Merge remote-tracking branch 'origin/master' into worktree/python-pypi-release-prep

# Conflicts:
#	docs/user/guide/python-sdk.i18n.yaml
#	docs/user/guide/python-sdk.md
#	docs/user/guide/python-sdk.zh.md
#	python/sdk/README.i18n.yaml
#	python/sdk/README.md
#	python/sdk/README.zh.md

.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.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 .agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md
-2026-08-02-typert-remote-method-calls.md: b316d1a42c4f69c8e1163f1f36249b61a7d126ef
-2026-08-02-typert-remote-method-calls.zh.md: 02714de3c522ce597e89976b6e03d455ff0bf872
+2026-08-02-typert-remote-method-calls.md: 04d4581a8f9a265e5374dae4b76ac8d7e1f91fc6
+2026-08-02-typert-remote-method-calls.zh.md: d0940d0cd95b04901caafa214058a272b23ded5d

.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md

@@ -238,7 +238,7 @@ import goalsRemote from '@deepseek-ai/dsh-goal/remote'
 
 This import brings the `.d.ts` map augmentation into the current TypeScript project while supplying the JS descriptor for the same contract as a value to the runtime. A business package that is not imported does not extend the current project's Remote API types.
 
-The business package's published files must include both `lib/typert.remote-client.d.ts.map` and the `src` file referenced by that map. The generated DTS refers to its adjacent map with `//# sourceMappingURL=typert.remote-client.d.ts.map`; the map source points from `lib` to the business source by a relative path such as `../src/index.ts`. The `/remote` export does not list the map separately; the package `files` field publishes it together with the source.
+The business package's published files must include `lib/typert.remote-client.d.ts.map`. The generated DTS refers to its adjacent map with `//# sourceMappingURL=typert.remote-client.d.ts.map`; the map source points from `lib` to the business source by a relative path such as `../src/index.ts`. The `/remote` export does not list the map separately; the package `files` field publishes it. That target is a development-time path: a workspace consumer resolves it through the package link, so the published payload keeps excluding `src` and a published map simply resolves nothing.
 
 Code that needs only static types may use `import type {} from '@deepseek-ai/dsh-goal/remote'`. This import is erased at runtime, loads no JS, and cannot trigger runtime registration. An environment that makes real calls must pass the contribution from a normal value import to the Client Remote Service.
 

.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.zh.md

@@ -238,7 +238,7 @@ import goalsRemote from '@deepseek-ai/dsh-goal/remote'
 
 该 import 让 `.d.ts` 的 map augmentation 进入当前 TypeScript project，同时把同一约定的 JS descriptor 作为值交给运行时。未 import 的业务包不会扩展当前 project 的 Remote API 类型。
 
-业务 package 的发布文件必须同时包含 `lib/typert.remote-client.d.ts.map` 和 map 指向的 `src` 文件。生成 DTS 以 `//# sourceMappingURL=typert.remote-client.d.ts.map` 引用相邻 map；map 中的 source 从 `lib` 相对指向业务源码，例如 `../src/index.ts`。`/remote` export 不单独列出 map，package `files` 负责把它与源码一起发布。
+业务 package 的发布文件必须包含 `lib/typert.remote-client.d.ts.map`。生成 DTS 以 `//# sourceMappingURL=typert.remote-client.d.ts.map` 引用相邻 map；map 中的 source 从 `lib` 相对指向业务源码，例如 `../src/index.ts`。`/remote` export 不单独列出 map，package `files` 负责发布它。该目标是开发期路径：workspace 消费者经 package link 解析它，因此发布产物仍然不含 `src`，已发布的 map 只是解析不到东西。
 
 仅需要静态类型时可以使用 `import type {} from '@deepseek-ai/dsh-goal/remote'`；这种 import 在运行时会被擦除，不会加载 JS，也不能触发任何运行时注册。需要真实调用的环境必须把普通 value import 得到的 contribution 交给 Client Remote Service。
 

.agents/notes/implemented/architecture/2026-08-04-declaring-a-provider-from-the-models-page.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 .agents/notes/implemented/architecture/2026-08-04-declaring-a-provider-from-the-models-page.md
-2026-08-04-declaring-a-provider-from-the-models-page.md: 3e7ff9c3bd58b73185c669a224a59cd017ecfb42
-2026-08-04-declaring-a-provider-from-the-models-page.zh.md: a4255f8e29b696e84ff3accf636714cdfc0855f1
+2026-08-04-declaring-a-provider-from-the-models-page.md: 179a31396d34228e7a0cd510edac4c535af3162e
+2026-08-04-declaring-a-provider-from-the-models-page.zh.md: 3fca60554769fbf5f5be0d2bc76edf3ab3b71578

.agents/notes/implemented/architecture/2026-08-04-declaring-a-provider-from-the-models-page.md

@@ -48,4 +48,4 @@ What it costs: only pi-ai routes can be hand-declared, because `llm-pi-ai` is th
 
 ## Testing
 
-`packages/client/ui-models/tests/provider-form.spec.tsx` drives the rendered page over a scripted wire face: adding, editing, and removing rows; a cleared optional field leaving the profile and a non-integer capacity never entering it; the interrogation carrying the edited endpoint, the unsaved key, and the profile's protocol; the picker's default selection, toggling, cancel, and adopt-keeps-tuned-rows; the empty, refused, and rejected-transport paths; the create writing one profile plus its credential; every gate on the create button; and the read-only posture. `protocolChoices` is covered against a schema that declares the union and one that does not. The stylesheet gate reads the package's own sources and fails any `<select>` that takes `.input` without `.selectInput`, because the OS arrow it would otherwise keep sits flush inside the 240px cap `select.input` imposes. The editor's own field inventory is asserted per route kind — a catalog route stops at the key and the endpoint, a declared one also carries the protocol — along with the protocol edit travelling as a single `api` path op, a rename travelling as a single `displayName` one, a cleared name unsetting rather than storing the empty string the adapter refuses, and a declared profile naming no protocol selecting nothing rather than the first choice. `apps/web/tests/models-settings.e2e.ts` reopens the declared route through the real wire, captures the card, and asserts the chosen protocol and the new name both reach `settings.yaml` and the row re-registers under the rename.
+`packages/client/ui-models/tests/provider-form.client.spec.tsx` drives the rendered page over a scripted wire face: adding, editing, and removing rows; a cleared optional field leaving the profile and a non-integer capacity never entering it; the interrogation carrying the edited endpoint, the unsaved key, and the profile's protocol; the picker's default selection, toggling, cancel, and adopt-keeps-tuned-rows; the empty, refused, and rejected-transport paths; the create writing one profile plus its credential; every gate on the create button; and the read-only posture. `protocolChoices` is covered against a schema that declares the union and one that does not. The stylesheet gate reads the package's own sources and fails any `<select>` that takes `.input` without `.selectInput`, because the OS arrow it would otherwise keep sits flush inside the 240px cap `select.input` imposes. The editor's own field inventory is asserted per route kind — a catalog route stops at the key and the endpoint, a declared one also carries the protocol — along with the protocol edit travelling as a single `api` path op, a rename travelling as a single `displayName` one, a cleared name unsetting rather than storing the empty string the adapter refuses, and a declared profile naming no protocol selecting nothing rather than the first choice. `apps/web/tests/models-settings.e2e.ts` reopens the declared route through the real wire, captures the card, and asserts the chosen protocol and the new name both reach `settings.yaml` and the row re-registers under the rename.

.agents/notes/implemented/architecture/2026-08-04-declaring-a-provider-from-the-models-page.zh.md

@@ -48,4 +48,4 @@ Status: implemented
 
 ## Testing
 
-`packages/client/ui-models/tests/provider-form.spec.tsx` 在脚本化的协议面之上驱动渲染后的页面：添加、编辑与移除行；被清空的可选字段离开 profile、非整数容量从不进入；询问携带已修改的端点、未保存的密钥，以及 profile 自身的协议；选择框的默认选中、勾选切换、取消，以及「采纳保留已调优的行」；空列表、被拒、传输被拒三条路径；创建写入一份 profile 加其凭据；创建按钮上的每一道门控；以及只读姿态。`protocolChoices` 针对「声明了该 union」与「没有声明」两种 schema 都有覆盖。样式 gate 读取本包自己的源码，任何只取 `.input` 而不取 `.selectInput` 的 `<select>` 都会失败——否则它保留的系统箭头会紧贴 `select.input` 所设 240px 上限的右边缘。编辑器自身的字段清单按路由种类各有断言——内置目录路由止于密钥与端点，已声明路由还带着协议——同时覆盖协议改动只以单条 `api` path op 传出、改名只以单条 `displayName` path op 传出、清空名称是取消设置而不是存入适配器会拒绝的空串，以及不写协议的已声明 profile 什么都不选中、而非选中第一个候选。`apps/web/tests/models-settings.e2e.ts` 经真实协议层重新打开这条已声明路由，捕获该卡片，并断言选定的协议与新名称都抵达了 `settings.yaml`、该行也以新名重新注册。
+`packages/client/ui-models/tests/provider-form.client.spec.tsx` 在脚本化的协议面之上驱动渲染后的页面：添加、编辑与移除行；被清空的可选字段离开 profile、非整数容量从不进入；询问携带已修改的端点、未保存的密钥，以及 profile 自身的协议；选择框的默认选中、勾选切换、取消，以及「采纳保留已调优的行」；空列表、被拒、传输被拒三条路径；创建写入一份 profile 加其凭据；创建按钮上的每一道门控；以及只读姿态。`protocolChoices` 针对「声明了该 union」与「没有声明」两种 schema 都有覆盖。样式 gate 读取本包自己的源码，任何只取 `.input` 而不取 `.selectInput` 的 `<select>` 都会失败——否则它保留的系统箭头会紧贴 `select.input` 所设 240px 上限的右边缘。编辑器自身的字段清单按路由种类各有断言——内置目录路由止于密钥与端点，已声明路由还带着协议——同时覆盖协议改动只以单条 `api` path op 传出、改名只以单条 `displayName` path op 传出、清空名称是取消设置而不是存入适配器会拒绝的空串，以及不写协议的已声明 profile 什么都不选中、而非选中第一个候选。`apps/web/tests/models-settings.e2e.ts` 经真实协议层重新打开这条已声明路由，捕获该卡片，并断言选定的协议与新名称都抵达了 `settings.yaml`、该行也以新名重新注册。

.agents/notes/implemented/architecture/2026-08-06-app-owned-command-line.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 .agents/notes/implemented/architecture/2026-08-06-app-owned-command-line.md
-2026-08-06-app-owned-command-line.md: 2480775f654fd5c2fecebc8d59e311acee878920
-2026-08-06-app-owned-command-line.zh.md: d754c125d5bc683156f5ac3f285e2cd711e6773b
+2026-08-06-app-owned-command-line.md: 6d84ba457564ef250e1acfbcc71fcc91b1d49aee
+2026-08-06-app-owned-command-line.zh.md: f964f7a7de7aae7e97b52fbc572443352dc5ae26

.agents/notes/implemented/architecture/2026-08-06-app-owned-command-line.md

@@ -12,7 +12,7 @@ After profiles, compositions were installable but their command lines were not.
 
 The launcher parses only what it owns — `--profile`, `--patch`, the config dumps — and hands **everything after its own flags** to the booted tree verbatim. The split is positional: the first token the launcher does not recognize starts the app's arguments (commander's `passThroughOptions` + `allowUnknownOption` + `helpOption(false)`). A bare `dsh -h`, which has no app to hand the flag to, still prints the launcher's own help.
 
-The new `@deepseek-ai/dsh-cmdline` package owns the handoff. A launcher calls `provideCmdline(ctx, host)` before any entry mounts, providing `ctx.cmdlineArgs` (whose whole interface is `get(): readonly string[]`) and `ctx.appExit`. Any ordinary app plugin may inject `cmdlineArgs`, call `parseCmdline(ctx, program, plan)` with its own commander program, and provide the returned value as an app-owned service. Its Loader row carries no launcher marker or special kind, and the launcher does not inspect the composition for an owner. Multiple plugins may read the same immutable snapshot; a profile with no reader ignores its app arguments. Rows configured from a provider inject its service and read direct lazy config expressions (`port: !!js ctx.webStartup.port ?? 3080`), so a flag beats the value written beside it and nothing is written back into any row.
+The new `@deepseek-ai/dsh-cmdline` package owns the handoff. A launcher calls `provideCmdline(ctx, host)` before any entry mounts, providing `ctx.cmdlineArgs` (whose whole interface is `get(): readonly string[]`) and `ctx.appExit`. Any ordinary app plugin may inject `cmdlineArgs`, call `parseCmdline(ctx, program)` with its own commander program, and provide the resolved value as an app-owned service from the program's action. Its Loader row carries no launcher marker or special kind, and the launcher does not inspect the composition for an owner. Multiple plugins may read the same immutable snapshot; a profile with no reader ignores its app arguments. Rows configured from a provider inject its service and read direct lazy config expressions (`port: !!js ctx.webStartup.port ?? 3080`), so a flag beats the value written beside it and nothing is written back into any row.
 
 The boot mounts the composition once. Cordis holds each row until its injections are active; Loader then interpolates that row's `!!js` against the injection-ready plugin context immediately before activation. Include keeps nested row expressions raw until their target row reaches this point. `--help` leaves the provider's service absent, so dependent rows never activate, and a live patch reload interpolates again against the service that remains active, so a served port cannot be silently reset.
 

.agents/notes/implemented/architecture/2026-08-06-app-owned-command-line.zh.md

@@ -12,7 +12,7 @@ profile 落地之后，组合可以安装，命令行却不能。`apps/cli` 仍
 
 启动器只解析属于自己的部分（`--profile`、`--patch`、配置 dump），并把**自己 flag 之后的一切**原样交给引导起来的配置树。切分按位置进行：启动器不认识的第一个 token 就是应用参数的起点（依靠 commander 的 `passThroughOptions` + `allowUnknownOption` + `helpOption(false)`）。裸的 `dsh -h` 没有可交付的应用，仍然打印启动器自己的 help。
 
-新包 `@deepseek-ai/dsh-cmdline` 持有这次交接。启动器在任何条目挂载之前调用 `provideCmdline(ctx, host)`，提供 `ctx.cmdlineArgs`（其全部接口就是 `get(): readonly string[]`）与 `ctx.appExit`。任何普通应用插件都可以注入 `cmdlineArgs`，用自己的 commander program 调用 `parseCmdline(ctx, program, plan)`，再把返回值作为应用自有服务提供出去。它的 Loader 行不携带启动器标记或特殊类型，启动器也不会检查组合中的所有者。多个插件可以读取同一份不可变快照；没有读取方的 profile 会忽略自己的应用参数。由提供方配置的行注入其服务，并在惰性配置表达式中直接读取它（`port: !!js ctx.webStartup.port ?? 3080`），因此 flag 胜过写在它旁边的值，也没有任何东西被写回任何一行。
+新包 `@deepseek-ai/dsh-cmdline` 持有这次交接。启动器在任何条目挂载之前调用 `provideCmdline(ctx, host)`，提供 `ctx.cmdlineArgs`（其全部接口就是 `get(): readonly string[]`）与 `ctx.appExit`。任何普通应用插件都可以注入 `cmdlineArgs`，用自己的 commander program 调用 `parseCmdline(ctx, program)`，再在 program 自己的 action 中把解析出的取值作为应用自有服务提供出去。它的 Loader 行不携带启动器标记或特殊类型，启动器也不会检查组合中的所有者。多个插件可以读取同一份不可变快照；没有读取方的 profile 会忽略自己的应用参数。由提供方配置的行注入其服务，并在惰性配置表达式中直接读取它（`port: !!js ctx.webStartup.port ?? 3080`），因此 flag 胜过写在它旁边的值，也没有任何东西被写回任何一行。
 
 boot 只挂载一次整套组合。Cordis 让每一行等待其注入激活；Loader 随后在激活前一刻，基于已注入就绪的插件上下文插值该行的 `!!js`。Include 会保留嵌套的行表达式，直到目标行到达这一时点。`--help` 会让提供方服务保持缺失，因此依赖行永不激活；活动 patch 重载会针对仍然在线的服务再次插值，所以已经服务中的端口不会被悄悄重置。
 

.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.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/architecture/2026-08-11-loader-entry-disabled-interpolation.md
+2026-08-11-loader-entry-disabled-interpolation.md: fd760ea0f15f19e5f287aaddc36fb8eeb5f519ba
+2026-08-11-loader-entry-disabled-interpolation.zh.md: 15f5a80931c58555dceab359d05e8515334513b2

.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.md

@@ -0,0 +1,25 @@
+# Agent Note: Loader interpolates the entry `disabled` field
+
+Status: implemented
+
+English | [中文](2026-08-11-loader-entry-disabled-interpolation.zh.md)
+
+## Problem
+
+The Windows platform layer (then a separate `windows.cordis.patch.yml` beside the base patch, since folded into the base rows — see Decision) disabled `tool-bash` on win32, but the shipped presets each mount a `tool-bash` row. Preset rows compose last, so the same-id row re-enabled the tool on Windows — the session had both `tool-bash` (PowerShell-backed) and `tool-pwsh`, silently, because no spec pinned the composed preset layer. Entry metadata had no conditional mechanism: `!!js` interpolates only under plugin `config`, and [postmortem 0002](../../../../docs/postmortem/0002-js-expression-disabled-filesystem-tools.md) documents that `disabled: !!js ...` stays a truthy expression object, disabling the row everywhere.
+
+## Decision
+
+The Loader interpolates the entry `disabled` field (`vendor/loader/src/config/entry.ts`): a `!!js` expression evaluates against the loader context at every mount decision. `disabled` is the only interpolated metadata field; `id`, `name`, `group`, and `inject` stay static. The raw node stays in the options, so write-back keeps the `!!js` form. The shipped presets (standard, code, cordis) declare the shell tool rows themselves and gate them by platform — `tool-bash` with `disabled: !!js process.platform === 'win32'` and its `tool-pwsh` twin with the inverted expression — so the preset layer exposes exactly one shell tool per host; the web-app overlay disables the host rows of both tools, letting each session's preset decide. `verify-cordis-config` now allows expressions in `disabled` only.
+
+The mechanism completes the platform-layer fold: the base bundle's `cordis.patch.yml` gates both shell stacks on its own rows — `bash-sandbox`/`tool-bash` carry `disabled: !!js process.platform === 'win32'`, and their twins `pwsh-sandbox`/`tool-pwsh` mount only on win32 with the inverted expression. The launcher's separate Windows platform layer (`windows.cordis.patch.yml` plus `apps/cli/src/windows-shell.ts` and its injection into boot, live recomposition, and config dumps) is deleted — the layer existed only because entry metadata was static, and with `disabled` interpolated the condition lives on the row it governs.
+
+## Alternatives considered
+
+**A declarative `platform` field on the row.** Static and gate-checkable, but a second composition mechanism beside `!!js`, and platform is only today's condition.
+
+**Preset-level platform overlays.** Rejected: the condition belongs on the row it governs — the same principle folds the launcher's separate Windows platform layer into the base rows.
+
+## Consequences
+
+A row can gate itself on platform or environment; a bad expression fails loud at boot. Every other metadata field remains literal and the gate keeps rejecting expressions there — the postmortem-0002 hazard is closed for `disabled` by evaluation, not prohibition. The Windows shell swap moved from a launcher-injected patch layer to the base bundle's own rows: win32 mounts the confined pwsh stack, POSIX carries the pwsh rows disabled, and one shared patch file serves both rosters — the [Windows pwsh default](../feature/2026-08-01-windows-pwsh-default.md) note's layer mechanism is superseded. The shell TOOL rows follow the same one-plane rule as every other preset-declared row: the web-app overlay disables the host `tool-bash`/`tool-pwsh` rows and the presets declare both with inverted platform gates, so a preset can drop or replace the shell tool per session on either host. The `minimal` preset's missing win32 PTY stack is a preset-metadata follow-up.

