Merge remote-tracking branch 'origin/master' into xtr/agent-loop-message-machine

# Conflicts:
#	docs/architecture.i18n.yaml
#	docs/architecture.md
#	docs/architecture.zh.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.i18n.yaml
#	docs/core-data-structures/core.md
#	docs/core-data-structures/core.zh.md
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/core-data-structures/session.i18n.yaml
#	docs/event-producer-consumer.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	packages/core/agent-loop/README.i18n.yaml
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/README.zh.md
#	packages/core/agent-loop/src/loop.ts
#	packages/core/agent/README.i18n.yaml
#	packages/core/agent/tests/llm-target.spec.ts
#	packages/core/session/tests/request-header.spec.ts

.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-06-13-twin-llm-adapters.md: 5c3308b281ce71407002e95dd6e794da2a421fa8
-2026-06-13-twin-llm-adapters.zh.md: 93b084973bccaeb802508e4e939a259c281f2608
+2026-06-13-twin-llm-adapters.md: b922891d4438553fd96a7f4f4226f378e66e8ad2
+2026-06-13-twin-llm-adapters.zh.md: d98b57a0a2e7c92453046022e8cb50aa52994c0f

.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md

@@ -12,10 +12,10 @@ English | [中文](2026-06-13-twin-llm-adapters.zh.md)
 
 Ship **two** adapters against the one contract from the start, deliberately built on different internals:
 
-- `dsh-llm-deepseek` — hand-rolled `fetch` + SSE parsing against the DeepSeek API.
+- `dsh-llm-deepseek` — direct `fetch` + in-repo translation against the DeepSeek API; SSE framing is delegated to `eventsource-parser` ([the SSE-parser swap](../simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md)). The twin identity is owning the fetch/translate internals rather than delegating to a full provider SDK, not hand-rolling transport plumbing.
 - `dsh-llm-pi-ai` — the same endpoint through the `@earendil-works/pi-ai` library (its own event vocabulary).
 
-The rule they enforce: **anything the StreamChunk vocabulary cannot express for BOTH implementations is a core-vocabulary bug**, caught immediately rather than at the next provider. The pair pinned down conventions now documented on `StreamChunk` in `dsh-llm/src/types.ts`: usage emitted before finish, nothing after finish, tool-call `arguments` as raw JSON strings end-to-end, and the two sanctioned error paths (throw from `stream()` *or* end with `finish {kind:'error'|'aborted'}`) that a consumer must handle on both sides — a divergence the library-backed adapter surfaced that a single hand-rolled adapter would have hidden.
+The rule they enforce: **anything the StreamChunk vocabulary cannot express for BOTH implementations is a core-vocabulary bug**, caught immediately rather than at the next provider. The pair pinned down conventions now documented on `StreamChunk` in `dsh-llm/src/types.ts`: usage emitted before finish, nothing after finish, tool-call `arguments` as raw JSON strings end-to-end, and the two sanctioned error paths (throw from `stream()` *or* end with `finish {kind:'error'|'aborted'}`) that a consumer must handle on both sides — a divergence the library-backed adapter surfaced that a single direct-fetch adapter would have hidden.
 
 ## Alternatives considered
 
@@ -24,4 +24,4 @@ The rule they enforce: **anything the StreamChunk vocabulary cannot express for
 
 ## Consequences
 
-The twin doubles adapter and key-gated e2e maintenance—both cover V4 Flash and Pro across representative reasoning modes—in exchange for continuous seam-neutrality validation and a second implementation example. Both use `apiKey`, `baseURL`, and `models`; the hand-rolled adapter exposes `thinking`/`reasoningEffort`, while pi-ai exposes one `reasoning` level. A future conformance suite could justify retiring one adapter through a superseding Agent Note.
+The twin doubles adapter and key-gated e2e maintenance—both cover V4 Flash and Pro across representative reasoning modes—in exchange for continuous seam-neutrality validation and a second implementation example. Both use `apiKey`, `baseURL`, and `models`; the direct-fetch adapter exposes `thinking`/`reasoningEffort`, while pi-ai exposes one `reasoning` level. A future conformance suite could justify retiring one adapter through a superseding Agent Note.

.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md

@@ -12,10 +12,10 @@ Status: implemented
 
 从一开始就针对同一份契约交付**两个**适配器，刻意基于不同的内部实现构建：
 
-- `dsh-llm-deepseek`：手写 `fetch` + SSE（Server-Sent Events）解析，直接对接 DeepSeek API。
+- `dsh-llm-deepseek`：直接 `fetch` + 仓库内翻译逻辑对接 DeepSeek API；SSE（Server-Sent Events）分帧委托给 `eventsource-parser`（[SSE 解析器替换](../simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md)）。孪生身份在于自行持有 fetch/translate 内部实现而非委托给完整的提供方 SDK，不在于手写传输层管道。
 - `dsh-llm-pi-ai`：通过 `@earendil-works/pi-ai` 库访问同一端点（该库有自己的事件词汇）。
 
-二者共同执行的规则是：**凡 StreamChunk 词汇无法为两个实现同时表达的内容，都是核心词汇的缺陷**——立即暴露，而非等到下一个提供方接入时才发现。这对孪生体确定了现已记录在 `dsh-llm/src/types.ts` 中 `StreamChunk` 上的约定：usage 在 finish 之前发出、finish 之后不再有任何事件、工具调用的 `arguments` 全程以原始 JSON 字符串传递，以及消费方必须在两侧都处理的两条合法错误路径（`stream()` 抛异常，*或者*以 `finish {kind:'error'|'aborted'}` 结束）。后一项分歧正是由基于库的适配器暴露出来的，单一手写适配器会将其隐藏。
+二者共同执行的规则是：**凡 StreamChunk 词汇无法为两个实现同时表达的内容，都是核心词汇的缺陷**——立即暴露，而非等到下一个提供方接入时才发现。这对孪生体确定了现已记录在 `dsh-llm/src/types.ts` 中 `StreamChunk` 上的约定：usage 在 finish 之前发出、finish 之后不再有任何事件、工具调用的 `arguments` 全程以原始 JSON 字符串传递，以及消费方必须在两侧都处理的两条合法错误路径（`stream()` 抛异常，*或者*以 `finish {kind:'error'|'aborted'}` 结束）。后一项分歧正是由基于库的适配器暴露出来的，单一直接 fetch 适配器会将其隐藏。
 
 ## 曾考虑的替代方案
 
@@ -24,4 +24,4 @@ Status: implemented
 
 ## 后果
 
-孪生体使适配器和需要密钥的 e2e 维护量翻倍——两者都覆盖 V4 Flash 和 Pro 在各代表性推理（reasoning）模式下的行为——换来的是持续的 seam 中立性验证和第二份实现示例。两个适配器均使用 `apiKey`、`baseURL` 和 `models`；手写适配器暴露 `thinking`/`reasoningEffort`，pi-ai 适配器暴露一个 `reasoning` 级别。未来如果有一致性测试套件，可以通过后续 Agent Note 论证退役其中一个适配器。
+孪生体使适配器和需要密钥的 e2e 维护量翻倍——两者都覆盖 V4 Flash 和 Pro 在各代表性推理（reasoning）模式下的行为——换来的是持续的 seam 中立性验证和第二份实现示例。两个适配器均使用 `apiKey`、`baseURL` 和 `models`；直接 fetch 适配器暴露 `thinking`/`reasoningEffort`，pi-ai 适配器暴露一个 `reasoning` 级别。未来如果有一致性测试套件，可以通过后续 Agent Note 论证退役其中一个适配器。

.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-07-20-routed-model-context-and-compaction-policy.md: b637ba24d4ba5fc25c8cdd515a821ee97883a326
-2026-07-20-routed-model-context-and-compaction-policy.zh.md: 084e762ec29ddc0aecb0bf422c147b9d3122726b
+2026-07-20-routed-model-context-and-compaction-policy.md: b00c744e4ac79983a1f492d710e7b1542278c4f4
+2026-07-20-routed-model-context-and-compaction-policy.zh.md: 88e26aa7a99e8deb434d9a8fd80784be410a999a

.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.md

@@ -14,9 +14,9 @@ Neither obvious configuration owner is sufficient. Compact-basic is optional and
 
 ### Adapters own exact-route capacity
 
-`LlmAdapter.resolveModelContext(provider, model)` optionally returns `LlmModelContext` for one exact route. `LlmService.resolveModelContext()` selects the registered route owner, validates a positive integer `contextWindow`, and returns a detached value. The query is independent of `listModels()`: an unlisted dynamic model may have capacity metadata, and `undefined` means only that the adapter cannot describe capacity.
+`LlmAdapter.resolveModel(provider, model, signal?)` returns aggregate metadata for one exact route, with optional `LlmModelContext` under its `context` field. `LlmService.resolveModelInfo()` selects the registered route owner, validates a positive integer `contextWindow`, and returns detached metadata. The query is independent of `listModels()`: an unlisted dynamic model may have capacity metadata, and an absent `context` means only that the adapter cannot describe capacity.
 
-The hand-rolled DeepSeek adapter accepts optional `contextWindow` on each configured model plus an adapter-wide `defaultContextWindow`. Exact model capacity wins; an entry without capacity and an unlisted pass-through id inherit the adapter default, or return `undefined` when it is absent. The two built-in model entries each publish an exact 128,000-token capacity. The pi-ai adapter resolves capacity from the same catalog descriptor that authoritatively resolves the request model.
+The hand-rolled DeepSeek adapter accepts optional `contextWindow` on each configured model plus an adapter-wide `defaultContextWindow`. Exact model capacity wins; an entry without capacity and an unlisted pass-through id inherit the adapter default, or omit `context` when it is absent. The two built-in model entries each publish an exact 128,000-token capacity. The pi-ai adapter resolves capacity from the same catalog descriptor that authoritatively resolves the request model.
 
 ### Token measurement remains model-agnostic
 

.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.zh.md

@@ -14,9 +14,9 @@ Status: implemented
 
 ### 适配器拥有精确路由容量
 
-`LlmAdapter.resolveModelContext(provider, model)` 可以为一条精确路由返回 `LlmModelContext`。`LlmService.resolveModelContext()` 选择已注册的路由所属方，验证 `contextWindow` 为正整数，并返回分离值。该查询独立于 `listModels()`：不在目录中的动态模型也可以拥有容量元数据，而 `undefined` 只表示适配器无法描述容量。
+`LlmAdapter.resolveModel(provider, model, signal?)` 返回一条精确路由的聚合元数据，其中可选的 `LlmModelContext` 位于 `context` 字段下。`LlmService.resolveModelInfo()` 选择已注册的路由所属方，验证 `contextWindow` 为正整数，并返回分离的元数据。该查询独立于 `listModels()`：不在目录中的动态模型也可以拥有容量元数据，而缺少 `context` 只表示适配器无法描述容量。
 
-手写 DeepSeek 适配器允许每个已配置模型提供可选 `contextWindow`，并支持适配器级 `defaultContextWindow`。精确模型容量优先；未提供容量的模型项与未列出的透传 id 会继承适配器默认值，若默认值也不存在则返回 `undefined`。两个内置模型项都公开精确的 128,000 token 容量。pi-ai 适配器从同一个目录描述符解析容量，该描述符也用于权威解析请求模型。
+手写 DeepSeek 适配器允许每个已配置模型提供可选 `contextWindow`，并支持适配器级 `defaultContextWindow`。精确模型容量优先；未提供容量的模型项与未列出的透传 id 会继承适配器默认值，若默认值也不存在则省略 `context`。两个内置模型项都公开精确的 128,000 token 容量。pi-ai 适配器从同一个目录描述符解析容量，该描述符也用于权威解析请求模型。
 
 ### Token 计量保持模型无关
 

.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-07-23-toolview-dissolution.md: a420c5945d0272cf8087d5f623e9c383c286d7c2
-2026-07-23-toolview-dissolution.zh.md: 47c1f392f5f7ddbf4e6c686b2574faa7987e6126
+2026-07-23-toolview-dissolution.md: 80c2688b152d1afe1236d4815633a5bf024db1d2
+2026-07-23-toolview-dissolution.zh.md: 928c5f445d601b2246d3ae2f9360232643814468

.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md

@@ -14,7 +14,7 @@ After the view ring dissolved into the slot system, the client kept exactly one
 
 The tool ring is gone as independent infrastructure: a tool row is a **keyed child slot each view declares for itself**, and the client has exactly one registration model. The justification above was hollow — a keyed slot's *key space* is already runtime-open (SlotMap declares slots, never keys; the ask-user composer's `key: 'question'` was the precedent), so the open tool-name set fits `entryKey` dispatch natively.
 
-Shipped shape (current-state narrative also in the [architecture note](2026-07-19-gui-web-client-architecture.md)): the chat entry's `children` table declares `'conversation.chat.toolview'` (keyed/session); the render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback` (the default card is domain property; the fallback option is ordinary renderSlot grammar). The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails` — details being a session-level facility, not chat-private), and `ToolRowProps` pre-composes it with the session standard kit for registrant components. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam — apply mounts `ConversationService` *after* the chat registration, so the service being present guarantees the slot is declared, by construction. Session-dimension differentiation happens inside the component (`useSessions` reading `parentId` — the decision sits where all the information already is); the bash sample is the third-party-posture exemplar. Trajectory/waterfall toolview slots share this exact shape (names fixed by the slot-naming discipline `<domain>.<entry>.<hole>`, one shared owner type) and land with their own row render sites — RendersCheck rejects a declaration nobody renders, so the type system, not convention, blocks early empty declarations.
+Shipped shape (current-state narrative also in the [architecture note](2026-07-19-gui-web-client-architecture.md)): the chat entry's `children` table declares `'conversation.chat.toolview'` (keyed/session); the render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback` (the default card is domain property; the fallback option is ordinary renderSlot grammar). The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails` — details being a session-level facility, not chat-private), and `ToolRowProps` pre-composes it with the session standard kit for registrant components. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam — apply mounts `ConversationService` *after* the chat registration, so the service being present guarantees the slot is declared, by construction. Session-dimension differentiation happens inside the component (`useSessions` reading `parentId` — the decision sits where all the information already is); the bash sample is the third-party-posture exemplar and paints the same ToolRow chrome as Think (`Bash · {description}`, with a scoped badge only in child sessions). Trajectory/waterfall toolview slots share this exact shape (names fixed by the slot-naming discipline `<domain>.<entry>.<hole>`, one shared owner type) and land with their own row render sites — RendersCheck rejects a declaration nobody renders, so the type system, not convention, blocks early empty declarations.
 
 Registry-era responsibilities all have successor homes: inject caching and row error isolation ride the framework renderer (entry×scope cache, per-entry `SlotErrorBoundary`); subscribe/getVersion ride the slot core's per-key version machinery; the future "store seat" is the ordinary store seat keyed slots already have (interaction-draft durability is its first named consumer); miss fallback is the call-site `fallback` option.
 

.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md

@@ -14,7 +14,7 @@ Status: implemented
 
 工具环作为独立基础设施已消失：工具行是**各视图为自己声明的 keyed 子槽**，client 全域只剩一种注册模型。上述理由是空的——keyed slot 的 *key 空间*本就运行时开放（SlotMap 声明槽、从不声明 key；ask-user composer 的 `key: 'question'` 即先例），开放的 tool 名集合天然适配 `entryKey` 分发。
 
-落地形态（现状叙述同见[架构注](2026-07-19-gui-web-client-architecture.md)）：chat 条目的 `children` 表声明 `'conversation.chat.toolview'`（keyed/session）；渲染点逐行以 `entryKey: toolName` 分发、以 `GenericToolCard` 作调用点 `fallback`（默认卡片是域产权；fallback 选项就是普通 renderSlot 文法）。owner 载荷是统一的 `ToolRowOwnerProps`（`callId`/`toolName`/`block`/`openDetails`——details 是会话级设施，非 chat 私货），`ToolRowProps` 把它与 session 标配 kit 预组合供注册方组件取用。注册方就是普通插件：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作加载序缝——apply 把 `ConversationService` 挂在 chat 注册*之后*，故服务在场即保证槽已声明，构造使然。会话维差异化在组件内完成（`useSessions` 读 `parentId`——决策放在已有全部信息的地方）；bash 样例即第三方姿态的样板。trajectory/waterfall 的 toolview 槽共用这套形状（槽名按槽名纪律 `<域>.<条目>.<孔位>` 定死，共用一张 owner 类型），随各自的行渲染点落地——RendersCheck 拒绝无人渲染的声明，挡住提前空声明的是类型系统而非约定。
+落地形态（现状叙述同见[架构注](2026-07-19-gui-web-client-architecture.md)）：chat 条目的 `children` 表声明 `'conversation.chat.toolview'`（keyed/session）；渲染点逐行以 `entryKey: toolName` 分发、以 `GenericToolCard` 作调用点 `fallback`（默认卡片是域产权；fallback 选项就是普通 renderSlot 文法）。owner 载荷是统一的 `ToolRowOwnerProps`（`callId`/`toolName`/`block`/`openDetails`——details 是会话级设施，非 chat 私货），`ToolRowProps` 把它与 session 标配 kit 预组合供注册方组件取用。注册方就是普通插件：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作加载序缝——apply 把 `ConversationService` 挂在 chat 注册*之后*，故服务在场即保证槽已声明，构造使然。会话维差异化在组件内完成（`useSessions` 读 `parentId`——决策放在已有全部信息的地方）；bash 样例即第三方姿态的样板，并与 Think 绘制同一套 ToolRow chrome（`Bash · {description}`，scoped badge 仅出现在子会话）。trajectory/waterfall 的 toolview 槽共用这套形状（槽名按槽名纪律 `<域>.<条目>.<孔位>` 定死，共用一张 owner 类型），随各自的行渲染点落地——RendersCheck 拒绝无人渲染的声明，挡住提前空声明的是类型系统而非约定。
 
 registry 时代的职责各有后继居所：inject 缓存与行错误隔离乘框架渲染器（entry×scope 缓存、per-entry `SlotErrorBoundary`）；subscribe/getVersion 乘 slot core 的 per-key 版本机；将来的「store 席位」就是 keyed slot 本就拥有的普通 store 席位（交互草稿耐久性是其首个具名消费者）；miss 兜底即调用点 `fallback` 选项。
 

.agents/notes/implemented/architecture/2026-07-24-adapter-owned-reasoning-effort-capabilities.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
+2026-07-24-adapter-owned-reasoning-effort-capabilities.md: cc66e4ec151fcc04445a91f4a3527cbddd130c33
+2026-07-24-adapter-owned-reasoning-effort-capabilities.zh.md: e0d28e1aca370068478e8fb1704defeaac3ab351

.agents/notes/implemented/architecture/2026-07-24-adapter-owned-reasoning-effort-capabilities.md

@@ -0,0 +1,33 @@
+# Agent Note: Adapter-owned reasoning effort capabilities
+
+Status: implemented
+
+English | [中文](2026-07-24-adapter-owned-reasoning-effort-capabilities.zh.md)
+
+## Problem
+
+Reasoning strength was adapter configuration only, so a conversation could not discover or change the selected model's supported levels between requests. Promoting one adapter's level union into `dsh-llm` would make every provider and model adopt names it may not support, while a provider-specific options bag would make the loop unable to validate or durably reconstruct the effective request.
+
+## Decision
+
+`dsh-llm` represents a reasoning effort as the opaque branded `ReasoningEffortId`. One adapter-owned `resolveModel(provider, model, signal?)` query returns `LlmResolvedModelInfo`: exact model identity plus optional context and reasoning metadata. `LlmService.resolveModelInfo()` validates and detaches that aggregate. When present, `reasoning.efforts` is a non-empty ordered list of ids with display metadata and may name one configured default. The core requires an explicit or configured effort to appear exactly in that list and never clamps or aliases a value.
+
+`LlmCallConfig` and `GenerateOptions` carry the optional effort. The agent loop prepares the post-`agent/request` config under the active turn signal before writing `request/header`, so defaults and dynamic changes are model-visible only after becoming durable facts. The prepared call retains the exact adapter registration across asynchronous exact-model resolution, durable header logging, and dispatch; direct `LlmService.stream()` calls likewise capture their final registration before awaiting resolution. A route with no registered adapter retains its proposed config so an `llm/stream` middleware can own and short-circuit it; terminal dispatch still rejects an unhandled route. A resumed loop retains the logged effort only when its initial provider/model route is unchanged; a route change discards the previous model's opaque id.
+
+The native DeepSeek adapter advertises `off`, `high`, and `max` when deployment policy permits thinking, and defaults to the configured effort or `high`. Its adapter-owned `off` maps to `thinking.type: disabled` with no `reasoning_effort`; `high` and `max` enable thinking and carry their official wire effort. A `thinking: disabled` deployment publishes only `off` and rejects attempts to enable thinking before provider I/O. The pi-ai adapter publishes each exact model's `getSupportedThinkingLevels()` result unchanged, including `off`, preserves an absent profile default as a provider default, and leaves provider wire-value mapping inside pi-ai. Its common stream options represent `off` by omitting `reasoning`, as required by pi-ai's own API.
+
+## Alternatives considered
+
+**Define the pi-ai `ThinkingLevel` union in core.** Rejected because current pi-ai canonical names are an adapter implementation detail; a future provider can expose a different identifier without requiring a core release.
+
+**Carry an untyped provider options object.** Rejected because the loop could neither validate a selected value nor put a stable provider-neutral fact in the request header.
+
+**Clamp unsupported levels.** Rejected because a silent substitution makes the user's selected control differ from the logged request intent and hides stale deployment configuration.
+
+**Normalize every adapter to a core-owned level list or remove `off`.** Rejected because the selectable vocabulary belongs to the exact model capability. A client can render an adapter's `off` option without requiring every adapter to expose it.
+
+## Consequences
+
+Clients can query one exact route once and render its identity, context capacity, and adapter-owned reasoning choices without knowing a global enum or synthesizing `off`. Adapter configuration remains the deployment-default and policy owner, while `agent/request` can replace the effective effort on each step within that policy. Invalid exact identity, context, or reasoning metadata fails with `INVALID_MODEL_INFO`, `INVALID_MODEL_CONTEXT`, or `INVALID_MODEL_REASONING`; unsupported explicit or configured values fail with `UNSUPPORTED_REASONING_EFFORT` before provider I/O.
+
+The aggregate exact-model query is asynchronous and may fail for adapters backed by authoritative catalogs. Its optional signal is the caller's cancellation boundary; an asynchronous adapter must settle promptly after abort so loop disposal can reach quiescence. Keyless service, adapter, loop, session, and request-header tests pin validation, defaulting, dynamic changes, logging, resume behavior, HMR registration ownership, and cancellation; runnable snapshots pin the resolved effort in real assembled request headers, while key-gated adapter tests exercise provider serialization.

