7
         version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader)
 
+  packages/ui/commands:
+    devDependencies:
+      '@deepseek-ai/dsh-agent':
+        specifier: workspace:^
+        version: link:../../core/agent
+      '@deepseek-ai/dsh-scope':
+        specifier: workspace:^
+        version: link:../../core/scope
+      '@deepseek-ai/dsh-session':
+        specifier: workspace:^
+        version: link:../../core/session
+      cordis:
+        specifier: ^4.0.0-rc.7
+        version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5)
+
   packages/ui/jsonrpc:
     dependencies:
       schemastery:
@@ -2266,6 +2391,9 @@ importers:
       '@deepseek-ai/dsh-agent-loop':
         specifier: workspace:^
         version: link:../../core/agent-loop
+      '@deepseek-ai/dsh-commands':
+        specifier: workspace:^
+        version: link:../commands
       '@deepseek-ai/dsh-llm':
         specifier: workspace:^
         version: link:../../llm/llm
@@ -2623,6 +2751,9 @@ importers:
       '@deepseek-ai/dsh-code-runtime-worker':
         specifier: workspace:^
         version: link:../../packages/code-runtime/code-runtime-worker
+      '@deepseek-ai/dsh-commands':
+        specifier: workspace:^
+        version: link:../../packages/ui/commands
       '@deepseek-ai/dsh-compact':
         specifier: workspace:^
         version: link:../../packages/compact/compact
diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json
index a9405ddd80..b35c38b032 100644
--- a/python/sdk-runtime/package.json
+++ b/python/sdk-runtime/package.json
@@ -18,6 +18,7 @@
     "@deepseek-ai/dsh-brand": "workspace:^",
     "@deepseek-ai/dsh-code-runtime": "workspace:^",
     "@deepseek-ai/dsh-code-runtime-worker": "workspace:^",
+    "@deepseek-ai/dsh-commands": "workspace:^",
     "@deepseek-ai/dsh-compact": "workspace:^",
     "@deepseek-ai/dsh-compact-basic": "workspace:^",
     "@deepseek-ai/dsh-fs": "workspace:^",
diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts
index f3e01abd5c..200308fca9 100644
--- a/scripts/gen-cordis-catalog.ts
+++ b/scripts/gen-cordis-catalog.ts
@@ -71,6 +71,16 @@ export const LINK_MAP: Record<string, string> = {
   FsVersion: 'filesystem.md',
   FsWriteIntent: 'filesystem.md',
   FsWriteOutcome: 'filesystem.md',
+  CreateGoalRequest: 'goal.md',
+  EditGoalRequest: 'goal.md',
+  GoalBlockReason: 'goal.md',
+  GoalChanged: 'goal.md',
+  GoalRef: 'goal.md',
+  GoalView: 'goal.md',
+  CommandDefinition: 'commands.md',
+  CommandDescriptor: 'commands.md',
+  CommandResult: 'commands.md',
+  CommandSurface: 'commands.md',
   LlmAdapter: 'llm-streaming.md',
   LlmService: 'llm-streaming.md',
   StreamChunk: 'llm-streaming.md',
diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts
index 35d18f6483..29c21c0969 100644
--- a/scripts/gen-doc-graphs.ts
+++ b/scripts/gen-doc-graphs.ts
@@ -58,6 +58,7 @@ const GROUP_ORDER = [
   'util',
   'llm',
   'core',
+  'goal',
   'bash',
   'sandbox',
   'fs',
@@ -152,6 +153,14 @@ const SERVICE_ROLES: ServiceRole[] = [
     consumers: ['tool-ask-user', 'tui', 'acp'],
     note: 'UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise.',
   },
+  {
+    key: 'commands',
+    pkg: 'commands',
+    title: 'Human command registry',
+    mode: 'core',
+    consumers: ['tui', 'acp'],
+    note: 'Plugins register direct human commands; TUI and ACP consume the same effective per-agent catalog without sending invocations to the model.',
+  },
   {
     key: 'skills',
     pkg: 'skill',
@@ -177,6 +186,13 @@ const SERVICE_ROLES: ServiceRole[] = [
     consumers: ['agent-spine-demo'],
     note: 'The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package.',
   },
+  {
+    key: 'goals',
+    pkg: 'goal',
+    title: 'Same-session goal domain',
+    mode: 'core',
+    note: 'Folds revisioned objective state from the session log and keeps live continuation activation process-local.',
+  },
   {
     key: 'bash',
     pkg: 'bash',
diff --git a/scripts/gen-module-graph.ts b/scripts/gen-module-graph.ts
index 520375c9ae..f803f164cf 100644
--- a/scripts/gen-module-graph.ts
+++ b/scripts/gen-module-graph.ts
@@ -21,6 +21,7 @@ const GROUP_ORDER = [
   'util',
   'llm',
   'core',
+  'goal',
   'bash',
   'fs',
   'skill',
diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts
index e6d037012a..9a351f52b1 100644
--- a/scripts/gen-tool-catalog.ts
+++ b/scripts/gen-tool-catalog.ts