.agents/notes/implemented/architecture/2026-08-11-loader-entry-disabled-interpolation.zh.md

@@ -0,0 +1,25 @@
+# Agent Note：Loader 插值条目 `disabled` 字段
+
+Status: implemented
+
+[English](2026-08-11-loader-entry-disabled-interpolation.md) | 中文
+
+## 问题
+
+Windows 平台层（当时是 base patch 旁独立的 `windows.cordis.patch.yml`，现已折入 base 行——见「决策」）在 win32 上禁用 `tool-bash`，但 shipped 预设各自挂载了一行 `tool-bash`。预设行最后组合，同名行在 Windows 上重新启用了该工具——会话同时拥有 `tool-bash`（PowerShell 后端）与 `tool-pwsh`，且是静默的，因为没有 spec pin 组合后的预设层。条目元数据没有条件机制：`!!js` 只在插件 `config` 下插值，[postmortem 0002](../../../../docs/postmortem/0002-js-expression-disabled-filesystem-tools.md) 记录了 `disabled: !!js ...` 保持真值表达式对象、在所有平台上禁用该行的事故。
+
+## 决策
+
+Loader 插值条目 `disabled` 字段（`vendor/loader/src/config/entry.ts`）：`!!js` 表达式在每次挂载决策时基于 loader 上下文求值。`disabled` 是唯一被插值的元数据字段；`id`、`name`、`group`、`inject` 保持静态。原始节点保留在 options 中，写回保持 `!!js` 形式。shipped 预设（standard、code、cordis）自己声明 shell 工具行并按平台门控——`tool-bash` 携带 `disabled: !!js process.platform === 'win32'`，其孪生行 `tool-pwsh` 以取反的表达式——因此预设层每台宿主恰好暴露一个 shell 工具；web-app overlay 禁用两个工具的 host 行，由每个会话的预设决定。`verify-cordis-config` 现在只允许 `disabled` 中的表达式。
+
+该机制补全了平台层折叠：base bundle 的 `cordis.patch.yml` 在自身行上按平台门控两个 shell 栈——`bash-sandbox`/`tool-bash` 携带 `disabled: !!js process.platform === 'win32'`，它们的孪生行 `pwsh-sandbox`/`tool-pwsh` 以取反的表达式仅在 win32 挂载。启动器的独立 Windows 平台层（`windows.cordis.patch.yml` 以及 `apps/cli/src/windows-shell.ts` 及其注入到 boot、live 重组合、config dump 的逻辑）被删除——该层只因条目元数据是静态的而存在，`disabled` 可插值后条件就落在它所治理的行上。
+
+## 备选方案
+
+**行上的声明式 `platform` 字段。** 静态且可被门禁检查，但它是 `!!js` 之外的第二种组合机制，且平台只是今天的条件。
+
+**预设级平台 overlay。** 被否：条件应当属于它所治理的行——同一原则把启动器独立的 Windows 平台层折入 base 行。
+
+## 后果
+
+行可以按平台或环境门控自身；错误的表达式在启动时响亮失败。其余元数据字段保持字面值，门禁继续拒绝那里的表达式——`disabled` 上的 postmortem-0002 隐患以「求值」而非「禁止」关闭。Windows shell 栈的切换从启动器注入的 patch 层移到 base bundle 自身的行上：win32 挂载受限 pwsh 栈，POSIX 携带被禁用的 pwsh 行，同一份 patch 文件服务两种阵容——[Windows 默认 pwsh](../feature/2026-08-01-windows-pwsh-default.md) note 的层机制已被取代。shell 工具行遵循与其他预设声明行相同的 one-plane 规则：web-app overlay 禁用 host 面的 `tool-bash`/`tool-pwsh` 行，预设以互逆的平台门控声明两者，因此任一宿主的每个会话都可以按预设丢弃或替换 shell 工具。`minimal` 预设缺失的 win32 PTY 栈是预设元数据的后续工作。

.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.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 .agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md
-2026-07-28-themed-scrollbars-and-reserved-gutter.md: 8ad5d801358823576c37d6b6824d7ce3fdcdac11
-2026-07-28-themed-scrollbars-and-reserved-gutter.zh.md: d6d2c64703df95ea2a4ff79435512eabdb3d2f81
+2026-07-28-themed-scrollbars-and-reserved-gutter.md: a820a92406ce4054f16922064772d03c6ac3ab83
+2026-07-28-themed-scrollbars-and-reserved-gutter.zh.md: 80104c4aca5986c3a1f49186ac4adf3169f46da5

.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md

@@ -20,7 +20,7 @@ The rules sit on `body`, not `html`. `design-platform.css` declares the `--dsw-a
 
 The two renderings are mutually exclusive, and the exclusion is enforced rather than assumed. A non-`auto` `scrollbar-width` or `scrollbar-color` makes Chromium and Safari discard every `::-webkit-scrollbar*` rule for that element, `::-webkit-scrollbar-thumb:hover` included. Declaring both unconditionally therefore leaves the hover token rendering nowhere at all: the engines that implement the hover pseudo-element are exactly the ones the standard properties silence, and Firefox has no hover pseudo-element to fall back on. The standard properties consequently sit inside `@supports not selector(::-webkit-scrollbar)`, which is true only where the pseudo-element is unimplemented, so Firefox takes the standard path and WebKit-based engines take the pseudo-element path. The WebKit rules are not gated in turn: an engine without those pseudo-elements drops them as unknown selectors, so a gate would only restate what selector matching already does. An engine too old for the `selector()` function makes the condition invalid, which evaluates false and selects the pseudo-element path — the correct side for the pre-16.4 Safari that is the realistic case for that reading.
 
-Both paths read one indirection pair, `--dsh-scrollbar-thumb` and `--dsh-scrollbar-thumb-hover`, bound on `body` to the l1 (base-surface) tokens. **This is the rebinding contract, and it is the part the CSS alone does not state**: an elevated surface sets `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` and `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)` on its own container, and that one rebind reaches the standard properties and the WebKit pseudo-elements together. The pair is rebound as a pair; rebinding the resting thumb alone leaves the hover state on the base-surface token. `transparent` is the pair's other legal target, added when the sidebar's bars [started following the pointer](../feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md); the gate below admits those two and nothing else. The mechanically discoverable subset is owned by `packages/client/ui-theme/tests/scrollbar-styles.spec.ts`: any sheet that both scrolls and paints an elevated surface must rebind, so this note no longer maintains a complete surface inventory. Most declare the pair on the elevated card rather than on the scrolling descendant, because elevation belongs to the surface and custom properties inherit to whichever child actually scrolls.
+Both paths read one indirection pair, `--dsh-scrollbar-thumb` and `--dsh-scrollbar-thumb-hover`, bound on `body` to the l1 (base-surface) tokens. **This is the rebinding contract, and it is the part the CSS alone does not state**: an elevated surface sets `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` and `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)` on its own container, and that one rebind reaches the standard properties and the WebKit pseudo-elements together. The pair is rebound as a pair; rebinding the resting thumb alone leaves the hover state on the base-surface token. `transparent` is the pair's other legal target, added when the sidebar's bars [started following the pointer](../feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md); the gate below admits those two and nothing else. The mechanically discoverable subset is owned by `packages/client/ui-theme/tests/scrollbar-styles.client.spec.ts`: any sheet that both scrolls and paints an elevated surface must rebind, so this note no longer maintains a complete surface inventory. Most declare the pair on the elevated card rather than on the scrolling descendant, because elevation belongs to the surface and custom properties inherit to whichever child actually scrolls.
 
 Four surfaces — `Menu`, `InputBar`, `QuestionComposer`, and `TodoPanel` — were initially missed, which is why the per-sheet rebinding contract is checked mechanically rather than by inspection.
 

.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.zh.md

@@ -20,7 +20,7 @@ Status: implemented
 
 两种渲染互斥，而这种互斥是被强制的，不是假定的。`scrollbar-width` 或 `scrollbar-color` 只要取非 `auto` 值，Chromium 与 Safari 就会丢弃该元素上的全部 `::-webkit-scrollbar*` 规则，`::-webkit-scrollbar-thumb:hover` 也在其中。因此无条件地同时声明会让 hover token 在任何地方都得不到渲染：实现了 hover 伪元素的引擎，恰恰就是被标准属性静音的那些，而 Firefox 没有 hover 伪元素可作退路。于是标准属性写在 `@supports not selector(::-webkit-scrollbar)` 之内，该条件只在伪元素未被实现处为真，因此 Firefox 走标准属性路径，WebKit 系引擎走伪元素路径。WebKit 规则不再反向加门禁：不实现这些伪元素的引擎会把它们当作未知选择器丢弃，因此加门禁只是重述选择器匹配本身已经做的事。对于旧到不支持 `selector()` 函数的引擎，该条件无效，从而求值为假并选中伪元素路径——对于这条判断下现实存在的 16.4 之前的 Safari，这正是正确的一侧。
 
-两条路径都读取同一组间接变量 `--dsh-scrollbar-thumb` 与 `--dsh-scrollbar-thumb-hover`，它们在 `body` 上绑定到 l1（基础表面）token。**这就是重新绑定约定，也是单看 CSS 无法得知的部分**：抬升表面在自己的容器上设置 `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` 与 `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)`，这一次重新绑定同时作用于标准属性和 WebKit 伪元素。这组变量必须成对重新绑定；只改静止态滑块会让 hover 状态仍留在基础表面的 token 上。这组变量另一个合法的目标是 `transparent`，它随侧边栏滚动条[改为跟随指针](../feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md)一并引入；下文的门禁只接受这两种目标。可由机械检查发现的子集归 `packages/client/ui-theme/tests/scrollbar-styles.spec.ts` 所有：任何既滚动又绘制抬升表面的样式表都必须重新绑定，因此本 note 不再维护完整的表面清单。多数把这组变量声明在抬升卡片上而非滚动的后代元素上，因为抬升层级属于这个表面，而自定义属性会继承到真正滚动的那个子元素。
+两条路径都读取同一组间接变量 `--dsh-scrollbar-thumb` 与 `--dsh-scrollbar-thumb-hover`，它们在 `body` 上绑定到 l1（基础表面）token。**这就是重新绑定约定，也是单看 CSS 无法得知的部分**：抬升表面在自己的容器上设置 `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` 与 `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)`，这一次重新绑定同时作用于标准属性和 WebKit 伪元素。这组变量必须成对重新绑定；只改静止态滑块会让 hover 状态仍留在基础表面的 token 上。这组变量另一个合法的目标是 `transparent`，它随侧边栏滚动条[改为跟随指针](../feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md)一并引入；下文的门禁只接受这两种目标。可由机械检查发现的子集归 `packages/client/ui-theme/tests/scrollbar-styles.client.spec.ts` 所有：任何既滚动又绘制抬升表面的样式表都必须重新绑定，因此本 note 不再维护完整的表面清单。多数把这组变量声明在抬升卡片上而非滚动的后代元素上，因为抬升层级属于这个表面，而自定义属性会继承到真正滚动的那个子元素。
 
 `Menu`、`InputBar`、`QuestionComposer` 与 `TodoPanel` 这四个表面最初被漏掉，因此逐样式表的重新绑定约定由机械检查而非人工审阅把关。
 

.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.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 .agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.md
-2026-07-30-hover-popup-pointer-grace.md: 3f60c98ec6453b633feebe408cbc0c0c49eedea1
-2026-07-30-hover-popup-pointer-grace.zh.md: f53d77bae7b7f223621c4c42779e1a6a616aa485
+2026-07-30-hover-popup-pointer-grace.md: 302592a2e9de8e749ef2450e8877a3ccbffd15d5
+2026-07-30-hover-popup-pointer-grace.zh.md: 4020a6f1f7ab52b6340a07f4c099906a7353a8a5

.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.md

@@ -32,4 +32,4 @@ The hover card is now hit-testable and covers 244px of whatever it overlays whil
 
 ## Testing
 
-`packages/client/ui-primitives/tests/hover-card.spec.tsx` and `tests/atoms.spec.tsx` pin the grace boundary, cancel-on-return, no-second-dwell, disarm-on-owner-close, and the no-arming-while-closed case. The reachability gestures themselves — hovering onto the card, and moving between an open list and its trigger — are pinned in the real browser by `apps/web/tests/workspace-management.e2e.ts`, since they depend on hit testing and layout that jsdom does not model.
+`packages/client/ui-primitives/tests/hover-card.client.spec.tsx` and `tests/atoms.spec.tsx` pin the grace boundary, cancel-on-return, no-second-dwell, disarm-on-owner-close, and the no-arming-while-closed case. The reachability gestures themselves — hovering onto the card, and moving between an open list and its trigger — are pinned in the real browser by `apps/web/tests/workspace-management.e2e.ts`, since they depend on hit testing and layout that jsdom does not model.

.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.zh.md

@@ -32,4 +32,4 @@ Status: implemented
 
 ## 测试
 
-`packages/client/ui-primitives/tests/hover-card.spec.tsx` 与 `tests/atoms.spec.tsx` 固定验证宽限期边界、折返取消、不重启停留计时、所有者关闭时解除待执行关闭，以及列表关闭时不启动关闭。可抵达性手势本身——把指针移到卡片上，以及在打开的列表与其触发按钮之间移动——由 `apps/web/tests/workspace-management.e2e.ts` 在真实浏览器中固定验证，因为它们依赖 jsdom 无法建模的命中测试与布局。
+`packages/client/ui-primitives/tests/hover-card.client.spec.tsx` 与 `tests/atoms.spec.tsx` 固定验证宽限期边界、折返取消、不重启停留计时、所有者关闭时解除待执行关闭，以及列表关闭时不启动关闭。可抵达性手势本身——把指针移到卡片上，以及在打开的列表与其触发按钮之间移动——由 `apps/web/tests/workspace-management.e2e.ts` 在真实浏览器中固定验证，因为它们依赖 jsdom 无法建模的命中测试与布局。

.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.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 .agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md
-2026-07-30-web-transcript-log-ordered-projection.md: 1c65eeec0fbf0dc550043bb809ae8d7310f0602b
-2026-07-30-web-transcript-log-ordered-projection.zh.md: 67bb41adde46ba7112896404ddc92a05f08f7aca
+2026-07-30-web-transcript-log-ordered-projection.md: f2eda6983ab88a420a4506be7766320dc5da0fa2
+2026-07-30-web-transcript-log-ordered-projection.zh.md: 4c8bb5d0b9b49762d12aba837cef9c0818740cb0

.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md

@@ -39,7 +39,7 @@ const COMPACT_PLUGIN: CompactCheckpointSource['plugin'] = 'compact'
 
 Renaming the Service Definition's plugin id is now a compile error in the client: `TS2322: Type '"compact"' is not assignable to type '"compaction"'`. The import must stay **type-only** — a value import of any `@deepseek-ai` package that is neither a platform module nor an inline-safe wire layer is rejected by the client purity gate (`packages/client/tsdown.client.ts`), whose own message records that type-only imports are erased and never reach it. A type-only leaf import needs both a `tsconfig.base.json` `paths` entry and `{"path": "../../compact/compact"}` in `packages/client/runtime/tsconfig.json` `references`: composite `rootDir` rules apply to erased imports as well, and without the reference the diagnostic is `TS6059`/`TS6307`.
 
-`packages/client/ui-conversation/tests/conversation-node-definitions.spec.ts` is the behavioral half, driving the compaction Definition with checkpoint and provenance records and proving that an older page can fill missing summary data. The Definition's type-only leaf import keeps the client isolated from the compact package root and the host-side `Context` merges reachable through it.
+`packages/client/ui-conversation/tests/conversation-node-definitions.client.spec.ts` is the behavioral half, driving the compaction Definition with checkpoint and provenance records and proving that an older page can fill missing summary data. The Definition's type-only leaf import keeps the client isolated from the compact package root and the host-side `Context` merges reachable through it.
 
 The divergence from the terminal is therefore narrow: both frontends recognize a checkpoint from the same declaration — the terminal value-imports `isCompactCheckpointSource` host-side, where no gate applies, and the client pins the type.
 