.agents/notes/implemented/architecture/2026-07-24-adapter-owned-reasoning-effort-capabilities.zh.md

@@ -0,0 +1,33 @@
+# Agent Note：适配器持有的推理强度能力
+
+Status: implemented
+
+[English](2026-07-24-adapter-owned-reasoning-effort-capabilities.md) | 中文
+
+## 问题
+
+推理强度过去只能在适配器中配置，因此对话无法在多次请求之间发现或更改所选模型支持的等级。若将某个适配器的等级联合类型提升到 `dsh-llm`，所有提供方和模型都必须采用一套自身可能并不支持的名称；若改用提供方特有的 options 对象，主循环又无法校验最终生效的请求，也无法通过持久化记录准确重建该请求。
+
+## 决策
+
+`dsh-llm` 使用不透明的品牌类型 `ReasoningEffortId` 表示推理强度。由适配器持有的单次 `resolveModel(provider, model, signal?)` 查询返回 `LlmResolvedModelInfo`，其中包含确切模型身份以及可选的上下文和推理元数据。`LlmService.resolveModelInfo()` 会校验该聚合结果并返回分离值。`reasoning.efforts` 存在时，是包含展示元数据的非空有序 ID 列表，并可指定一个由配置确定的默认值。核心要求显式指定或配置指定的推理强度与列表中的某个 ID 完全一致，且绝不自动调整或为值提供别名。
+
+`LlmCallConfig` 和 `GenerateOptions` 携带可选的推理强度。agent loop（智能体循环）在活跃轮次信号的控制下准备 `agent/request` 处理完成后的配置，再写入 `request/header`，因此默认值和动态变更只有成为持久化事实后才对模型可见。准备完成的调用在异步确切模型解析、请求头持久记录和分派全程保留同一项确切的适配器注册；直接调用 `LlmService.stream()` 时，也会在等待解析前捕获最终的适配器注册。没有已注册适配器的路由会保留原定配置，使 `llm/stream` 中间件可以接管并短路该请求；若仍未得到处理，最终分发会拒绝该路由。恢复后的主循环仅在初始提供方/模型路由未变时保留日志中记录的推理强度；如果路由发生变化，则丢弃上一模型的不透明 ID。
+
+当部署策略允许思考时，原生 DeepSeek 适配器声明 `off`、`high` 和 `max`，默认使用配置指定的推理强度，若未配置则使用 `high`。由适配器持有的 `off` 映射为 `thinking.type: disabled`，且不带 `reasoning_effort`；`high` 和 `max` 会启用思考并携带各自的官方协议强度值。配置为 `thinking: disabled` 的部署仅声明 `off`，并会在提供方 I/O 前拒绝启用思考的尝试。pi-ai 适配器原样发布每个确切模型的 `getSupportedThinkingLevels()` 结果，其中包括 `off`；profile 未指定默认值时保留提供方默认行为，并将提供方协议值的映射留在 pi-ai 内部。按照 pi-ai 自身 API 的要求，其通用流选项通过省略 `reasoning` 来表示 `off`。
+
+## 备选方案
+
+**在核心中定义 pi-ai 的 `ThinkingLevel` 联合类型。** 不予采纳：pi-ai 当前的规范名称属于适配器实现细节；未来的提供方可以暴露不同的标识符，而无需为此发布新的核心版本。
+
+**携带无类型约束的提供方 options 对象。** 不予采纳：主循环既无法校验选定值，也无法在请求头中写入稳定且与提供方无关的事实。
+
+**自动调整不支持的等级。** 不予采纳：静默替换会导致用户选定的控制项与日志记录的请求意图不一致，还会掩盖陈旧的部署配置。
+
+**将每个适配器规范化为核心持有的等级列表，或移除 `off`。** 不予采纳：可选值集合属于确切模型的能力。客户端可以渲染某个适配器的 `off` 选项，而无需要求所有适配器都暴露该选项。
+
+## 影响
+
+客户端只需查询一次确切路由，即可渲染其身份、上下文容量和由适配器持有的推理选项，而无需了解全局枚举或自行合成 `off`。适配器配置仍是部署默认值和策略的归属方，`agent/request` 则可以在该策略范围内为每个步骤替换实际生效的推理强度。确切身份、上下文或推理元数据无效时，分别抛出 `INVALID_MODEL_INFO`、`INVALID_MODEL_CONTEXT` 或 `INVALID_MODEL_REASONING`；显式指定或配置指定的值不受支持时，会在提供方 I/O 前抛出 `UNSUPPORTED_REASONING_EFFORT`。
+
+确切模型元数据的聚合查询采用异步方式，并且对于由权威目录支持的适配器可能失败。可选信号构成调用方的取消边界；异步适配器必须在信号中止后迅速完成结算，使主循环的资源释放达到完全停稳。无密钥的服务、适配器、主循环、会话和请求头测试为校验、默认值解析、动态变更、日志记录、恢复行为、HMR（热模块替换）期间的注册所有权和取消提供回归保障；可运行快照锁定实际组装请求头中的已解析推理强度，仅在有密钥时运行的适配器测试则覆盖提供方序列化。

.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-06-29-todo-write-tool.md: df1bee2801b0e01b290b63f6edbe2e5b1be80cb7
-2026-06-29-todo-write-tool.zh.md: 7fa5cb2aad2b32ef0662df04ff6576be14a3a8e7
+2026-06-29-todo-write-tool.md: 760373d64f462e3717a174d5793e6d47ab76b0b4
+2026-06-29-todo-write-tool.zh.md: fd29e6049e6a729c2c7e78860ad7c065422da60e

.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md

@@ -10,7 +10,7 @@ The harness gives the model bash and subagent tools but no way to record a struc
 
 ## Decision
 
-Add a model-facing `todo_write(todos: [{ content, status }])` tool whose whole-list state lives on the event-sourced session log as a new `todo/write` `SessionEventMap` variant. Interactive hosts render from the durable event; the TUI folds it directly, while the [automation-only ACP bridge](../simplification/2026-07-23-acp-automation-only-protocol.md) deliberately omits todo presentation.
+Add a model-facing `todo_write(todos: [{ content, status }])` tool whose whole-list state lives on the event-sourced session log as a new `todo/write` `SessionEventMap` variant. Interactive hosts render from the durable event: the TUI folds it directly, the web client projects it into `ConversationSnapshot.todos` ([web todo display](2026-07-23-web-todo-display.md)), while the [automation-only ACP bridge](../simplification/2026-07-23-acp-automation-only-protocol.md) deliberately omits todo presentation.
 
 ### Whole-list replace, three-state status
 
@@ -18,7 +18,7 @@ The model sends the entire list every call; the new list replaces the old (last-
 
 ### State on the session log, not a service
 
-The list is appended as a `todo/write` event carrying the full `{ todos }` snapshot. The harness is event-sourced — the LLM history, tool calls, and turn structure all live on the log — so the todo list lives there too. This buys durability, replay, and resume reconstruction for free: a reopened session re-derives the current list from the latest `todo/write`, with no separate persistence backend, in-memory service to rehydrate, or extra wiring. An in-memory `ctx.todos` service would have to reinvent all of that.
+The list is appended as a `todo/write` event carrying the full `{ todos }` snapshot. The harness is event-sourced — the LLM history, tool calls, and turn structure all live on the log — so the todo list lives there too. This buys durability, replay, and resume reconstruction for free: a reopened session re-derives the current list from the latest `todo/write`, with no separate persistence backend, in-memory service to rehydrate, or extra wiring. An in-memory `ctx.todos` service would have to reinvent all of that. (Full-log consumers get this reconstruction outright; the web client's paged window gets it from the tail history page's host-computed projection — see the [web todo display note](2026-07-23-web-todo-display.md).)
 
 ### NOT a surface event
 

.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md

@@ -10,7 +10,7 @@ harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结
 
 ## 决策
 
-新增一个面向模型的 `todo_write(todos: [{ content, status }])` 工具，其整列表状态作为新的 `todo/write` `SessionEventMap` 变体存储在事件溯源的会话日志上。交互式宿主从持久事件渲染；TUI 直接折叠它，而[仅面向自动化的 ACP（Agent Client Protocol）桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)有意省略 todo 展示。
+新增一个面向模型的 `todo_write(todos: [{ content, status }])` 工具，其整列表状态作为新的 `todo/write` `SessionEventMap` 变体存储在事件溯源的会话日志上。交互式宿主从持久事件渲染：TUI 直接折叠它，web 客户端将其投影进 `ConversationSnapshot.todos`（[web todo 展示](2026-07-23-web-todo-display.md)），而[仅面向自动化的 ACP（Agent Client Protocol）桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)有意省略 todo 展示。
 
 ### 整列表替换，三态 status
 
@@ -18,7 +18,7 @@ harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结
 
 ### 状态在会话日志上，而非服务
 
-列表作为 `todo/write` 事件追加到日志，携带完整的 `{ todos }` 快照。harness 是事件溯源的——LLM（大语言模型）历史、工具调用和轮次结构都在日志上——所以 todo 列表也在那里。这免费获得了持久性、回放和恢复重建：重新打开的会话从最新的 `todo/write` 重新推导当前列表，无需独立的持久化后端、无需重新注水的内存服务、无需额外接线。一个内存中的 `ctx.todos` 服务需要重新发明以上所有。
+列表作为 `todo/write` 事件追加到日志，携带完整的 `{ todos }` 快照。harness 是事件溯源的——LLM（大语言模型）历史、工具调用和轮次结构都在日志上——所以 todo 列表也在那里。这免费获得了持久性、回放和恢复重建：重新打开的会话从最新的 `todo/write` 重新推导当前列表，无需独立的持久化后端、无需重新注水的内存服务、无需额外接线。一个内存中的 `ctx.todos` 服务需要重新发明以上所有。（全量 log 消费者直接获得这份重建；web 客户端的分页窗口则从尾页 history 携带的 host 计算投影获得——见 [web todo 展示 Note](2026-07-23-web-todo-display.md)。）
 
 ### 不是 surface 事件
 

.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-07-17-dedicated-full-screen-tui-front-door.md: aac67ffec89606d04d5abfd233d0469e2241b102
-2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 0f64e2ce14b18d315f75913b82c731e77758e377
+2026-07-17-dedicated-full-screen-tui-front-door.md: 8d7c7b00c8d9b15ea3f2419ed44ca88209e60dad
+2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 49e9541c9f98c9f3beba11945ff452fc38bd9ede

.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md

@@ -22,9 +22,9 @@ The selected front door receives the exact generated or resumed `SessionId` used
 
 The TUI rebuilds the transcript from the active `session.surface` and reprojects it whenever an event carries a `surfaceOp`, so resumed and compacted history matches the model-visible conversation. It renders Markdown text and reasoning, token totals, the latest `todo/write` plan, and tool cards produced through each tool definition's `presentCall` and `presentResult` methods. Long card bodies retain a configurable head/tail preview with the hidden-line count; one terminal control expands or collapses every card. Pending chunks and tool calls update the same components that completed events settle.
 
-Editor input calls `agent.send()` while idle and `agent.steer()` while a turn is running. Cancellation, reasoning visibility, tool-card expansion, redraw, transcript clearing, and exit are terminal-only controls. The idle footer derives context occupancy from `tokenMeter` and shows the selected model; during a run, elapsed activity and the Escape interrupt hint replace that summary. `/status` remains available in either state and appends a detailed terminal-only snapshot: session identity and timestamps, selected model and reasoning visibility, lifecycle counts folded from the event log, the same deduplicated usage buckets and KV-cache rate as the footer, and context use from `tokenMeter` plus the selected model's advertised capacity. The plugin registers the shared `userInteraction` provider and presents queued questions in a wide bottom-left keyboard panel with batch progress, numbered options, and aligned descriptions; agent behavior and answer logging remain owned by their existing services.
+Editor input calls `agent.send()` while idle and `agent.steer()` while a turn is running. Cancellation, reasoning visibility, tool-card expansion, redraw, transcript clearing, and exit are terminal-only controls. The idle footer derives context occupancy from `tokenMeter` and shows the selected model and explicit reasoning effort; during a run, elapsed activity and the Escape interrupt hint replace that summary. `/status` remains available in either state and appends a detailed terminal-only snapshot: session identity and timestamps, selected model, reasoning effort/default state and reasoning visibility, lifecycle counts folded from the event log, the same deduplicated usage buckets and KV-cache rate as the footer, and context use from `tokenMeter` plus the selected model's advertised capacity. The plugin registers the shared `userInteraction` provider and presents queued questions in a wide bottom-left keyboard panel with batch progress, numbered options, and aligned descriptions; agent behavior and answer logging remain owned by their existing services.
 
-The `/model` command presents the advisory `ctx.llm` catalog as a keyboard selector and changes only this TUI session's target; argument forms remain available for direct selection. Agent-scoped prompt-assembly and request waterfalls snapshot one provider/model pair per step, so `{{provider}}` / `{{model}}` interpolation and request routing cannot split when a command arrives during assembly. The latest logged request header restores a used target; a selection that never reaches a request remains process-local.
+The `/model` command presents the advisory `ctx.llm` catalog as a keyboard selector and changes only this TUI session's target; argument forms remain available for direct selection. Each model row owns the adapter-advertised reasoning-effort order and default: Shift+Tab cycles that row's efforts, includes provider-default behavior when the adapter advertises no default, and leaves models without selectable metadata unchanged. Agent-scoped prompt-assembly and request waterfalls snapshot one provider/model/reasoning-effort target per step, so `{{provider}}` / `{{model}}` interpolation and request routing cannot split when a command arrives during assembly. The latest logged request header restores a used target; a selection that never reaches a request remains process-local.
 
 ### Terminal ownership
 
@@ -49,4 +49,4 @@ The implemented [TUI terminal-state snapshot Agent Note](../testing/2026-07-18-t
 - The TUI carries a pi-tui dependency and a strict TTY requirement; non-TTY deployments use the Headless app or a structured protocol.
 - Session projection makes resume and compaction consistent with the durable conversation, but one configured session owns the transcript and editor.
 - Tool packages extend terminal cards through their existing presentation methods without adding tool-specific branches to the TUI.
-- Model selection uses adapter-advertised metadata without turning catalog membership into request validation; unused selections are not durable state.
+- Model and reasoning-effort selection use adapter-advertised metadata without turning catalog membership into request validation; unused selections are not durable state.

.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md

@@ -22,9 +22,9 @@ DeepSeek Harness 将 [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README
 
 TUI 从活跃的 `session.surface` 重建 transcript（文本记录），并在事件携带 `surfaceOp` 时重新投影，因此恢复或压缩后的历史与模型可见会话保持一致。TUI 渲染 Markdown 文本与推理、token 用量、最新 `todo/write` 计划，以及各工具定义通过 `presentCall` 和 `presentResult` 方法生成的工具卡片。较长的工具卡片正文会保留可配置的头尾预览，并显示隐藏行数；一个终端控制可以展开或收起全部卡片。进行中的分片与工具调用会更新同一组组件，随后由完成事件收束状态。
 
-agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调用 `agent.steer()`。取消、推理显隐、工具卡片展开、重绘、清空 transcript 和退出都只是终端控制。空闲态页脚根据 `tokenMeter` 得出上下文占用率，并显示所选模型；agent 运行期间，该摘要会替换为带已用时长的活动指示和 Escape 中断提示。`/status` 在这两种状态下均可用，并会追加一份仅在终端显示的详细快照，其中包括会话标识与时间戳、所选模型及推理显隐状态、从事件日志归并得出的生命周期计数、与页脚一致的去重用量分项和 KV 缓存命中率，以及 `tokenMeter` 给出的上下文用量和所选模型公布的容量。插件注册共享的 `userInteraction` 提供方，在左下角宽幅键盘操作面板中呈现排队的问题，面板显示批次进度、带编号的选项和对齐的描述；agent 行为和答案日志仍由既有服务负责。
+agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调用 `agent.steer()`。取消、推理显隐、工具卡片展开、重绘、清空 transcript 和退出都只是终端控制。空闲态页脚根据 `tokenMeter` 得出上下文占用率，并显示所选模型和显式选定的推理强度；agent 运行期间，该摘要会替换为带已用时长的活动指示和 Escape 中断提示。`/status` 在这两种状态下均可用，并会追加一份仅在终端显示的详细快照，其中包括会话标识与时间戳、所选模型、推理强度（或默认状态）及推理显隐状态、从事件日志归并得出的生命周期计数、与页脚一致的去重用量分项和 KV 缓存命中率，以及 `tokenMeter` 给出的上下文用量和所选模型公布的容量。插件注册共享的 `userInteraction` 提供方，在左下角宽幅键盘操作面板中呈现排队的问题，面板显示批次进度、带编号的选项和对齐的描述；agent 行为和答案日志仍由既有服务负责。
 
-`/model` 命令将建议性的 `ctx.llm` 目录呈现为键盘选择器，并且只更改当前 TUI 会话的目标；带参数的形式仍可直接选择目标。agent 作用域内的 prompt 组装和请求两条 waterfall（瀑布式事件）会为每个 step 快照一次同一个提供方/模型字段组合，因此即使命令在组装期间到达，`{{provider}}` / `{{model}}` 插值与请求路由也不会分裂。系统通过日志中最新的请求头恢复已经使用过的目标；未被请求使用的选择只保留在当前进程中。
+`/model` 命令将建议性的 `ctx.llm` 目录呈现为键盘选择器，并且只更改当前 TUI 会话的目标；带参数的形式仍可直接选择目标。每个模型行都持有适配器公布的推理强度顺序和默认值：按 Shift+Tab 可循环切换该行的推理强度；如果适配器没有公布默认值，循环中还会包含提供方默认行为；没有可选元数据的模型则保持不变。agent 作用域内的 prompt 组装和请求两条 waterfall（瀑布式事件）会为每个步骤快照一次同一个提供方/模型/推理强度目标，因此即使命令在组装期间到达，`{{provider}}` / `{{model}}` 插值与请求路由也不会分裂。系统通过日志中最新的请求头恢复已经使用过的目标；未被请求使用的选择只保留在当前进程中。
 
 ### 终端所有权
 
@@ -49,4 +49,4 @@ agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调
 - TUI 会引入 pi-tui 依赖并严格要求 TTY；非 TTY 部署使用 Headless app 或结构化协议。
 - 会话投影使恢复和压缩与持久会话保持一致，但只有一个已配置会话拥有 transcript 和编辑器。
 - 工具包通过既有呈现方法扩展终端卡片，无需在 TUI 中增加工具专用分支。
-- 模型选择使用适配器提供的目录元数据，但不会把目录成员关系变成请求校验；未使用的选择不属于持久化状态。
+- 模型和推理强度选择使用适配器公布的元数据，但不会把目录成员关系变成请求校验；未使用的选择不属于持久化状态。

.agents/notes/implemented/feature/2026-07-23-web-assistant-markdown.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-07-23-web-assistant-markdown.md: ce98a16fa43e2743c18826ee7f2344c38e7c70e7
-2026-07-23-web-assistant-markdown.zh.md: 0d6fd2f9e6b91f76830586ecf4c29774e5d6978a
+2026-07-23-web-assistant-markdown.md: 38d193271d88b3a8f32ba1b191e8a6d432176281
+2026-07-23-web-assistant-markdown.zh.md: be3cd041c6012af142fc27934fda125dfc4cf6de

.agents/notes/implemented/feature/2026-07-23-web-assistant-markdown.md

@@ -12,13 +12,17 @@ The Web conversation preserves assistant Markdown source through session events,
 
 `@deepseek-ai/dsh-client-ui-primitives` exports `MarkdownText` as the untrusted assistant-text renderer, and `ui-conversation` selects it only for assistant `text` blocks. Finalized history, the streaming tail, and interrupted partials already share `AssistantMarkdown`, so they receive the same renderer without changing events or snapshots. User and steering messages keep `MessageText` and remain literal.
 
-`MarkdownText` uses `react-markdown` with `remark-gfm` to build React elements from an AST. It covers CommonMark blocks plus GFM tables, task lists, strikethrough, and autolinks without `dangerouslySetInnerHTML`, raw-HTML parsing, or syntax highlighting. The dependency is explicit in `ui-primitives`; because that pure library is seeded by the Web shell, the parser is part of the initial browser bundle.
+`MarkdownText` uses `react-markdown` with `remark-gfm` to build React elements from an AST. It covers CommonMark blocks plus GFM tables, task lists, strikethrough, and autolinks without raw-HTML parsing. Fenced code routes through the shared `CodeBlock`, which highlights registered grammars with the client's shiki singleton (`--shiki-*` tokens) and falls back to plain monospace otherwise. While a turn streams, fences stay on the plain arm so growing fences are not retokenized every chunk.
+
+Visual spacing, tables, links, blockquotes, inline code, and code-block chrome follow deepsuite `@deepseek/md` (`markdown.css` / `code-block.css`) and the same `--dsw-alias-markdown-*`, `--dsw-font-markdown-*`, `--dsw-alias-border-l*`, and `--dsw-alias-label-*` tokens. Links use `--dsw-alias-state-business-primary` (deepsuite's sheet uses `--dsw-alias-brand-text`, which is blue only under newDesign; design-platform keeps brand-text near-black and is not retuned here). `CodeBlock` ships a language banner and a copy control (`复制` / `复制成功`). Citation pills, KaTeX, heading anchors, the thinking-small markdown variant, and custom □/☑ task markers are out of scope until matching product DOM exists; GFM task lists keep native checkboxes.
+
+The dependency is explicit in `ui-primitives`; because that pure library is seeded by the Web shell, the parser and highlighter are part of the initial browser bundle.
 
 ## Untrusted output policy
 
-Assistant-authored destinations are restricted to absolute HTTP, HTTPS, and mailto URLs. HTTP(S) links open in a new tab with `rel="noopener noreferrer"`; relative destinations and other protocols render as non-navigable text. Markdown images render only their alt text, so model output cannot initiate a remote image request. Raw HTML remains inert source text because no HTML parser enters the pipeline.
+Assistant-authored destinations are restricted to absolute HTTP, HTTPS, and mailto URLs. HTTP(S) links open in a new tab with `rel="noopener noreferrer"`; relative destinations and other protocols render as non-navigable text. Markdown images render only their alt text, so model output cannot initiate a remote image request. Raw HTML remains inert source text because no HTML parser enters the pipeline. Shiki output is a static span tree generated from the fence text (no scripts or user HTML).
 
-The renderer uses existing `--dsw-*` typography and color tokens. Fenced code and GFM tables own horizontal overflow so long content cannot widen the conversation column.
+Fenced code and GFM tables own horizontal overflow so long content cannot widen the conversation column.
 
 ## Alternatives considered
 
@@ -30,6 +34,8 @@ The renderer uses existing `--dsw-*` typography and color tokens. Fenced code an
 
 **Enable raw HTML or remote images with sanitization.** Neither capability has a current product need, while both enlarge the executable or network privacy boundary. They remain disabled rather than adding sanitizer and image-policy dependencies.
 
+**Port deepsuite Prism `highlight.css` and the mdast pipeline.** Appearance parity is owned by CSS Modules and shared `--dsw-*` tokens; highlighting stays on the existing shiki allowlist so the client does not take a second highlighter or Prism class contract.
+
 ## Consequences
 
-Assistant replies render semantic Markdown consistently during streaming and replay, while tool cards, reasoning rows, interactions, user bubbles, and the host protocol remain unchanged. Streaming reparses the current text after each accumulated update; incomplete Markdown can temporarily change structure, but the isolated tail bounds React invalidation and the final event does not switch renderers. The initial Web shell grows by the Markdown parser and GFM runtime, and future extensions such as syntax highlighting or remote media require a separate bundle and security decision.
+Assistant replies render semantic Markdown consistently during streaming and replay, while tool cards, reasoning rows, interactions, user bubbles, and the host protocol remain unchanged. Streaming reparses the current text after each accumulated update; incomplete Markdown can temporarily change structure, but the isolated tail bounds React invalidation and the final event does not switch renderers. Code fences share one chrome and copy path with tool and details surfaces. The initial Web shell includes the Markdown parser, GFM runtime, and shiki allowlist; cite/math/anchor/thinking-small surfaces remain deferred.