@@ -10,6 +10,8 @@ import { globSync, readFileSync, writeFileSync } from 'node:fs'
 import { basename, resolve } from 'node:path'
 import { Context } from 'cordis'
 import type { ToolSchema } from '@deepseek-ai/dsh-llm'
+import AgentRegistry from '@deepseek-ai/dsh-agent'
+import GoalService from '@deepseek-ai/dsh-goal'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools'
 import { BashExecutor } from '@deepseek-ai/dsh-bash'
@@ -30,6 +32,7 @@ import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
 import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis'
 import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
 import * as ToolFsSearch from '@deepseek-ai/dsh-tool-fs-search'
+import * as ToolGoal from '@deepseek-ai/dsh-tool-goal'
 import * as ToolSkill from '@deepseek-ai/dsh-tool-skill'
 import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks'
 import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
@@ -224,6 +227,20 @@ const TOOL_PACKAGES: ToolPackage[] = [
     note:
       'glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.',
   },
+  {
+    pkg: '@deepseek-ai/dsh-tool-goal',
+    dir: 'tool-goal',
+    source: 'packages/goal/tool-goal/src/index.ts',
+    requires: ['ctx.tools', 'ctx.agents', 'ctx.goals', 'ctx.systemPrompt', 'a calling Agent in an authorized open turn'],
+    writes: ['tool/call', 'context/message goal snapshot for mutations', 'tool/result'],
+    async mount(ctx) {
+      await ctx.plugin(AgentRegistry)
+      await ctx.plugin(GoalService)
+      await ctx.plugin(ToolGoal)
+    },
+    note:
+      'create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds.',
+  },
   {
     pkg: '@deepseek-ai/dsh-tool-skill',
     dir: 'tool-skill',
diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json
index 032a22eb19..f6bf07f691 100644
--- a/scripts/type-equiv.manifest.json
+++ b/scripts/type-equiv.manifest.json
@@ -27,6 +27,25 @@
     { "doc": "docs/core-data-structures/scope.md", "symbol": "Scoped", "source": "packages/core/scope/src/index.ts" },
     { "doc": "docs/core-data-structures/scope.md", "symbol": "Scope", "source": "packages/core/scope/src/index.ts" },
 
+    { "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": "EditGoalRequest", "source": "packages/goal/goal/src/types.ts" },
+    { "doc": "docs/core-data-structures/goal.md", "symbol": "GoalChanged", "source": "packages/goal/goal/src/types.ts" },
+
+    { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandInputDescriptor", "source": "packages/ui/commands/src/index.ts" },
+    { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandDefinition", "source": "packages/ui/commands/src/index.ts" },
+    { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandInvocation", "source": "packages/ui/commands/src/index.ts" },
+    { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandResult", "source": "packages/ui/commands/src/index.ts" },
+    { "doc": "docs/core-data-structures/commands.md", "symbol": "CommandDescriptor", "source": "packages/ui/commands/src/index.ts" },
+    { "doc": "docs/core-data-structures/commands.md", "symbol": "ParsedCommand", "source": "packages/ui/commands/src/index.ts" },
+
     { "doc": "docs/core-data-structures/system-prompt.md", "symbol": "AssembleContext", "source": "packages/core/system-prompt/src/index.ts" },
     { "doc": "docs/core-data-structures/system-prompt.md", "symbol": "PromptSection", "source": "packages/core/system-prompt/src/index.ts" },
     { "doc": "docs/core-data-structures/system-prompt.md", "symbol": "ToolProviderResult", "source": "packages/core/system-prompt/src/index.ts" },
diff --git a/tsconfig.base.json b/tsconfig.base.json
index 53f69b2cf5..ffcb649335 100644
--- a/tsconfig.base.json
+++ b/tsconfig.base.json
@@ -49,6 +49,7 @@
         "./packages/skill/*/src",
         "./packages/compact/*/src",
         "./packages/context/*/src",
+        "./packages/goal/*/src",
         "./packages/guard/*/src",
         "./packages/subagent/*/src",
         "./packages/tasks/*/src",
diff --git a/tsconfig.build.json b/tsconfig.build.json
index 0504806166..19f4e9029e 100644
--- a/tsconfig.build.json
+++ b/tsconfig.build.json
@@ -25,6 +25,10 @@
     { "path": "./packages/session-query/session-query" },
     { "path": "./packages/core/system-prompt" },
     { "path": "./packages/core/agent" },
+    { "path": "./packages/ui/commands" },
+    { "path": "./packages/goal/goal" },
+    { "path": "./packages/goal/tool-goal" },