.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.zh.md

@@ -39,7 +39,7 @@ const COMPACT_PLUGIN: CompactCheckpointSource['plugin'] = 'compact'
 
 重命名 Service Definition 的插件 id 现在会在客户端产生编译错误：`TS2322: Type '"compact"' is not assignable to type '"compaction"'`。该导入必须保持**仅类型**——任何既非平台模块又非 inline-safe wire 层的 `@deepseek-ai` 包值导入都会被客户端纯度门禁（`packages/client/tsdown.client.ts`）拒绝，而它自己的报错信息就记录着仅类型导入会被擦除、永不抵达该门禁。仅类型的叶子导入同时需要 `tsconfig.base.json` 的一条 `paths` 条目和 `packages/client/runtime/tsconfig.json` `references` 中的 `{"path": "../../compact/compact"}`：composite 的 `rootDir` 规则同样适用于被擦除的导入，缺少该引用时的诊断是 `TS6059`/`TS6307`。
 
-`packages/client/ui-conversation/tests/conversation-node-definitions.spec.ts` 是行为侧的另一半，用检查点与溯源记录驱动压缩 Definition，并证明后续加载的旧分页可以补齐缺失的摘要数据。Definition 仅类型导入该叶子路径，使客户端继续与 compact 包根及经由它可达的宿主侧 `Context` 合并隔离。
+`packages/client/ui-conversation/tests/conversation-node-definitions.client.spec.ts` 是行为侧的另一半，用检查点与溯源记录驱动压缩 Definition，并证明后续加载的旧分页可以补齐缺失的摘要数据。Definition 仅类型导入该叶子路径，使客户端继续与 compact 包根及经由它可达的宿主侧 `Context` 合并隔离。
 
 因此与终端的分歧很窄：两个前端都从同一份声明识别检查点——终端在宿主侧值导入 `isCompactCheckpointSource`（那里不适用任何门禁），客户端钉住类型。
 

.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.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 .agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md
-2026-07-31-composer-text-layers-share-one-scrollport.md: ba11384409714d6a64a964d63197705acf39d213
-2026-07-31-composer-text-layers-share-one-scrollport.zh.md: 7a2500a6253c7cf50a57458b66c9b80503414ace
+2026-07-31-composer-text-layers-share-one-scrollport.md: 6097779529f86e6d994296ae396f108c63f01abc
+2026-07-31-composer-text-layers-share-one-scrollport.zh.md: 753d67d538d0c17512444639d60b7b5c8ff80e9a

.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md

@@ -71,7 +71,7 @@ Revealing the caret is the one thing that now depends on the browser rather than
 
 ## Testing
 
-The unit spec in [input-bar.spec.tsx](../../../../packages/client/ui-conversation/tests/input-bar.spec.tsx) asserts what jsdom can see: that one scrolling box contains both the textarea and the backdrop, that the backdrop's text is now the draft and nothing else, and that a late persisted draft reveals its caret without taking focus from another control. jsdom reports `scrollHeight === clientHeight` for every element and never scrolls one, so the geometry belongs to the browser scenario; the wheel-chaining cases stub the scrollport's metrics rather than the textarea's.
+The unit spec in [input-bar.spec.tsx](../../../../packages/client/ui-conversation/tests/input-bar.client.spec.tsx) asserts what jsdom can see: that one scrolling box contains both the textarea and the backdrop, that the backdrop's text is now the draft and nothing else, and that a late persisted draft reveals its caret without taking focus from another control. jsdom reports `scrollHeight === clientHeight` for every element and never scrolls one, so the geometry belongs to the browser scenario; the wheel-chaining cases stub the scrollport's metrics rather than the textarea's.
 
 [composer-draft-scroll.e2e.ts](../../../../apps/web/tests/composer-draft-scroll.e2e.ts) measures the rest in chromium against the built client: a 40-line draft in a fresh workspace's blank composer, zero model calls. Every metric is read in the caret's own coordinate frame — where the textarea places line n, offset included — against a DOM Range over the backdrop's text for the same line, because that difference is what a user sees. The decisive case changes the offset and re-reads that difference **before the task ends**, which is before any `scroll` listener could have run: 0 with one scrollport, and the full delta with a mirror. A vacuity guard asserts the draft overflows the capped box first, and separate cases cover the cap, one wrap width across all three layers, a wheel gesture, a trailing-newline draft, and the caret-reveal path that the textarea's own scrolling used to handle — typing after scrolling away must bring the scrollport back to the caret.
 

.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md

@@ -71,7 +71,7 @@ composer 的文本由两层叠放绘制（见 [InputBar](../../../../packages/cl
 
 ## 测试
 
-[input-bar.spec.tsx](../../../../packages/client/ui-conversation/tests/input-bar.spec.tsx) 中的单元用例断言 jsdom 能看见的部分：同一个滚动盒同时包含 textarea 与 backdrop，backdrop 的文本现在就是草稿本身、不多不少，且渲染后才到达的持久化草稿会回视其光标，同时不从其他控件夺走焦点。jsdom 对任何元素都报告 `scrollHeight === clientHeight` 且从不滚动，因此几何属于浏览器场景；滚轮接力用例改为桩接滚动容器的度量，而非 textarea 的。
+[input-bar.spec.tsx](../../../../packages/client/ui-conversation/tests/input-bar.client.spec.tsx) 中的单元用例断言 jsdom 能看见的部分：同一个滚动盒同时包含 textarea 与 backdrop，backdrop 的文本现在就是草稿本身、不多不少，且渲染后才到达的持久化草稿会回视其光标，同时不从其他控件夺走焦点。jsdom 对任何元素都报告 `scrollHeight === clientHeight` 且从不滚动，因此几何属于浏览器场景；滚轮接力用例改为桩接滚动容器的度量，而非 textarea 的。
 
 [composer-draft-scroll.e2e.ts](../../../../apps/web/tests/composer-draft-scroll.e2e.ts) 在 chromium 中针对构建产物度量其余部分：全新工作区的空白 composer 中一份 40 行草稿，零模型调用。每个度量都在光标自己的坐标系里读取——即 textarea 把第 n 行放在哪，含其自身偏移——再与 backdrop 同一行文本上的 DOM Range 相比，因为这个差值正是用户看到的东西。决定性的用例改变偏移，并**在本任务结束之前**重新读取该差值，也就是在任何 `scroll` 监听可能运行之前：单一滚动容器下为 0，镜像方案下则是整个增量。空洞性保护先断言草稿确实超过了带上限的盒子；其余用例分别覆盖高度上限、三层同一折行宽度、滚轮手势、以换行结尾的草稿，以及过去由 textarea 自身滚动承担的光标回视路径——滚离光标后输入，必须把滚动容器带回光标处。
 

.agents/notes/implemented/bug-fix/2026-08-05-context-meter-blind-to-compaction.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 .agents/notes/implemented/bug-fix/2026-08-05-context-meter-blind-to-compaction.md
-2026-08-05-context-meter-blind-to-compaction.md: 10ded250cec9c92d90803bdf5969cc7f5aa54c50
-2026-08-05-context-meter-blind-to-compaction.zh.md: ca3fe59eecde82bb97b44af4c3383546d5672753
+2026-08-05-context-meter-blind-to-compaction.md: b90208eda25101aeb55130cd1b6563dbfaee8a9a
+2026-08-05-context-meter-blind-to-compaction.zh.md: 85387c50ebc981fc2f7f02d07432da677f69ef90

.agents/notes/implemented/bug-fix/2026-08-05-context-meter-blind-to-compaction.md

@@ -43,4 +43,4 @@ The panel's composition rows still do not sum to the header, and now for one cle
 
 ## Testing
 
-`packages/llm/token-meter/tests/token-usage-projection.spec.ts` covers the carry-forward across surface growth and a compaction (the sample holding still while the projection shrinks) and the zero clamp when heuristic error would drive the figure negative. `packages/client/ui-conversation/tests/context-meter.spec.tsx` pins the ring reading the projected figure, and `chat-stats.spec.tsx` pins `contextOccupancy`'s preference and its fallback. The end-to-end numbers above came from driving `BasicCompactService.compactNow` through a real `AgentLoop` with the projection registry mounted.
+`packages/llm/token-meter/tests/token-usage-projection.spec.ts` covers the carry-forward across surface growth and a compaction (the sample holding still while the projection shrinks) and the zero clamp when heuristic error would drive the figure negative. `packages/client/ui-conversation/tests/context-meter.client.spec.tsx` pins the ring reading the projected figure, and `chat-stats.spec.tsx` pins `contextOccupancy`'s preference and its fallback. The end-to-end numbers above came from driving `BasicCompactService.compactNow` through a real `AgentLoop` with the projection registry mounted.

.agents/notes/implemented/bug-fix/2026-08-05-context-meter-blind-to-compaction.zh.md

@@ -43,4 +43,4 @@ AFTER  compact:  ring=4%  header=~4227/100000   rows=[system 18, tools 0, messag
 
 ## 测试
 
-`packages/llm/token-meter/tests/token-usage-projection.spec.ts` 覆盖了投影值在表层增长与一次压缩期间的延续更新（样本保持不动而投影值缩小），以及启发式误差会把数字压到负数时的零钳制。`packages/client/ui-conversation/tests/context-meter.spec.tsx` 钉住圆环读取投影值这一点，`chat-stats.spec.tsx` 钉住 `contextOccupancy` 的优先级与回退。上面那组端到端数字来自在挂载了投影注册表的真实 `AgentLoop` 上驱动 `BasicCompactService.compactNow`。
+`packages/llm/token-meter/tests/token-usage-projection.spec.ts` 覆盖了投影值在表层增长与一次压缩期间的延续更新（样本保持不动而投影值缩小），以及启发式误差会把数字压到负数时的零钳制。`packages/client/ui-conversation/tests/context-meter.client.spec.tsx` 钉住圆环读取投影值这一点，`chat-stats.spec.tsx` 钉住 `contextOccupancy` 的优先级与回退。上面那组端到端数字来自在挂载了投影注册表的真实 `AgentLoop` 上驱动 `BasicCompactService.compactNow`。

.agents/notes/implemented/bug-fix/2026-08-05-workspace-blank-session-reuse-membership.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 .agents/notes/implemented/bug-fix/2026-08-05-workspace-blank-session-reuse-membership.md
-2026-08-05-workspace-blank-session-reuse-membership.md: 910a10e9ada1a835df7a38a04fb04c504b0921df
-2026-08-05-workspace-blank-session-reuse-membership.zh.md: 0581b768679d78716c1bf70cfffec825c7281783
+2026-08-05-workspace-blank-session-reuse-membership.md: 0d46a0ccf6924c508db2e6c0f3591468e2956722
+2026-08-05-workspace-blank-session-reuse-membership.zh.md: e67810dc3a45d494f64a2b774557d04297b6fce3

.agents/notes/implemented/bug-fix/2026-08-05-workspace-blank-session-reuse-membership.md

@@ -26,4 +26,4 @@ Stray blank sessions remain visible in Ungrouped (the user can still open them)
 
 ## Testing
 
-`packages/client/runtime/tests/workspaces-service.spec.ts` covers the four outcomes: a member blank session is reused (no create RPC); a stray blank with matching cwd is **not** reused and a fresh accounted session is created (regression case); an archived blank is not reused; a rejected first prompt keeps a member blank eligible. The full client suite (`pnpm run test:gui`) stays green.
+`packages/client/runtime/tests/workspaces-service.client.spec.ts` covers the four outcomes: a member blank session is reused (no create RPC); a stray blank with matching cwd is **not** reused and a fresh accounted session is created (regression case); an archived blank is not reused; a rejected first prompt keeps a member blank eligible. The full client suite (`pnpm run test:gui`) stays green.

.agents/notes/implemented/bug-fix/2026-08-05-workspace-blank-session-reuse-membership.zh.md

@@ -26,4 +26,4 @@ Status: implemented
 
 ## 测试
 
-`packages/client/runtime/tests/workspaces-service.spec.ts` 覆盖四种结果：成员空白会话被复用（无 create RPC）；cwd 匹配但非成员的游离空白会话**不被**复用、改为创建全新入账会话（回归用例）；已归档空白会话不被复用；首次提示词被拒后成员空白会话仍可复用。完整客户端套件（`pnpm run test:gui`）保持绿色。
+`packages/client/runtime/tests/workspaces-service.client.spec.ts` 覆盖四种结果：成员空白会话被复用（无 create RPC）；cwd 匹配但非成员的游离空白会话**不被**复用、改为创建全新入账会话（回归用例）；已归档空白会话不被复用；首次提示词被拒后成员空白会话仍可复用。完整客户端套件（`pnpm run test:gui`）保持绿色。

.agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.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 .agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.md
-2026-08-06-onboarding-step-owned-takeover-chrome.md: 35b9d16aaba4ca9f124a9972c43b2a107ea0309f
-2026-08-06-onboarding-step-owned-takeover-chrome.zh.md: 2f3331965aa94aa01bf0ce21d4bbb421397ee5bd
+2026-08-06-onboarding-step-owned-takeover-chrome.md: 97f5335412f256bf7e60f36731c9e0c4475ee99e
+2026-08-06-onboarding-step-owned-takeover-chrome.zh.md: 054072764a7b9a25586899a93596fdc922e71dcb

.agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.md

@@ -32,4 +32,4 @@ A future step that registers without wrapping its visible content in `Onboarding
 
 ## Testing
 
-`packages/client/ui-primitives/tests/onboarding-surface.spec.tsx` pins the primitive: body portal around the content, mask/stage class presence, `#root` inert held for exactly the mount lifetime, and the no-`#root` composition. `packages/client/ui-settings-general/tests/settings-root.spec.tsx` pins the inverted shell contract: no takeover chrome and no inert while a mounted step renders nothing. `apps/web/tests/onboarding-deepseek-config.e2e.ts` gains the defect's assembled regression pin: a configured world reloads while every `settings.describe` response is held open at the browser's network boundary — widening the steps' deciding window from loopback-invisible to hundreds of milliseconds, which is what keeps the assertions non-vacuous — and an 8 ms in-page sampler proves the takeover chrome never mounts and `#root` never turns inert. The file's existing scenarios and the step specs (`ui-settings-general`, `ui-models`) pass unchanged — the mask selector and geometry pins survive because the stylesheet moved verbatim.
+`packages/client/ui-primitives/tests/onboarding-surface.client.spec.tsx` pins the primitive: body portal around the content, mask/stage class presence, `#root` inert held for exactly the mount lifetime, and the no-`#root` composition. `packages/client/ui-settings-general/tests/settings-root.client.spec.tsx` pins the inverted shell contract: no takeover chrome and no inert while a mounted step renders nothing. `apps/web/tests/onboarding-deepseek-config.e2e.ts` gains the defect's assembled regression pin: a configured world reloads while every `settings.describe` response is held open at the browser's network boundary — widening the steps' deciding window from loopback-invisible to hundreds of milliseconds, which is what keeps the assertions non-vacuous — and an 8 ms in-page sampler proves the takeover chrome never mounts and `#root` never turns inert. The file's existing scenarios and the step specs (`ui-settings-general`, `ui-models`) pass unchanged — the mask selector and geometry pins survive because the stylesheet moved verbatim.

.agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.zh.md

@@ -32,4 +32,4 @@
 
 ## 测试
 
-`packages/client/ui-primitives/tests/onboarding-surface.spec.tsx` 钉住原语行为：内容外的 body portal、遮罩／展示层类名存在、`#root` 的 `inert` 恰好持续挂载生命周期，以及无 `#root` 的组合。`packages/client/ui-settings-general/tests/settings-root.spec.tsx` 钉住反转后的外壳约定：已挂载步骤什么都不渲染时，无接管界面框架、无 inert。`apps/web/tests/onboarding-deepseek-config.e2e.ts` 新增本缺陷的整装回归钉：已配置世界刷新页面，同时在浏览器网络边界扣住所有 `settings.describe` 响应——把步骤的判定窗口从 loopback 下不可见拉宽到数百毫秒，这正是断言保持非空洞的关键——页内 8ms 采样器证明接管界面框架从未挂载、`#root` 从未变为 inert。该文件的既有场景与步骤 spec（`ui-settings-general`、`ui-models`）原样通过——样式表逐字迁移，遮罩选择器与几何钉子得以幸存。
+`packages/client/ui-primitives/tests/onboarding-surface.client.spec.tsx` 钉住原语行为：内容外的 body portal、遮罩／展示层类名存在、`#root` 的 `inert` 恰好持续挂载生命周期，以及无 `#root` 的组合。`packages/client/ui-settings-general/tests/settings-root.client.spec.tsx` 钉住反转后的外壳约定：已挂载步骤什么都不渲染时，无接管界面框架、无 inert。`apps/web/tests/onboarding-deepseek-config.e2e.ts` 新增本缺陷的整装回归钉：已配置世界刷新页面，同时在浏览器网络边界扣住所有 `settings.describe` 响应——把步骤的判定窗口从 loopback 下不可见拉宽到数百毫秒，这正是断言保持非空洞的关键——页内 8ms 采样器证明接管界面框架从未挂载、`#root` 从未变为 inert。该文件的既有场景与步骤 spec（`ui-settings-general`、`ui-models`）原样通过——样式表逐字迁移，遮罩选择器与几何钉子得以幸存。

.agents/notes/implemented/bug-fix/2026-08-06-reader-scroll-attribution-observed-top-ledger.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 .agents/notes/implemented/bug-fix/2026-08-06-reader-scroll-attribution-observed-top-ledger.md
-2026-08-06-reader-scroll-attribution-observed-top-ledger.md: ef5ddbeb9bea1393f474dfb4c809ae2e19bfea5c
-2026-08-06-reader-scroll-attribution-observed-top-ledger.zh.md: 7a1142cdd793cfce46bfd3908ab28345701aec7a
+2026-08-06-reader-scroll-attribution-observed-top-ledger.md: 66a1ca361cf28bf0beab95fa81da9cac3527474c
+2026-08-06-reader-scroll-attribution-observed-top-ledger.zh.md: ce7cd6d0ade2702a6f717340cb7c9b354d0387c2

.agents/notes/implemented/bug-fix/2026-08-06-reader-scroll-attribution-observed-top-ledger.md

@@ -18,7 +18,7 @@ A shrink clamp whose layout regrows within the same rendering update before the
 
 ## Testing
 
-Unit specs in `packages/client/ui-conversation/tests/chat-view.spec.tsx` pin the ledger contract directly: a `readerScroll` helper delivers a position the component never wrote, programmatic deliveries land on the ledger, and the stream-finalization shrink clamp keeps following. Two scenarios in `apps/web/tests/chat-scroll-contract.e2e.ts` extend the [browser e2e lane](../testing/2026-07-24-web-gui-browser-e2e-lane.md): keyboard paging over a settled transcript and a touch-style momentum fling against paced streaming, both red under the wheel-only implementation and green under the ledger.
+Unit specs in `packages/client/ui-conversation/tests/chat-view.client.spec.tsx` pin the ledger contract directly: a `readerScroll` helper delivers a position the component never wrote, programmatic deliveries land on the ledger, and the stream-finalization shrink clamp keeps following. Two scenarios in `apps/web/tests/chat-scroll-contract.e2e.ts` extend the [browser e2e lane](../testing/2026-07-24-web-gui-browser-e2e-lane.md): keyboard paging over a settled transcript and a touch-style momentum fling against paced streaming, both red under the wheel-only implementation and green under the ledger.
 