.agents/notes/implemented/feature/2026-07-23-web-assistant-markdown.zh.md

@@ -12,13 +12,17 @@ Web 对话通过会话事件、历史回放与流式累积保留 assistant Markd
 
 `@deepseek-ai/dsh-client-ui-primitives` 导出 `MarkdownText`，用作不受信任的 assistant 文本渲染器；`ui-conversation` 仅为 assistant `text` 块选择该渲染器。已完成的历史消息、流式输出尾部与被中断的部分输出已经共用 `AssistantMarkdown`，因此无需更改事件或快照，它们便会采用同一渲染器。用户消息与 steering 消息继续使用 `MessageText`，并保持按字面渲染。
 
-`MarkdownText` 使用 `react-markdown` 与 `remark-gfm`，从 AST 构建 React 元素。它支持 CommonMark 块，以及 GFM 表格、任务列表、删除线与自动链接，但不使用 `dangerouslySetInnerHTML`，不解析原始 HTML，也不进行语法高亮。`ui-primitives` 显式声明该依赖；由于这一纯库由 Web shell 预置，解析器会成为初始浏览器 bundle 的一部分。
+`MarkdownText` 使用 `react-markdown` 与 `remark-gfm`，从 AST 构建 React 元素。它覆盖 CommonMark 块，以及 GFM 表格、任务列表、删除线与自动链接，且不解析原始 HTML。围栏代码经共享的 `CodeBlock` 路由；该组件用客户端的 shiki 单例（`--shiki-*` token）高亮已注册语法，否则回退为纯等宽文本。轮次流式输出期间，围栏停留在纯文本分支，以免每收到一个分片就对增长中的围栏重新分词。
+
+视觉间距、表格、链接、引用块、行内代码与代码块外框遵循 deepsuite `@deepseek/md`（`markdown.css` / `code-block.css`），并使用同一套 `--dsw-alias-markdown-*`、`--dsw-font-markdown-*`、`--dsw-alias-border-l*` 与 `--dsw-alias-label-*` token。链接使用 `--dsw-alias-state-business-primary`（deepsuite 的样式表使用 `--dsw-alias-brand-text`，仅在 newDesign 下为蓝色；design-platform 将 brand-text 保持为近黑色，此处不做重新调色）。`CodeBlock` 提供语言横幅与复制控件（`复制` / `复制成功`）。引用胶囊、KaTeX、标题锚点、thinking-small markdown 变体，以及自定义 □/☑ 任务标记均不在范围内，直至存在匹配的产品 DOM；GFM 任务列表继续使用原生复选框。
+
+该依赖在 `ui-primitives` 中显式声明；由于这一纯库由 Web shell 预置，解析器与高亮器会成为初始浏览器 bundle 的一部分。
 
 ## 不受信任输出策略
 
-assistant 生成的目标地址仅限绝对 HTTP、HTTPS 与 mailto URL。HTTP(S) 链接会在新标签页中打开，并带有 `rel="noopener noreferrer"`；相对目标地址与其他协议会渲染为不可导航的文本。Markdown 图片仅渲染替代文本，因此模型输出无法发起远程图片请求。由于管线中未引入 HTML 解析器，原始 HTML 仍是不会生效的源文本。
+assistant 生成的目标地址仅限绝对 HTTP、HTTPS 与 mailto URL。HTTP(S) 链接会在新标签页中打开，并带有 `rel="noopener noreferrer"`；相对目标地址与其他协议会渲染为不可导航的文本。Markdown 图片仅渲染替代文本，因此模型输出无法发起远程图片请求。由于管线中未引入 HTML 解析器，原始 HTML 仍是不会生效的源文本。Shiki 输出是由围栏文本生成的静态 span 树（不含脚本或用户 HTML）。
 
-渲染器使用现有的 `--dsw-*` 排版与颜色 token。围栏代码块与 GFM 表格各自处理横向溢出，因此较长内容无法撑宽对话栏。
+围栏代码与 GFM 表格各自处理横向溢出，因此较长内容无法撑宽对话栏。
 
 ## 考虑过的替代方案
 
@@ -30,6 +34,8 @@ assistant 生成的目标地址仅限绝对 HTTP、HTTPS 与 mailto URL。HTTP(S
 
 **通过净化启用原始 HTML 或远程图片。**当前产品并不需要这两项功能，但二者都会扩大可执行行为或网络隐私边界。因此它们保持禁用，无需增加净化器与图片策略依赖。
 
+**移植 deepsuite 的 Prism `highlight.css` 与 mdast 管线。**外观一致性由 CSS Modules 与共享的 `--dsw-*` token 负责；高亮仍走现有的 shiki 允许列表，使客户端不必引入第二套高亮器或 Prism class 契约。
+
 ## 后果
 
-assistant 回复在流式输出与回放期间都会一致地渲染为语义化 Markdown，而工具卡片、推理行、交互、用户气泡和宿主协议保持不变。每次累积更新后，流式输出都会重新解析当前文本；未完成的 Markdown 可能暂时改变结构，但独立的尾部会限定 React 失效范围，最终事件也不会切换渲染器。初始 Web shell 的体积会因加入 Markdown 解析器与 GFM 运行时而增大；语法高亮或远程媒体等后续扩展需要另行作出 bundle 与安全决策。
+assistant 回复在流式输出与回放期间都会一致地渲染为语义化 Markdown，而工具卡片、推理行、交互、用户气泡和宿主协议保持不变。每次累积更新后，流式输出都会重新解析当前文本；未完成的 Markdown 可能暂时改变结构，但独立的尾部会限定 React 失效范围，最终事件也不会切换渲染器。代码围栏与工具及详情表层共用同一外框与复制路径。初始 Web shell 包含 Markdown 解析器、GFM 运行时与 shiki 允许列表；cite/math/anchor/thinking-small 表层仍暂缓。

.agents/notes/implemented/feature/2026-07-23-web-todo-display.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 .agents/notes/implemented/feature/2026-07-23-web-todo-display.md
+2026-07-23-web-todo-display.md: 830f55c86c893c4942a1a9d3b8529395d5f5e38b
+2026-07-23-web-todo-display.zh.md: e68928d7eddaaa92ac831722a738ee2002342b38

.agents/notes/implemented/feature/2026-07-23-web-todo-display.md

@@ -0,0 +1,36 @@
+# Agent Note: Web todo display — snapshot side-effect channel + two render surfaces
+
+Status: implemented
+
+English | [中文](2026-07-23-web-todo-display.zh.md)
+
+## Problem
+
+`todo_write` appends `todo/write` whole-list snapshots to the session log; the TUI renders a persistent plan panel (the automation-only ACP bridge deliberately omits todo presentation). The web client dropped the event entirely: the host mux stream already forwards every session event, but `todo/write` is not a surface type (it never folds into `ConversationSnapshot.nodes`), and no side-effect branch accumulated it — the browser had no consumption point and no display surface.
+
+## Decision
+
+Consume `todo/write` as a Session side effect, not a surface node, and render it on two surfaces matching the split the TUI already draws.
+
+### Side-effect channel, converging with window replay
+
+`applyEventSideEffects` gains a `todo/write` case (whole list, last write wins). Unlike partial/openCalls, `rebuildDerivedFromWindow` deliberately does NOT reset it: the value is session-level — taken from the tail history page's full-log projection — and an arbitrary window may not contain the latest write, so an older-page prepend keeps it and only an in-window or live write overwrites it. Every `installWindow` caller is a tail request (`doOpen`, its gap re-pull, `repairGap`; `loadOlder` prepends without it), which the host answers with the projection or omits it only when the full log holds no `todo/write` — so an absent field is the authoritative empty list and is assigned as such. That distinction matters on rollback: a live write whose host crashed before persisting leaves the log empty, and preserving the prior value instead would strand the rolled-back plan on screen indefinitely. `ConversationSnapshot.todos` is the read surface. This follows the event's own contract ("log-only UI state; never derived history"): surfacing each write as a conversation node would render superseded lists as if they were still standing.
+
+### TodoPanel: the durable list as a persistent strip
+
+The panel mounts through the `conversation.input.dock` slot (a plain registrant plugin, `todoDockEntry`, the QueueDock posture: `inject: ['slots', 'conversation']` as the load-order seam, `order: -1` above the queue rows), hidden while empty, collapsible with the in-progress item as the collapsed one-line hint; ✓/●/○ glyphs mirror the TUI plan panel. It reads `snapshot.todos` via the standard-kit `useSession` hook the dock entry receives — no store, no service, no ctx. The inner component stays props-complete and framework-free; the dock adapter is a one-line wrapper.
+
+### TodoRow: the per-call row through the keyed toolview slot
+
+The dedicated `todo_write` chat row is a plain registrant plugin (`todoToolview`, mounted from `apply`) that registers into the keyed `conversation.chat.toolview` slot via `ctx.slots.register` — the same seam and load-order posture as the bash sample (`inject: ['slots', 'conversation']`), but a product registration. The summary derives from call args (`N/M done · active item`); unparseable args fall back to the generic row summary; clicking opens the details column with the raw args. No `ToolEventView` is added for todo — presentation is client-owned, and the durable list renders from the session event, not the tool card.
+
+## Alternatives considered
+
+- **Fold todo writes into `nodes` as surface entries** — replayed windows would render every superseded list; the event is deliberately not a surface type.
+- **Hardcoding the panel inside `ConversationRoot`** — the original landing spot before the input-dock slot existed; the dock is the architecture's home for always-on strips above the composer, and a hardcode bypasses the slot registry's disposal and ordering.
+- **Details column for the panel** — the details slot is single-occupant and selection-driven, a different lifetime than an always-on strip.
+- **Host-computed view (a todo `ToolEventView`)** — presentation belongs to the client; the wire already carries the whole snapshot in the event payload.
+
+## Consequences
+
+Replay correctness is owned by one code path: any future change to window rebuild keeps todos consistent for free, and the fixture (fx-alpha turn 65) plus the assembled keyless snapshot (`apps/web/tests/todo-display.snapshot.ts`) pin the full chain (row summary and state, dock panel content, collapse round-trip) over the built client graph. `todos` is a required `ConversationSnapshot` field, so scripted fakes in specs must carry it. The TUI panel is untouched (the automation-only ACP bridge deliberately omits todo presentation); the web surfaces render the same event, adding one wire field and no new event type. That field is how cold-load reconstruction stays host-backed: the tail history page carries `todos` — the full-log latest `todo/write`, computed independently of the page window (the same backscan posture the view pairing uses) — so a reopened session restores the plan even when the last write precedes the window; that value survives an older-page prepend, is overwritten by any later write, and resets to empty when a tail response carries no projection.

.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md

@@ -0,0 +1,36 @@
+# Agent Note: Web todo 展示——快照副作用通道 + 两个渲染面
+
+Status: implemented
+
+[English](2026-07-23-web-todo-display.md) | 中文
+
+## Problem
+
+`todo_write` 把 `todo/write` 的整份列表快照追加进会话日志；TUI 渲染一块常驻的 plan 面板（自动化专用的 ACP 桥接刻意不做 todo 呈现）。Web 客户端把这个事件整个丢弃了：host mux 流本已转发每一个会话事件，但 `todo/write` 不是 surface 类型（它从不 fold 进 `ConversationSnapshot.nodes`），也没有任何副作用分支累积它——浏览器既无消费点，也无展示面。
+
+## Decision
+
+把 `todo/write` 当作 Session 副作用消费，而非 surface 节点，并在两个面上渲染它，这两个面正对应 TUI 已经绘制的那套划分。
+
+### 副作用通道，与窗口回放收敛
+
+`applyEventSideEffects` 新增一个 `todo/write` 分支（整份列表，后写覆盖先写）。与 partial/openCalls 不同，`rebuildDerivedFromWindow` 刻意不重置它：该值是会话级的——取自尾页 history 携带的全量 log 投影——而任意窗口未必包含最近一次写入，因此往前翻页保留它，只有窗口内或实时的写入才会覆盖。`installWindow` 的每个调用方都是尾页请求（`doOpen`、其补洞重拉、`repairGap`；`loadOlder` 只往前拼接、不走它），而 host 对尾页请求要么带上投影、要么仅在全量 log 没有任何 `todo/write` 时省略——因此字段缺失就是权威的空列表，直接照此赋值。这个区分在回滚场景上要紧：实时写入若在 host 持久化前崩溃，log 里就是空的，此时保留旧值会让已回滚的计划永远留在屏幕上。`ConversationSnapshot.todos` 是读取面。这遵循事件自身的契约（「仅日志 UI 状态，绝非派生历史」）：把每次写入作为对话节点呈现，会让已被取代的列表看起来仍然有效。
+
+### TodoPanel：长驻列表作为一条常驻横条
+
+面板经 `conversation.input.dock` slot 挂载（普通注册者插件 `todoDockEntry`，QueueDock 同款姿势：`inject: ['slots', 'conversation']` 载序 seam，`order: -1` 排在队列条上方），空列表时隐藏，可折叠——折叠态以进行中项作为单行提示；✓/●/○ 字形与 TUI plan 面板一致。它经 dock entry 收到的标准件 `useSession` hook 读取 `snapshot.todos`——无 store、无 service、无 ctx。内部组件保持 props 完备且框架无关；dock 适配件只是一行包装。
+
+### TodoRow：经 keyed toolview slot 的逐调用行
+
+专用的 `todo_write` 对话行是一个普通注册者插件（`todoToolview`，由 `apply` 挂载），经 `ctx.slots.register` 注册进 keyed 的 `conversation.chat.toolview` slot——与 bash 样例同一接缝、同一载序姿态（`inject: ['slots', 'conversation']`），但属产品级注册。摘要由调用 args 推导（`N/M done · active item`）；无法解析的 args 回退到通用行摘要；点击会以原始 args 打开 details 列。todo 不新增任何 `ToolEventView`——呈现归客户端所有，常驻列表从会话事件渲染，而非工具卡。
+
+## Alternatives considered
+
+- **把 todo 写入作为 surface 条目折叠进 `nodes`**——回放的窗口会渲染每一份已被取代的列表；该事件被刻意设计成非 surface 类型。
+- **面板硬编码进 `ConversationRoot`**——input-dock slot 出现之前的原始落点；dock 是本架构给"composer 上方常开横条"安排的家，硬编码绕开了 slot 注册表的 disposal 与定序。
+- **面板放进 details 列**——details slot 单占用且由选中驱动，生命周期不同于一条常开横条。
+- **host 计算的视图（一个 todo `ToolEventView`）**——呈现属于客户端；协议已在事件载荷里携带整份快照。
+
+## Consequences
+
+回放正确性由一条代码路径掌管：未来对窗口重建的任何改动都免费保持 todos 一致；fx-alpha 第 65 轮的 fixture（测试前置数据）加 assembled keyless snapshot（`apps/web/tests/todo-display.snapshot.ts`）在构建产物客户端全图上钉住整条链（行摘要与状态、dock 面板内容、折叠往返）。`todos` 是 `ConversationSnapshot` 的必填字段，所以 spec 里脚本化的 fake 必须带上它。TUI 面板未受改动（自动化专用的 ACP 桥接刻意不做 todo 呈现）；Web 各面渲染同一个事件，只新增一个协议字段，不新增事件类型。冷加载重建正是靠这个字段由 host 兜底：history 尾页附带 `todos`——全量 log 上最新一次 `todo/write` 的投影，独立于分页窗口计算（与 view 配对同一种 backscan 姿势）——因此重开会话时即使最后一次写入落在窗口之前，计划也照常恢复；该值跨往前翻页保留，之后的任何写入照常覆盖，而尾页响应不带投影时复位为空。

.agents/notes/implemented/feature/2026-07-27-user-message-icon-actions.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
+2026-07-27-user-message-icon-actions.md: 869e7a2518a3ec927c0689a10816a410dc5f0862
+2026-07-27-user-message-icon-actions.zh.md: 353e5ac765bb2fbab9932449cf2247768a1f412f

.agents/notes/implemented/feature/2026-07-27-user-message-icon-actions.md

@@ -0,0 +1,27 @@
+# Agent Note: User-message IconActions under the bubble
+
+Status: implemented
+
+English | [中文](2026-07-27-user-message-icon-actions.zh.md)
+
+## Problem
+
+The chat user bubble had no under-bubble action chrome. The Harness design (figma `User_Bubble/message_container`) shows three IconActions — copy, branch in new chat, and edit — right-aligned under the bubble, matching the product action-bar pattern used elsewhere.
+
+## Decision
+
+`MessageItem` owns the actions for `kind: 'user'` only. Layout is a column (`align-items: flex-end`, 6px gap): bubble, then a 28px action row with 10px gaps and 28px circular icon buttons (`IconCopyOutline16`, `IconBranchOutline16`, `IconEditOutline16`). Tooltips carry Chinese labels. Actions stay visible by default; `@media (hover: hover)` hides them until the row is hovered or focus-within, so touch / `hover: none` devices keep discoverable controls (opacity alone still hit-tests).
+
+Copy writes the bubble's joined text blocks to the clipboard (`navigator.clipboard.writeText`, with an `execCommand` fallback). Branch and edit are present chrome with no handlers yet — they reserve the design seats without inventing session-fork or edit-resubmit behavior.
+
+Steering bubbles keep the badge-only form and do not show these actions.
+
+## Alternatives considered
+
+**Wire branch/edit to real session fork and draft-edit now.** Rejected for this change: those product flows are not specified; shipping inert buttons matches the requested scope and avoids half-built mutation paths.
+
+**Always hide with `opacity: 0` outside hover.** Rejected for touch: without `@media (hover: hover)`, idle opacity still hit-tests while looking empty. Hover-capable pointers keep the fade; others keep the actions visible.
+
+## Consequences
+
+User messages expose copy immediately; branch/edit remain clickable stubs until a later decision owns their behavior. Tests pin the three buttons, copy payload, and steering exclusion.

.agents/notes/implemented/feature/2026-07-27-user-message-icon-actions.zh.md

@@ -0,0 +1,27 @@
+# Agent Note: 用户消息气泡下方的 IconActions
+
+Status: implemented
+
+[English](2026-07-27-user-message-icon-actions.md) | 中文
+
+## 问题
+
+聊天用户气泡下方没有操作栏。Harness 设计稿（figma `User_Bubble/message_container`）在气泡下方右对齐展示三个 IconActions——复制、在新对话中分支、编辑——与产品其他位置使用的操作栏模式一致。
+
+## 决策
+
+仅当 `kind: 'user'` 时，`MessageItem` 拥有这些操作。布局为纵向列（`align-items: flex-end`，间距 6px）：先是气泡，再是高度 28px 的操作行；行内间距 10px，圆形图标按钮尺寸为 28px（`IconCopyOutline16`、`IconBranchOutline16`、`IconEditOutline16`）。Tooltip 承载中文标签。操作默认保持可见；`@media (hover: hover)` 下在悬停或 focus-within 前隐藏，以便触摸／`hover: none` 设备仍能发现控件（仅靠 opacity 仍会命中测试）。
+
+复制将气泡内拼接后的文本块写入剪贴板（`navigator.clipboard.writeText`，并以 `execCommand` 作为回退）。分支与编辑目前仅有外观、尚无处理函数——它们预留设计席位，但不发明会话 fork 或编辑重提交流程。
+
+steering（中途引导）气泡保持仅徽章形态，不展示这些操作。
+
+## 考虑过的替代方案
+
+**现在就把分支／编辑接到真实的会话 fork 与草稿编辑。**本次变更不予采纳：这些产品流程尚未定稿；交付无行为按钮符合请求范围，也避免半成品的变更路径。
+
+**在悬停外始终以 `opacity: 0` 隐藏。**因触摸不予采纳：若无 `@media (hover: hover)`，空闲 opacity 看起来空白但仍会命中测试。具备悬停能力的指针保留淡入；其他设备保持操作可见。
+
+## 后果
+
+用户消息立即可用复制；分支／编辑仍为可点击的占位，直至后续决策明确其行为。测试钉死三个按钮、复制载荷，以及对 steering 的排除。

.agents/notes/proposed/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.i18n.yaml → .agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-07-26-eventsource-parser-for-deepseek-sse.md: 8a93b7f6c7aa0d428f25e87c44e1d29e884ecc81
-2026-07-26-eventsource-parser-for-deepseek-sse.zh.md: b16109d9458f487c7e463cf02e6b2d22fbbde015
+2026-07-26-eventsource-parser-for-deepseek-sse.md: e7835bc738b3dec5aefd6011848525f6604e852e
+2026-07-26-eventsource-parser-for-deepseek-sse.zh.md: 933b993d479026d8f2bd2dc3173abd9e60823806

.agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md

@@ -0,0 +1,28 @@
+# Agent Note: Replace the hand-rolled SSE parser in llm-deepseek with eventsource-parser
+
+Status: implemented
+
+English | [中文](2026-07-26-eventsource-parser-for-deepseek-sse.zh.md)
+
+## Problem
+
+`packages/llm/llm-deepseek/src/sse.ts` hand-implemented Server-Sent Events parsing: a streaming `TextDecoder`, event-block splitting on `\r?\n\r?\n`, `data:` payload extraction and joining, comment/field skipping, the `[DONE]` sentinel, a `STREAM_CLOSED` error on EOF without it, and a flush of a final unterminated event block. The file was ~67 lines with ~108 lines of dedicated tests (`tests/sse.spec.ts`) re-proving SSE spec behavior — UTF-8 split across chunks, CRLF handling, multi-`data:` joining, no-space-after-colon — that a maintained parser already guarantees. Its only consumer is `adapter.ts` (`yield* translate(parseSse(response.body))`).
+
+This is exactly the surface `eventsource-parser` owns: the de-facto standard SSE parser (it underlies the Vercel AI SDK and the MCP SDK), zero-dependency, actively maintained, and already present in this repo's lockfile transitively via `@modelcontextprotocol/sdk` — so adopting it directly adds no new supply-chain surface in practice.
+
+## Decision
+
+`sse.ts` delegates SSE framing to `EventSourceParserStream` from `eventsource-parser/stream`: `parseSse` pipes the response body through `new TextDecoderStream()` then `new EventSourceParserStream()` and keeps only the DeepSeek protocol shim — yield each event's `data`, terminate on `[DONE]`, and throw `LlmError('STREAM_CLOSED')` when the stream ends without the sentinel. All required builtins (`TextDecoderStream`, `pipeThrough`, async-iterable `ReadableStream`) exist at the Node ^22.19 engine floor. The spec-conformance tests are gone; `tests/sse.spec.ts` pins only the `[DONE]`/`STREAM_CLOSED`/EOF contract. `eventsource-parser` is `llm-deepseek`'s second runtime dependency after schemastery. The [twin-adapters note](../architecture/2026-06-13-twin-llm-adapters.md) and the `dsh-llm` JSDoc that branded this adapter "hand-rolled fetch + SSE parsing" now describe it as direct fetch with library-framed SSE.
+
+The library also strips a leading BOM (the hand-rolled parser would fail to match `data:` after one) and offers `maxBufferSize` hardening the hand-rolled parser lacked.
+
+## Alternatives considered
+
+- **Keep the hand-rolled parser.** Defensible under the [twin-adapters decision](../architecture/2026-06-13-twin-llm-adapters.md): the adapter is deliberately the hand-rolled design-verification twin of the pi-ai adapter. But that note's load-bearing distinction is owning the fetch/translate internals versus delegating to a full provider SDK; a ~700-byte SSE micro-parser is transport plumbing, not the design under verification. The twin-adapters note now states that reading explicitly.
+- **`createParser({onEvent})` callback API instead of the stream.** Works fed by a manual `TextDecoder` loop, but the `pipeThrough` composition deletes more of the hand-rolled code.
+
+## Consequences
+
+- The remaining shim only encodes the DeepSeek `[DONE]`/`STREAM_CLOSED` protocol; SSE framing edge cases are eventsource-parser's contract and are no longer re-proven here.
+- One deliberate robustness deviation is dropped: the hand-rolled parser flushed a final event block that lacked its terminating blank line, so a trailing `data: [DONE]` without `\n\n` still yielded DONE. eventsource-parser is spec-strict and only dispatches on the blank line, so that shape is now `STREAM_CLOSED`. Real providers and `dsh-llm-mock-server` always terminate events properly — the flush was a robustness nicety, not an observed provider shape — and `tests/sse.spec.ts` pins the new truncation verdict for that tail.
+- The documented "hand-rolled" identity of the twin adapter narrows to the fetch/translate internals; the twin-adapters note was updated in the same change rather than leaving the claim stale.

.agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md

@@ -0,0 +1,28 @@
+# Agent Note: 用 eventsource-parser 替换 llm-deepseek 中手写的 SSE 解析器
+
+Status: implemented
+
+[English](2026-07-26-eventsource-parser-for-deepseek-sse.md) | 中文
+
+## 问题
+
+`packages/llm/llm-deepseek/src/sse.ts` 曾手写实现 SSE（Server-Sent Events）解析：一个流式 `TextDecoder`、按 `\r?\n\r?\n` 切分事件块、提取并拼接 `data:` 载荷、跳过注释与其他字段、`[DONE]` 哨兵、在未见哨兵即 EOF 时抛出 `STREAM_CLOSED` 错误，以及对最后一个未终结事件块的 flush。该文件约 67 行，另有约 108 行专属测试（`tests/sse.spec.ts`）重复验证 SSE 规范行为——UTF-8 字符被切分到多个分片、CRLF 处理、多条 `data:` 拼接、冒号后无空格——而这些行为，持续维护的解析器早已有保证。它唯一的消费方是 `adapter.ts`（`yield* translate(parseSse(response.body))`）。
+
+这恰好是 `eventsource-parser` 负责的接口面：事实标准的 SSE 解析器（Vercel AI SDK 和 MCP SDK 都构建在它之上），零依赖，持续维护，并且已通过 `@modelcontextprotocol/sdk` 作为传递依赖出现在本仓库的 lockfile 中——因此直接采用它实际上不增加新的供应链接触面。
+
+## 决策
+
+`sse.ts` 将 SSE 分帧委托给 `eventsource-parser/stream` 的 `EventSourceParserStream`：`parseSse` 把响应 body 依次管道接入 `new TextDecoderStream()` 和 `new EventSourceParserStream()`，只保留 DeepSeek 协议垫层——逐个产出事件的 `data`，遇到 `[DONE]` 终止，流在未见哨兵时结束则抛出 `LlmError('STREAM_CLOSED')`。所需的全部内置能力（`TextDecoderStream`、`pipeThrough`、可异步迭代的 `ReadableStream`）在 Node ^22.19 引擎下限即已存在。规范符合性测试已删除；`tests/sse.spec.ts` 只固定 `[DONE]`/`STREAM_CLOSED`/EOF 契约。`eventsource-parser` 是 `llm-deepseek` 继 schemastery 之后的第二个运行时依赖。曾把该适配器标为「手写 fetch + SSE 解析」的[孪生适配器 Agent Note（agent 决策记录）](../architecture/2026-06-13-twin-llm-adapters.md)与 `dsh-llm` JSDoc，现在将其描述为直接 fetch 加库分帧的 SSE。
+
+该库还会剥离开头的 BOM（手写解析器在 BOM 之后会无法匹配 `data:`），并提供手写解析器缺少的 `maxBufferSize` 加固能力。
+
+## 曾考虑的替代方案
+
+- **保留手写解析器。** 依据[孪生适配器决策](../architecture/2026-06-13-twin-llm-adapters.md)，这一选择有辩护余地：该适配器有意作为 pi-ai 适配器的手写设计验证孪生体。但那份 Agent Note 起支撑作用的区分在于「自行持有 fetch/translate 内部实现」与「委托给完整的提供方 SDK」；一个约 700 字节的 SSE 微型解析器属于传输层管道，不是被验证的设计本身。孪生适配器 Agent Note 现已明确写出这一解读。
+- **改用 `createParser({onEvent})` 回调 API 而非流。** 配合手动的 `TextDecoder` 循环可以工作，但 `pipeThrough` 组合方式能删除更多手写代码。
+
+## 后果
+
+- 剩下的垫层只编码 DeepSeek 的 `[DONE]`/`STREAM_CLOSED` 协议；SSE 分帧边界情形属于 eventsource-parser 的契约，不再在这里重复验证。
+- 放弃了一处有意为之的健壮性偏离：手写解析器会 flush 缺少终结空行的最后一个事件块，因此末尾的 `data: [DONE]` 即使没有 `\n\n` 也仍产出 DONE。eventsource-parser 严格遵循规范，只在空行处分发事件，所以这种形态现在是 `STREAM_CLOSED`。真实提供方和 `dsh-llm-mock-server` 总是正确终结事件——该 flush 只是健壮性上的锦上添花，并非实际观测到的提供方形态——`tests/sse.spec.ts` 固定了对该尾部的新截断判定。
+- 孪生适配器有文档记录的「手写」身份收窄到 fetch/translate 内部实现；孪生适配器 Agent Note 在同一次变更中更新，而不是让声明陈旧下去。

.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-2026-07-24-web-gui-browser-e2e-lane.md: c4e34b3f44162c7021cb25681eea7e49ac78f672
-2026-07-24-web-gui-browser-e2e-lane.zh.md: 466e1c0fc16aac21b87b68cfedaec4fb22a417e2
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md
+2026-07-24-web-gui-browser-e2e-lane.md: d9e0a9660ecd6aeb75e835e68f92c0a268423872
+2026-07-24-web-gui-browser-e2e-lane.zh.md: e8c7d1c4596f20d88bd08423549fb6a9f7b0654b

.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md

@@ -18,7 +18,7 @@ A plain shared-fixture module (the [testing-policy sanctioned shape](../../../..
 
 `launchWebScaffold()` boots the real web composition from the shipped `apps/cli/cordis.yml` through the vendored Loader's include mechanism — the same tree and mechanism `AppCLIEntry` drives for `dsh web`. Divergences ride include patches over that tree, the ACP `cordis.snapshot.yml` pattern expressed in-process: temp `persistenceRoot`, `workspace-context` disabled (recorded fixtures must not embed this repo's AGENTS.md), `session-title-llm` disabled (its fire-and-forget title call would race the loop for the session's replay cursor), the webserver row pinned to port 0 with the built dist, and in keyless modes `llm-deepseek` disabled. A patch id that stops matching a row fails the boot sweep loudly instead of drifting. The boot runs `chdir`'d to the temp workspace so the api-gateway's `process.cwd()` session default, tool cwds, and fixtures agree; the `dsh web` bin's own glue (argv, profile json, AppCLIEntry) stays held by the keyless CLI smokes in `smoke-real.e2e.ts`. Setup rollback and ordinary close both dispose the Cordis tree before removing the two owned temp roots, attempt every cleanup independently, and report cleanup failures without masking the setup failure.
 
-Keyless model displacement is the disabled adapter row plus `installLlmReplay` filling the open seam on the settled root ctx in providers-catalog mode — never catch-all: with the adapter row disabled no adapter exists, so catch-all would leave `resolveModelContext` unroutable and `compact-basic`'s post-step pressure check would warn every step instead of being provably inert (the published 128k `contextWindow` keeps it inert for small fixtures). The direct install rather than an inserted replay plugin row is deliberate: it returns the `ReplayHandle` the teardown consumption check needs. A scenario with no fixture leaves the seam empty, so a stray stream fails loud with NO_ADAPTER.
+Keyless model displacement is the disabled adapter row plus `installLlmReplay` filling the open seam on the settled root ctx in providers-catalog mode — never catch-all: with the adapter row disabled no adapter exists, so catch-all would leave `resolveModelInfo` unroutable and `compact-basic`'s post-step pressure check would warn every step instead of being provably inert (the published 128k `contextWindow` keeps it inert for small fixtures). The direct install rather than an inserted replay plugin row is deliberate: it returns the `ReplayHandle` the teardown consumption check needs. A scenario with no fixture leaves the seam empty, so a stray stream fails loud with NO_ADAPTER.
 
 `seedSession()` seeds cold sessions through the real persistence API — a throwaway `Context` mounting `SessionStore` + `SessionPersistenceJsonl` against the host's root, `create()` + `append()`, one `utimes` backdate for deterministic sidebar order (the `semantic-checkpoint.snapshot.ts` precedent) — never raw file writes, so the seeder knows nothing of bucket hashing, filename encoding, or compression, and the host's zstd default needs no boot knob. Seeds are validated at seed time (parseable, ending in `turn/end` — an open final turn would be mutated by resume's crash repair).
 

.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.zh.md

@@ -18,7 +18,7 @@ Web GUI 以一条真实组装链交付——chromium 页面 → client 插件 bu
 
 `launchWebScaffold()` 通过 vendored Loader 的 include 机制，从交付的 `apps/cli/cordis.yml` 启动真实 web 组合——与 `AppCLIEntry` 为 `dsh web` 驱动的是同一棵树、同一套机制。差异全部经 include patch 覆盖在这棵树上，即 ACP `cordis.snapshot.yml` 模式的进程内表达：临时 `persistenceRoot`；禁用 `workspace-context`（录制的 fixture 不得嵌入本仓库的 AGENTS.md）；禁用 `session-title-llm`（其发后不管的标题调用会与循环争抢会话的回放游标）；webserver 行钉到端口 0 加已构建 dist；无密钥模式下禁用 `llm-deepseek`。patch 的 id 一旦不再匹配任何行，boot 扫描会大声失败而不是漂移。boot 在临时工作区 `chdir` 下运行，使 api-gateway 的 `process.cwd()` 会话默认值、工具 cwd 与 fixture 一致；`dsh web` bin 自身的胶水（argv、profile json、AppCLIEntry）仍由 `smoke-real.e2e.ts` 中的无密钥 CLI 冒烟把守。初始化回滚和正常关闭都会先对 Cordis 树执行 dispose（资源释放），再删除 scaffold 持有的两个临时根目录；每项清理都会独立尝试，并会报告清理失败而不掩盖初始化失败。
 
-无密钥的模型替换 = 禁用适配器行的 patch 加 `installLlmReplay` 在停稳的根 ctx 上以提供方目录（providers-catalog）模式填充开放的 seam——绝不用 catch-all：适配器行被禁用后不存在任何适配器，catch-all 会让 `resolveModelContext` 无路由可走，`compact-basic` 的步后压力检查将步步告警，而不是被可证明地闲置（发布的 128k `contextWindow` 使该路径对小 fixture 保持闲置）。选择直接安装而非插入回放插件行是刻意的：直接安装返回收尾消费检查所需的 `ReplayHandle`。没有 fixture 的场景让 seam 保持空置，任何离群的流式调用都会以 NO_ADAPTER 大声失败。
+无密钥的模型替换 = 禁用适配器行的 patch 加 `installLlmReplay` 在停稳的根 ctx 上以提供方目录（providers-catalog）模式填充开放的 seam——绝不用 catch-all：适配器行被禁用后不存在任何适配器，catch-all 会让 `resolveModelInfo` 无路由可走，`compact-basic` 的步后压力检查将步步告警，而不是被可证明地闲置（发布的 128k `contextWindow` 使该路径对小 fixture 保持闲置）。选择直接安装而非插入回放插件行是刻意的：直接安装返回收尾消费检查所需的 `ReplayHandle`。没有 fixture 的场景让 seam 保持空置，任何离群的流式调用都会以 NO_ADAPTER 大声失败。
 
 `seedSession()` 通过真实持久化 API 播种冷会话——一次性 `Context` 挂载 `SessionStore` + `SessionPersistenceJsonl` 指向 host 的根目录，`create()` + `append()`，一次 `utimes` 回拨保证侧栏顺序确定（`semantic-checkpoint.snapshot.ts` 先例）——绝不裸写文件，因此播种器对桶哈希、文件名编码、压缩一无所知，host 的 zstd 默认值也无需任何启动开关。种子在播种时即校验（可解析、以 `turn/end` 结尾——未闭合的最终轮次会被恢复（resume）的崩溃修复改写）。
 

.agents/notes/proposed/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md

@@ -1,33 +0,0 @@
-# Agent Note: Replace the hand-rolled SSE parser in llm-deepseek with eventsource-parser
-
-Status: proposed
-
-English | [中文](2026-07-26-eventsource-parser-for-deepseek-sse.zh.md)
-
-## Problem
-
-`packages/llm/llm-deepseek/src/sse.ts` hand-implements Server-Sent Events parsing: a streaming `TextDecoder`, event-block splitting on `\r?\n\r?\n`, `data:` payload extraction and joining, comment/field skipping, the `[DONE]` sentinel, a `STREAM_CLOSED` error on EOF without it, and a flush of a final unterminated event block. The file is ~67 lines with ~108 lines of dedicated tests (`tests/sse.spec.ts`) re-proving SSE spec behavior — UTF-8 split across chunks, CRLF handling, multi-`data:` joining, no-space-after-colon — that a maintained parser already guarantees. Its only consumer is `adapter.ts` (`yield* translate(parseSse(response.body))`).
-
-This is exactly the surface `eventsource-parser` owns: the de-facto standard SSE parser (it underlies the Vercel AI SDK and the MCP SDK), zero-dependency, actively maintained, and already present in this repo's lockfile transitively via `@modelcontextprotocol/sdk` — so adopting it directly adds no new supply-chain surface in practice.
-
-## Proposal
-
-Replace `sse.ts` with `EventSourceParserStream` from `eventsource-parser/stream`: `response.body.pipeThrough(new TextDecoderStream()).pipeThrough(new EventSourceParserStream())`, keeping only the DeepSeek protocol shim (~10–25 lines): yield each event's `data`, terminate on `[DONE]`, and throw `LlmError('STREAM_CLOSED')` when the stream ends without the sentinel. All required builtins (`TextDecoderStream`, `pipeThrough`, async-iterable `ReadableStream`) exist at the Node ^22.19 engine floor. Delete the spec-conformance tests; keep the `[DONE]`/`STREAM_CLOSED`/EOF contract tests. Add `eventsource-parser` to `llm-deepseek`'s dependencies (its second runtime dep after schemastery). Update the [twin-adapters note](../../implemented/architecture/2026-06-13-twin-llm-adapters.md) and the `dsh-llm` JSDoc that brand this adapter "hand-rolled fetch + SSE parsing" in the same PR.
-
-The library also strips a leading BOM (the hand-rolled parser would fail to match `data:` after one) and offers `maxBufferSize` hardening the current parser lacks.
-
-## Alternatives considered
-
-- **Keep the hand-rolled parser.** Defensible under the [twin-adapters decision](../../implemented/architecture/2026-06-13-twin-llm-adapters.md): the adapter is deliberately the hand-rolled design-verification twin of the pi-ai adapter. But the note's load-bearing distinction is owning the fetch/translate internals versus delegating to a full provider SDK; a ~700-byte SSE micro-parser is transport plumbing, not the design under verification. Whether that reading stands is the twin-note owner's call — this proposal explicitly needs their sign-off.
-- **`createParser({onEvent})` callback API instead of the stream.** Works fed by a manual `TextDecoder` loop, but the `pipeThrough` composition deletes more of the hand-rolled code.
-
-## Acceptance criteria
-
-- `sse.ts`'s parsing internals are gone; the remaining shim only encodes the DeepSeek `[DONE]`/`STREAM_CLOSED` protocol.
-- `llm-deepseek` unit tests and the real-API e2e suite pass; keyless snapshots are unchanged (parsing is transport-internal and payload extraction is equivalent).
-- The twin-adapters note and `dsh-llm` JSDoc no longer claim hand-rolled SSE parsing.
-
-## Risks
-
-- One deliberate robustness deviation is lost: the hand-rolled parser flushes a final event block that lacks its terminating blank line, and `tests/sse.spec.ts` pins that a trailing `data: [DONE]` without `\n\n` still yields DONE. eventsource-parser is spec-strict and only dispatches on the blank line, so that shape becomes `STREAM_CLOSED`. Real providers and `dsh-llm-mock-server` always terminate events properly, so the pinned behavior is a robustness nicety, not an observed provider shape — drop the test, or keep a tiny buffer-tail check if the deviation is judged load-bearing.
-- Dilutes the documented "hand-rolled" identity of the twin adapter; mitigated by updating the note in the same change rather than leaving the claim stale.

.agents/notes/proposed/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md

@@ -1,33 +0,0 @@
-# Agent Note: 用 eventsource-parser 替换 llm-deepseek 中手写的 SSE 解析器
-
-Status: proposed
-
-[English](2026-07-26-eventsource-parser-for-deepseek-sse.md) | 中文
-
-## 问题
-
-`packages/llm/llm-deepseek/src/sse.ts` 手写实现了 SSE（Server-Sent Events）解析：一个流式 `TextDecoder`、按 `\r?\n\r?\n` 切分事件块、提取并拼接 `data:` 载荷、跳过注释与其他字段、`[DONE]` 哨兵、在未见哨兵即 EOF 时抛出 `STREAM_CLOSED` 错误，以及对最后一个未终结事件块的 flush。该文件约 67 行，另有约 108 行专属测试（`tests/sse.spec.ts`）重复验证 SSE 规范行为——UTF-8 字符被切分到多个分片、CRLF 处理、多条 `data:` 拼接、冒号后无空格——而这些行为，持续维护的解析器早已有保证。它唯一的消费方是 `adapter.ts`（`yield* translate(parseSse(response.body))`）。
-
-这恰好是 `eventsource-parser` 负责的接口面：事实标准的 SSE 解析器（Vercel AI SDK 和 MCP SDK 都构建在它之上），零依赖，持续维护，并且已通过 `@modelcontextprotocol/sdk` 作为传递依赖出现在本仓库的 lockfile 中——因此直接采用它实际上不增加新的供应链接触面。
-
-## 提案
-
-用 `eventsource-parser/stream` 的 `EventSourceParserStream` 替换 `sse.ts`：`response.body.pipeThrough(new TextDecoderStream()).pipeThrough(new EventSourceParserStream())`，只保留 DeepSeek 协议垫层（约 10–25 行）：逐个产出事件的 `data`，遇到 `[DONE]` 终止，流在未见哨兵时结束则抛出 `LlmError('STREAM_CLOSED')`。所需的全部内置能力（`TextDecoderStream`、`pipeThrough`、可异步迭代的 `ReadableStream`）在 Node ^22.19 引擎下限即已存在。删除规范符合性测试；保留 `[DONE]`/`STREAM_CLOSED`/EOF 契约测试。将 `eventsource-parser` 加入 `llm-deepseek` 的依赖（这是它继 schemastery 之后的第二个运行时依赖）。在同一个 PR（Pull Request）中更新[孪生适配器 Agent Note（agent 决策记录）](../../implemented/architecture/2026-06-13-twin-llm-adapters.md)以及 `dsh-llm` 中把该适配器标为「手写 fetch + SSE 解析」的 JSDoc。
-
-该库还会剥离开头的 BOM（手写解析器在 BOM 之后会无法匹配 `data:`），并提供当前解析器缺少的 `maxBufferSize` 加固能力。
-
-## 曾考虑的替代方案
-
-- **保留手写解析器。** 依据[孪生适配器决策](../../implemented/architecture/2026-06-13-twin-llm-adapters.md)，这一选择有辩护余地：该适配器有意作为 pi-ai 适配器的手写设计验证孪生体。但那份 Agent Note 起支撑作用的区分在于「自行持有 fetch/translate 内部实现」与「委托给完整的提供方 SDK」；一个约 700 字节的 SSE 微型解析器属于传输层管道，不是被验证的设计本身。这一解读是否成立由孪生 Agent Note 的所有者裁定——本提案明确需要其签署确认。
-- **改用 `createParser({onEvent})` 回调 API 而非流。** 配合手动的 `TextDecoder` 循环可以工作，但 `pipeThrough` 组合方式能删除更多手写代码。
-
-## 验收标准
-
-- `sse.ts` 的解析内部实现消失；剩下的垫层只编码 DeepSeek 的 `[DONE]`/`STREAM_CLOSED` 协议。
-- `llm-deepseek` 单元测试与真实 API 的 e2e 套件通过；无密钥快照不变（解析属于传输层内部，载荷提取等价）。
-- 孪生适配器 Agent Note 与 `dsh-llm` 的 JSDoc 不再声称手写 SSE 解析。
-
-## 风险
-
-- 会失去一处有意为之的健壮性偏离：手写解析器会 flush 缺少终结空行的最后一个事件块，`tests/sse.spec.ts` 固定了「末尾的 `data: [DONE]` 即使没有 `\n\n` 也仍产出 DONE」这一行为。eventsource-parser 严格遵循规范，只在空行处分发事件，因此这种形态会变成 `STREAM_CLOSED`。真实提供方和 `dsh-llm-mock-server` 总是正确终结事件，所以被固定的行为只是健壮性上的锦上添花，并非实际观测到的提供方形态：可以删除该测试；若判定该偏离确有支撑作用，也可以保留一个小型的缓冲区尾部检查。
-- 稀释了孪生适配器有文档记录的「手写」身份；缓解方式是在同一次变更中更新那份 Agent Note，而不是让声明陈旧下去。

.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-07-26-dependency-swaps-rejected-by-nih-audit.md: a1d15b89f85b41e1044d9597dee6a1a0190240e6
-2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md: 4893784effdee7605f9194a80010b5a5033edbc1
+2026-07-26-dependency-swaps-rejected-by-nih-audit.md: f55bc2a9b7fb2a9599760734fca2a295665b95a2
+2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md: f740e0717cffd1b2ff4f3f5db8c9775afdfe79f0

.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md

@@ -18,7 +18,7 @@ Adopt the following dependency swaps. Rejected — per-item evidence below; a fu
 - **`vscode-languageserver-types` for lsp-local's wire-type subset**: ~80 type lines and ~45 guard lines, but upstream guards differ in both directions (accept `uri: undefined` the repo must reject; require `targetRange` the repo tolerates absent), and the initialize-result shapes live in `vscode-languageserver-protocol`, dragging `vscode-jsonrpc` in as a runtime dep — ~1 MB for 80 spec-exact lines.
 - **`json-rpc-2.0` for `dsh-jsonrpc`**: deletable correlation/dispatch is real (~100–130 lines) but the NDJSON wire must stay bit-identical for the hand-rolled Python SDK client, the package is single-maintainer, and the [GUI RPC note](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md) already treats this package as a frozen narrow surface. `vscode-jsonrpc` is a worse fit still (Content-Length framing, cancellation vocabulary the protocol lacks).
 - **`jsonrpcclient` for the Python SDK client**: v4 builds/parses messages only — ~20 lines — while the 500 lines that matter (subprocess lifecycle, threaded reader, id correlation, bidirectional server-role responses) stay; the library is in low-maintenance mode.
-- **`eventsource-parser` for apiproxy's `readSse`**: only ~15 lines of framing are deletable, both wire ends are in-repo so spec conformance is moot, and it would add a dep to a browser-safe package. (Contrast with the [llm-deepseek proposal](../../proposed/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md), where a real provider sits across the wire.)
+- **`eventsource-parser` for apiproxy's `readSse`**: only ~15 lines of framing are deletable, both wire ends are in-repo so spec conformance is moot, and it would add a dep to a browser-safe package. (Contrast with the [llm-deepseek proposal](../../implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md), where a real provider sits across the wire.)
 