+    { "path": "./packages/goal/goal-session" },
     { "path": "./packages/context/time-context" },
     { "path": "./packages/ui/user-interaction" },
     { "path": "./packages/ui/user-approval" },
diff --git a/tsconfig.json b/tsconfig.json
index 1bf732aff2..8e36c20f00 100644
--- a/tsconfig.json
+++ b/tsconfig.json
@@ -38,6 +38,10 @@
     { "path": "./packages/session-query/session-query" },
     { "path": "./packages/core/system-prompt" },
     { "path": "./packages/core/agent" },
+    { "path": "./packages/ui/commands" },
+    { "path": "./packages/goal/goal" },
+    { "path": "./packages/goal/tool-goal" },
+    { "path": "./packages/goal/goal-session" },
     { "path": "./packages/context/time-context" },
     { "path": "./packages/ui/user-interaction" },
     { "path": "./packages/ui/user-approval" },
diff --git a/website/zh-CN/api/harness/commands.md b/website/zh-CN/api/harness/commands.md
new file mode 100644
index 0000000000..3b92682dac
--- /dev/null
+++ b/website/zh-CN/api/harness/commands.md
@@ -0,0 +1,91 @@
+<!-- Generated by scripts/gen-website-api.ts — do not edit by hand. Run `pnpm run gen-website-api` to regenerate. -->
+
+# ctx.commands
+
+`CommandService` — provided by `@deepseek-ai/dsh-commands`.
+
+Human-command registry. Plain-context definitions are global; definitions registered through a command-injected child of an agent context shadow globals for that agent.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L207)
+
+### ctx.commands.register(definition)
+
+```ts website-api
+/**
+ * Register a global or calling-agent-scoped command.
+ * @param definition - discovery metadata and direct UI handler.
+ * @returns the exact effect disposer that unregisters this definition.
+ */
+register(definition: CommandDefinition): () => void
+```
+
+Register a global or calling-agent-scoped command.
+
+- `definition` — discovery metadata and direct UI handler.
+
+**Returns** the exact effect disposer that unregisters this definition.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L220)
+
+### ctx.commands.list(agent)
+
+```ts website-api
+/**
+ * List the effective immutable command descriptors for one agent.
+ * @param agent - exact receiving agent and scoped-layer key.
+ * @returns name-sorted descriptors after scoped shadowing.
+ */
+list(agent: Agent): readonly CommandDescriptor[]
+```
+
+List the effective immutable command descriptors for one agent.
+
+- `agent` — exact receiving agent and scoped-layer key.
+
+**Returns** name-sorted descriptors after scoped shadowing.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L247)
+
+### ctx.commands.find(agent, name)
+
+```ts website-api
+/**
+ * Resolve one effective command definition.
+ * @param agent - exact receiving agent and scoped-layer key.
+ * @param name - command name without a slash.
+ * @returns the scoped shadow or global definition.
+ */
+find(agent: Agent, name: string): CommandDefinition | undefined
+```
+
+Resolve one effective command definition.
+
+- `agent` — exact receiving agent and scoped-layer key.
+- `name` — command name without a slash.
+
+**Returns** the scoped shadow or global definition.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L260)
+
+### ctx.commands.execute(agent, line, signal)
+
+```ts website-api
+/**
+ * Parse and execute a known command without sending it to the model.
+ * @param agent - exact receiving agent.
+ * @param line - complete slash-command line.
+ * @param signal - cancellation signal owned by the UI request.
+ * @returns a detached result, or `undefined` when syntax or name does not resolve.
+ */
+async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise<CommandResult | undefined>
+```
+
+Parse and execute a known command without sending it to the model.
+
+- `agent` — exact receiving agent.
+- `line` — complete slash-command line.
+- `signal` — cancellation signal owned by the UI request.
+
+**Returns** a detached result, or `undefined` when syntax or name does not resolve.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/commands/src/index.ts#L271)
diff --git a/website/zh-CN/api/harness/goals.md b/website/zh-CN/api/harness/goals.md
new file mode 100644
index 0000000000..828a5eced3
--- /dev/null
+++ b/website/zh-CN/api/harness/goals.md
@@ -0,0 +1,203 @@
+<!-- Generated by scripts/gen-website-api.ts — do not edit by hand. Run `pnpm run gen-website-api` to regenerate. -->
+
+# ctx.goals
+
+`GoalService` — provided by `@deepseek-ai/dsh-goal`.