 The lane's Chromium cannot synthesize any non-wheel device scrolling, which bounds what the e2e can drive for real: `Input.synthesizeScrollGesture` with a touch source and hand-rolled `Input.dispatchTouchEvent` sequences deliver DOM events but never move a scroller (headless and headed-under-Xvfb alike); the `default` gesture source synthesizes wheel events; and compositor scrollbars ignore synthetic mouse input entirely, with a gutter visible only when `--hide-scrollbars` is removed. Keyboard is the one working non-wheel primitive, so it carries the real-input-pipeline proof, and the fling scenario replays touch's signature — per-frame decaying displacements the component never authored — through the scrollport directly.
 

.agents/notes/implemented/bug-fix/2026-08-06-reader-scroll-attribution-observed-top-ledger.zh.md

@@ -18,7 +18,7 @@ ChatView 的贴底跟随此前只把滚轮／触控板手势识别为读者输
 
 ## 测试
 
-`packages/client/ui-conversation/tests/chat-view.spec.tsx` 中的单元测试直接钉住 ledger 约定：`readerScroll` 辅助函数交付一个组件从未写入过的位置，程序化交付落在 ledger 上，流收尾阶段的收缩钳制保持跟随。`apps/web/tests/chat-scroll-contract.e2e.ts` 中的两个场景扩展了[浏览器 e2e 车道](../testing/2026-07-24-web-gui-browser-e2e-lane.md)：在已停稳的 transcript 上做键盘翻页，以及对着按节奏推进的流式输出做一次触控式惯性快滑（momentum fling）；两者在仅认滚轮的实现下均为红、在 ledger 下均为绿。
+`packages/client/ui-conversation/tests/chat-view.client.spec.tsx` 中的单元测试直接钉住 ledger 约定：`readerScroll` 辅助函数交付一个组件从未写入过的位置，程序化交付落在 ledger 上，流收尾阶段的收缩钳制保持跟随。`apps/web/tests/chat-scroll-contract.e2e.ts` 中的两个场景扩展了[浏览器 e2e 车道](../testing/2026-07-24-web-gui-browser-e2e-lane.md)：在已停稳的 transcript 上做键盘翻页，以及对着按节奏推进的流式输出做一次触控式惯性快滑（momentum fling）；两者在仅认滚轮的实现下均为红、在 ledger 下均为绿。
 
 该车道的 Chromium 无法合成任何非滚轮的设备滚动，这限定了 e2e 能真实驱动的范围：触控来源的 `Input.synthesizeScrollGesture` 与手工构造的 `Input.dispatchTouchEvent` 序列都能交付 DOM 事件，却从不移动滚动容器（无头模式与 Xvfb 下的有头模式皆然）；`default` 手势来源合成的是滚轮事件；合成器滚动条则完全无视合成的鼠标输入，且只有移除 `--hide-scrollbars` 后才能看到滚动条槽。键盘是唯一可用的非滚轮原语，因此由它承担真实输入流水线的证明；快滑场景则把触控的特征（组件从未写入过的逐帧衰减位移）直接回放进滚动容器。
 

.agents/notes/implemented/bug-fix/2026-08-07-code-mode-executor-collapse.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/bug-fix/2026-08-07-code-mode-executor-collapse.md
+2026-08-07-code-mode-executor-collapse.md: 3b64675f90f830628dcde427d4388153ec7accf1
+2026-08-07-code-mode-executor-collapse.zh.md: 51b35ad44b9758805784834d1d036ba374140dd9

.agents/notes/implemented/bug-fix/2026-08-07-code-mode-executor-collapse.md

@@ -0,0 +1,46 @@
+# Agent Note: Code Mode collapses the executor, not just the wire
+
+Status: implemented
+
+English | [中文](2026-08-07-code-mode-executor-collapse.zh.md)
+
+## Problem
+
+`mode: 'code'` collapsed only the announcement surface, not the execution surface. `wireSchemas()` sent the model exactly one tool — `run_code` — but the executor resolved every call through `get()`, which returns the full visible map plus the reserved transport. A model that emitted a native tool name (`write`, `read`, `bash`, `subagent`, …) bypassed `run_code` entirely: the call traversed the normal pipeline and executed, even though no schema for it had ever been advertised. Providers do not intercept unadvertised tool names, so schema omission enforced nothing.
+
+The package contract names this exact anti-pattern: schema omission is not enforcement when a direct caller can bypass it; denial must be tested through the executor.
+
+## Decision
+
+`ToolRegistry` resolves callable definitions through a new private `resolveExecution(name, scope, nested)` that applies the mode collapse at the operation boundary that owns it. When `modeFor(scope)` resolves to `code`, a model-direct call (`nested = false`) may only name the reserved `run_code` transport; every native name resolves to `undefined` and surfaces as the executor's existing `UNKNOWN_TOOL` error, whose message names the route back through `run_code` because the name IS declared to this model (an already-aborted caller signal keeps the cancellation contract: `ABORTED_BEFORE_DISPATCH`, with the visible tool's finalizer applied). The effective scope mode includes declarations inherited from an agent preset, so its wire schema and execution permissions remain aligned. A collapsed call terminates at `createExecution` — the first stage of `prepare` — BEFORE the extensible policy pipeline, so `tools/pre-execute` listeners, approval `ask`, and guards never observe a call that is deterministically denied; a human is never prompted to approve it. A nested sub-dispatch (`nested = true` — a `parent` token set, which only the `run_code` SDK binding sets in production code) may call any visible tool, so programs keep every binding the generated SDK declared.
+
+Four execution-path lookups — `executionMode`, `dispatchToolBody`, `postExecute`, `normalizeDispatchResult` — go through `resolveExecution`. `createExecution` applies the same collapse via the shared `collapses(name, nested)` predicate so it can distinguish a collapsed call from a genuinely unknown name before the policy pipeline. The public registry view (`get`) and SDK projection (`schemas`) keep their semantics: presentation, inspection, and binding enumeration still see the full visible set. The wire (`wireSchemas`) and the executor now agree. A collapsed call with non-JSON-serializable arguments reports the parameter `TypeError` (the invalid-args contract), not `UNKNOWN_TOOL` — the body still never runs and policy still does not.
+
+The collapse is a security-relevant invariant, so acceptance is pinned through the executor: a model-direct native call under `code` returns `UNKNOWN_TOOL`, the same tool via an SDK sub-dispatch succeeds, and `native`/`both` direct calls plus `run_code` itself are unchanged. The base [Code Mode foundation](../feature/2026-06-15-code-mode.md) owns the transport design this note layers the execution boundary onto.
+
+## Alternatives considered
+
+### Filter `get()` / the registry view by mode
+
+The view is consumed by presenters, `tool-cordis` inspection, and the SDK binder; collapsing it would hide from the program surface tools that must still bind, and would change the public resolution contract for every consumer, not just the executor.
+
+### Filter at the agent-loop entry
+
+The loop is not the only executor caller, and the distinction that matters (model-direct vs transport sub-dispatch) rides on the execution input, not at the loop boundary. An entry filter would also re-encode mode semantics the registry already owns.
+
+### Reject via a shipped guard
+
+Guards are an optional plugin extension; a security invariant must not depend on a deployment composing the right plugin. The registry owns the mode decision and must enforce it itself.
+
+### Keep schema omission only (status quo)
+
+No provider guarantees interception of unadvertised names; the reported session proves it does not happen.
+
+## Consequences
+
+- `mode: 'code'` now enforces what it announces: a model-direct native call becomes `UNKNOWN_TOOL`, which the model can correct by routing through `run_code` (a pre-aborted call still resolves `ABORTED_BEFORE_DISPATCH`, per the cancellation contract).
+- `both` and `native` behavior is unchanged; SDK sub-dispatches are unchanged (the `parent` token is the discriminator).
+- A collapsed call is rejected at `prepare`, BEFORE the extensible policy pipeline: pre-execute listeners, approval `ask`, and guards never observe it. `executionMode` also fails closed (`exclusive`), so scheduling has no observable difference.
+- Native-tool guidance sections (`tool:read`, `tool:write`, `tool:bash`, etc.) remain in the system prompt because they describe capabilities available through the generated SDK as well as native function calls, and several carry cross-tool routing policy (`read` over `bash cat`, `read` before `write` for the default fs-policy, `subagent` over `workflow`) that no single tool description can hold. The executor collapse, not prompt filtering, prevents model-direct native calls.
+- The prompt STATES the collapse, in the `tools:code-only` section ordered ahead of the 100-199 guidance band. Those sections name their tool without qualifying how it is reached, so a model that read only them emitted a native call, received `UNKNOWN_TOOL` for a tool the same prompt declared, and concluded the deployment was inconsistent rather than correcting itself. The denial carries the route for the same reason. `both` renders the rule empty: its native calls do execute, so stating it there would be false — which is why `both-mode-turn` no longer shares `code-mode-turn`'s expected prompt.
+- Any future composite transport that sets a `parent` token opts its sub-dispatches into the full table, matching the nested-call semantics the token already documents.

.agents/notes/implemented/bug-fix/2026-08-07-code-mode-executor-collapse.zh.md

@@ -0,0 +1,46 @@
+# Agent Note: Code Mode 塌缩执行器而非仅通告面
+
+Status: implemented
+
+[English](2026-08-07-code-mode-executor-collapse.md) | 中文
+
+## 问题
+
+`mode: 'code'` 只塌缩了通告面，没有塌缩执行面。`wireSchemas()` 只向模型发送一个工具——`run_code`——但执行器通过 `get()` 解析所有调用，而 `get()` 返回完整的可见工具表外加保留的传输工具。模型一旦发出原生工具名（`write`、`read`、`bash`、`subagent` 等），就能完全绕过 `run_code`：调用照常走完整流水线并执行成功，尽管它的 schema 从未被通告过。模型提供方不拦截未通告的工具名，因此不发 schema 等于没有约束。
+
+包契约点名了这个反模式：当直接调用方可以绕过时，schema 省略不算强制执行；拒绝必须经执行器验证。
+
+## 决策
+
+`ToolRegistry` 通过新增的私有 `resolveExecution(name, scope, nested)` 解析可执行定义，在拥有该决策的操作边界上应用模式塌缩。当 `modeFor(scope)` 解析为 `code` 时，模型直呼（`nested = false`）只允许命名保留的 `run_code` 传输工具；任何原生名字都解析为 `undefined`，并以执行器既有的 `UNKNOWN_TOOL` 错误呈现，其消息会指出改走 `run_code` 的正确路径——因为这个名字对当前模型而言是**已声明过**的（已中止的调用方 signal 保留取消契约：`ABORTED_BEFORE_DISPATCH`，并应用可见工具的 finalizer）。有效的 scope 模式包括从 agent preset 继承的声明，因此其 wire schema 与执行权限保持一致。被塌缩的调用在 `createExecution`（`prepare` 的第一阶段）即终止——在可扩展策略流水线之前，因此 `tools/pre-execute` 监听器、approval `ask` 与 guard 永远不会观察到一个注定被拒绝的调用，人类也不会被提示去批准它。嵌套子调用（`nested = true`——即设置了 `parent` token，生产代码中只有 `run_code` SDK 绑定会设置）可以调用任意可见工具，因此程序保留生成 SDK 声明的全部绑定。
+
+执行链路的四处查表——`executionMode`、`dispatchToolBody`、`postExecute`、`normalizeDispatchResult`——改走 `resolveExecution`。`createExecution` 通过共享的 `collapses(name, nested)` 谓词应用同一塌缩，以便在策略流水线之前区分被塌缩的调用与真正未知的名字。公共注册表视图（`get`）与 SDK 投影（`schemas`）语义不变：展示、检查与绑定枚举仍看到完整可见集合。通告（`wireSchemas`）与执行器现在一致。带非 JSON 可序列化参数的塌缩调用报告参数 `TypeError`（invalid-args 契约），而非 `UNKNOWN_TOOL`——函数体仍不会运行，策略也不会执行。
+
+塌缩是安全相关的不变量，因此验收经执行器钉死：`code` 模式下模型直呼原生工具返回 `UNKNOWN_TOOL`；同一工具经 SDK 子调用成功；`native`/`both` 模式直呼与 `run_code` 本身行为不变。本 note 把执行边界叠加在基础 [Code Mode 基础](../feature/2026-06-15-code-mode.md) 之上，传输设计由后者拥有。
+
+## 备选方案
+
+### 按模式过滤 `get()` / 注册表视图
+
+视图被展示方、`tool-cordis` 检查与 SDK 绑定消费；塌缩视图会从程序表面隐藏仍必须绑定的工具，并改变所有消费者的公共解析契约，而不只是执行器。
+
+### 在 agent-loop 入口过滤
+
+loop 不是唯一的执行器调用方，且真正要紧的区分（模型直呼 vs 传输子调用）挂在执行输入上，不在 loop 边界。入口过滤还会重复编码注册表已经拥有的模式语义。
+
+### 通过内置 guard 拒绝
+
+guard 是可选的插件扩展；安全不变量不能依赖部署恰好组装了正确的插件。模式决策归注册表所有，必须由它自己执行。
+
+### 只保留 schema 省略（维持现状）
+
+没有提供方保证拦截未通告的名字；被报告的会话证明拦截不会发生。
+
+## 后果
+
+- `mode: 'code'` 现在兑现其通告：模型直呼原生工具变为 `UNKNOWN_TOOL`，模型可以通过改走 `run_code` 自行纠正（已中止的调用仍按取消契约解析为 `ABORTED_BEFORE_DISPATCH`）。
+- `both` 与 `native` 行为不变；SDK 子调用不变（判别信号是 `parent` token）。
+- 被塌缩的调用在 `prepare` 阶段即被拒绝——在可扩展策略流水线之前：pre-execute 监听器、approval `ask` 与 guard 永远不会观察到它。`executionMode` 同样 fail-closed（`exclusive`），调度无可观察差异。
+- 原生工具指引段（`tool:read`、`tool:write`、`tool:bash` 等）保留在系统提示词中，因为它们同时描述了通过生成 SDK 及原生函数调用可用的能力，其中若干段还承载着任何单个工具描述都装不下的跨工具路由策略（`read` 优先于 `bash cat`、默认 fs-policy 要求先 `read` 再 `write`、一两个委派用 `subagent` 而非 `workflow`）。防止模型直呼原生工具的是执行器塌缩，而非提示词过滤。
+- 提示词会**声明**这条塌缩，位于排在 100–199 指导段之前的 `tools:code-only` 段。那些段只写出工具名而不限定其可达方式，因此只读到它们的模型会发出原生调用，为一个同一份提示词刚刚声明过的工具收到 `UNKNOWN_TOOL`，进而判定部署不一致，而不是自行纠正。拒绝信息给出正确路径也是同一原因。`both` 下该规则渲染为空：它的原生调用确实会执行，在那里声明就是假话——这也是 `both-mode-turn` 不再与 `code-mode-turn` 共用期望提示词的原因。
+- 未来任何设置 `parent` token 的组合传输，其子调用自动走全表，与该 token 已有的嵌套调用语义一致。

.agents/notes/implemented/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.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 .agents/notes/implemented/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.md
-2026-08-11-preset-authoring-agent-validates-its-own-composition.md: 6b9cdf32b70e3ab4adc9f3b0e20bb3d2245486c7
-2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md: e6e8dabcd886a6331d294744b667552caa01e7b4
+2026-08-11-preset-authoring-agent-validates-its-own-composition.md: eb21094f0d859a31d5f16d780cada6818a508b36
+2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md: 02c245348a9c7e9968472044d7ff95e1ff21120c

.agents/notes/implemented/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.md

@@ -32,7 +32,9 @@ The agent reaches the roster service the way `cordis_mount` documents: a tempora
 
 "Whether a row publishes a service" resolves through `cordis_inspect what:"services"`, which names the owning fiber of every live service.
 
-The guidance keeps `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` as the answer to "where do my presets live" — it is where every `dsh` launcher puts them — while routing the path an agent actually reads or edits through `list()` or `resolve()`. `Config.roots` defaults to `[]` and `apps/cli` patches both roots in, `writableRoot()` takes the first `user` one, and no call reports either path; `authorable` answers only whether a writable root exists, and `list()` cannot reveal a user root that holds nothing yet. Stating the path is therefore right for talking to a person and wrong for feeding a file tool.
+The guidance keeps `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` as the answer to "where do my presets live" while routing the path an agent actually reads or edits through `list()` or `resolve()`. Stating the path is right for talking to a person and wrong for feeding a file tool: a deployment may configure other roots, and `list()` cannot reveal a user root that holds nothing yet.
+
+That path is now a property of the package rather than of one launcher. `AgentPresets` derives `<dshHome>/.agent-presets` as a `user` root unless `includeUserRoot` is false, the way [`dsh-skill-local`](../../../../packages/skill/skill-local/README.md) derives `<dshHome>/skills`, and `apps/cli` supplies only the SHIPPED root — the one path an installed app alone can resolve. The asymmetry it replaces cost a bug: with both roots patched in by one launcher, `dsh run` booted a roster with no roots at all and failed resolving `standard` (fixed then by teaching every launcher the patch). The derived root is appended after every configured root, so a shipped id still shadows a home directory claiming it, and `writableRoot()` still prefers an explicitly configured `user` root. It is resolved once at construction: a root set that changed between a `list()` and the `copy()` acting on its answer would author into a directory the caller never saw.
 
 The prohibition on touching the shipped install is promoted from a paragraph inside the authoring steps to a top `## Off-limits` section, extended to cover editing the host composition as a workaround. The new self-validation calls do not weaken it: `copy()` refuses an id any root supplies, and `remove()` refuses a preset that ships with the deployment.
 