 **Retry, timers, async:**
 

.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md

@@ -18,7 +18,7 @@ Status: rejected — 下列每一项替换在证据上都未达到净简化门
 - **以 `vscode-languageserver-types` 承担 lsp-local 的协议类型子集**：约 80 行类型加约 45 行守卫，但上游守卫在两个方向上都与本仓库不一致（接受本仓库必须拒绝的 `uri: undefined`；强制要求本仓库容忍缺失的 `targetRange`），而且 initialize 结果的形状住在 `vscode-languageserver-protocol` 里，会把 `vscode-jsonrpc` 拖成运行时依赖——为 80 行严格贴合规范的代码付出约 1 MB。
 - **以 `json-rpc-2.0` 替换 `dsh-jsonrpc`**：可删除的关联/分发代码确实存在（约 100–130 行），但 NDJSON 协议格式（wire format）必须与手写的 Python SDK 客户端逐位一致，该包只有单一维护者，且 [GUI RPC 决策](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md)已把这个包当作冻结的窄接口面对待。`vscode-jsonrpc` 更不合适（Content-Length 分帧、该协议并不具备的取消词汇）。
 - **以 `jsonrpcclient` 承担 Python SDK 客户端**：v4 只做消息的构造/解析——约 20 行——而真正要紧的 500 行（子进程生命周期、线程化读取器、id 关联、双向的服务端角色应答）全都保留；该库处于低维护模式。
-- **以 `eventsource-parser` 替换 apiproxy 的 `readSse`**：可删除的分帧只有约 15 行，线路两端都在仓库内，规范符合性无关紧要，而且这会给一个浏览器安全的包添加依赖。（对比 [llm-deepseek 提案](../../proposed/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md)：那里线路对面是真实的提供方。）
+- **以 `eventsource-parser` 替换 apiproxy 的 `readSse`**：可删除的分帧只有约 15 行，线路两端都在仓库内，规范符合性无关紧要，而且这会给一个浏览器安全的包添加依赖。（对比 [llm-deepseek 提案](../../implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md)：那里线路对面是真实的提供方。）
 
 **重试、定时器与异步：**
 

AGENTS.md

@@ -12,7 +12,7 @@ DeepSeek Harness SDK is a plugin-based agent harness on vendored Cordis: **every
 vendor/      Vendored Cordis source — manifest + sync procedure in vendor/README.md
 packages/    @deepseek-ai/dsh-<pkg> workspaces at packages/<group>/<pkg>/
   core/        product API spine: session, system-prompt, tools, agent, agent-loop
-  llm/         LLM seam + DeepSeek adapters (hand-rolled + pi-ai design twin)
+  llm/         LLM seam + DeepSeek adapters (direct-fetch + pi-ai design twin)
   bash/        bash executor seam + local impl + model-facing bash tools
   pty/         persistent PTY seam/backend/tools
   fs/          filesystem seam + local impl + policy gate + read/write/edit tools

apps/web/tests/code-mode-fixture.snapshot.ts

@@ -144,7 +144,7 @@ it('renders the fixture run_code turn: code parent row, nested sub-rows, error s
       "errorSubRow": true,
       "parentRow": "CodeRead the notes files and summarize",
       "subRows": [
-        "$List notes",
+        "BashList notes",
         "Readnotes/demo.txt",
         "Readnotes/missing.txt",
       ],
@@ -213,9 +213,9 @@ it('trajectory and waterfall surface the run_code sub-calls with real timing', a
   }).toMatchInlineSnapshot(`
     {
       "subCells": [
-        "#53Subbash · {"command":"ls notes","description":"List notes"}+0.8s",
-        "#54Subread · {"path":"notes/demo.txt"}+0.8s",
-        "#55Subread · {"path":"notes/missing.txt"}+0.8s",
+        "#51Subbash · {"command":"ls notes","description":"List notes"}+0.8s",
+        "#52Subread · {"path":"notes/demo.txt"}+0.8s",
+        "#53Subread · {"path":"notes/missing.txt"}+0.8s",
       ],
     }
   `)

apps/web/tests/scaffold.ts

@@ -64,7 +64,7 @@ const CONFIG_PATH = join(REPO_ROOT, 'apps/cli/cordis.yml')
 
 // Replay publishes the provider catalog the gateway routes to (providers
 // mode, never catch-all: with llm-deepseek disabled no adapter exists, so a
-// catch-all would leave resolveModelContext unroutable and compact-basic's
+// catch-all would leave resolveModelInfo unroutable and compact-basic's
 // post-step pressure check would warn every step). The published
 // contextWindow keeps that pressure path provably inert for small fixtures.
 const REPLAY_PROVIDERS = [{ id: 'deepseek', name: 'DeepSeek', models: [{ id: 'deepseek-v4-flash', contextWindow: 128_000 }] }]

apps/web/tests/todo-display.snapshot.ts

@@ -0,0 +1,189 @@
+// @vitest-environment jsdom
+// Todo display snapshot over the BUILT client graph (the code-mode-fixture
+// idiom: real bundles via AppWebEntry, keyless FixtureApiClient transport).
+// Opens the fixture history session and pins the todo_write turn's two
+// surfaces: the dedicated TodoRow in the chat flow (keyed toolview, summary
+// derived from the call args) and the TodoPanel plan strip riding the
+// 'conversation.input.dock' slot (fed by ConversationSnapshot.todos, seeded
+// by the tail history page), including the collapse interaction.
+import { readFileSync } from 'node:fs'
+import { join } from 'node:path'
+import { act, cleanup, fireEvent, screen, waitFor, within } from '@testing-library/react'
+import { afterEach, beforeEach, expect, it, vi } from 'vitest'
+import type { WebBootEntry } from '@deepseek-ai/dsh-client-modules/client'
+import { AppWebEntry } from '@deepseek-ai/dsh-client-web'
+
+const PLUGINS: readonly (WebBootEntry & { dir: string })[] = [
+  { id: '@deepseek-ai/dsh-client-connection', dir: 'connection', url: '/plugins/connection.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', url: '/plugins/runtime.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
+  { id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', url: '/plugins/ui-theme.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-locale', dir: 'locale', url: '/plugins/locale.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', url: '/plugins/ui-layout.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-runtime'] },
+  { id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', url: '/plugins/ui-sidebar.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  { id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', url: '/plugins/ui-conversation.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  {
+    id: '@deepseek-ai/dsh-client-ui-workspace',
+    dir: 'ui-workspace',
+    url: '/plugins/ui-workspace.js',
+    rev: 'fx',
+    inject: [
+      '@deepseek-ai/dsh-client-runtime',
+      '@deepseek-ai/dsh-client-ui-conversation',
+      '@deepseek-ai/dsh-client-ui-sidebar',
+    ],
+  },
+]
+
+const bundles = new Map(PLUGINS.map(plugin => [
+  plugin.url,
+  readFileSync(join(process.cwd(), 'packages/client', plugin.dir, 'lib/client.js'), 'utf8'),
+]))
+
+interface FixtureWindow extends Window {
+  __DSH_BOOT__?: { rev: string; entries: WebBootEntry[] }
+  __ModuleLoader__?: unknown
+}
+
+class ResizeObserverStub {
+  observe(): void {}
+  disconnect(): void {}
+  unobserve(): void {}
+}
+
+const win = window as FixtureWindow
+let unmount: (() => void) | undefined
+
+beforeEach(() => {
+  localStorage.clear()
+  document.title = 'DeepSeek Harness'
+  vi.stubGlobal('ResizeObserver', ResizeObserverStub)
+  vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) =>
+    setTimeout(() => { callback(0) }, 0) as unknown as number)
+  vi.stubGlobal('cancelAnimationFrame', (id: number) => { clearTimeout(id) })
+})
+
+afterEach(() => {
+  act(() => { unmount?.() })
+  unmount = undefined
+  cleanup()
+  delete win.__DSH_BOOT__
+  delete win.__ModuleLoader__
+  delete (globalThis as Record<string, unknown>).__fxTiming
+  document.body.innerHTML = ''
+  document.head.querySelectorAll('style[data-plugin]').forEach((style) => { style.remove() })
+  document.title = ''
+  history.replaceState(null, '', '/')
+  vi.unstubAllGlobals()
+})
+
+/** Boot the complete built client graph against the populated fixture branch. */
+function boot(): void {
+  history.replaceState(null, '', '/?fixture')
+  const root = document.createElement('div')
+  root.id = 'root'
+  document.body.appendChild(root)
+  win.__DSH_BOOT__ = { rev: 'fx', entries: PLUGINS.map(({ dir: _dir, ...plugin }) => plugin) }
+  act(() => {
+    const entry = new AppWebEntry(root, {
+      fetchBundle: (url) => {
+        const code = bundles.get(url)
+        return code === undefined ? Promise.reject(new Error(`missing built bundle ${url}`)) : Promise.resolve(code)
+      },
+      executeBundle: (code) => { (0, eval)(code) },
+    })
+    void entry.run()
+    unmount = () => { entry.dispose() }
+  })
+}
+
+/** Collapse decorative whitespace while preserving the text a user sees. */
+function visibleText(element: Element): string {
+  return (element.textContent ?? '').replace(/\s+/g, ' ').trim()
+}
+
+/** Open the fixture history session (the alpha log carrying the todo_write turn) and wait for its tail. */
+async function openFixtureSession(): Promise<void> {
+  const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
+  // Anchor on the expandable Workspace group row: the title and the blank
+  // session row can both read "fixture", and the session-count meta shifts
+  // when a blank session joins the group.
+  const group = (await within(tree).findAllByText('fixture'))
+    .map(el => el.closest<HTMLElement>('[role="treeitem"]'))
+    .find(el => el?.getAttribute('aria-expanded') !== null)
+  if (group === null || group === undefined) throw new Error('fixture Workspace group missing')
+  if (group.getAttribute('aria-expanded') === 'false') {
+    fireEvent.click(within(group).getByText('fixture'))
+    await waitFor(() => {
+      expect(group.getAttribute('aria-expanded')).toBe('true')
+    })
+  }
+  const session = await within(tree).findByText('Fixture 历史会话')
+  fireEvent.click(session)
+  await waitFor(() => {
+    expect(document.querySelector('[data-sample="todo-row"]')).not.toBeNull()
+  }, { timeout: 10_000 })
+}
+
+it('renders the todo_write turn: dedicated tool row + the dock plan strip', async () => {
+  boot()
+  await openFixtureSession()
+
+  const row = document.querySelector('[data-sample="todo-row"]')
+  if (row === null) throw new Error('todo row missing')
+  const panel = document.querySelector('[data-testid="todo-panel"]')
+  if (panel === null) throw new Error('todo panel missing from the input dock')
+
+  expect({
+    row: visibleText(row),
+    rowState: row.getAttribute('data-state'),
+    panelHeader: visibleText(panel.querySelector('button') ?? panel),
+    panelItems: [...panel.querySelectorAll('li')].map(item => ({
+      status: item.getAttribute('data-status'),
+      text: visibleText(item),
+    })),
+  }).toMatchInlineSnapshot(`
+    {
+      "panelHeader": "Plan1/3",
+      "panelItems": [
+        {
+          "status": "completed",
+          "text": "✓梳理需求",
+        },
+        {
+          "status": "in_progress",
+          "text": "●实现 fixture 样本",
+        },
+        {
+          "status": "pending",
+          "text": "○浏览器验收",
+        },
+      ],
+      "row": "☰更新任务清单1/3 已完成 · 实现 fixture 样本",
+      "rowState": "ok",
+    }
+  `)
+})
+
+it('collapses the plan strip to the in-progress hint and restores it', async () => {
+  boot()
+  await openFixtureSession()
+
+  const panel = document.querySelector('[data-testid="todo-panel"]')
+  if (panel === null) throw new Error('todo panel missing from the input dock')
+  const header = panel.querySelector('button')
+  if (header === null) throw new Error('todo panel header missing')
+
+  fireEvent.click(header)
+  expect({
+    collapsedHeader: visibleText(header),
+    listGone: panel.querySelector('ul') === null,
+  }).toMatchInlineSnapshot(`
+    {
+      "collapsedHeader": "Plan1/3实现 fixture 样本",
+      "listGone": true,
+    }
+  `)
+
+  fireEvent.click(header)
+  expect(panel.querySelectorAll('li')).toHaveLength(3)
+})

docs/architecture.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-architecture.md: 456b97da984c39cfbd3284d31d81d115ecd00a3b
-architecture.zh.md: e1aefb596483978f287b05ba446dc0d642a042c8
+architecture.md: 34e56dd955e6ac5ad8fad236bdf7ae9cfc810a83
+architecture.zh.md: ea105b869eba799d00dfaa134ed34d14c7505fc8

docs/architecture.md

@@ -90,7 +90,7 @@ forever:
       assemble system prompt and tool schemas
       snapshot the derived messages (the reconstruction boundary)
       'step/start'
-      agent/request (config only) -> log request/header -> llm/stream (frozen)
+      agent/request (config only) -> prepare reasoning/default under turn signal -> log request/header -> llm/stream (frozen, registration-bound)
       'assistant/chunk'
       'assistant/message'
       schedule tool calls by ctx.tools.executionMode:
@@ -120,7 +120,7 @@ Pruning precedes summaries; overflow retries require durable progress. Recovery
 
 Adapter failures close the step before `agent/request-error` receives the exact `Error`, normalized `LlmFailure`, and turn signal. A handling listener calls `agent.retry()`; the loop closes the failed turn and opens another from durable history without an idle notification. Exhaustion leaves the failed `turn/end` terminal. Failed chunks commit no message or tool call.
 
-Other failures use `agent/error`. Cancellation and disposal beat recovery; undispatched tools get synthetic `tool/call`/`ABORTED_BEFORE_DISPATCH` pairs. Effective `cancel(cause)` emits its cause before clearing queues and aborting; observers cannot veto and idle calls emit nothing. Durability records `aborted` for user or parent cancellation and `disposed` for teardown, which awaits quiescence. The cause changes reporting, not late result-context handling ([decision](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)).
+Other failures use `agent/error`. Cancellation and disposal beat recovery; the turn signal also cancels asynchronous model-capability preparation before any request header is committed, and undispatched tools get synthetic `tool/call`/`ABORTED_BEFORE_DISPATCH` pairs. Effective `cancel(cause)` emits its cause before clearing queues and aborting; observers cannot veto and idle calls emit nothing. Durability records `aborted` for user or parent cancellation and `disposed` for teardown, which awaits quiescence. The cause changes reporting, not late result-context handling ([decision](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)).
 
 Turn and step events are turn-enclosed; idle injected `user/message` events may sit between turns. Reload closes an interrupted tail with a synthetic turn end. Post-close failures use only `agent/error`. Each turn has one [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap).
 

docs/architecture.zh.md

@@ -90,7 +90,7 @@ forever:
       assemble system prompt and tool schemas
       snapshot the derived messages (the reconstruction boundary)
       'step/start'
-      agent/request (config only) -> log request/header -> llm/stream (frozen)
+      agent/request (config only) -> prepare reasoning/default under turn signal -> log request/header -> llm/stream (frozen, registration-bound)
       'assistant/chunk'
       'assistant/message'
       schedule tool calls by ctx.tools.executionMode:
@@ -120,7 +120,7 @@ idle inject:
 
 适配器故障会先关闭步骤，再由 `agent/request-error` 接收准确的 `Error`、标准化的 `LlmFailure` 和轮次信号。负责处理的监听器调用 `agent.retry()`；循环关闭失败轮次，并从持久历史开启另一个轮次，中间不发出空闲通知。重试耗尽后，失败的 `turn/end` 即为终态记录。失败分片不会提交消息或工具调用。
 
-其他故障使用 `agent/error`。取消和资源释放优先于恢复；尚未分派的工具会得到合成的 `tool/call`/`ABORTED_BEFORE_DISPATCH` 对。实际生效的 `cancel(cause)` 在清空队列和中止前发出原因；观察方不能否决，空闲调用不发事件。用户或父级取消持久记录为 `aborted`，等待停稳的资源释放记录为 `disposed`。原因只改变报告方式，不改变延迟完成的结果上下文处理（[决策](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)）。
+其他故障使用 `agent/error`。取消和资源释放优先于恢复；轮次信号还会在提交任何请求头之前取消异步模型能力准备，尚未分派的工具会得到合成的 `tool/call`/`ABORTED_BEFORE_DISPATCH` 对。实际生效的 `cancel(cause)` 在清空队列和中止前发出原因；观察方不能否决，空闲调用不发事件。用户或父级取消持久记录为 `aborted`，等待停稳的资源释放记录为 `disposed`。原因只改变报告方式，不改变延迟完成的结果上下文处理（[决策](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)）。
 
 轮次和步骤事件均位于轮次边界内；空闲时注入的 `user/message` 可以位于两个轮次之间。重新加载会用合成的轮次结束事件闭合中断尾部。关闭后的故障只使用 `agent/error`。每个轮次有一个 [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap)。
 

docs/config-catalog.md

@@ -565,18 +565,19 @@ Requires: `llm`
 /**
  * Plugin config, validated by the same-named schemastery schema. Every field
  * is optional in yml: credentials/endpoint fall back to the environment (a
- * missing API key fails plugin load, not the first call), and omitted
- * thinking fields send nothing on the wire, so the provider default applies.
+ * missing API key fails plugin load, not the first call), omitted thinking
+ * mode uses the provider default, and omitted reasoning effort resolves to
+ * `high`.
  */
 export interface Config {
   /** API key; falls back to $DEEPSEEK_API_KEY. Required one way or the other. */
   apiKey?: string
   /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */
   baseURL?: string
-  /** Thinking-mode default for every request (provider default: enabled). */
+  /** Deployment thinking policy; `disabled` limits every conversation request to `off`. */
   thinking?: 'enabled' | 'disabled'
-  /** Thinking effort (only meaningful with thinking enabled). */
-  reasoningEffort?: 'high' | 'max'
+  /** Default thinking effort (default `high`); `off` disables thinking per request. */
+  reasoningEffort?: 'off' | 'high' | 'max'
   /** Positive context capacity used when the selected model has no exact value. */
   defaultContextWindow?: number
   /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */
@@ -585,7 +586,7 @@ export interface Config {
   streamIdleTimeoutMs?: number
 }
 
-/** One optional model entry advertised by the hand-written adapter. */
+/** One optional model entry advertised by the direct-fetch adapter. */
 export interface DeepSeekCatalogModel {
   /** Wire model id accepted by the configured endpoint. */
   id: string
@@ -598,7 +599,7 @@ export interface DeepSeekCatalogModel {
 }
 ```
 
-Source: [`packages/llm/llm-deepseek/src/index.ts:34`](../packages/llm/llm-deepseek/src/index.ts)
+Source: [`packages/llm/llm-deepseek/src/index.ts:35`](../packages/llm/llm-deepseek/src/index.ts)
 
 ## `@deepseek-ai/dsh-llm-pi-ai`
 
@@ -622,7 +623,7 @@ export interface PiAiProviderProfile {
   /** Provider request headers; Harness attribution wins reserved names. */
   headers?: Record<string, string>
   /** Provider-neutral pi-ai reasoning level. */
-  reasoning?: ThinkingLevel
+  reasoning?: ModelThinkingLevel
   /** Token budgets used by reasoning providers that support them. */
   thinkingBudgets?: ThinkingBudgets
   /** Prompt-cache retention preference. */
@@ -638,7 +639,7 @@ export interface PiAiProviderProfile {
 }
 ```
 
-Depends on: `CacheRetention` (`@earendil-works/pi-ai`) · `ThinkingBudgets` (`@earendil-works/pi-ai`) · `ThinkingLevel` (`@earendil-works/pi-ai`) · `Transport` (`@earendil-works/pi-ai`)
+Depends on: `CacheRetention` (`@earendil-works/pi-ai`) · `ModelThinkingLevel` (`@earendil-works/pi-ai`) · `ThinkingBudgets` (`@earendil-works/pi-ai`) · `Transport` (`@earendil-works/pi-ai`)
 
 Source: [`packages/llm/llm-pi-ai/src/config.ts:48`](../packages/llm/llm-pi-ai/src/config.ts)
 
@@ -688,7 +689,7 @@ export interface ReplayModelConfig {
 }
 ```
 
-Source: [`packages/support/llm-replay/src/index.ts:590`](../packages/support/llm-replay/src/index.ts)
+Source: [`packages/support/llm-replay/src/index.ts:598`](../packages/support/llm-replay/src/index.ts)
 
 ## `@deepseek-ai/dsh-llm-retry`
 
@@ -1781,7 +1782,7 @@ export interface TuiConfig {
 }
 ```
 
-Source: [`packages/ui/tui/src/index.ts:270`](../packages/ui/tui/src/index.ts)
+Source: [`packages/ui/tui/src/index.ts:273`](../packages/ui/tui/src/index.ts)
 
 ## `@deepseek-ai/dsh-tui-demo`
 

docs/cookbook/adding-an-llm-adapter.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-adding-an-llm-adapter.md: f20442b8c2ce823452a3ea13409f202185d12d04
-adding-an-llm-adapter.zh.md: 2864dd1e18742c7449e24f22504a5a38976ab450
+#   pnpm run verify-translation-pairing --write docs/cookbook/adding-an-llm-adapter.md
+adding-an-llm-adapter.md: a7f9dced70041653a0cb815147a07b6386d79e3e
+adding-an-llm-adapter.zh.md: 3515927585201326b713bb03cd863886ce7846bd

docs/cookbook/adding-an-llm-adapter.md

@@ -2,7 +2,7 @@
 
 English | [中文](adding-an-llm-adapter.zh.md)
 
-How to connect a new model provider. Reference implementations: `packages/llm/llm-deepseek` (hand-rolled HTTP/SSE) and `packages/llm/llm-pi-ai` (wrapping an LLM library). Read the `StreamChunk` doc in `packages/llm/llm/src/types.ts` first — it records the protocol conventions both adapters were verified against.
+How to connect a new model provider. Reference implementations: `packages/llm/llm-deepseek` (direct HTTP, SSE framed by `eventsource-parser`) and `packages/llm/llm-pi-ai` (wrapping an LLM library). Read the `StreamChunk` doc in `packages/llm/llm/src/types.ts` first — it records the protocol conventions both adapters were verified against.
 
 ## The shape
 
@@ -32,7 +32,7 @@ Registration is effect-based (HMR-safe); one adapter per provider route — dupl
 - A `GenerateOptions` field your provider cannot honor (e.g. a `stop` list on a provider without stop sequences): throw `LlmError(..., 'UNSUPPORTED')` rather than silently dropping it.
 - If the provider requires response ids, signatures, or other native metadata on follow-up calls, emit the minimal lossless-JSON projection as `finish.replayState`. Validate it when rebuilding history. `LlmService` passes it only when the historical provider route and target provider route are currently owned by the exact same adapter instance; your adapter decides whether same-model, cross-model, or cross-provider restoration is legal. Never infer native replay from provider/model names alone when state is absent.
 
-Provider-specific request knobs (thinking modes, effort levels) belong in the ADAPTER's Config, not in `GenerateOptions` — the core vocabulary stays provider-neutral.
+Provider-specific thinking-mode toggles remain in the adapter's Config. Exact model metadata uses one provider-neutral capability seam: implement `resolveModel()` with provider/model identity and optional `context` and `reasoning` fields, declare a configured `defaultEffort` only when one exists, and honor the resolver's optional `AbortSignal`. Reasoning efforts are ordered opaque ids mapped to provider requests by the adapter. Preserve the adapter's authoritative selectable list, including an adapter-defined `off` when supported, without exposing final wire spellings or clamping unsupported values; an id need not equal its wire representation.
 