+
+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#L135)
+
+### ctx.goals.get(agent)
+
+```ts website-api
+/**
+ * Read the current goal for one exact live agent.
+ * @param agent - owning live agent.
+ * @returns a fresh view or `undefined` when no goal is current.
+ * @throws {@link GoalError} when the agent is not the registry's live instance.
+ */
+get(agent: Agent): GoalView | undefined
+```
+
+Read the current goal for one exact live agent.
+
+- `agent` — owning 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#L161)
+
+### ctx.goals.disarm(agent)
+
+```ts website-api
+/**
+ * Remove process-local continuation authority without changing durable goal
+ * phase or revision. Lifecycle owners use this before unloading a driver;
+ * a later human-authorized {@link resume} records the new activation edge.
+ * @param agent - owning live agent.
+ * @returns a fresh disarmed view, or `undefined` when no goal is current.
+ */
+disarm(agent: Agent): GoalView | undefined
+```
+
+Remove process-local continuation authority without changing durable goal phase or revision. Lifecycle owners use this before unloading a driver; a later human-authorized resume records the new activation edge.
+
+- `agent` — owning live agent.
+
+**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#L175)
+
+### ctx.goals.create(agent, request)
+
+```ts website-api
+/**
+ * Create and arm a goal. A completed goal may be replaced; every other
+ * current phase must be cleared or resumed instead.
+ * @param agent - owning live agent.
+ * @param request - objective and optional round cap.
+ * @returns the created live view.
+ */
+create(agent: Agent, request: CreateGoalRequest): GoalView
+```
+
+Create and arm a goal. A completed goal may be replaced; every other current phase must be cleared or resumed instead.
+
+- `agent` — owning live agent.
+- `request` — objective and optional round cap.
+
+**Returns** the created live view.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L190)
+
+### ctx.goals.edit(agent, ref, request)
+
+```ts website-api
+/**
+ * Edit objective and/or round cap without changing phase.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @param request - at least one replacement field.
+ * @returns the edited view.
+ */
+edit(agent: Agent, ref: GoalRef, request: EditGoalRequest): GoalView
+```
+
+Edit objective and/or round cap without changing phase.
+
+- `agent` — owning live agent.
+- `ref` — expected current revision.
+- `request` — at least one replacement field.
+
+**Returns** the edited view.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L215)
+
+### ctx.goals.pause(agent, ref)
+
+```ts website-api
+/**
+ * Pause an active goal and disarm automatic continuation.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @returns the paused view.
+ */
+pause(agent: Agent, ref: GoalRef): GoalView
+```
+
+Pause an active goal and disarm automatic continuation.
+
+- `agent` — owning live agent.
+- `ref` — expected current revision.
+
+**Returns** the paused view.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L236)
+
+### ctx.goals.resume(agent, ref)
+
+```ts website-api
+/**
+ * Resume and arm a stopped goal, or rearm an active goal after a
+ * session-start edge, while its round budget still has capacity.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @returns the active view.
+ */
+resume(agent: Agent, ref: GoalRef): GoalView
+```
+
+Resume and arm a stopped goal, or rearm an active goal after a session-start edge, while its round budget still has capacity.
+
+- `agent` — owning live agent.
+- `ref` — expected current revision.
+
+**Returns** the active view.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L247)
+
+### ctx.goals.complete(agent, ref)
+
+```ts website-api
+/**
+ * Mark a current non-complete goal complete and disarm it.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @returns the completed view.
+ */
+complete(agent: Agent, ref: GoalRef): GoalView
+```
+
+Mark a current non-complete goal complete and disarm it.
+
+- `agent` — owning live agent.
+- `ref` — expected current revision.
+
+**Returns** the completed view.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L272)
+
+### 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.
+ * @param reason - policy-owned stable code and human-readable explanation.
+ * @returns the blocked view with its durable reason.
+ */
+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 with its durable reason.
+
+[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/goal/goal/src/index.ts#L290)
+
+### ctx.goals.clear(agent, ref)
+
+```ts website-api
+/**
+ * Clear the current goal while retaining a durable tombstone and history.
+ * @param agent - owning live agent.
+ * @param ref - expected current revision.
+ * @returns the tombstone ref whose revision is one past the cleared snapshot.
+ */
+clear(agent: Agent, ref: GoalRef): GoalRef
+```
+
+Clear the current goal while retaining a durable tombstone and history.
+
+- `agent` — owning live agent.
+- `ref` — expected current revision.
+
+**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#L311)