.agents/notes/implemented/bug-fix/2026-08-11-preset-authoring-agent-validates-its-own-composition.zh.md

@@ -32,7 +32,9 @@ agent 按 `cordis_mount` 自身文档所述的方式够到 roster 服务：挂
 
 「某行是否发布服务」改由 `cordis_inspect what:"services"` 回答，它会给出每个存活服务的持有 fiber。
 
-指导保留 `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` 作为「我的 preset 在哪」的答案——每个 `dsh` 启动器都把它们放在那里——同时把 agent 实际读取或编辑的路径改走 `list()` 或 `resolve()`。`Config.roots` 默认为 `[]`，两个根均由 `apps/cli` 补入，`writableRoot()` 取其中第一个 `user` 根，且没有任何调用会报告任一路径；`authorable` 只回答是否存在可写根，而 `list()` 无法揭示一个尚且为空的用户根。因此写出该路径对人讲是对的，喂给文件工具是错的。
+指导保留 `${DSH_HOME:-$HOME/.dsh}/.agent-presets/` 作为「我的 preset 在哪」的答案，同时把 agent 实际读取或编辑的路径改走 `list()` 或 `resolve()`。写出该路径对人讲是对的，喂给文件工具是错的：部署可以配置其他根目录，而 `list()` 无法揭示一个尚且为空的用户根。
+
+该路径如今是本包的属性，而非某个启动器的属性。除非 `includeUserRoot` 为 false，`AgentPresets` 自行推导 `<dshHome>/.agent-presets` 作为 `user` 根，正如 [`dsh-skill-local`](../../../../packages/skill/skill-local/README.md) 推导 `<dshHome>/skills`；`apps/cli` 只提供**随附**根——那是唯有已安装 app 才能解析的路径。它取代的那种不对称曾付出过代价：两个根都由单一启动器补入时，`dsh run` 启动的 roster 一个根都没有，解析 `standard` 直接失败（当时的修法是让每个启动器都执行该 patch）。推导出的根追加在全部已配置根之后，因此随附 id 仍会遮蔽占用它的家目录目录，而 `writableRoot()` 仍优先选择显式配置的 `user` 根。它在构造时解析一次：若根目录集合在一次 `list()` 与依据其答案执行的 `copy()` 之间发生变化，写入的将是调用方从未见过的目录。
 
 禁止改动随发布安装的约束，从创作步骤中的一段提升为顶部的 `## Off-limits` 一节，并扩展到禁止改宿主组装绕行。新增的自校验调用不削弱它：`copy()` 拒绝任何根已提供的 id，`remove()` 拒绝随部署发布的 preset。
 

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.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 .agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md
-2026-07-20-dsh-cli-personal-config.md: ed04725e92848bbab550a27ef2f4c021536f765e
-2026-07-20-dsh-cli-personal-config.zh.md: cc97987f803f7fb513e94ce0ce079558f5e3dc75
+2026-07-20-dsh-cli-personal-config.md: bc2aff322de01bb9c6beebb1679b2ff9909d1fe3
+2026-07-20-dsh-cli-personal-config.zh.md: 507a7188a4a77d904e3204499290f3ed22abab2c

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md

@@ -6,7 +6,7 @@ English | [中文](2026-07-20-dsh-cli-personal-config.zh.md)
 
 ## Problem
 
-A developer's own preferences — which provider and model the TUI uses, personal credentials, a private adapter route — had nowhere to live except edits to committed files. Pointing the TUI demo at a personal Anthropic-proxy Opus route meant patching `examples/tui-agent/cordis.yml` and `.env` in the working tree, which risks committing secrets and repeats per checkout. There was also no installable command: running the agent in an arbitrary project directory required invoking the repo's demo script from the repo root. Loader metadata is static, so "conditional composition uses overlays" (AGENTS.md) — but overlays only existed as committed sibling files, not as a machine-level layer.
+A developer's own preferences — which provider and model the TUI uses, personal credentials, a private adapter route — had nowhere to live except edits to committed files. Pointing the TUI demo at a personal Anthropic-proxy Opus route meant patching `examples/tui-agent/cordis.yml` and `.env` in the working tree, which risks committing secrets and repeats per checkout. There was also no installable command: running the agent in an arbitrary project directory required invoking the repo's demo script from the repo root. Loader metadata is static except the entry `disabled` field (see the [loader `disabled` interpolation decision](../architecture/2026-08-11-loader-entry-disabled-interpolation.md)), so "conditional composition uses overlays" (AGENTS.md) — but overlays only existed as committed sibling files, not as a machine-level layer.
 
 ## Decision
 

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md

@@ -6,7 +6,7 @@ Status: implemented
 
 ## Problem
 
-开发者自己的偏好——TUI 使用哪个提供方和模型、个人凭证、私有的适配器路由——除了改动已提交的文件之外无处安放。要把 TUI 示例指向个人的 Anthropic 代理 Opus 路由，只能在工作区里改 `examples/tui-agent/cordis.yml` 和 `.env`，既有提交密钥的风险，又要在每个 checkout 里重复一遍。也没有可安装的命令：想在任意项目目录里运行这个 agent，必须回到仓库根目录调用示例脚本。Loader 元数据是静态的，所以「条件组合使用 overlay」（AGENTS.md）——但 overlay 此前只以已提交的同级文件形式存在，没有机器级的层。
+开发者自己的偏好——TUI 使用哪个提供方和模型、个人凭证、私有的适配器路由——除了改动已提交的文件之外无处安放。要把 TUI 示例指向个人的 Anthropic 代理 Opus 路由，只能在工作区里改 `examples/tui-agent/cordis.yml` 和 `.env`，既有提交密钥的风险，又要在每个 checkout 里重复一遍。也没有可安装的命令：想在任意项目目录里运行这个 agent，必须回到仓库根目录调用示例脚本。Loader 元数据是静态的——条目 `disabled` 字段除外（见 [loader `disabled` 插值决策](../architecture/2026-08-11-loader-entry-disabled-interpolation.md)）——所以「条件组合使用 overlay」（AGENTS.md）；但 overlay 此前只以已提交的同级文件形式存在，没有机器级的层。
 
 ## Decision
 

.agents/notes/implemented/feature/2026-07-23-web-todo-display.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 .agents/notes/implemented/feature/2026-07-23-web-todo-display.md
-2026-07-23-web-todo-display.md: bb66ef8512badea090b3b22030eef3f43f3b1119
-2026-07-23-web-todo-display.zh.md: 5b3534e20956a4412814a782532d1337c08ff027
+2026-07-23-web-todo-display.md: 3d6720bca80cbcfa4d163d91c0fdffe5e7ed624f
+2026-07-23-web-todo-display.zh.md: 692993731d921ed9502dc66d1ca60e1ed0648c0a

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

@@ -33,4 +33,4 @@ The dedicated `todo_write` chat row is a plain registrant plugin (`todoToolview`
 
 ## 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 71) plus `packages/client/ui-conversation/tests/todo-panel.spec.tsx` pin the full chain (row summary and state, dock panel content, collapse round-trip). `todos` is a required `ConversationSnapshot` field, so scripted fakes in specs must carry it. 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 standing plan (latest `todo/write` with no later `turn/start`), computed independently of the page window (the same backscan posture the view pairing uses) — so a reopened session restores the plan when it still stands and the last write precedes the window; that value survives an older-page prepend, is overwritten by any later write, clears on a later `turn/start`, and resets to empty when a tail response carries no projection.
+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 71) plus `packages/client/ui-conversation/tests/todo-panel.client.spec.tsx` pin the full chain (row summary and state, dock panel content, collapse round-trip). `todos` is a required `ConversationSnapshot` field, so scripted fakes in specs must carry it. 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 standing plan (latest `todo/write` with no later `turn/start`), computed independently of the page window (the same backscan posture the view pairing uses) — so a reopened session restores the plan when it still stands and the last write precedes the window; that value survives an older-page prepend, is overwritten by any later write, clears on a later `turn/start`, and resets to empty when a tail response carries no projection.

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

@@ -33,4 +33,4 @@ Status: implemented
 
 ## 后果
 
-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会自然保持 todos 一致；fx-alpha 第 71 轮的 fixture（测试前置数据）加上 `packages/client/ui-conversation/tests/todo-panel.spec.tsx` 固定整条链（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。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。这个由 host 提供的字段正是冷加载重建的依据：history 尾页附带 `todos`——全量 log 上当前有效的计划（其后没有更晚 `turn/start` 的最近一次 `todo/write`），独立于分页窗口计算（与 view 配对同一种 backscan 姿势）——因此重开会话时若计划仍然有效且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，更晚的 `turn/start` 会清空，而尾页响应不带投影时复位为空。
+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会自然保持 todos 一致；fx-alpha 第 71 轮的 fixture（测试前置数据）加上 `packages/client/ui-conversation/tests/todo-panel.client.spec.tsx` 固定整条链（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。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。这个由 host 提供的字段正是冷加载重建的依据：history 尾页附带 `todos`——全量 log 上当前有效的计划（其后没有更晚 `turn/start` 的最近一次 `todo/write`），独立于分页窗口计算（与 view 配对同一种 backscan 姿势）——因此重开会话时若计划仍然有效且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，更晚的 `turn/start` 会清空，而尾页响应不带投影时复位为空。

.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.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 .agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md
-2026-07-25-session-list-browsing-and-manual-order.md: 3d2125bdf67a70a1a5bca43c5d5acb09fda178b7
-2026-07-25-session-list-browsing-and-manual-order.zh.md: 161ebd2857073d4dd9cfc2883880cd3e2d91c040
+2026-07-25-session-list-browsing-and-manual-order.md: 52a0fe0c94106cb4178c57e737b1c9a3f458f803
+2026-07-25-session-list-browsing-and-manual-order.zh.md: a6c44579c685479ca460da8e52ea885f20e4776b

.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md

@@ -14,7 +14,7 @@ Two existing mechanisms stood in the way. First, the host durably promoted the a
 
 ### Flat rows and viewing state
 
-The group-by menu offers two modes, WorkSpace / In one list. WorkSpace mode renders peer session rows within each group in the manual order from `WorkspaceView.sessionIds`; In one list combines every session and sorts them strictly newest-first by `updatedAt`. Neither mode projects `parentId` into a list hierarchy; fork lineage remains session data only. [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the complete fork behavior. The mode choice persists in the browser (`dsh.workspace.view`) across reloads.
+The group-by menu offers two modes, WorkSpace / In one list. WorkSpace mode renders peer session rows within each group in the manual order from `WorkspaceView.sessionIds`; In one list combines every session and sorts them strictly newest-first by `updatedAt`. Neither mode projects `parentId` into a list hierarchy; fork lineage remains session data only. [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the complete fork behavior. The mode choice persists in the browser (`dsh.workspace.view`) across reloads. [Workspace Sidebar Order and Folding](2026-08-11-workspace-sidebar-order-and-folding.md) later added a browser-local recent-update view without changing the Host account's manual-order authority.
 
 ### Row interactions
 
@@ -50,7 +50,7 @@ ui-sidebar shrinks to the column-geometry shell: brand row, fold state machine,
 
 ## Consequences
 
-- Manual order is the sole authority over the workspace account: an order the user arranges is never scrambled by activity; the cost is losing float-to-top-on-activity, whose signal now rides the row status dot and time label. The `WorkspaceView.sessionIds` wire contract is reworded to the manual-order semantics.
+- Manual order is the sole authority over the Host workspace account: activity never mutates `WorkspaceView.sessionIds`. A later browser-local recent-update view may promote active rows without changing that account; its separate semantics are defined in [Workspace Sidebar Order and Folding](2026-08-11-workspace-sidebar-order-and-folding.md).
 - The two-fact shell/region contract funnels every future workspace-domain feature (Delete confirmation, cross-group moves, Ungrouped adoption) into the single ui-workspace package; ui-sidebar no longer evolves with session-list features.
 - Flat mode supports neither reordering nor a create-in-workspace entry point (switching back to grouped view is required) — an accepted scope reduction.
 - Wiring session Delete and growing the wire status enum remain future iterations.

.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.zh.md

@@ -14,7 +14,7 @@ Status: implemented
 
 ### 平铺行与浏览态
 
-group-by 菜单提供 WorkSpace / In one list 两种模式。WorkSpace 模式按 `WorkspaceView.sessionIds` 的手动序在各组内展示同级 session 行；In one list 把所有 session 合并后严格按 `updatedAt` 新→旧排序。两种模式都不把 `parentId` 投影成列表层级，fork 谱系只保留为 session 数据；完整 fork 行为由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。模式选择持久化在浏览器(`dsh.workspace.view`),刷新保持。
+group-by 菜单提供 WorkSpace / In one list 两种模式。WorkSpace 模式按 `WorkspaceView.sessionIds` 的手动序在各组内展示同级 session 行；In one list 把所有 session 合并后严格按 `updatedAt` 新→旧排序。两种模式都不把 `parentId` 投影成列表层级，fork 谱系只保留为 session 数据；完整 fork 行为由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。模式选择持久化在浏览器(`dsh.workspace.view`),刷新保持。[Workspace 侧边栏顺序与折叠](2026-08-11-workspace-sidebar-order-and-folding.md)随后加入浏览器本地的最近更新视图，而未改变 Host 记账的手动顺序权威。
 
 ### 行交互
 
@@ -50,7 +50,7 @@ ui-sidebar 缩为列几何壳:品牌行、折叠状态机、New Session、Settin
 
 ## Consequences
 
-- 手动序是唯一的 workspace 账本序权威:用户排好的顺序不再被活动打乱;代价是「最近活跃浮到最上」的行为消失,活跃感知转由行内状态点与时间标签承担。`WorkspaceView.sessionIds` 的 wire 约定随之改为手动序措辞。
+- 手动序是 Host workspace 账本的唯一顺序权威：活动绝不改动 `WorkspaceView.sessionIds`。后续加入的浏览器本地最近更新视图可以把活跃行提到最前，但不会改变该账本；其独立语义见 [Workspace 侧边栏顺序与折叠](2026-08-11-workspace-sidebar-order-and-folding.md)。
 - 壳/区域两事实约定把 workspace 域的后续功能(Delete 确认、跨组移动、Ungrouped 收编)全部收进 ui-workspace 单包;ui-sidebar 不再随 session 列表功能演进。
 - 平铺模式不支持排序与分组入口(建到指定 workspace 需切回分组视图),是拍板接受的范围收窄。
 - session Delete 的功能接线与状态枚举扩 wire,留待后续迭代。

.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.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 .agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md
-2026-07-25-workspace-ui-product-flow.md: 98e963195126df2ec8291a11b3d9fc7a2baeb0df
-2026-07-25-workspace-ui-product-flow.zh.md: 486093be0b8d10c2ae0b8083b305ecad5386351c
+2026-07-25-workspace-ui-product-flow.md: 76d279bf2101d7487fe4f5231c7cea4809e166f4
+2026-07-25-workspace-ui-product-flow.zh.md: e15ead7b437d8f2324f7ea51222eb4fcfb4a9e4a

.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.md

@@ -20,6 +20,7 @@ The Host provides the following GUI wiring on the Workspace entity:
 | --- | --- |
 | `workspace.list` | Returns persistent Workspaces in order and filters out Session ids that fail header validation |
 | `workspace.create({ path })` | Adopts an existing directory by canonical path; basename-derived display titles may repeat |
+| `workspace.insertBefore({ workspaceId, beforeWorkspaceId? })` | Moves one Workspace within durable registry order and returns the complete committed order |
 | `workspace.delete({ workspaceId })` | Removes the Workspace registration while retaining its directory and session logs; its Sessions become Ungrouped |
 | `session.create({ workspaceId, sessionId? })` | Resolves cwd from the Workspace, idempotently creates a Session with an optional preallocated id, and attaches it |
 | `session.create({ cwd })` | Remains available to non-Workspace callers and creates an Ungrouped Session |
@@ -49,7 +50,7 @@ On initial entry, the application waits until both the Workspace and Session bas
 
 When no Workspace exists, the page creates a frontend Workspace object named `workspace` and a frontend Session that targets it. Neither writes to the Host, and the composer always accepts input; the first send materializes the Workspace, attaches the Session, and sends the message in that order.
 
-Top-level New Session, the plus button on a Workspace row, and the Workspace picker all invoke the same New Session action. An explicit Workspace id becomes the target directly; when none is specified, the action uses the most recent Workspace, or the Workspace Intent if no real Workspace exists. The Workspace picker's one Add workspace action ([one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md); it was a pair of Use-an-existing-folder and create-by-name actions when this was decided) immediately creates a real Workspace when the user confirms a directory, then retargets the frontend Session to it; an explicitly created empty Workspace remains even if the user sends no message.
+Top-level New Session, the plus button on a Workspace row, and the Workspace picker all invoke the same New Session action. An explicit Workspace id becomes the target directly; when none is specified, the action uses the current Session's Workspace, then the most recent Workspace, and enters the blank New Session page when no real Workspace exists. The Workspace picker's one Add workspace action ([one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md); it was a pair of Use-an-existing-folder and create-by-name actions when this was decided) immediately creates a real Workspace when the user confirms a directory, then retargets the frontend Session to it; an explicitly created empty Workspace remains even if the user sends no message.
 
 A new Workspace takes its display name from the directory it was created in. Distinct canonical paths may share the same basename-derived title ([identity decision](../bug-fix/2026-07-31-same-basename-workspace-adoption.md)); the explicit rename operation retains its duplicate-title check. Moving Sessions across Workspaces, manual adoption from Ungrouped, and separate display-name and directory-name inputs remain outside this flow.
 
@@ -67,11 +68,11 @@ Lost RPC responses, Host frames arriving before completions, and completions arr
 
 ### Sidebar and ordering
 
-Workspace groups strictly follow the persistent order returned by the Host. Bootstrap determines the historical order once, explicitly created Workspaces are placed first, and Session activity does not move Workspace groups.
+Workspace groups follow the persistent order returned by the Host. Bootstrap determines the historical order once, explicitly created Workspaces are placed first, and `workspace.insertBefore` durably applies user drag order. Session activity does not move Workspace groups.
 
-Within each group, order strictly follows `Workspace.sessionIds`. A newly attached Session is placed first; when a Session later becomes active, the Host moves only that id to the front and persists the change. The Client does not reorder the entire group by time after the Session list arrives, so it never displays one Workspace order and then jumps to another during hydration.
+The Host account remains the manual `Workspace.sessionIds` order: a newly attached Session is placed first and activity does not mutate it. The grouped browser can instead select a browser-local recent-update view that promotes a Session when its `updatedAt` advances and remains manually editable. Five Sessions are visible per open Workspace until the user transiently expands the remainder. The durable Workspace reorder and browser-local Session order are defined in [Workspace Sidebar Order and Folding](2026-08-11-workspace-sidebar-order-and-folding.md).
 