 ## Structure that worked
 

docs/cookbook/adding-an-llm-adapter.zh.md

@@ -2,7 +2,7 @@
 
 [English](adding-an-llm-adapter.md) | 中文
 
-如何接入一个新的模型提供方。参考实现：`packages/llm/llm-deepseek`（手写 HTTP/SSE）与 `packages/llm/llm-pi-ai`（封装 LLM 库）。请先阅读 `packages/llm/llm/src/types.ts` 中的 `StreamChunk` 文档——它记录了两个适配器都经过验证的协议约定。
+如何接入一个新的模型提供方。参考实现：`packages/llm/llm-deepseek`（直接 HTTP，SSE 由 `eventsource-parser` 分帧）与 `packages/llm/llm-pi-ai`（封装 LLM 库）。请先阅读 `packages/llm/llm/src/types.ts` 中的 `StreamChunk` 文档——它记录了两个适配器都经过验证的协议约定。
 
 ## 基本形态
 
@@ -32,7 +32,7 @@ export function apply(ctx: Context, config: Config) {
 - 如果 `GenerateOptions` 中某个字段你的提供方无法支持（例如提供方不支持 stop sequences 时收到 `stop` 列表）：抛出 `LlmError(..., 'UNSUPPORTED')`，而非静默丢弃。
 - 如果提供方在后续调用中需要响应 ID、签名或其他原生元数据，请将其最小无损 JSON 投影作为 `finish.replayState` 发出。重建历史时验证该状态。只有历史提供方路由和目标提供方路由当前由完全相同的适配器实例拥有时，`LlmService` 才会传递该状态；由适配器决定同模型、跨模型或跨提供方恢复是否合法。状态缺失时，切勿仅根据提供方/模型名称推断原生回放。
 
-提供方特有的请求旋钮（thinking 模式、effort 级别）放在**适配器**的 Config 中，而非 `GenerateOptions` 中——核心词汇保持提供方无关。
+提供方特有的 thinking 模式开关仍放在适配器的 Config 中。确切模型元数据使用一处提供方无关的能力 seam：实现 `resolveModel()`，返回提供方/模型身份以及可选的 `context` 和 `reasoning` 字段；仅当存在配置指定的默认值时才声明 `defaultEffort`；响应传给解析器的可选 `AbortSignal`。推理强度是由适配器映射到提供方请求的有序不透明 ID。请保留适配器给出的权威可选列表，包括适配器在支持时定义的 `off`；不得暴露最终协议值的具体拼写，也不得自动调整不支持的值。ID 无需与其协议表示相同。
 
 ## 经验证有效的结构
 

docs/cordis-catalog/events.md

@@ -541,7 +541,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t
 
 Types: [GenerateOptions](../core-data-structures/core.md) · [LlmService](../core-data-structures/llm-streaming.md) · [StreamChunk](../core-data-structures/llm-streaming.md)
 
-Source: [`packages/llm/llm/src/index.ts:52`](../../packages/llm/llm/src/index.ts)
+Source: [`packages/llm/llm/src/index.ts:53`](../../packages/llm/llm/src/index.ts)
 
 ## `session/*`
 

docs/cordis-catalog/services.md

@@ -730,33 +730,57 @@ listProviders(): LlmProviderInfo[]
 async listModels(provider: string): Promise<LlmModelInfo[]>
 
 /**
- * Resolve context capacity from the adapter that owns one exact route.
- * This query is independent of the advisory model catalog: an unlisted model
- * may return metadata, while `undefined` never rejects later routing.
+ * Resolve and validate all metadata from the adapter that owns one exact
+ * route. The result is detached from adapter-owned objects; catalog
+ * membership remains advisory and does not control request routing.
  * @param provider - registered provider route to inspect.
  * @param model - exact model id passed to the adapter.
- * @returns detached context metadata, or `undefined` when the adapter has none.
+ * @param signal - optional cancellation for adapter-owned asynchronous lookup.
+ * @returns exact model identity plus available context and reasoning metadata.
  */
-async resolveModelContext( provider: string, model: string, ): Promise<LlmModelContext | undefined>
+async resolveModelInfo( provider: string, model: string, signal?: AbortSignal, ): Promise<LlmResolvedModelInfo>
+
+/**
+ * Validate a conversation call config against its exact model capability and
+ * materialize an adapter-configured default. Unsupported explicit efforts
+ * reject before provider I/O; no clamping or aliasing is performed. This
+ * standalone query does not bind a later dispatch; use {@link prepareCall}
+ * when logging and streaming must share one adapter registration.
+ * @param config - provider/model route and optional request controls.
+ * @param signal - optional cancellation for adapter-owned capability lookup.
+ * @returns a detached config only when a default must be materialized.
+ */
+async resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>
+
+/**
+ * Resolve one call under its current adapter registration. The returned
+ * one-shot handle keeps that registration across header logging and dispatch,
+ * so HMR cannot combine one adapter's capability result with another adapter.
+ * @param config - provider/model route and optional request controls.
+ * @param signal - optional cancellation for adapter-owned capability lookup.
+ * @returns a prepared config and its registration-bound stream entry point.
+ */
+async prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>
 
 /**
  * Stream one model call as raw chunks (token-level deltas). Throws
  * `LlmError` with code `NO_ADAPTER` if no adapter is registered for
  * `options.provider`. Replay state is retained only when the same adapter
  * instance owns its historical provider and the target provider. Final
- * adapter selection, dispatch, and iteration failures retain their original
- * Error identity and are tagged in a call-local scope for narrow agent-loop
- * request recovery; middleware and nested-call failures remain untagged for
- * the outer call.
+ * adapter selection remains fixed through asynchronous exact-model resolution
+ * and dispatch. Selection, dispatch, and iteration failures retain their
+ * original Error identity and are tagged in a call-local scope for narrow
+ * agent-loop request recovery; middleware and nested-call failures remain
+ * untagged for the outer call.
  * @param options - the full request; `options.provider` selects the adapter.
  * @returns the chunk stream, possibly wrapped by `llm/stream` listeners.
  */
 stream(options: GenerateOptions): AsyncIterable<StreamChunk>
 ```
 
-Types: [GenerateOptions](../core-data-structures/core.md) · [LlmAdapter](../core-data-structures/llm-streaming.md) · [LlmModelContext](../core-data-structures/core.md) · [LlmModelInfo](../core-data-structures/core.md) · [LlmProviderInfo](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md)
+Types: [GenerateOptions](../core-data-structures/core.md) · [LlmAdapter](../core-data-structures/llm-streaming.md) · [LlmCallConfig](../core-data-structures/core.md) · [LlmModelInfo](../core-data-structures/core.md) · [LlmProviderInfo](../core-data-structures/core.md) · [LlmResolvedModelInfo](../core-data-structures/core.md) · [PreparedLlmCall](../core-data-structures/llm-streaming.md) · [StreamChunk](../core-data-structures/llm-streaming.md)
 
-Source: [`packages/llm/llm/src/index.ts:159`](../../packages/llm/llm/src/index.ts)
+Source: [`packages/llm/llm/src/index.ts:177`](../../packages/llm/llm/src/index.ts)
 
 ## `ctx.permission` — `PermissionService`
 
@@ -1342,7 +1366,7 @@ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId):
 
 Types: [CreateSessionOptions](../core-data-structures/persistence.md) · [OutOfBandSessionEventType](../core-data-structures/session.md) · [Session](../core-data-structures/session.md) · [SessionEvent](../core-data-structures/core.md) · [SessionEventMap](../core-data-structures/session.md) · [SessionId](../core-data-structures/core.md) · [TurnTrigger](../core-data-structures/session.md)
 
-Source: [`packages/core/session/src/index.ts:595`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:600`](../../packages/core/session/src/index.ts)
 
 ## `ctx.sessionTitle` — `SessionTitleService`
 
@@ -1878,7 +1902,7 @@ The concrete provider retains pi-tui, focus, and terminal lifecycle state. Plugi
 abstract openOverlay(request: TuiOverlayRequest): TuiOverlaySession
 ```
 
-Source: [`packages/ui/tui/src/index.ts:150`](../../packages/ui/tui/src/index.ts)
+Source: [`packages/ui/tui/src/index.ts:153`](../../packages/ui/tui/src/index.ts)
 
 ## `ctx.userInteraction` — `UserInteractionService`
 

docs/core-data-structures/core.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-core.md: 3c4742253c884536ffde1df34ffc35d10369b92e
-core.zh.md: 23398beb9fad565648eeaee4c8ec2b386117728a
+core.md: 86aea325f5401d728a9b4aa147d78db9163a32c1
+core.zh.md: d09fb48419c14959eefb5a1df1c593b36c188cf5

docs/core-data-structures/core.md

@@ -199,7 +199,7 @@ interface LlmModelInfo {
 }
 ```
 
-Correctness-sensitive model capacity is queried separately from the advisory catalog and is owned by the adapter serving the exact route.
+Correctness-sensitive metadata is resolved separately from the advisory catalog and is owned by the adapter serving the exact route. Context capacity and reasoning choices share one exact-model result so consumers do not repeat authoritative model resolution.
 
 ```ts type-equiv
 /** Provider-owned context capacity for one exact provider/model route. */
@@ -209,12 +209,56 @@ interface LlmModelContext {
 }
 ```
 
+Reasoning effort is another exact-route capability. The core brands identifiers but does not enumerate their values; each adapter owns the ordered set, display names, and optional deployment default.
+
+```ts type-equiv
+/** Adapter-owned identifier for one model's selectable reasoning effort. */
+type ReasoningEffortId = Branded<'ReasoningEffortId'>
+```
+
+```ts type-equiv
+/** Display metadata for one adapter-owned reasoning effort. */
+interface LlmReasoningEffortInfo {
+  /** Opaque stable value accepted by {@link GenerateOptions.reasoningEffort}. */
+  id: ReasoningEffortId
+  /** Human-readable effort name for selectors and diagnostics. */
+  name: string
+  /** Optional user-facing distinction from otherwise similar efforts. */
+  description?: string
+}
+```
+
+```ts type-equiv
+/** Selectable reasoning efforts for one exact provider/model route. */
+interface LlmModelReasoningInfo {
+  /** Supported efforts in adapter-preferred display order. */
+  efforts: readonly LlmReasoningEffortInfo[]
+  /**
+   * Adapter-configured default materialized into requests when callers omit
+   * an effort. Absence preserves the provider's own default.
+   */
+  defaultEffort?: ReasoningEffortId
+}
+```
+
+```ts type-equiv
+/** Exact-route model metadata resolved by its owning adapter. */
+interface LlmResolvedModelInfo extends LlmModelInfo {
+  /** Provider-owned context capacity when known. */
+  context?: LlmModelContext
+  /** Adapter-owned selectable reasoning levels when exposed. */
+  reasoning?: LlmModelReasoningInfo
+}
+```
+
 ```ts type-equiv
 /** A single model request, fully assembled. */
 interface GenerateOptions {
   /** Registered provider route selecting the adapter instance. */
   provider: string
   model: string
+  /** Adapter-owned reasoning effort selected for this exact model. */
+  reasoningEffort?: ReasoningEffortId
   /**
    * Ordered conversation messages, exactly as the provider sees them (after
    * the `system` slot). A loop-built request assembles them as
@@ -290,21 +334,23 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition`
 
 The loop builds each request from logged state. `EpochHeader` records call config, rendered prompt, and authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset) through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability Agent Note](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md).
 
-`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, or sampling. Requests reaching `llm/stream` are deep-frozen, so mutation throws, and carry a process-local loop identity so observers do not confuse separately logged frozen auxiliary calls with conversation requests.
+`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, reasoning effort, or sampling. After the waterfall, the loop prepares the exact model capability under the turn signal, rejects unsupported explicit effort ids without clamping, materializes an adapter-configured default, and logs the effective value. The prepared call keeps one adapter registration through dispatch. Requests reaching `llm/stream` are deep-frozen, so mutation throws, and carry a process-local loop identity so observers do not confuse separately logged frozen auxiliary calls with conversation requests.
 
 On the wire, a loop-built request reads the `system` slot (the rendered prompt assembly) followed by the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The dev invariant recomputes exactly this equation against every loop-built request.
 
-FIXME(call-config-shape): revisit the exact definition of this type — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit here out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them.
+FIXME(call-config-shape): revisit which remaining fields are genuinely epoch-level for cache purposes (`model` and the model-owned reasoning effort are explicit; the sampling scalars sit here out of caution).
 
 ```ts type-equiv
 /**
- * Provider + model + sampling scalars of one conversation's requests. Every field maps
- * 1:1 onto the same-named `GenerateOptions` field; the loop builds requests
- * from the logged header rather than accepting these per call.
+ * Provider, model, reasoning effort, and sampling scalars of one conversation's
+ * requests. Every field maps 1:1 onto the same-named `GenerateOptions` field;
+ * the loop builds requests from the logged header rather than accepting these
+ * per call.
  */
 interface LlmCallConfig {
   provider: string
   model: string
+  reasoningEffort?: ReasoningEffortId
   temperature?: number
   maxTokens?: number
   stop?: string[]

docs/core-data-structures/core.zh.md

@@ -205,7 +205,7 @@ interface LlmModelInfo {
 }
 ```
 
-对正确性敏感的模型容量与参考目录分开查询，并归服务该确切路由的适配器所有。
+对正确性敏感的元数据与参考目录分开解析，并归服务该确切路由的适配器所有。上下文容量和推理选项共用同一个确切模型结果，消费方因而无需重复执行权威模型解析。
 
 ```ts type-equiv
 /** Provider-owned context capacity for one exact provider/model route. */
@@ -215,12 +215,56 @@ interface LlmModelContext {
 }
 ```
 
+推理强度是另一项针对确切路由的能力。核心为标识符添加品牌类型，但不枚举其值；有序集合、展示名称和可选的部署默认值均由各适配器持有。
+
+```ts type-equiv
+/** Adapter-owned identifier for one model's selectable reasoning effort. */
+type ReasoningEffortId = Branded<'ReasoningEffortId'>
+```
+
+```ts type-equiv
+/** Display metadata for one adapter-owned reasoning effort. */
+interface LlmReasoningEffortInfo {
+  /** Opaque stable value accepted by {@link GenerateOptions.reasoningEffort}. */
+  id: ReasoningEffortId
+  /** Human-readable effort name for selectors and diagnostics. */
+  name: string
+  /** Optional user-facing distinction from otherwise similar efforts. */
+  description?: string
+}
+```
+
+```ts type-equiv
+/** Selectable reasoning efforts for one exact provider/model route. */
+interface LlmModelReasoningInfo {
+  /** Supported efforts in adapter-preferred display order. */
+  efforts: readonly LlmReasoningEffortInfo[]
+  /**
+   * Adapter-configured default materialized into requests when callers omit
+   * an effort. Absence preserves the provider's own default.
+   */
+  defaultEffort?: ReasoningEffortId
+}
+```
+
+```ts type-equiv
+/** Exact-route model metadata resolved by its owning adapter. */
+interface LlmResolvedModelInfo extends LlmModelInfo {
+  /** Provider-owned context capacity when known. */
+  context?: LlmModelContext
+  /** Adapter-owned selectable reasoning levels when exposed. */
+  reasoning?: LlmModelReasoningInfo
+}
+```
+
 ```ts type-equiv
 /** A single model request, fully assembled. */
 interface GenerateOptions {
   /** Registered provider route selecting the adapter instance. */
   provider: string
   model: string
+  /** Adapter-owned reasoning effort selected for this exact model. */
+  reasoningEffort?: ReasoningEffortId
   /**
    * Ordered conversation messages, exactly as the provider sees them (after
    * the `system` slot). A loop-built request assembles them as
@@ -296,21 +340,23 @@ interface ToolSchema {
 
 循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、渲染后的提示词以及权威返回工具顺序（由 `toolOrder` 配置；未配置时按字典序）。结合派生历史，请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note（agent 决策记录）](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。
 
-`agent/request` 接收冻结的调用配置种子，并可返回替代值以切换提供方、模型或采样参数。到达 `llm/stream` 的请求会被深度冻结，因此变更会抛异常；请求还携带进程本地循环标识，使观察者不会把单独记录的冻结辅助调用误认成对话请求。
+`agent/request` 接收冻结的调用配置种子，并可返回替代值以切换提供方、模型、推理强度或采样参数。waterfall 结束后，循环会在轮次信号控制下完成确切模型的能力准备，拒绝显式指定但不受支持的推理强度 ID（不自动调整），填入适配器配置的默认值，并记录最终生效值。准备完成的调用直至分派完成始终持有同一项适配器注册。到达 `llm/stream` 的请求会被深度冻结，因此变更会抛异常；请求还携带进程本地循环标识，使观察者不会把单独记录的冻结辅助调用误认成对话请求。
 
 在协议格式上，循环构建的请求先读取 `system` 槽位（渲染后的提示词组装），再读取派生历史——边界快照，其尾部在轮次首步是最新的 `user/message`，在后续步骤是上一步的工具结果。开发不变式针对每个循环构建的请求精确重算此等式。
 
-FIXME(call-config-shape)：重新审视此类型的精确定义——出于缓存目的，哪些字段确实属于 epoch 层级（`model` 肯定属于；采样标量目前出于谨慎放在这里），以及适配器需要时，提供方特有的额外项（推理选项、额外 body 参数）应归属何处。
+FIXME(call-config-shape)：重新审视其余哪些字段出于缓存目的确实属于 epoch 层级（`model` 和模型持有的推理强度已明确属于；采样标量目前出于谨慎保留在此）。
 
 ```ts type-equiv
 /**
- * Provider + model + sampling scalars of one conversation's requests. Every field maps
- * 1:1 onto the same-named `GenerateOptions` field; the loop builds requests
- * from the logged header rather than accepting these per call.
+ * Provider, model, reasoning effort, and sampling scalars of one conversation's
+ * requests. Every field maps 1:1 onto the same-named `GenerateOptions` field;
+ * the loop builds requests from the logged header rather than accepting these
+ * per call.
  */
 interface LlmCallConfig {
   provider: string
   model: string
+  reasoningEffort?: ReasoningEffortId
   temperature?: number
   maxTokens?: number
   stop?: string[]

docs/core-data-structures/llm-streaming.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-llm-streaming.md: 0b2c81b1cb264a949cf3c1a1a22f45633cddab65
-llm-streaming.zh.md: a9391855ae170dd5f5b1a163cb0b586e15be41ea
+#   pnpm run verify-translation-pairing --write docs/core-data-structures/llm-streaming.md
+llm-streaming.md: 9151ba569af6b640144c1850d616b6f762b68a8b
+llm-streaming.zh.md: ae4a6843b9bf4f09169b17271c7edea76f8f2051

docs/core-data-structures/llm-streaming.zh.md

@@ -67,7 +67,7 @@ interface LlmFailure {
 - **每个提供方 HTTP 请求都携带应用归属头。** 适配器发送 `attributionHeaders()`（见下文）作为 `User-Agent` 基线，并通过协议级测试加以证明（mock 服务器断言收到的 header，或对基于库的适配器使用库的 header 钩子）。
 - **回放状态归适配器所有。** 成功的 `finish` 可以携带重建提供方原生响应所需的无损 JSON 状态。循环会将其与组装后的 assistant 消息一起存储。后续请求中，仅当历史提供方与目标提供方当前注册到完全相同的适配器实例时，`LlmService` 才会传递该状态。该适配器负责校验状态并拥有所有跨模型或跨提供方转换；其他适配器只会收到提供方无关的内容与 provenance，不会收到私有状态。
 
-该契约由两个有意保持独立的实现锁定：`dsh-llm-deepseek`（手写 fetch/SSE（Server-Sent Events））和 `dsh-llm-pi-ai`（通过 `@earendil-works/pi-ai` 实现的通用多提供方适配器）。基于库的适配器覆盖 finish 分片错误路径，而传输边界测试证明每个空闲 watchdog 都会停止其实际请求。
+该契约由两个有意保持独立的实现锁定：`dsh-llm-deepseek`（直接 fetch，SSE（Server-Sent Events）分帧经由 `eventsource-parser`）和 `dsh-llm-pi-ai`（通过 `@earendil-works/pi-ai` 实现的通用多提供方适配器）。基于库的适配器覆盖 finish 分片错误路径，而传输边界测试证明每个空闲 watchdog 都会停止其实际请求。
 