-A frontend Session Intent appears as a “New session” row and temporarily counts toward the group's Session total only when it targets a real Workspace. When it targets a Workspace Intent, neither the Workspace nor the Session appears in the sidebar. After the Intent is published, the real row with the same preallocated id takes its place; after refresh, both the Intent row and temporary count disappear. Search mode neither retains nor filters Intent rows.
+The current blank Session appears as a “New session” row without a count, time label, or row menu; other blank Sessions remain hidden and eligible for per-Workspace reuse. Search excludes blank rows.
 
 Real Sessions that cannot be assigned to any Workspace appear under Ungrouped. Host `session-added` and `workspace-changed` events may arrive in either order; list merging does not depend on frame order.
 
@@ -105,15 +106,15 @@ The Sidebar and conversation empty hero receive standardized actions through slo
 - Frontend Sessions and Workspaces preserve object identity across materialization; input, errors, focus, and sidebar projections always originate from the object layer.
 - The first send advances through Workspace, Session, and prompt in order; successful stages are not rolled back, input is not lost before the prompt is accepted, and creation retries use the same SessionId.
 - Workspace list performs one reentrant bootstrap using only headers; an initialized empty registry does not initialize again after restart, and membership reads validate both the index and canonical cwd.
-- The initial default target is determined exactly once after both baselines are ready; Workspace groups are not reordered as a whole by hydration or Session activity, and an active Session moves only itself to the front.
-- A frontend Session under a real Workspace temporarily counts toward the sidebar total, while a Workspace Intent remains hidden; neither publication nor refresh leaves duplicate rows or counts.
+- The initial default target is determined exactly once after both baselines are ready; Workspace groups are not reordered by hydration or Session activity, and explicit Workspace drag order survives reconnect.
+- The current blank Session can appear as a single New Session row without exposing other reusable blanks or a Session count.
 - The UI and Host admit distinct same-basename directories as separate Workspaces, while the explicit rename operation rejects duplicate titles; cwd-only Sessions, Sessions with invalid historical cwd values, and unattached Sessions remain Ungrouped.
 - Confirmed Workspace deletion removes only the registration, retains the current Session, directory, files, and session log, and survives reload; package tests pin unary/frame/baseline races and failure rollback.
 - Keyless runnable snapshots cover the zero state, explicit creation, and the first send; package-level tests cover bootstrap, membership validation, ordering, idempotency, failure recovery, and arbitrary frame order.
 
 ## Consequences
 
-- SessionHeader does not record last-active time, so historical bootstrap can initialize order only by `createdAt`; real Session activity events move individual entries afterward.
+- SessionHeader does not record last-active time, so historical bootstrap can initialize the Host manual order only by `createdAt`; the browser's optional recent-update view begins from Session summaries after hydration.
 - Historical Sessions with a missing cwd, an invalid directory, or a failed realpath remain Ungrouped; this iteration has no manual-adoption entry point.
 - Refreshing the page discards unmaterialized Workspace and Session Intents and input not yet accepted by the Host; this is the page-local contract.
 - Explicit Create Workspace writes to disk immediately, so leaving without sending still leaves an empty Workspace.

.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md

@@ -20,6 +20,7 @@ Host 在 Workspace entity 上提供以下 GUI 接线：
 | --- | --- |
 | `workspace.list` | 返回持久有序的 Workspace，并过滤未通过 header 校验的 Session id |
 | `workspace.create({ path })` | 按 canonical path 收编已有目录；由 basename 派生的显示名可以重复 |
+| `workspace.insertBefore({ workspaceId, beforeWorkspaceId? })` | 在持久注册表顺序内移动一个 Workspace，并返回完整的已提交顺序 |
 | `workspace.delete({ workspaceId })` | 移除 Workspace 注册记录，同时保留目录和会话日志；相关 Session 进入 Ungrouped |
 | `session.create({ workspaceId, sessionId? })` | 从 Workspace 解析 cwd，以可选预分配 id 幂等创建 Session 并 attach |
 | `session.create({ cwd })` | 保留给非 Workspace 调用方，创建 Ungrouped Session |
@@ -49,7 +50,7 @@ Session 自己持有首条输入并驱动一条内部流水线：必要时以预
 
 完全没有 Workspace 时，页面创建默认名为 `workspace` 的前端 Workspace 对象和指向它的前端 Session。两者不写 Host，composer 始终可输入；首次发送才依次 materialize Workspace、attach Session、发送消息。
 
-顶部 New Session、Workspace 行内加号和 Workspace picker 最终都调用同一 New Session 动作：显式 Workspace id 直接成为目标，未指定时使用最近 Workspace，没有真实 Workspace 时使用 Workspace Intent。Workspace picker 的单一 Add workspace 动作（见[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)；本决策做出时是 Use an existing folder 与按名称创建两个动作）会在用户确认目录时立即创建真实 Workspace，再把前端 Session 定位到该 Workspace；即使用户不发送消息，显式创建的空 Workspace 也保留。
+顶部 New Session、Workspace 行内加号和 Workspace picker 最终都调用同一 New Session 动作：显式 Workspace id 直接成为目标，未指定时先使用当前 Session 所属 Workspace，再使用最近 Workspace；没有真实 Workspace 时进入空白 New Session 页面。Workspace picker 的单一 Add workspace 动作（见[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md)；本决策做出时是 Use an existing folder 与按名称创建两个动作）会在用户确认目录时立即创建真实 Workspace，再把前端 Session 定位到该 Workspace；即使用户不发送消息，显式创建的空 Workspace 也保留。
 
 新建 Workspace 的显示名取自其所在目录。不同 canonical path 可以拥有相同的 basename 派生显示名（见[身份决策](../bug-fix/2026-07-31-same-basename-workspace-adoption.md)）；显式的重命名操作仍保留显示名重名检查。跨 Workspace 移动 Session、从 Ungrouped 手动收编以及分别输入显示名和目录名仍不在此动线范围内。
 
@@ -67,11 +68,11 @@ RPC 响应丢失、Host frame 先于 completion 和 completion 先于 Host frame
 
 ### Sidebar 与排序
 
-Workspace 组严格使用 Host 返回的持久顺序。Bootstrap 一次性确定历史顺序，显式创建的新 Workspace 放在首位；Session 活跃不会移动 Workspace 组。
+Workspace 组使用 Host 返回的持久顺序。Bootstrap 一次性确定历史顺序，显式创建的新 Workspace 放在首位，`workspace.insertBefore` 则持久应用用户拖拽顺序；Session 活跃不会移动 Workspace 组。
 
-组内严格使用 `Workspace.sessionIds`。新 attach 的 Session 放在首位，后续某个 Session 活跃时 Host 只前移该 id 并持久化。Client 不在 Session list 到达后按时间整体重排，因此不会先显示一套 Workspace 顺序再因 hydration 瞬间跳动。
+Host 记账保持手动的 `Workspace.sessionIds` 顺序：新 attach 的 Session 放在首位，活动不会改动该顺序。分组浏览器可以改选浏览器本地的最近更新视图；当 Session 的 `updatedAt` 增大时该视图会把它移到首位，同时仍允许手动调整。每个打开的 Workspace 默认显示五条 Session，用户可临时展开其余条目。持久 Workspace 重排序和浏览器本地 Session 顺序见 [Workspace 侧边栏顺序与折叠](2026-08-11-workspace-sidebar-order-and-folding.md)。
 
-前端 Session Intent 只有在目标是真实 Workspace 时才作为 「New session」 行显示，并临时计入该组 Session 数量；目标是 Workspace Intent 时，Workspace 与 Session 都不进入 sidebar。Intent 发布后由同一预分配 id 对应的真实行接替，刷新后 Intent 行和临时计数一起消失。搜索模式不保存或筛选 Intent 行。
+当前空白 Session 会显示为一条「New session」行，但不显示数量、时间标签或行菜单；其他空白 Session 保持隐藏，并可由对应 Workspace 复用。搜索会排除空白行。
 
 无法归入任何 Workspace 的真实 Session 进入 Ungrouped。Host `session-added` 与 `workspace-changed` 可以任意顺序到达，列表合并不依赖 frame 顺序。
 
@@ -105,15 +106,15 @@ Sidebar 与 conversation empty hero 通过 slot 获得标准化动作：`startSe
 - 前端 Session 与 Workspace 在 materialize 前后保持对象身份，输入、错误、焦点和 sidebar 投影始终来自对象层。
 - 首发按 Workspace、Session、提示词顺序推进，各成功阶段不回滚，输入在提示词被接受前不丢失，创建重试使用同一 SessionId。
 - Workspace list 只读取 header 完成一次可重入 bootstrap；initialized 的空 registry 重启不重复初始化，成员读取同时校验索引与 canonical cwd。
-- 初始默认目标只在两份基线 ready 后确定一次；Workspace 组不因 hydration 或 Session 活跃整体重排，单个活跃 Session 只前移自身。
-- 真实 Workspace 下的前端 Session 临时计入 sidebar 数量，Workspace Intent 保持隐藏，发布与刷新都不会留下重复行或重复计数。
+- 初始默认目标只在两份基线 ready 后确定一次；Workspace 组不因 hydration 或 Session 活跃重排，显式 Workspace 拖拽顺序在重连后仍然保持。
+- 当前空白 Session 可显示为唯一的 New Session 行，同时不暴露其他可复用空白会话，也不显示 Session 数量。
 - UI 与 Host 会将 canonical path 不同但 basename 相同的目录接纳为独立 Workspace，而显式的重命名操作会拒绝重复显示名；cwd-only Session、无效历史 cwd 和未 attach Session 保持 Ungrouped。
 - 经确认的 Workspace 删除只移除注册记录，保留当前 Session、目录、文件和会话日志，并在刷新后保持该状态；包级测试固定一元响应／帧／基线竞态和失败回滚行为。
 - keyless runnable snapshot 覆盖零态、显式创建和首次发送；包级测试覆盖 bootstrap、成员校验、排序、幂等、失败恢复及任意 frame 顺序。
 
 ## Consequences
 
-- SessionHeader 不记录最后活跃时间，历史 bootstrap 只能按 `createdAt` 初始化；此后由真实 Session 活跃事件逐项前移。
+- SessionHeader 不记录最后活跃时间，历史 bootstrap 只能按 `createdAt` 初始化 Host 手动顺序；浏览器可选的最近更新视图在 hydration 后从 Session 摘要开始建立。
 - 历史 cwd 缺失、目录无效或 realpath 失败的 Session 留在 Ungrouped；本期没有手动收编入口。
 - 页面刷新会丢弃未 materialize 的 Workspace/Session Intent 和尚未被 Host 接受的输入，这是 page-local 约定。
 - 显式 Create Workspace 立即落盘，用户不发送就离开也会留下空 Workspace。

.agents/notes/implemented/feature/2026-07-26-code-dispatch-ui-foundation.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 .agents/notes/implemented/feature/2026-07-26-code-dispatch-ui-foundation.md
-2026-07-26-code-dispatch-ui-foundation.md: 4115a1898de7d2cce01346c3f005fcd19c325f4c
-2026-07-26-code-dispatch-ui-foundation.zh.md: aeb57b93d781163dd0a4747ac03053c65deda1db
+2026-07-26-code-dispatch-ui-foundation.md: 94316e774f231a2f2d5e9bcc8d1a30fd4a2ec733
+2026-07-26-code-dispatch-ui-foundation.zh.md: 2c9ee5b93e20b5c09950e2896a888f90863b8bd0

.agents/notes/implemented/feature/2026-07-26-code-dispatch-ui-foundation.md

@@ -16,7 +16,7 @@ Three changes, one per obstacle:
 
 1. **`run_code` gains a required `description` parameter** (bash's exact contract: active voice, 5-10 words, shown in the UI; whitespace-only rejected at execute). `presentCall` now titles the card with the description and moves the program to `rawInput`. The prompt-side cost is a few tokens per call; the return is that every surface — TUI card, ACP title, web row — gets a human-readable label without parsing TypeScript.
 2. **`tool/code-dispatch` logs the sub-call's complete model-facing outcome** — `content: ContentBlock[]` + `isError`, the `tool/result` vocabulary — replacing `resultSummary` and deleting the summarize/cwd-normalization machinery outright. A UI renders a sub-call through the identical code path as a native result, including error text and non-text blocks. The event stays log-only (`deriveMessages()` ignores it): nothing about model context changes.
-3. **`DSH_TOOLS_MODE` env var on the `dsh` config tree** (`native`|`code`|`both`; unset keeps the schema default): the `tools` row reads it via `!!js`, and the worker code runtime is mounted unconditionally (Loader metadata is static, so no conditional row exists; a native boot only registers the service — workers spawn per run). This is an explicitly temporary configuration hook: per-session tool-mode selection owned by the web UI is the design goal, and the env var dies when that lands.
+3. **`DSH_TOOLS_MODE` env var on the `dsh` config tree** (`native`|`code`|`both`; unset keeps the schema default): the `tools` row reads it via `!!js`, and the worker code runtime is mounted unconditionally (Loader metadata was static when this shipped — no conditional row existed; the later [`disabled` interpolation decision](../architecture/2026-08-11-loader-entry-disabled-interpolation.md) makes one possible but changes nothing here — a native boot only registers the service, workers spawn per run). This is an explicitly temporary configuration hook: per-session tool-mode selection owned by the web UI is the design goal, and the env var dies when that lands.
 
 ## Alternatives considered
 

.agents/notes/implemented/feature/2026-07-26-code-dispatch-ui-foundation.zh.md

@@ -16,7 +16,7 @@ Status: implemented
 
 1. **`run_code` 新增必填的 `description` 参数**（与 bash 完全相同的约定：主动语态、5-10 个词、展示在 UI 中；仅含空白的取值在执行时被拒绝）。`presentCall` 现在以该 description 作为卡片标题，并把程序文本移入 `rawInput`。提示词侧的成本是每次调用多出几个 token；换来的是每个表面——TUI 卡片、ACP（Agent Client Protocol）标题、Web 行——都无需解析 TypeScript 就能获得可供人阅读的标签。
 2. **`tool/code-dispatch` 记录子调用面向模型的完整结果**（`content: ContentBlock[]` 加 `isError`，即 `tool/result` 的词汇），取代 `resultSummary`，并把摘要与 cwd 归一化机制彻底删除。UI 渲染子调用走的代码路径与渲染原生结果完全相同，包括错误文本和非文本块。该事件保持仅日志（`deriveMessages()` 忽略它）：模型上下文没有任何变化。
-3. **`dsh` 配置树上的 `DSH_TOOLS_MODE` 环境变量**（`native`|`code`|`both`；未设置时保持 schema 默认值）：`tools` 行通过 `!!js` 读取它，worker 代码运行时则无条件挂载（loader 元数据是静态的，因此不存在条件行；native 启动只是注册该服务，worker 要到每次运行时才 spawn）。这是一个明确标注为临时的配置钩子：设计目标是让 Web UI 拥有按会话的工具模式选择，该目标落地后，这个环境变量随即退役。
+3. **`dsh` 配置树上的 `DSH_TOOLS_MODE` 环境变量**（`native`|`code`|`both`；未设置时保持 schema 默认值）：`tools` 行通过 `!!js` 读取它，worker 代码运行时则无条件挂载（本项交付时 loader 元数据仍是静态的，因此不存在条件行；后来的 [`disabled` 插值决策](../architecture/2026-08-11-loader-entry-disabled-interpolation.md) 让条件行成为可能，但此处不变——native 启动只是注册该服务，worker 要到每次运行时才 spawn）。这是一个明确标注为临时的配置钩子：设计目标是让 Web UI 拥有按会话的工具模式选择，该目标落地后，这个环境变量随即退役。
 
 ## 曾考虑的替代方案
 

.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.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 .agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
-2026-07-26-todo-parallel-in-progress.md: 5664960ce94dfac60d89cb363ea62459dd51f59e
-2026-07-26-todo-parallel-in-progress.zh.md: f346f89fcae5e8607c5608bbf7541ada0bae4593
+2026-07-26-todo-parallel-in-progress.md: 3d7b80e94762f8ca24b716c42619bf20d9a13608
+2026-07-26-todo-parallel-in-progress.zh.md: 28e32c949de09b5c0722cd1c7e9d91c1542a6cf7

.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md

@@ -51,4 +51,4 @@ Two known gaps are deferred. The `summarySuffix` span carries no accessible name
 
 ## Consequences
 
-A todo list can now faithfully mirror parallel execution, and every surface renders several active markers at once: the plan strip's header counts the active items, and the row needed the derivation above. A composition that sets `allowParallelInProgress: true` no longer rejects a formerly-invalid snapshot shape; one that sets `false` keeps the old rejection, and the durable-log invariant accepts both. The model-facing description changed, which re-recorded the tool-catalog page and every snapshot sidecar carrying the todo schema. No count is recorded here: the set grows with every pinning scenario that lands. The operative rule is that a branch changing the tool description must refresh whichever sidecars landed after it branched — including the numbered `tool-schemas.<n>.expected.json` files pinning a subagent class, whose schemas the parent scenario does not cover — and `pnpm run test:snapshot:refresh` does it keylessly over the whole corpus. The web fixture's todo sample now runs two items `in_progress`, so both fixture-driven surfaces render a parallel plan. `packages/client/ui-conversation/tests/todo-panel.spec.tsx` pins the row summary and the plan strip over src, the ACP `todo-write` scenario records a three-todo plan with two active, and `apps/web/tests/todo-row.snapshot.ts` pins both surfaces in the assembled application — booted from the built `packages/client/*/lib/client.js` bundles, so it is the one place the keyed registration and the bundled wiring are under test. That last file records `summary`, `suffix`, and the strip's header as separate fields, so folding the `+N` count back into the summary string changes the expected output even though the concatenated text would read the same.
+A todo list can now faithfully mirror parallel execution, and every surface renders several active markers at once: the plan strip's header counts the active items, and the row needed the derivation above. A composition that sets `allowParallelInProgress: true` no longer rejects a formerly-invalid snapshot shape; one that sets `false` keeps the old rejection, and the durable-log invariant accepts both. The model-facing description changed, which re-recorded the tool-catalog page and every snapshot sidecar carrying the todo schema. No count is recorded here: the set grows with every pinning scenario that lands. The operative rule is that a branch changing the tool description must refresh whichever sidecars landed after it branched — including the numbered `tool-schemas.<n>.expected.json` files pinning a subagent class, whose schemas the parent scenario does not cover — and `pnpm run test:snapshot:refresh` does it keylessly over the whole corpus. The web fixture's todo sample now runs two items `in_progress`, so both fixture-driven surfaces render a parallel plan. `packages/client/ui-conversation/tests/todo-panel.client.spec.tsx` pins the row summary and the plan strip over src, the ACP `todo-write` scenario records a three-todo plan with two active, and `apps/web/tests/todo-row.snapshot.ts` pins both surfaces in the assembled application — booted from the built `packages/client/*/lib/client.js` bundles, so it is the one place the keyed registration and the bundled wiring are under test. That last file records `summary`, `suffix`, and the strip's header as separate fields, so folding the `+N` count back into the summary string changes the expected output even though the concatenated text would read the same.

.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md

@@ -51,4 +51,4 @@ Status: implemented
 
 ## 后果
 
-现在 todo 列表可以忠实反映并行执行，并且每个展示面都能一次渲染多个活跃标记：计划横条的表头会计数活跃条目，工具行则需要上述推导。设置 `allowParallelInProgress: true` 的组合不再拒绝一种此前无效的快照形状；设置为 `false` 的组合仍保留旧的拒绝行为，而持久日志不变式两者都接受。面向模型的描述发生了变化，这重新记录了 tool-catalog 页面以及每个带有 todo schema 的快照伴随文件。此处不记录数量：该集合会随每个新落地的 pin 场景增长。有效规则是：改动工具描述的分支必须刷新它分叉之后落地的那些伴随文件——包括固定 subagent 类工具的编号文件 `tool-schemas.<n>.expected.json`，其 schema 不被父场景覆盖——`pnpm run test:snapshot:refresh` 可以无 key 地对整个语料完成刷新。web fixture（测试前置数据）的 todo 样本现在有两个条目处于 `in_progress`，因此两个由 fixture 驱动的展示面渲染的都是并行计划。`packages/client/ui-conversation/tests/todo-panel.spec.tsx` 在 src 上固定工具行摘要与计划横条，ACP（Agent Client Protocol）`todo-write` 场景录制的是三条目、两个活跃的计划，而 `apps/web/tests/todo-row.snapshot.ts` 在组装后的应用中固定这两个面——它从构建产物 `packages/client/*/lib/client.js` 启动，因此是唯一覆盖 keyed 注册与打包接线的地方。该文件把 `summary`、`suffix` 与横条表头记录为独立字段，因此即便拼接后的文本读起来一样，把 `+N` 计数折回摘要字符串也会改变预期输出。
+现在 todo 列表可以忠实反映并行执行，并且每个展示面都能一次渲染多个活跃标记：计划横条的表头会计数活跃条目，工具行则需要上述推导。设置 `allowParallelInProgress: true` 的组合不再拒绝一种此前无效的快照形状；设置为 `false` 的组合仍保留旧的拒绝行为，而持久日志不变式两者都接受。面向模型的描述发生了变化，这重新记录了 tool-catalog 页面以及每个带有 todo schema 的快照伴随文件。此处不记录数量：该集合会随每个新落地的 pin 场景增长。有效规则是：改动工具描述的分支必须刷新它分叉之后落地的那些伴随文件——包括固定 subagent 类工具的编号文件 `tool-schemas.<n>.expected.json`，其 schema 不被父场景覆盖——`pnpm run test:snapshot:refresh` 可以无 key 地对整个语料完成刷新。web fixture（测试前置数据）的 todo 样本现在有两个条目处于 `in_progress`，因此两个由 fixture 驱动的展示面渲染的都是并行计划。`packages/client/ui-conversation/tests/todo-panel.client.spec.tsx` 在 src 上固定工具行摘要与计划横条，ACP（Agent Client Protocol）`todo-write` 场景录制的是三条目、两个活跃的计划，而 `apps/web/tests/todo-row.snapshot.ts` 在组装后的应用中固定这两个面——它从构建产物 `packages/client/*/lib/client.js` 启动，因此是唯一覆盖 keyed 注册与打包接线的地方。该文件把 `summary`、`suffix` 与横条表头记录为独立字段，因此即便拼接后的文本读起来一样，把 `+N` 计数折回摘要字符串也会改变预期输出。

.agents/notes/implemented/feature/2026-07-28-web-terminal-card.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 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
-2026-07-28-web-terminal-card.md: 84e5cdb786944b014fd3a687cfefad6768174006
-2026-07-28-web-terminal-card.zh.md: 58c236bda9c45e13fda0f965f84af24b3c831bb4
+2026-07-28-web-terminal-card.md: ef6da52b4166b61579cf3ef98e760c2f1c42b679
+2026-07-28-web-terminal-card.zh.md: 80c555f227b4e6dd96adcfb666f52e9bb42e2d41

.agents/notes/implemented/feature/2026-07-28-web-terminal-card.md

@@ -55,9 +55,9 @@ Inline rendering is licensed for the terminal intent alone. A future intent that
 
 ## Testing
 
-`packages/client/ui-primitives/tests/ansi.spec.ts` pins the parse layer: token mapping for the basic colors, literal rgb for the values with no token, the background-run pair, every decoration and the `textDecoration` collision between two of them, the sanitizing of OSC strings and non-CSI escapes and inert controls, the cursor replay (redraws leaving a longer frame's tail standing, a trailing backspace erasing nothing, erase-in-line in all three parameter forms, tab stops, wide characters, SGR threading across lines, and a cursor/erase sequence never entering a cell style), and CRLF preservation. Each replay case was checked against a real terminal first. `packages/client/ui-primitives/tests/terminal-block.spec.tsx` pins the component: cwd shortening, the running/empty/settled arms, signal outranking exit code, the trailing-newline terminator rule, the head/tail cap with its `aria-expanded` toggle, the run-state dot across all three reachable states plus its position ahead of the prompt label, the one-row-per-command-line prompt and its single dot on the first row, and the copy control asserting raw output on both the accepted and refused clipboard paths, plus `writeClipboard` directly.
+`packages/client/ui-primitives/tests/ansi.client.spec.ts` pins the parse layer: token mapping for the basic colors, literal rgb for the values with no token, the background-run pair, every decoration and the `textDecoration` collision between two of them, the sanitizing of OSC strings and non-CSI escapes and inert controls, the cursor replay (redraws leaving a longer frame's tail standing, a trailing backspace erasing nothing, erase-in-line in all three parameter forms, tab stops, wide characters, SGR threading across lines, and a cursor/erase sequence never entering a cell style), and CRLF preservation. Each replay case was checked against a real terminal first. `packages/client/ui-primitives/tests/terminal-block.client.spec.tsx` pins the component: cwd shortening, the running/empty/settled arms, signal outranking exit code, the trailing-newline terminator rule, the head/tail cap with its `aria-expanded` toggle, the run-state dot across all three reachable states plus its position ahead of the prompt label, the one-row-per-command-line prompt and its single dot on the first row, and the copy control asserting raw output on both the accepted and refused clipboard paths, plus `writeClipboard` directly.
 
-`packages/client/ui-tool/tests/terminal-card.spec.tsx` pins the wiring at every render site: `terminalCardModel`'s derivation and each of its null arms, the result title replacing the pending one, the cwd resolving against the session workspace across all four of its cases, the panel resetting the card's expand state when the selection changes, the chat row's expand-gated body against the panel's full-height one, `BashRow`'s resident card and its agreement with its own summary row's state dot, and the panel's Output section including the run_code sub-dispatch and the out-of-window head. That file is written against no gate pressure — `packages/client/ui-tool/src/*` sits on the coverage `exclude` list in `vitest.config.ts`, so a coverage run over this package measures none of these files.
+`packages/client/ui-tool/tests/terminal-card.client.spec.tsx` pins the wiring at every render site: `terminalCardModel`'s derivation and each of its null arms, the result title replacing the pending one, the cwd resolving against the session workspace across all four of its cases, the panel resetting the card's expand state when the selection changes, the chat row's expand-gated body against the panel's full-height one, `BashRow`'s resident card and its agreement with its own summary row's state dot, and the panel's Output section including the run_code sub-dispatch and the out-of-window head. That file is written against no gate pressure — `packages/client/ui-tool/src/*` sits on the coverage `exclude` list in `vitest.config.ts`, so a coverage run over this package measures none of these files.
 
 `apps/web/tests/terminal-card.snapshot.ts` pins the assembled application over the built client bundles: the same render intent at both conversation render sites and in both chat-row shapes, because a bash call reaches a resident card only through the keyed `BashRow` registration and every other terminal-declaring tool name lands on the render-site fallback row, whose body is expand-gated. Fixture turn 65 is named `bash` and turn 60 stays `fx-bash` so one fixture covers both shapes, and turn 60's command is two lines so the built-bundle snapshot pins the per-line prompt and its single dot (`dotsPerPromptRow: [1, 0]`). That terminal turn is ordered BEFORE the todo turn on purpose: the standing plan retires at the next `turn/start`, so appending it after would have emptied the dock's plan strip and taken the todo surfaces' own coverage with it; that turn also carries what turn 60's two prompt rows cannot — SGR runs resolved to `--dsw-*` tokens, output past the chat cap, a nested cwd, and a non-zero exit authored beside the sample. The sample's body deliberately carries NO `[exit code: N]` line: the real bash presenter consumes that marker out of the body precisely because the card shows the exit as its own pill, so leaving it in would pin a frame showing the exit twice — one the product path cannot produce.
 

.agents/notes/implemented/feature/2026-07-28-web-terminal-card.zh.md

@@ -55,9 +55,9 @@ Web client 却对它视而不见。`packages/client/ui-tool/src/client/tool/mode
 
 ## Testing
 
-`packages/client/ui-primitives/tests/ansi.spec.ts` 固定解析层：基本色的 token 映射、无对应 token 取值的字面 rgb、带背景分段的前后景配对、每一项装饰以及其中两项之间的 `textDecoration` 冲突、OSC 串与非 CSI 转义及无显示意义控制符的剥除、光标重放（较短重绘让上一帧尾巴留存、末尾退格不擦除任何东西、行内擦除的全部三种参数形式、制表位、宽字符、SGR 跨行延续，以及光标／擦除序列绝不进入单元格样式），以及 CRLF 的保留。每一条重放用例都先对照真实终端核实过。`packages/client/ui-primitives/tests/terminal-block.spec.tsx` 固定组件：cwd 缩短、运行中／空／已落定三条分支、信号优先于退出码、末尾终止符规则、首尾高度上限及其 `aria-expanded` 开关、运行状态点全部三种可达状态及其位于提示符标签之前的位置、每条命令行一行的提示区及其位于第一行的单枚状态点，以及复制控件在剪贴板接受与拒绝两条路径上都断言原始输出，另有对 `writeClipboard` 的直接固定。
+`packages/client/ui-primitives/tests/ansi.client.spec.ts` 固定解析层：基本色的 token 映射、无对应 token 取值的字面 rgb、带背景分段的前后景配对、每一项装饰以及其中两项之间的 `textDecoration` 冲突、OSC 串与非 CSI 转义及无显示意义控制符的剥除、光标重放（较短重绘让上一帧尾巴留存、末尾退格不擦除任何东西、行内擦除的全部三种参数形式、制表位、宽字符、SGR 跨行延续，以及光标／擦除序列绝不进入单元格样式），以及 CRLF 的保留。每一条重放用例都先对照真实终端核实过。`packages/client/ui-primitives/tests/terminal-block.client.spec.tsx` 固定组件：cwd 缩短、运行中／空／已落定三条分支、信号优先于退出码、末尾终止符规则、首尾高度上限及其 `aria-expanded` 开关、运行状态点全部三种可达状态及其位于提示符标签之前的位置、每条命令行一行的提示区及其位于第一行的单枚状态点，以及复制控件在剪贴板接受与拒绝两条路径上都断言原始输出，另有对 `writeClipboard` 的直接固定。
 
-`packages/client/ui-tool/tests/terminal-card.spec.tsx` 固定每个渲染点上的接线：`terminalCardModel` 的推导及其每一处 null 分支、结果标题替换待定标题、cwd 针对会话 workspace 解析的全部四种情形、切换选中调用时面板重置卡片展开态、对话行受展开控制的输出体与面板的全高输出体的对比、`BashRow` 的常驻卡片及其与自身摘要行状态点的一致性，以及面板 Output 区段（含 run_code 子派发与超出窗口的调用头）。该文件在没有门禁压力的情况下写成——`packages/client/ui-tool/src/*` 位于 `vitest.config.ts` 的覆盖率 `exclude` 列表中，因此覆盖率运行不会统计其中任何文件。
+`packages/client/ui-tool/tests/terminal-card.client.spec.tsx` 固定每个渲染点上的接线：`terminalCardModel` 的推导及其每一处 null 分支、结果标题替换待定标题、cwd 针对会话 workspace 解析的全部四种情形、切换选中调用时面板重置卡片展开态、对话行受展开控制的输出体与面板的全高输出体的对比、`BashRow` 的常驻卡片及其与自身摘要行状态点的一致性，以及面板 Output 区段（含 run_code 子派发与超出窗口的调用头）。该文件在没有门禁压力的情况下写成——`packages/client/ui-tool/src/*` 位于 `vitest.config.ts` 的覆盖率 `exclude` 列表中，因此覆盖率运行不会统计其中任何文件。
 
 `apps/web/tests/terminal-card.snapshot.ts` 在构建后的客户端产物上固定组装完整的应用：同一渲染意图在两个对话渲染点、以及两种对话行形态下的表现——因为 bash 调用只有经由带键的 `BashRow` 注册才得到常驻卡片，而其他任何声明 terminal 的工具名都落到渲染点兜底行上，其输出体受展开控制。fixture 第 65 轮名为 `bash`、第 60 轮保持 `fx-bash`，于是一份 fixture 覆盖两种形态，而第 60 轮的命令为两行，使构建产物快照钉住逐行提示区及其单枚状态点（`dotsPerPromptRow: [1, 0]`）。该终端轮有意排在 todo 轮**之前**：站立计划会在下一次 `turn/start` 时退役，若追加在其后就会让 dock 的计划条变空，并连带毁掉 todo 表面自身的覆盖；该轮还承载第 60 轮两个提示行无法覆盖的部分——解析到 `--dsw-*` token 的 SGR 分段、超出对话上限的输出、嵌套 cwd，以及在样本旁另行标注的非零退出码。样本正文有意**不含** `[exit code: N]` 行：真实的 bash presenter 正是因为卡片以徽章单独呈现退出状态，才把该标记从正文中消费掉；若保留它，钉住的将是一帧把退出状态显示两次的画面——而产品路径产不出这一帧。
 

.agents/notes/implemented/feature/2026-07-30-web-diff-card.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 .agents/notes/implemented/feature/2026-07-30-web-diff-card.md
-2026-07-30-web-diff-card.md: d8b0cf32e42af45e16e6f7059c873c384d4a9229
-2026-07-30-web-diff-card.zh.md: 51df03c3f8b79cd8415a15bd30e92e3c152f335e
+2026-07-30-web-diff-card.md: 465a6fc9e2fbe61fd1a2e6f11590d01e2553d506
+2026-07-30-web-diff-card.zh.md: d674b1a323f15f52592b51b6188e0b80d1ba977c

.agents/notes/implemented/feature/2026-07-30-web-diff-card.md

@@ -44,9 +44,9 @@ The multi-file arm of `DiffBlock` (one card, several path headers) has no produc
 
 ## Testing
 
-`packages/client/ui-primitives/tests/diff-block.spec.tsx` pins the component: the create arm (added-only, no removed side), the edit arm (removed above added), the same-file `⋯` gap versus a new file's own header, the empty-diffs null render, the footer counts and their singular/plural, the head/tail cap with its `aria-expanded` toggle, and the copy control asserting the prefixed diff text on both the accepted and refused clipboard paths. Per-file 100%.
+`packages/client/ui-primitives/tests/diff-block.client.spec.tsx` pins the component: the create arm (added-only, no removed side), the edit arm (removed above added), the same-file `⋯` gap versus a new file's own header, the empty-diffs null render, the footer counts and their singular/plural, the head/tail cap with its `aria-expanded` toggle, and the copy control asserting the prefixed diff text on both the accepted and refused clipboard paths. Per-file 100%.
 
-`packages/client/ui-tool/tests/diff-card.spec.tsx` pins the wiring at every render site: `diffCardModel`'s derivation and each of its null arms, the result hunks replacing the call-time diff, a window-truncated call still rendering from the result, the chat row's diff body, `FileMutationRow`'s resident card and its path link opening cwd-resolved through the host, its registration under both `write` and `edit`, and the panel's Output section.
+`packages/client/ui-tool/tests/diff-card.client.spec.tsx` pins the wiring at every render site: `diffCardModel`'s derivation and each of its null arms, the result hunks replacing the call-time diff, a window-truncated call still rendering from the result, the chat row's diff body, `FileMutationRow`'s resident card and its path link opening cwd-resolved through the host, its registration under both `write` and `edit`, and the panel's Output section.
 
 The fixture (`packages/client/connection/src/client/fixture.ts`) carries three diff turns so a `?fixture` server and the per-package wiring suite exercise all three arms at both render sites: a single-hunk edit (turn 62, keyed `FileMutationRow`), a create/write (turn 63), and a multi-hunk edit (turn 67, the `⋯` gap between two scattered hunks in one file). The built-boot snapshot (`apps/web/tests/built-boot.snapshot.ts`) is a boot-assembly smoke that asserts only that the graph mounts and reaches chat content (`data-sample="bash-global"`); by its own contract it carries no diff-behavior assertions, which the wiring suite owns.
 