 ## `AppIdentity`：应用归属
 
@@ -157,14 +157,30 @@ declare class BlockAssembler {
 
 ## seam
 
-`LlmAdapter` 是提供方 seam：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerInfo()` 与异步 `listModels()` 方法为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单独的 `resolveModelContext()` 查询会暴露确切路由上对正确性敏感的容量信息，但不会让目录成员关系具有权威性；缺失表示元数据未知，而不是路由无效。适配器查找发生在 `llm/stream` waterfall（瀑布式事件）的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface（`ctx.llm.stream()`）与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。
+`LlmAdapter` 是提供方 seam：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerInfo()` 与异步 `listModels()` 方法为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单次异步 `resolveModel()` 查询返回确切模型身份，以及可选的对正确性敏感的上下文容量、由模型持有的有序推理强度 ID 和部署默认值；字段缺失表示元数据或能力不可用，而不表示目录成员关系无效。解析器会接收可选的取消信号，并且必须在信号中止后迅速完成结算。`LlmService.resolveModelInfo()` 会校验聚合结果并返回分离值。服务通过最终适配器边界的 `resolveCallConfig()` 校验推理强度并填入默认值，因此直接调用也无法绕过对不支持推理强度的拒绝；直接分派会在等待解析前捕获一项适配器注册。agent loop 则使用 `prepareCall()`，使模型解析、请求头持久记录和分派全程使用同一项注册。适配器查找发生在 `llm/stream` waterfall（瀑布式事件）的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface（`ctx.llm.stream()`）与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。
+
+```ts type-equiv
+/** One model call whose config and adapter registration were resolved together. */
+interface PreparedLlmCall {
+  /** Detached, deep-frozen config with any adapter-owned default materialized. */
+  readonly config: LlmCallConfig
+  /**
+   * Dispatch this call once through the registration captured during
+   * preparation. The request's call-config fields must match {@link config};
+   * reuse or mismatch fails with `INVALID_PREPARED_CALL`.
+   * @param options - fully assembled request carrying the prepared config.
+   * @returns the chunk stream, including the `llm/stream` waterfall.
+   */
+  stream(options: GenerateOptions): AsyncIterable<StreamChunk>
+}
+```
 
 ```ts public-api
 /**
  * Provider-wire adapter for the harness message and stream vocabulary. Register implementations
  * with `ctx.llm.registerAdapter(providers, adapter)`. Every provider HTTP request must include
- * `attributionHeaders()`; prove that at the wire or library header-hook boundary. The hand-rolled
- * DeepSeek and pi-ai adapters intentionally exercise this contract through different internals.
+ * `attributionHeaders()`; prove that at the wire or library header-hook boundary. The direct-fetch
+ * DeepSeek and library-backed pi-ai adapters intentionally exercise this contract through different internals.
  */
 declare abstract class LlmAdapter {
   /**
@@ -182,16 +198,19 @@ declare abstract class LlmAdapter {
    */
   listModels(_provider: string): Promise<readonly LlmModelInfo[]>;
   /**
-   * Resolve context capacity for one model accepted by this adapter. Absence
-   * means the adapter does not know the capacity, not that routing is invalid.
-   * @param _provider - one provider route owned by this adapter.
-   * @param _model - exact model id passed to {@link GenerateOptions.model}.
-   * @returns provider-owned context metadata, or `undefined` when unavailable.
+   * Resolve all metadata available for one exact model. This query is
+   * independent of the advisory catalog and does not validate request routing.
+   * @param provider - one provider route owned by this adapter.
+   * @param model - exact model id passed to {@link GenerateOptions.model}.
+   * @param _signal - cancellation for this exact-model lookup; asynchronous
+   *   implementations must settle promptly after it aborts.
+   * @returns provider/model identity plus any context and reasoning metadata.
    */
-  resolveModelContext(
-    _provider: string,
-    _model: string,
-  ): Promise<LlmModelContext | undefined>;
+  resolveModel(
+    provider: string,
+    model: string,
+    _signal?: AbortSignal,
+  ): Promise<LlmResolvedModelInfo>;
   /**
    * Stream one model call as raw chunks. The only required method.
    * @param options - the fully-assembled request; implementations must honor `options.signal`.

docs/core-data-structures/session.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-session.md: 506059dd63625aa987d75b00d0d383fea4441fa9
-session.zh.md: d120c13b1e766617b318dddfbb45d7ad2695a6bb
+#   pnpm run verify-translation-pairing --write docs/core-data-structures/session.md
+session.md: 59bcf027c3ec728c5583478c7d17bd6eef2dc2fa
+session.zh.md: 01b6f080b5fcf7b83ca46b99a8d80113a6ebe8bf

docs/core-data-structures/session.md

@@ -155,7 +155,7 @@ The request envelope — the `EpochHeader` (call config + rendered system prompt
  * empty optional fields are absent.
  */
 interface EpochHeader {
-  /** The conversation's call configuration (provider, model, and sampling scalars). */
+  /** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */
   config: LlmCallConfig
   /** Rendered system prompt text; absent for a system-less request. */
   system?: string

docs/core-data-structures/session.zh.md

@@ -157,7 +157,7 @@ interface TodoItem {
  * empty optional fields are absent.
  */
 interface EpochHeader {
-  /** The conversation's call configuration (provider, model, and sampling scalars). */
+  /** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */
   config: LlmCallConfig
   /** Rendered system prompt text; absent for a system-less request. */
   system?: string

docs/event-producer-consumer.md

@@ -30,7 +30,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `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:169`](../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:52`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`llm-replay`](../packages/support/llm-replay), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-title`](../packages/session-title/session-title) |
+| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:53`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`llm-replay`](../packages/support/llm-replay), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-title`](../packages/session-title/session-title) |
 | `session/created` | `emit` | [`packages/core/session/src/index.ts:70`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | `apiproxy`, [`compact`](../packages/compact/compact), [`goal`](../packages/goal/goal), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`llm-retry`](../packages/llm/llm-retry), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`user-approval`](../packages/ui/user-approval) |
 | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:80`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), `apiproxy`, [`session-persistence`](../packages/session-persistence/session-persistence), [`session-title`](../packages/session-title/session-title) |
 | `session/event` | `emit` | [`packages/core/session/src/index.ts:92`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/acp/acp), `apiproxy`, [`cli-demo`](../packages/examples/cli-demo), [`compact`](../packages/compact/compact), [`compact-basic`](../packages/compact/compact-basic), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`llm-retry`](../packages/llm/llm-retry), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-title`](../packages/session-title/session-title), [`token-meter`](../packages/llm/token-meter), [`tui`](../packages/ui/tui), [`user-approval`](../packages/ui/user-approval), [`workspace-context`](../packages/context/workspace-context) |

docs/tool-catalog.md

@@ -1137,7 +1137,7 @@ Record and update a structured task list for the current work. Send the ENTIRE l
       "description": "The COMPLETE task list, replacing any previous list.",
       "items": {
         "type": "object",
-        "additionalProperties": true,
+        "additionalProperties": false,
         "properties": {
           "content": {
             "type": "string",

docs/user/develop/practice/llm-adapter.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-llm-adapter.md: 3e83289b8072ef231f83c0fa3cfe3260547b42fa
-llm-adapter.zh.md: 92fcf9b22f4bb356ada4c46f9a03ef0cc2d159da
+llm-adapter.md: 3bf005647d3e7908f1d1553374266c1d6c12c2e6
+llm-adapter.zh.md: b967d112ed6879b11486ab7aedf64653089d93de

docs/user/develop/practice/llm-adapter.md

@@ -110,7 +110,9 @@ async function* exampleChunks(): AsyncIterable<StreamChunk> {
 
 ## GenerateOptions
 
-`stream()` receives the exported `GenerateOptions` type. It includes the model, conversation history, system prompt, tool schemas, generation parameters, stop sequences, and abort signal; treat the TypeScript type exported by `@deepseek-ai/dsh-llm` as authoritative. Map supported fields to the provider API. If the provider cannot honor a field, throw `LlmError` with a stable code instead of silently dropping it.
+`stream()` receives the exported `GenerateOptions` type. It includes the model, adapter-owned reasoning-effort id, conversation history, system prompt, tool schemas, generation parameters, stop sequences, and abort signal; treat the TypeScript type exported by `@deepseek-ai/dsh-llm` as authoritative. Map supported fields to the provider API. If the provider cannot honor a field, throw `LlmError` with a stable code instead of silently dropping it.
+
+Override `resolveModel(provider, model, signal?)` to return exact provider/model identity plus optional `context` and `reasoning` metadata in one lookup. Reasoning metadata contains ordered opaque ids and display names plus an optional configured default; preserve the adapter's authoritative selectable list, including `off` when its upstream capability API returns it, instead of promoting those values into a core enum. Honor the optional signal for asynchronous lookup so cancellation and disposal reach quiescence. The service validates the aggregate and rejects unsupported explicit efforts before `stream()`; omitting `reasoning` means that model has no selectable reasoning-effort capability.
 
 ## Register an adapter
 

docs/user/develop/practice/llm-adapter.zh.md

@@ -110,7 +110,9 @@ async function* exampleChunks(): AsyncIterable<StreamChunk> {
 
 ## GenerateOptions
 
-`stream()` 接收仓库导出的 `GenerateOptions`。它包含模型名、对话历史、系统提示词、tool schema、生成参数、停止序列和中止信号；完整字段以 `@deepseek-ai/dsh-llm` 导出的 TypeScript 类型为准。适配器必须将支持的字段映射到具体 API；无法支持的字段应抛出带稳定 code 的 `LlmError`，不能静默丢弃。
+`stream()` 接收仓库导出的 `GenerateOptions`。它包含模型名、由适配器持有的推理强度 ID、对话历史、系统提示词、tool schema、生成参数、停止序列和中止信号；完整字段以 `@deepseek-ai/dsh-llm` 导出的 TypeScript 类型为准。适配器必须将支持的字段映射到具体 API；无法支持的字段应抛出带稳定 code 的 `LlmError`，不能静默丢弃。
+
+请覆写 `resolveModel(provider, model, signal?)`，在一次查询中返回确切的提供方/模型身份以及可选的 `context` 和 `reasoning` 元数据。推理元数据包含有序的不透明 ID、展示名称，以及可选的配置默认值；请保留适配器给出的权威可选列表，包括其上游能力 API 返回的 `off`，而不要将这些值提升为核心枚举。异步查询必须响应这个可选信号，让取消和资源释放都能达到完全停稳。服务会校验聚合结果，并在调用 `stream()` 前拒绝显式指定但不受支持的推理强度；省略 `reasoning` 表示该模型没有可选的推理强度能力。
 
 ## 注册适配器
 

examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md

@@ -162,7 +162,7 @@ interface ToolArgsMap {
       content: string;
       /** pending (not started) | in_progress (now) | completed (done). */
       status: "pending" | "in_progress" | "completed";
-    } & Record<string, JsonValue>)[];
+    })[];
   } & Record<string, JsonValue>;
   /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */
   update_goal: {

examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json

@@ -366,7 +366,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md

@@ -145,7 +145,7 @@ interface ToolArgsMap {
       content: string;
       /** pending (not started) | in_progress (now) | completed (done). */
       status: "pending" | "in_progress" | "completed";
-    } & Record<string, JsonValue>)[];
+    })[];
   } & Record<string, JsonValue>;
   /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */
   update_goal: {

examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json

@@ -309,7 +309,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md

@@ -145,7 +145,7 @@ interface ToolArgsMap {
       content: string;
       /** pending (not started) | in_progress (now) | completed (done). */
       status: "pending" | "in_progress" | "completed";
-    } & Record<string, JsonValue>)[];
+    })[];
   } & Record<string, JsonValue>;
   /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */
   update_goal: {

examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md

@@ -145,7 +145,7 @@ interface ToolArgsMap {
       content: string;
       /** pending (not started) | in_progress (now) | completed (done). */
       status: "pending" | "in_progress" | "completed";
-    } & Record<string, JsonValue>)[];
+    })[];
   } & Record<string, JsonValue>;
   /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */
   update_goal: {

examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json

@@ -288,7 +288,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json

@@ -325,7 +325,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json

@@ -417,7 +417,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json

@@ -492,7 +492,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json

@@ -288,7 +288,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json

@@ -288,7 +288,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json

@@ -288,7 +288,7 @@
             "description": "The COMPLETE task list, replacing any previous list.",
             "items": {
               "type": "object",
-              "additionalProperties": true,
+              "additionalProperties": false,
               "properties": {
                 "content": {
                   "type": "string",

examples/headless-agent/tests/fixtures/cli-mock-llm.ts

@@ -1,8 +1,33 @@
 import type { Context } from 'cordis'
-import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm'
+import {
+  CallId,
+  LlmAdapter,
+  ReasoningEffortId,
+  type GenerateOptions,
+  type LlmResolvedModelInfo,
+  type StreamChunk,
+} from '@deepseek-ai/dsh-llm'
+
+const HIGH = ReasoningEffortId('high')
+const OFF = ReasoningEffortId('off')
 
 /** Keyless headless-agent adapter: one real bash call followed by a final answer. */
 class CliMockAdapter extends LlmAdapter {
+  override async resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
+    return {
+      provider,
+      id: model,
+      name: model,
+      reasoning: {
+        efforts: [
+          { id: OFF, name: 'Off' },
+          { id: HIGH, name: 'High' },
+        ],
+        defaultEffort: HIGH,
+      },
+    }
+  }
+
   async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
     const toolResult = options.messages.at(-1)?.content.find(block => block.type === 'tool-result')
     if (toolResult === undefined) {
@@ -34,4 +59,8 @@ export const inject = ['llm']
 /** Register the keyless `cli-mock` adapter. */
 export function apply(ctx: Context): void {
   ctx.llm.registerAdapter(['cli-mock'], new CliMockAdapter())
+  ctx.on('agent/request', async (_agent, _turn, step, _signal, next) => {
+    const config = await next()
+    return step === 2 ? { ...config, reasoningEffort: OFF } : config
+  })
 }

examples/headless-agent/tests/headless.snapshot.ts

@@ -28,6 +28,7 @@ const ralphScenarioDir = join(snapshotsDir, 'ralph-loop')
 const ralphConfigPath = fileURLToPath(new URL('../ralph.cordis.snapshot.yml', import.meta.url))
 const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
 const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
+const reasoningConfigPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', import.meta.url))
 const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
 
 interface JsonObject {
@@ -124,6 +125,46 @@ async function persistedLogs(cwd: string): Promise<PersistedLog[]> {
 }
 
 describe('headless stream-json snapshots', () => {
+  it('logs the model default and a dynamic next-step reasoning effort', async () => {
+    const result = await runLoaderSmoke({
+      label: 'reasoning effort headless stream-json snapshot',
+      tempDirPrefix: 'headless-snapshot-reasoning-effort-',
+      binScript,
+      configPath: reasoningConfigPath,
+      binArgs: ['--config', reasoningConfigPath, '--output-format', 'stream-json', 'prove dynamic reasoning effort'],
+      tsconfigPath,
+    })
+
+    expect(result.stderr).toBe('')
+    const headers = parseJsonl(result.stdout)
+      .map(record => record.event)
+      .filter((event): event is JsonObject => (
+        event !== null
+        && typeof event === 'object'
+        && !Array.isArray(event)
+        && 'type' in event
+        && event.type === 'request/header'
+      ))
+      .map((event) => {
+        const data = event.data as JsonObject
+        return (data.header as JsonObject).config
+      })
+    expect(headers).toMatchInlineSnapshot(`
+      [
+        {
+          "model": "cli-mock",
+          "provider": "cli-mock",
+          "reasoningEffort": "high",
+        },
+        {
+          "model": "cli-mock",
+          "provider": "cli-mock",
+          "reasoningEffort": "off",
+        },
+      ]
+    `)
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+
   it('replays the advanced toolchain through the one-shot app', async () => {
     const prompt = await scenarioPrompt(advancedScenarioDir, 'advanced-toolchain')
     const fixtureFiles = [

examples/tui-agent/README.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-README.md: fdf3972f98f8ff9690b71469ae415dc18d339f10
-README.zh.md: 71f7ae949d034757a20adfae2cbe566011edc584
+#   pnpm run verify-translation-pairing --write examples/tui-agent/README.md
+README.md: ea8695d37ea247a38644392a4572c1ea9855fd44
+README.zh.md: b3f6dc18536b159379eac7433367ccf2cd8fcc53

examples/tui-agent/README.md

@@ -19,7 +19,7 @@ Type a coding task. The agent works through the `read`/`write`/`edit` filesystem
 
 The `todo_write` task tracker is opt-in and not in the shipped config: add `@deepseek-ai/dsh-tool-todo` to `cordis.yml` (or a personal-config overlay under `~/.dsh`) to expose it. Once loaded, the model records a whole-list plan to the session log and the TUI renders it.
 
-The TUI renders Markdown history, reasoning, tool-owned terminal/diff/generic cards, token totals, and — when `todo_write` is loaded — the latest plan. Long tool bodies keep a head/tail preview; Ctrl+O expands or collapses every card. Enter submits or steers while the agent runs, Ctrl+R toggles reasoning, Escape cancels, and `/help` lists commands. `/plan` selects plan mode for the next step; `/plan <message>` also submits the message into that step, while `/plan off` selects the default mode without model input. `/status` expands the current session's identity, activity counts, exact token/cache buckets, context use, and timestamps without interrupting a running turn. `/model` opens a keyboard selector for the current provider catalog; use Up/Down and Enter, or `/model <model>` and `/model <provider>/<model>` for direct selection. `ask_user_question` opens a wide bottom-left keyboard panel with batch progress and numbered options.
+The TUI renders Markdown history, reasoning, tool-owned terminal/diff/generic cards, token totals, and — when `todo_write` is loaded — the latest plan. Long tool bodies keep a head/tail preview; Ctrl+O expands or collapses every card. Enter submits or steers while the agent runs, Ctrl+R toggles reasoning, Escape cancels, and `/help` lists commands. `/plan` selects plan mode for the next step; `/plan <message>` also submits the message into that step, while `/plan off` selects the default mode without model input. `/status` expands the current session's identity, activity counts, exact token/cache buckets, context use, and timestamps without interrupting a running turn. `/model` opens a keyboard selector for the current provider catalog; use Up/Down to focus a model, Shift+Tab to cycle its advertised reasoning efforts, and Enter to select, or use `/model <model>` and `/model <provider>/<model>` for direct selection. `ask_user_question` opens a wide bottom-left keyboard panel with batch progress and numbered options.
 
 ### Resuming a prior session
 
@@ -53,7 +53,7 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads
 | Entry | Demonstrates |
 |---|---|
 | `hmr` (`@cordisjs/plugin-hmr`) | the dev/demo edit-reload loop — a **leaf** entry (not baked into the app) because it depends on the Loader's internal module access |
-| `llm-deepseek` | real `LlmAdapter` via config (`!!js process.env.…` secrets); swap one line to `@deepseek-ai/dsh-llm-pi-ai` for the library-backed twin |
+| `llm-deepseek` | the default native adapter |
 | `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash` schema (`tool-bash`) and generic `task_*` controls (`tool-tasks`) come from `dsh-agent-spine-demo`, so only the executor is a leaf choice |
 | `tui-agent` (`@deepseek-ai/dsh-tui-demo`) | the app bundle: the agent-spine demo + JSONL persistence + the pi-tui channel + a pre-created `main` agent |
 | `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix |

examples/tui-agent/README.zh.md

@@ -19,7 +19,7 @@ pnpm run demo:tui
 
 `todo_write` 任务跟踪器是选用的，不在已交付配置中：请将 `@deepseek-ai/dsh-tool-todo` 添加到 `cordis.yml`（或在 `~/.dsh` 下使用个人配置覆盖）以公开该工具。加载后，模型会把整表计划记录到会话日志，TUI 则渲染它。
 
-TUI 渲染 Markdown 历史、推理、工具所有的终端／diff／通用卡片、token 总量，以及加载 `todo_write` 时的最新计划。较长的工具正文保留首尾预览；Ctrl+O 展开或折叠所有卡片。Enter 用于提交，或在 agent 运行时进行 steering（中途引导）；Ctrl+R 切换推理，Escape 取消，`/help` 列出命令。`/plan` 为下一步骤选择 plan mode；`/plan <message>` 还会将消息提交到该步骤，`/plan off` 则在没有模型输入的情况下选择默认 mode。`/status` 会展开当前会话的标识、活动计数、精确 token／缓存 bucket、上下文用量和时间戳，而不中断正在运行的轮次。`/model` 打开当前提供方目录的键盘选择器；使用 Up/Down 和 Enter，或使用 `/model <model>` 和 `/model <provider>/<model>` 直接选择。`ask_user_question` 会打开一个位于左下方的宽键盘面板，包含批次进度和编号选项。
+TUI 渲染 Markdown 历史、推理、工具所有的终端／diff／通用卡片、token 总量，以及加载 `todo_write` 时的最新计划。较长的工具正文保留首尾预览；Ctrl+O 展开或折叠所有卡片。Enter 用于提交，或在 agent 运行时进行 steering（中途引导）；Ctrl+R 切换推理，Escape 取消，`/help` 列出命令。`/plan` 为下一步骤选择 plan mode；`/plan <message>` 还会将消息提交到该步骤，`/plan off` 则在没有模型输入的情况下选择默认 mode。`/status` 会展开当前会话的标识、活动计数、精确 token／缓存 bucket、上下文用量和时间戳，而不中断正在运行的轮次。`/model` 打开当前提供方目录的键盘选择器；使用 Up/Down 聚焦模型，使用 Shift+Tab 循环切换为该模型公布的推理强度，再用 Enter 选择；也可以使用 `/model <model>` 和 `/model <provider>/<model>` 直接选择。`ask_user_question` 会打开一个位于左下方的宽键盘面板，包含批次进度和编号选项。
 
 ### 恢复早先的会话
 
@@ -53,7 +53,7 @@ pnpm run demo:code-mode acp    # the acp-agent example's same-shaped overlay
 | 配置项 | 演示内容 |
 |---|---|
 | `hmr` (`@cordisjs/plugin-hmr`) | 开发／演示的编辑-重载循环：它是 **叶节点** 配置项（不内置到应用），因为它依赖 Loader 的内部模块访问 |
-| `llm-deepseek` | 通过配置提供真实 `LlmAdapter`（`!!js process.env.…` 密钥）；将一行替换为 `@deepseek-ai/dsh-llm-pi-ai` 即可使用库后端对照实现 |
+| `llm-deepseek` | 默认原生适配器 |
 | `bash` (`dsh-bash-local`) | 执行器实现：bash seam 的可替换一半。面向模型的 `bash` schema（`tool-bash`）和通用 `task_*` 控制（`tool-tasks`）由 `dsh-agent-spine-demo` 提供，因此叶节点只选择执行器 |
 | `tui-agent` (`@deepseek-ai/dsh-tui-demo`) | 应用组合包：agent-spine 演示 + JSONL 持久化 + pi-tui 通道 + 预创建的 `main` agent |
 | `subagent`, `subagent-spawn`, `subagent-fork` | subagent 提供方注册表加两个进程内后端：新子 agent，以及用父 agent 已完成轮次前缀播种的子 agent |

examples/tui-agent/tests/fixtures/tui-scripted-llm.ts

@@ -1,6 +1,11 @@
 import type { Context } from 'cordis'
-import type { GenerateOptions, LlmModelContext, LlmModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm'
-import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
+import type {
+  GenerateOptions,
+  LlmModelInfo,
+  LlmResolvedModelInfo,
+  StreamChunk,
+} from '@deepseek-ai/dsh-llm'
+import { CallId, LlmAdapter, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
 
 const CONTROL_PROBE = '\u001b]2;MODEL_CONTROLLED\u0007\u001b[999CMODEL_CURSOR\u009b31mMODEL_C1'
 const INITIAL_TEXT = `I need one decision before I continue. ${CONTROL_PROBE}`
@@ -35,8 +40,28 @@ class ScriptedTuiAdapter extends LlmAdapter {
     ])
   }
 
-  override resolveModelContext(_provider: string, _model: string): Promise<LlmModelContext> {
-    return Promise.resolve({ contextWindow: 128_000 })
+  override resolveModel(
+    provider: string,
+    model: string,
+  ): Promise<LlmResolvedModelInfo> {
+    return Promise.resolve({
+      provider,
+      id: model,
+      name: model === 'tui-scripted-model-pro' ? 'Scripted Pro' : 'Scripted Base',
+      context: { contextWindow: 128_000 },
+      ...model !== 'tui-scripted-model-pro'
+        ? {}
+        : {
+          reasoning: {
+            efforts: [
+              { id: ReasoningEffortId('off'), name: 'Off' },
+              { id: ReasoningEffortId('high'), name: 'High' },
+              { id: ReasoningEffortId('max'), name: 'Max' },
+            ],
+            defaultEffort: ReasoningEffortId('high'),
+          },
+        },
+    })
   }
 
   override async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
@@ -47,8 +72,12 @@ class ScriptedTuiAdapter extends LlmAdapter {
       for (const chunk of textChunks(TITLE_TEXT)) yield chunk
       return
     }
-    if (options.model !== 'tui-scripted-model-pro' || !options.system?.includes('tui-scripted-model-pro')) {
-      throw new Error('the scripted TUI request did not apply the selected model to routing and prompt variables')
+    if (
+      options.model !== 'tui-scripted-model-pro'
+      || !options.system?.includes('tui-scripted-model-pro')
+      || options.reasoningEffort !== ReasoningEffortId('max')
+    ) {
+      throw new Error('the scripted TUI request did not apply the selected model and reasoning effort')
     }
     const lastMessage = options.messages.at(-1)
     // The loop appends plugin-sourced context (the plan-mode notice, the

examples/tui-agent/tests/tui-keyless-smoke.e2e.ts

@@ -103,7 +103,7 @@ function smoke(overrides: Partial<TuiPtySmokeOptions> & { label: string }): Prom
 // other route (see fixtures/tui-scripted-llm.ts).
 const SELECT_PRO_MODEL = [
   { waitFor: 'scripted TUI ready.', send: '/model\r' },
-  { waitFor: 'Select model', send: '\x1b[B\r' },
+  { waitFor: 'Select model', send: '\x1b[B\x1b[Z\r' },
 ] as const
 
 describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
@@ -156,6 +156,7 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
       ],
     })
     expect(output).toContain('I need one decision before I continue.')
+    expect(output).toContain('Reasoning effort: Max.')
     expect(output).toContain('Entering plan mode (applies from the next step). Use /plan off to leave.')
     expect(output).toContain('Leaving plan mode (applies from the next step).')
     expect(output).toContain('Default mode confirmed.')

packages/client/connection/src/client/fixture.ts

@@ -6,7 +6,7 @@
 // approval/question requests exercise replay and composer takeover with stable rpcIds.
 
 import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
-import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types'
+import type { SessionEvent, SessionId, TodoItem } from '@deepseek-ai/dsh-session/types'
 import type {
   ApiProxy, ClientRequest, ClientResponse, HistoryEntry, HostFrame, MuxFrame, RpcReceipt,
   RpcRequest, RpcResponse, RpcResult, ServerRequest, ServerResponse, SessionSummary,
@@ -167,6 +167,22 @@ function buildAlphaLog(): SessionEvent[] {
     push({ type: 'step/end', data: { turn, step: 0 } })
     push({ type: 'turn/end', data: { turn, reason: { kind: 'completed' } } })
   }
+  // Turn 65: todo_write sample — the TodoRow toolview in the flow plus the
+  // todo/write snapshot event feeding the TodoPanel plan strip.
+  const fixtureTodos = [
+    { content: '梳理需求', status: 'completed' },
+    { content: '实现 fixture 样本', status: 'in_progress' },
+    { content: '浏览器验收', status: 'pending' },
+  ]
+  const todoArgs = JSON.stringify({ todos: fixtureTodos })
+  toolTurn(65, 'todo_write', todoArgs, 'Updated todo list: 1 pending, 1 in progress, 1 completed.')
+  // The real tool appends the snapshot mid-execution — between tool/call and
+  // tool/result — so the fixture reproduces that exact ordering (the last
+  // toolTurn events run ... tool/call, tool/result, step/end, turn/end).
+  const callIndex = events.length - 4
+  const callTime = events[callIndex]?.time as number
+  events.splice(callIndex + 1, 0, { type: 'todo/write', time: callTime + 400, data: { todos: fixtureTodos } })
+  events.forEach((e, i) => { e.seq = i })
   return events as unknown as SessionEvent[]
 }
 
@@ -281,6 +297,15 @@ function pageOf(
   return { events, hasMore: start > 0 }
 }
 
+/** Current todo projection over the full log (host parallel: latest todo/write, last write wins). */
+function backscanTodos(log: readonly SessionEvent[]): TodoItem[] | undefined {
+  for (let i = log.length - 1; i >= 0; i--) {
+    const event = log[i]
+    if (event !== undefined && event.type === 'todo/write') return event.data.todos
+  }
+  return undefined
+}
+
 interface StreamConn<F> {
   push(envelope: RpcRequest<F>): void
 }
@@ -619,12 +644,14 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
         const log = logs.get(request.payload.sessionId) ?? []
         // Snapshot at request time, deliver after the transit delay (mirrors a real host under latency).
         const page = pageOf(log, request.payload.beforeSeq, request.payload.maxMessages ?? 50)
+        // Tail page carries the session-level todo projection (host parallel: full-log backscan).
+        const todos = request.payload.beforeSeq === undefined ? backscanTodos(log) : undefined
         const doomed = failNextHistory
         failNextHistory = false
         const delay = historyDelayMs
         if (delay > 0) await new Promise(resolve => setTimeout(resolve, delay))
         if (doomed) throw new Error('fixture: simulated history transport failure')
-        return ok(request, page)
+        return ok(request, { ...page, ...todos === undefined ? {} : { todos } })
       },
       prompt: (request) => {
         const { sessionId: id, mode, content } = request.payload

packages/client/connection/tests/fixture.spec.ts

@@ -71,6 +71,21 @@ describe('createFixtureApi', () => {
     expect(empty.result.value).toEqual({ events: [], hasMore: false })
   })
 
+  it('emits the todo/write snapshot at the real tool boundary: between tool/call and tool/result, timestamps monotonic', async () => {
+    const api = createFixtureApi()
+    const tail = await api.sessions.history(req({ sessionId: sid('fx-alpha'), maxMessages: 10 }))
+    if (!tail.result.ok) throw new Error('history failed')
+    const events = tail.result.value.events.map(e => e.event)
+    const todoAt = events.findIndex(e => e.type === 'todo/write')
+    expect(todoAt).toBeGreaterThan(0)
+    // Production ordering (the tool appends mid-execution): call → snapshot → result.
+    expect(events[todoAt - 1]?.type).toBe('tool/call')
+    expect(events[todoAt + 1]?.type).toBe('tool/result')
+    const times = events.slice(todoAt - 1, todoAt + 2).map(e => e.time)
+    expect(times[0]).toBeLessThanOrEqual(times[1] ?? 0)
+    expect(times[1]).toBeLessThanOrEqual(times[2] ?? 0)
+  })
+
   it('create adds a session and pushes host/session-added to open host streams', async () => {
     const api = createFixtureApi()
     const abort = new AbortController()

packages/client/runtime/README.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-README.md: 4724ebc75d441252245a0e811a4ae34f8b529a98
-README.zh.md: 6a0076742efccaf946910c77c77a9b74194b9dc5
+#   pnpm run verify-translation-pairing --write packages/client/runtime/README.md
+README.md: d7b7bbc4e4e05893689a8f2dcac82763b4c67ef8
+README.zh.md: d2054170cd6f31505793812fff46cc0f2356ad75

packages/client/runtime/README.md

@@ -2,7 +2,7 @@
 
 English | [中文](README.zh.md)
 
-Client cordis boot and React-free object services: SlotsService wraps SlotCore and supplies renderer data sources; SessionsService owns Session objects, list/scope/history state; WorkspacesService depends on SessionsService and owns Workspace objects, list/actions, default-target derivation, and the New Session blank-reuse entry (`connectWorkspace`). The runtime fans the shared Host stream into both managers. Client sessions are always Host-born (Session+Agent+cwd in one `session.create`); the client holds no pre-entity session state — a session's Agent scope (the client mirror of host dsh-scope, keyed by the shared agent/session id) is born when its row enters the list mirror and dies with the prune. Contract: api-contracts v3 §4.
+Client cordis boot and React-free object services: SlotsService wraps SlotCore and supplies renderer data sources; SessionsService owns Session objects, list/scope/history state; WorkspacesService depends on SessionsService and owns Workspace objects, list/actions, default-target derivation, and the New Session blank-reuse entry (`connectWorkspace`). The runtime fans the shared Host stream into both managers. Client sessions are always Host-born (Session+Agent+cwd in one `session.create`); the client holds no pre-entity session state — a session's Agent scope (the client mirror of host dsh-scope, keyed by the shared agent/session id) is born when its row enters the list mirror and dies with the prune. Contract: api-contracts v3 §4. `ConversationSnapshot` carries `todos` — the session's current todo projection: taken from the tail history page's full-log value (host-computed, independent of the page window), preserved across an older-page prepend, and overwritten by each live `todo/write` (last write wins). A tail response that omits the field means the log holds no `todo/write`, so the list resets to empty — a plan the log never kept (a write lost to a host crash) disappears on the next open or resync.
 
 ## Workspace and Session lists
 

packages/client/runtime/README.zh.md

@@ -2,7 +2,7 @@
 
 [English](README.md) | 中文
 
-客户端 cordis 启动与不依赖 React 的对象服务：SlotsService 包装 SlotCore 并提供 renderer 数据源；SessionsService 拥有 Session 对象、列表／scope／history 状态；WorkspacesService 依赖 SessionsService，拥有 Workspace 对象、列表／操作、默认目标派生，以及 New Session 空会话复用入口（`connectWorkspace`）。运行时把共享 Host 流分发给两个 manager。客户端 Session 一律由 Host 出生（一次 `session.create` 同瞬产出 Session+Agent+cwd）；客户端不持有任何实体化之前的会话状态——Agent scope（host dsh-scope 的客户端镜像，以 agent/session 共用 id 为键）在会话行进入列表镜像时出生，随 prune 死亡。契约：api-contracts v3 §4。
+客户端 cordis 启动与不依赖 React 的对象服务：SlotsService 包装 SlotCore 并提供 renderer 数据源；SessionsService 拥有 Session 对象、列表／scope／history 状态；WorkspacesService 依赖 SessionsService，拥有 Workspace 对象、列表／操作、默认目标派生，以及 New Session 空会话复用入口（`connectWorkspace`）。运行时把共享 Host 流分发给两个 manager。客户端 Session 一律由 Host 出生（一次 `session.create` 同瞬产出 Session+Agent+cwd）；客户端不持有任何实体化之前的会话状态——Agent scope（host dsh-scope 的客户端镜像，以 agent/session 共用 id 为键）在会话行进入列表镜像时出生，随 prune 死亡。契约：api-contracts v3 §4。`ConversationSnapshot` 携带 `todos`——会话当前的 todo 投影：取自尾页 history 携带的全量 log 值（host 计算，独立于分页窗口），跨往前翻页保留，并被每次实时 `todo/write` 覆盖（后写胜出）。尾页响应省略该字段即表示 log 中没有任何 `todo/write`，因此列表复位为空——log 从未留下的计划（写入因 host 崩溃丢失）会在下一次打开或 resync 时消失。
 
 ## Workspace 与 Session 列表
 

packages/client/runtime/src/client/index.ts

@@ -30,7 +30,7 @@ export type {
 export type {
   AssistantBlock, AssistantMessageNode, CodeSubCall, ComposerPhase, ContextMessageNode, ConversationNode,
   ConversationSnapshot, QueuedMessage, RunningToolCall,
-  SteeringMessageNode, ToolResultNode, UnknownSurfaceNode, UserMessageNode,
+  SteeringMessageNode, TodoItem, ToolResultNode, UnknownSurfaceNode, UserMessageNode,
 } from './sessions/conversation.ts'
 export { PendingWait } from './sessions/pending.ts'
 export type { PendingInteraction, PendingKind, PendingPayloads } from './sessions/pending.ts'

packages/client/runtime/src/client/sessions/conversation.ts

@@ -4,11 +4,14 @@
 // string here (narrow to real brands when convenient).
 
 import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
+import type { TodoItem } from '@deepseek-ai/dsh-session/types'
 import type {
   RpcError, SessionId, ToolCallView, ToolResultView,
 } from '@deepseek-ai/dsh-client-connection/client'
 import type { PendingInteraction } from './pending.ts'
 
+export type { TodoItem }
+
 /** Assistant content blocks sorted by what the UI cares about
  *  (text body / collapsible reasoning / tool-call card head / other fallback). */
 export type AssistantBlock =
@@ -240,4 +243,7 @@ export interface ConversationSnapshot {
    */
   blank: boolean
   lastAgentError: string | null
+  /** Current whole-list `todo/write` projection — the tail page's full-log value, then each live
+   *  write (last write wins); empty = the log holds no plan. */
+  todos: readonly TodoItem[]
 }

packages/client/runtime/src/client/sessions/session.ts

@@ -2,7 +2,7 @@
 
 import type { Context } from 'cordis'
 import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
-import type { SessionEvent } from '@deepseek-ai/dsh-session/types'
+import type { SessionEvent, TodoItem } from '@deepseek-ai/dsh-session/types'
 import type {
   HistoryEntry, IApiClient, MuxFrame, RpcError, RpcId, RpcResult,
   SessionId, ToolEventView,
@@ -99,6 +99,9 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
   private queueCache: { rev: number; value: QueuedMessage[] } | null = null
   private frozenRev = 0
   private nodesCache: { folded: readonly ConversationNode[]; frozenRev: number; value: readonly ConversationNode[] } | null = null
+  /** Current whole-list todo/write projection: each tail history response replaces it (an omitted
+   *  field is the authoritative empty list) and every live write overwrites it. */
+  private todos: readonly TodoItem[] = []
   /** `run_code` sub-dispatches by parent callId (window-derived, like openCalls). Appends
    *  copy-on-write the per-parent array so published snapshot references never mutate. */
   private codeDispatches = new Map<string, readonly CodeSubCall[]>()
@@ -490,13 +493,13 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
         this.openError = result.error
         return
       }
-      this.installWindow(result.value.events, result.value.hasMore)
+      this.installWindow(result.value.events, result.value.hasMore, result.value.todos)
       // Gap detection (§D.3-4): baseline past the window tail and liveBuffer did not cover it -> pull the tail page once more.
       const tailSeq = this.windowTailSeq()
       if (this.subscribedLastSeq !== null && tailSeq !== null && this.subscribedLastSeq > tailSeq) {
         result = (await this.api.sessions.history({ sessionId: this.sessionId, maxMessages: PAGE_MESSAGES })).result
         if (generation !== this.openGeneration) return
-        if (result.ok) this.installWindow(result.value.events, result.value.hasMore)
+        if (result.ok) this.installWindow(result.value.events, result.value.hasMore, result.value.todos)
       }
       this.openState = 'open'
     } catch (error) {
@@ -514,11 +517,19 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
    *  Stitching MUST NOT route through acceptLiveEvent: openState is still 'loading' here
    *  (doOpen flips it after install), so recursing would push every buffered event straight
    *  back into liveBuffer where nothing ever drains it — a silent drop loop (audit S1). */
-  private installWindow(entries: HistoryEntry[], hasMore: boolean): void {
+  private installWindow(entries: HistoryEntry[], hasMore: boolean, todos: readonly TodoItem[] | undefined): void {
     this.events = entries.map(e => e.event)
     this.views = entries.map(e => e.view)
     this.baseSeq = this.events[0]?.seq ?? 0
     this.hasMore = hasMore
+    // Session-level projection from the tail page (full-log latest todo/write,
+    // independent of the window); an in-window write below re-derives the same
+    // value, and later live events keep overwriting it. Every caller here is a
+    // tail request (no beforeSeq), which the host answers with the projection
+    // or omits it only when the full log holds no todo/write — so an absent
+    // field is the authoritative empty list, not a missing carrier. Assigning
+    // it clears a plan the log never kept (a write lost to a host crash).
+    this.todos = todos ?? []
     this.foldAdapter.reset(this.events, this.baseSeq, this.views)
     this.rebuildDerivedFromWindow()
     const buffered = this.liveBuffer
@@ -569,7 +580,7 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
       const { result } = await this.api.sessions.history({ sessionId: this.sessionId, maxMessages: PAGE_MESSAGES })
       // Failure or superseded by a full resync: drop — the resync path rebuilds and clears the buffer itself.
       if (result.ok && generation === this.openGeneration && this.openState === 'open') {
-        this.installWindow(result.value.events, result.value.hasMore)
+        this.installWindow(result.value.events, result.value.hasMore, result.value.todos)
       }
     } catch (error) {
       console.error('[web-runtime] gap repair failed:', error)
@@ -689,6 +700,10 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
         if (this.openCalls.delete(String(event.data.callId))) this.callsRev++
         return
       }
+      case 'todo/write': {
+        this.todos = event.data.todos
+        return
+      }
       case 'turn/end': {
         // Aborted turns never finalize. The accumulated partial is VALUE, not residue: freeze it
         // into an interrupted terminal node (pulse stops, text survives) instead of deleting it.
@@ -733,7 +748,10 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
 
   /** Re-derive state (partial/openCalls/frozenNodes) from raw window events after a rebuild — keeps
    *  paging/stitching consistent, and makes the live freeze and the history replay converge on the
-   *  same interrupted nodes (chunks are logged, so the replayed sweep re-freezes identical text). */
+   *  same interrupted nodes (chunks are logged, so the replayed sweep re-freezes identical text).
+   *  todos is deliberately NOT reset: it is session-level (seeded by the tail page's full-log
+   *  projection, not derivable from an arbitrary window). The window always extends to the log
+   *  tail, so an in-window todo/write can only overwrite it with the same latest value. */
   private rebuildDerivedFromWindow(): void {
     this.partial = null
     this.openCalls.clear()
@@ -803,6 +821,7 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
       promptError: this.promptError,
       blank: this.blankBit,
       lastAgentError: this.lastAgentError,
+      todos: this.todos,
     }
   }
 }

packages/client/runtime/tests/event-script.ts

@@ -40,6 +40,8 @@ export const ev = {
     at(seq, { type: 'step/end', data: { turn, step } }),
   turnEnd: (seq: number, turn: number, reason: 'completed' | 'cancelled' = 'completed'): SessionEvent =>
     at(seq, { type: 'turn/end', data: { turn, reason: { kind: reason } } }),
+  todoWrite: (seq: number, todos: { content: string; status: 'pending' | 'in_progress' | 'completed' }[]): SessionEvent =>
+    at(seq, { type: 'todo/write', data: { todos } }),
 }
 
 /** One complete plain turn (turn/start → user → step → assistant → turn/end), 6 events from startSeq. */

packages/client/runtime/tests/fake-api.ts

@@ -62,7 +62,7 @@ export class FakeApiClient implements IApiClient {
   onList: (payload: unknown) => Promise<RpcResponse<{ items: never[] }>> = () => Promise.resolve(ok({ items: [] }))
   onCreate: (payload: unknown) => Promise<RpcResponse<{ sessionId: SessionId }>> = () => Promise.resolve(ok({ sessionId: 'fk-new' as SessionId }))
   onHistory: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number })
-  => Promise<RpcResponse<{ events: never[]; hasMore: boolean }>> =
+  => Promise<RpcResponse<{ events: never[]; hasMore: boolean; todos?: { content: string; status: 'pending' | 'in_progress' | 'completed' }[] }>> =
     () => Promise.resolve(ok({ events: [], hasMore: false }))
 
   onPrompt: (payload: unknown) => Promise<RpcResponse<{ accepted: true }>> = () => Promise.resolve(ok({ accepted: true as const }))

packages/client/runtime/tests/session.spec.ts

@@ -22,9 +22,9 @@ function makeSession(api = new FakeApiClient()): { api: FakeApiClient; session:
   return { api, session: new Session(SID, api) }
 }
 
-function histResponse(events: SessionEvent[], hasMore = false) {
+function histResponse(events: SessionEvent[], hasMore = false, todos?: { content: string; status: 'pending' | 'in_progress' | 'completed' }[]) {
   // history now returns HistoryEntry[] ({event, view?}); these tests are view-less.
-  return Promise.resolve(ok({ events: entries(events) as never[], hasMore }))
+  return Promise.resolve(ok({ events: entries(events) as never[], hasMore, ...todos === undefined ? {} : { todos } }))
 }
 
 describe('open', () => {
@@ -153,6 +153,42 @@ describe('live event path', () => {
     })
   })
 
+  it('folds todo/write into snapshot.todos last-write-wins, live and on window replay', async () => {
+    const listA = [{ content: '搭骨架', status: 'completed' as const }, { content: '写组件', status: 'in_progress' as const }]
+    const listB = [{ content: '搭骨架', status: 'completed' as const }, { content: '写组件', status: 'completed' as const }]
+    const { session } = await opened()
+    expect(session.getSnapshot().todos).toEqual([])
+    const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) }
+    feed(ev.todoWrite(6, listA))
+    expect(session.getSnapshot().todos).toEqual(listA)
+    feed(ev.todoWrite(7, listB))
+    expect(session.getSnapshot().todos).toEqual(listB)
+    // Window replay converges on the same last snapshot (history contains both writes).
+    const replayed = makeSession()
+    replayed.api.onHistory = () => histResponse([...plainTurn(0, 0, 'a', 'b'), ev.todoWrite(6, listA), ev.todoWrite(7, listB)])
+    await replayed.session.open()
+    expect(replayed.session.getSnapshot().todos).toEqual(listB)
+  })
+
+  it('seeds todos from the tail page projection when the last write precedes the window', async () => {
+    const list = [{ content: '窗口外的计划', status: 'in_progress' as const }]
+    // Cold open: the page window carries NO todo/write; the projection rides the response.
+    const { api, session } = makeSession()
+    api.onHistory = () => histResponse(plainTurn(100, 9, '问', '答'), true, list)
+    await session.open()
+    expect(session.getSnapshot().todos).toEqual(list)
+    // Paging an older window in must not clear the session-level projection.
+    api.onHistory = () => histResponse(plainTurn(94, 8, '旧问', '旧答'), false)
+    await session.loadOlder()
+    expect(session.getSnapshot().todos).toEqual(list)
+    // A later live write still overrides the seeded projection.
+    session.handleMuxEnvelope('r' as never, {
+      type: 'session/event', sessionId: SID,
+      event: ev.todoWrite(106, [{ content: '新计划', status: 'pending' as const }]),
+    })
+    expect(session.getSnapshot().todos).toEqual([{ content: '新计划', status: 'pending' }])
+  })
+
   it('repairs a seq gap by repulling the tail page instead of appending a hole', async () => {
     const { api, session } = await opened(plainTurn(0, 0, 'a', 'b')) // tail seq = 5
     const repaired = [...plainTurn(0, 0, 'a', 'b'), ...plainTurn(6, 1, 'c', 'd')]
@@ -166,6 +202,37 @@ describe('live event path', () => {
     const seqs = session.getSnapshot().nodes.map(n => n.seq)
     expect(seqs).toEqual([1, 3, 7, 9]) // both turns' user/assistant, no hole, no duplicate 9
   })
+
+  it('gap repair adopts the repull response projection (a missed todo/write outside the new tail page)', async () => {
+    const { api, session } = await opened(plainTurn(0, 0, 'a', 'b')) // tail seq = 5
+    expect(session.getSnapshot().todos).toEqual([])
+    // The missed range contained a todo/write that the repulled page no longer
+    // covers; the response's session-level projection is the only carrier.
+    const current = [{ content: '断线期间写的', status: 'in_progress' as const }]
+    api.onHistory = () => histResponse([...plainTurn(0, 0, 'a', 'b'), ...plainTurn(8, 1, 'c', 'd')], false, current)
+    session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event: ev.assistant(11, 1, 'd') })
+    await vi.waitFor(() => {
+      expect(api.callsOf('session.history').length).toBe(2)
+    })
+    await Promise.resolve()
+    expect(session.getSnapshot().todos).toEqual(current)
+  })
+
+  it('clears the plan when a tail response omits the projection (a write the log never kept)', async () => {
+    // Live write lands, then the host crashes before persisting it: the
+    // authoritative log holds no todo/write, so the resync tail response
+    // carries no projection — an omitted field on a tail request is the empty
+    // list, not a missing carrier, and the rolled-back plan must disappear.
+    const { api, session } = await opened(plainTurn(0, 0, 'a', 'b'))
+    session.handleMuxEnvelope('r' as never, {
+      type: 'session/event', sessionId: SID,
+      event: ev.todoWrite(6, [{ content: '丢失的计划', status: 'in_progress' as const }]),
+    })
+    expect(session.getSnapshot().todos).toEqual([{ content: '丢失的计划', status: 'in_progress' }])
+    api.onHistory = () => histResponse(plainTurn(0, 0, 'a', 'b'))
+    await session.resync()
+    expect(session.getSnapshot().todos).toEqual([])
+  })
 })
 
 describe('paging', () => {

packages/client/ui-conversation/README.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-README.md: b9ec555f158722ea1f41e01c4b3f7131d3fe3467
-README.zh.md: b1e3c1f4331148ebf1c58b4bcd4869270bb44311
+#   pnpm run verify-translation-pairing --write packages/client/ui-conversation/README.md
+README.md: b242812411d513931ecd2767622f9e23fb0aaa34
+README.zh.md: 77f68e02d8d9161c413ae7d224121bc53547ba12