.agents/notes/implemented/feature/2026-07-30-web-diff-card.zh.md

@@ -44,9 +44,9 @@ chat 行把 diff 常驻渲染在路径链接摘要之下，上限 `CHAT_DIFF_MAX
 
 ## Testing
 
-`packages/client/ui-primitives/tests/diff-block.spec.tsx` 钉住组件：新建支路（只有新增、无删除侧）、编辑支路（删除在新增之上）、同文件 `⋯` gap 对比新文件自己的头、空 diffs 的 null 渲染、页脚计数及其单复数、头尾上限及其 `aria-expanded` 切换、以及复制控件在接受与拒绝两条剪贴板路径上断言带前缀的 diff 文本。Per-file 100%。
+`packages/client/ui-primitives/tests/diff-block.client.spec.tsx` 钉住组件：新建支路（只有新增、无删除侧）、编辑支路（删除在新增之上）、同文件 `⋯` gap 对比新文件自己的头、空 diffs 的 null 渲染、页脚计数及其单复数、头尾上限及其 `aria-expanded` 切换、以及复制控件在接受与拒绝两条剪贴板路径上断言带前缀的 diff 文本。Per-file 100%。
 
-`packages/client/ui-tool/tests/diff-card.spec.tsx` 钉住每个渲染点的接线：`diffCardModel` 的派生及其每个 null 支路、result hunk 替换 call 时 diff、窗口截断的 call 仍从 result 渲染、chat 行的 diff 体、`FileMutationRow` 的常驻卡片及其路径链接经 host 以 cwd 解析打开、其在 `write` 与 `edit` 下的注册、以及面板的 Output 区。
+`packages/client/ui-tool/tests/diff-card.client.spec.tsx` 钉住每个渲染点的接线：`diffCardModel` 的派生及其每个 null 支路、result hunk 替换 call 时 diff、窗口截断的 call 仍从 result 渲染、chat 行的 diff 体、`FileMutationRow` 的常驻卡片及其路径链接经 host 以 cwd 解析打开、其在 `write` 与 `edit` 下的注册、以及面板的 Output 区。
 
 fixture（`packages/client/connection/src/client/fixture.ts`）携带三个 diff turn，使 `?fixture` 服务与 per-package 接线测试套件在两个渲染点演练全部三个支路：单 hunk 编辑（turn 62，keyed `FileMutationRow`）、新建/写入（turn 63）、多 hunk 编辑（turn 67，一个文件内两处分散 hunk 之间的 `⋯` gap）。built-boot snapshot（`apps/web/tests/built-boot.snapshot.ts`）是启动装配 smoke，只断言图挂载并抵达 chat 内容（`data-sample="bash-global"`）；按其自身约定它不带 diff 行为断言，那由接线套件负责。
 

.agents/notes/implemented/feature/2026-07-30-web-read-card-frontend.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 .agents/notes/implemented/feature/2026-07-30-web-read-card-frontend.md
-2026-07-30-web-read-card-frontend.md: 1d9b6d7fa0c8b5391d175a53507db88a84234b91
-2026-07-30-web-read-card-frontend.zh.md: 2678d50e851e4b3a079f59c7db6ec08ecc5c4aed
+2026-07-30-web-read-card-frontend.md: 98e31d4192f7522f9d0e23bce56372a70f8c50b6
+2026-07-30-web-read-card-frontend.zh.md: 294821ec9f1b35f58c399aa77d21b629557cd059

.agents/notes/implemented/feature/2026-07-30-web-read-card-frontend.md

@@ -40,9 +40,9 @@ A read row in the Web chat now carries the file content resident, a deliberate d
 
 ## Testing
 
-`packages/client/ui-primitives/tests/read-block.spec.tsx` pins the primitive and the token path: `highlightLines`' per-line css-variables runs, its trailing-terminator-line drop and the genuinely-blank-final-line case, its `undefined` for an unknown/absent language, and its lazy path (a lazy grammar returns plain on first touch, then highlights after the import registers and the subscriber fires); and `ReadBlock`'s gutter-numbered rows keeping the file's own numbers, the highlighted-vs-plain content arms, the banner (label, language, the count note only when the read is a window), the head/tail height cap with its `aria-expanded` toggle, the copy control writing the window's raw text on both the accepted and refused clipboard paths, and the empty-window arm hiding the copy control. `code-block.spec.tsx` covers `highlightToHtml` including its lazy path over every read-card grammar (each dynamic import thunk touched once). Both `ReadBlock.tsx` and `highlight.ts` (and `CodeBlock.tsx`) hold per-file 100% coverage across the two specs.
+`packages/client/ui-primitives/tests/read-block.client.spec.tsx` pins the primitive and the token path: `highlightLines`' per-line css-variables runs, its trailing-terminator-line drop and the genuinely-blank-final-line case, its `undefined` for an unknown/absent language, and its lazy path (a lazy grammar returns plain on first touch, then highlights after the import registers and the subscriber fires); and `ReadBlock`'s gutter-numbered rows keeping the file's own numbers, the highlighted-vs-plain content arms, the banner (label, language, the count note only when the read is a window), the head/tail height cap with its `aria-expanded` toggle, the copy control writing the window's raw text on both the accepted and refused clipboard paths, and the empty-window arm hiding the copy control. `code-block.spec.tsx` covers `highlightToHtml` including its lazy path over every read-card grammar (each dynamic import thunk touched once). Both `ReadBlock.tsx` and `highlight.ts` (and `CodeBlock.tsx`) hold per-file 100% coverage across the two specs.
 
-`packages/client/ui-tool/tests/read-card.spec.tsx` pins the wiring at every render site: `readCardModel`'s derivation and each null arm (running read, no view, generic view, unknown card), the result title replacing the relativized path, the path relativization against the workspace, the copy-not-alias of the frozen line array; the resident card in `GenericToolCard`'s fallback and in the keyed `ReadRow` (plus its path link opening the host, its running/error/stopped states, and its `read`-key registration); and the panel's Output section rendering the read card at full height while keeping the JSON Input section, with the running-read placeholder and non-read flattened-pre arms. That file sits on the coverage `exclude` list (`ui-tool/src/*`), so it is written against no gate pressure.
+`packages/client/ui-tool/tests/read-card.client.spec.tsx` pins the wiring at every render site: `readCardModel`'s derivation and each null arm (running read, no view, generic view, unknown card), the result title replacing the relativized path, the path relativization against the workspace, the copy-not-alias of the frozen line array; the resident card in `GenericToolCard`'s fallback and in the keyed `ReadRow` (plus its path link opening the host, its running/error/stopped states, and its `read`-key registration); and the panel's Output section rendering the read card at full height while keeping the JSON Input section, with the running-read placeholder and non-read flattened-pre arms. That file sits on the coverage `exclude` list (`ui-tool/src/*`), so it is written against no gate pressure.
 
 The fixture (`packages/client/connection/src/client/fixture.ts`) gains turn 66, a `read` call whose result view is a windowed read (lines starting at file line 41, `totalLines` 180, a `ts` hint), so the built-boot snapshot and a live `?fixture` server show the read card with its gutter numbers, highlighting, and count note. It is named `read` to exercise the keyed `ReadRow`. The turn 64 `run_code` sample's nested read sub-dispatches do not exercise the render-site fallback read card: `session.ts` folds them with `resultView: null`, so they cover only the fallback row's generic row shape, not a read card inside it; the fallback-row read card is pinned by `read-card.spec.tsx`'s `web_fetch` case. Turn 66 is ordered before the todo turn (now 67) for the same reason the terminal sample is: the standing plan retires at the next `turn/start`.
 

.agents/notes/implemented/feature/2026-07-30-web-read-card-frontend.zh.md

@@ -40,9 +40,9 @@ Web 聊天里的读取行现在常驻承载文件内容，是相对纯摘要行
 
 ## Testing
 
-`packages/client/ui-primitives/tests/read-block.spec.tsx` 固定 primitive 与 token 路径：`highlightLines` 的逐行 css-variables 运行、它对尾部终止行的丢弃与真正空白末行的情形、它对未知/缺省语言返回 `undefined`、以及它的 lazy 路径（lazy 语法首次触碰返回纯文本，import 注册且订阅者触发后再高亮）；还有 `ReadBlock` 的带行号行保留文件自身编号、高亮与纯文本两条内容分支、横幅（标签、语言、仅当读取是窗口时的计数提示）、头/尾高度上限及其 `aria-expanded` 切换、复制控件在接受与拒绝两条剪贴板路径上写入窗口原始文本、以及空窗口分支隐藏复制控件。`code-block.spec.tsx` 覆盖 `highlightToHtml`，含它对每种读取卡片语法的 lazy 路径（每个动态 import thunk 各触碰一次）。`ReadBlock.tsx`、`highlight.ts`（及 `CodeBlock.tsx`）在这两个 spec 上均保持每文件 100% 覆盖。
+`packages/client/ui-primitives/tests/read-block.client.spec.tsx` 固定 primitive 与 token 路径：`highlightLines` 的逐行 css-variables 运行、它对尾部终止行的丢弃与真正空白末行的情形、它对未知/缺省语言返回 `undefined`、以及它的 lazy 路径（lazy 语法首次触碰返回纯文本，import 注册且订阅者触发后再高亮）；还有 `ReadBlock` 的带行号行保留文件自身编号、高亮与纯文本两条内容分支、横幅（标签、语言、仅当读取是窗口时的计数提示）、头/尾高度上限及其 `aria-expanded` 切换、复制控件在接受与拒绝两条剪贴板路径上写入窗口原始文本、以及空窗口分支隐藏复制控件。`code-block.spec.tsx` 覆盖 `highlightToHtml`，含它对每种读取卡片语法的 lazy 路径（每个动态 import thunk 各触碰一次）。`ReadBlock.tsx`、`highlight.ts`（及 `CodeBlock.tsx`）在这两个 spec 上均保持每文件 100% 覆盖。
 
-`packages/client/ui-tool/tests/read-card.spec.tsx` 固定每个渲染点的接线：`readCardModel` 的派生与每条 null 分支（运行中读取、无视图、通用视图、未知卡片）、结果标题替换化简后的路径、路径相对工作区的化简、冻结行数组的复制而非别名；`GenericToolCard` 回退中与 keyed `ReadRow` 中的常驻卡片（外加其路径链接打开宿主、其 running/error/stopped 状态、以及其 `read` 键注册）；还有面板 Output 区段以全高渲染读取卡片同时保留 JSON Input 区段，含运行中读取占位与非读取摊平 pre 两条分支。该文件位于覆盖 `exclude` 列表（`ui-tool/src/*`），因此不承受门槛压力。
+`packages/client/ui-tool/tests/read-card.client.spec.tsx` 固定每个渲染点的接线：`readCardModel` 的派生与每条 null 分支（运行中读取、无视图、通用视图、未知卡片）、结果标题替换化简后的路径、路径相对工作区的化简、冻结行数组的复制而非别名；`GenericToolCard` 回退中与 keyed `ReadRow` 中的常驻卡片（外加其路径链接打开宿主、其 running/error/stopped 状态、以及其 `read` 键注册）；还有面板 Output 区段以全高渲染读取卡片同时保留 JSON Input 区段，含运行中读取占位与非读取摊平 pre 两条分支。该文件位于覆盖 `exclude` 列表（`ui-tool/src/*`），因此不承受门槛压力。
 
 fixture（`packages/client/connection/src/client/fixture.ts`）增加 turn 66，一次 `read` 调用，其结果视图是窗口读取（行号从文件行 41 起、`totalLines` 180、`ts` 提示），使内置启动快照和实时 `?fixture` 服务器展示带行号、高亮和计数提示的读取卡片。它命名为 `read` 以驱动 keyed `ReadRow`。turn 64 的 `run_code` 样例中的嵌套读取子派发并不驱动渲染点回退读取卡片：`session.ts` 把它们折叠为 `resultView: null`，因此它们只覆盖回退行的通用行形状，而非回退行内的读取卡片；回退行读取卡片由 `read-card.spec.tsx` 的 `web_fetch` 用例钉住。turn 66 排在 todo turn（现为 67）之前，与终端样例同因：常驻计划在下一次 `turn/start` 退场。
 

.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.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 .agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md
-2026-07-30-web-result-card-frontend.md: c048c4f93f72e4a1da5c6426497e9274d65ac266
-2026-07-30-web-result-card-frontend.zh.md: a7090818dc023f857e01e43773adccfba585cc55
+2026-07-30-web-result-card-frontend.md: 6a00e0820af2c4010554df444a7585fb226294bf
+2026-07-30-web-result-card-frontend.zh.md: 727466dbbde1a7d06673713f635e16769eda00e0

.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md

@@ -36,9 +36,9 @@ The whole-row collapse/expand interaction shared by every resident card (termina
 
 ## Testing
 
-`packages/client/ui-primitives/tests/web-block.spec.tsx` pins the component per-file to the 100% gate: both kinds; the title-or-hostname-or-raw-URL label fallback; the safe-link attributes on both kinds (an http(s) URL becoming an external anchor with `target`/`rel`, a `javascript:`/`file:`/unparseable URL rendering as a plain span with no href); the snippet and date shown or omitted on present/empty/absent; the truncation indicator gated on the flag; and the full source list rendering inside one scroll container with no expand control and `<li value>` numbering every source contiguously from 1.
+`packages/client/ui-primitives/tests/web-block.client.spec.tsx` pins the component per-file to the 100% gate: both kinds; the title-or-hostname-or-raw-URL label fallback; the safe-link attributes on both kinds (an http(s) URL becoming an external anchor with `target`/`rel`, a `javascript:`/`file:`/unparseable URL rendering as a plain span with no href); the snippet and date shown or omitted on present/empty/absent; the truncation indicator gated on the flag; and the full source list rendering inside one scroll container with no expand control and `<li value>` numbering every source contiguously from 1.
 
-`packages/client/ui-tool/tests/web-card.spec.tsx` mirrors `terminal-card.spec.tsx` at every wiring boundary: `webCardModel`'s derivation projecting every source field, its truncation and absent-answer arms, the fetch derivation, and each null arm (running, null result view, generic result view, unknown card tag, unknown web `kind`); the keyed `WebRow`'s resident card for both kinds, its summary-row-alone running and failed arms; the `GenericToolCard` fallback growing the resident card for a web-declaring tool and keeping the plain row for a non-web call; the details panel's Output section for both kinds — including a `web_fetch`'s body flattened below its URL/status card — and its flattened fallback for a non-web result; and the keyed registration under both `web_search` and `web_fetch` with one component. That file sits on the coverage `exclude` list (`ui-tool/src/*`), so a coverage run measures none of it.
+`packages/client/ui-tool/tests/web-card.client.spec.tsx` mirrors `terminal-card.spec.tsx` at every wiring boundary: `webCardModel`'s derivation projecting every source field, its truncation and absent-answer arms, the fetch derivation, and each null arm (running, null result view, generic result view, unknown card tag, unknown web `kind`); the keyed `WebRow`'s resident card for both kinds, its summary-row-alone running and failed arms; the `GenericToolCard` fallback growing the resident card for a web-declaring tool and keeping the plain row for a non-web call; the details panel's Output section for both kinds — including a `web_fetch`'s body flattened below its URL/status card — and its flattened fallback for a non-web result; and the keyed registration under both `web_search` and `web_fetch` with one component. That file sits on the coverage `exclude` list (`ui-tool/src/*`), so a coverage run measures none of it.
 
 The fixture (`packages/client/connection/src/client/fixture.ts`) adds turns 66 (`web_search`) and 67 (`web_fetch`), authored inline because the client-side fixture cannot import the web tool: turn 66's result view carries an answer and three sources exercising the citation list (a titled source with a snippet and date, a source with no title so its hostname labels the link, and a source with a date but no snippet) with the capped indicator on; turn 67's carries the fetched URL and a 200 status. Both keep a generic pending call view and add the `web` card only at result time, matching the contract's result-only web shape, and are named after the real tools so they hit the keyed `WebRow`. They are ordered before the todo turn (renumbered to 68) for the same reason the terminal turn is: the standing plan retires at the next `turn/start`, so a turn appended after it would empty the dock's plan strip. This drives the built-boot snapshot and a live `?fixture` server.
 

.agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.zh.md

@@ -36,9 +36,9 @@ Status: implemented
 
 ## Testing
 
-`packages/client/ui-primitives/tests/web-block.spec.tsx` 把组件钉到 per-file 100% 门槛:两种 kind;标题-或-主机名-或-原始 URL 的标签回退;两种 kind 上的安全链接属性（http(s) URL 成为带 `target`/`rel` 的外链,`javascript:`/`file:`/无法解析的 URL 渲染为无 href 的纯 span）;snippet 与日期在存在/为空/缺失时的显示或省略;由标志位控制的截断提示;以及完整 source 列表渲染在单个滚动容器内、无展开控件、`<li value>` 从 1 起为每条 source 连续编号。
+`packages/client/ui-primitives/tests/web-block.client.spec.tsx` 把组件钉到 per-file 100% 门槛:两种 kind;标题-或-主机名-或-原始 URL 的标签回退;两种 kind 上的安全链接属性（http(s) URL 成为带 `target`/`rel` 的外链,`javascript:`/`file:`/无法解析的 URL 渲染为无 href 的纯 span）;snippet 与日期在存在/为空/缺失时的显示或省略;由标志位控制的截断提示;以及完整 source 列表渲染在单个滚动容器内、无展开控件、`<li value>` 从 1 起为每条 source 连续编号。
 
-`packages/client/ui-tool/tests/web-card.spec.tsx` 在每个接线边界镜像 `terminal-card.spec.tsx`:`webCardModel` 的派生投影每个 source 字段、其截断与缺失 answer 的支路、fetch 派生、以及每个 null 支路（运行中、null result view、generic result view、未知 card 标签、未知 web `kind`）;键控 `WebRow` 对两种 kind 的常驻卡片、其仅摘要行的运行中与失败支路;`GenericToolCard` 兜底为 web 声明工具长出常驻卡片、并为非 web 调用保持纯行;详情面板 Output 区对两种 kind —— 含 `web_fetch` 正文摊平在其 URL/状态卡片下方 —— 及其对非 web 结果的摊平回退;以及在 `web_search` 与 `web_fetch` 两键下用一个组件的键控注册。该文件位于覆盖率 `exclude` 列表（`ui-tool/src/*`）,因此覆盖率运行不度量它。
+`packages/client/ui-tool/tests/web-card.client.spec.tsx` 在每个接线边界镜像 `terminal-card.spec.tsx`:`webCardModel` 的派生投影每个 source 字段、其截断与缺失 answer 的支路、fetch 派生、以及每个 null 支路（运行中、null result view、generic result view、未知 card 标签、未知 web `kind`）;键控 `WebRow` 对两种 kind 的常驻卡片、其仅摘要行的运行中与失败支路;`GenericToolCard` 兜底为 web 声明工具长出常驻卡片、并为非 web 调用保持纯行;详情面板 Output 区对两种 kind —— 含 `web_fetch` 正文摊平在其 URL/状态卡片下方 —— 及其对非 web 结果的摊平回退;以及在 `web_search` 与 `web_fetch` 两键下用一个组件的键控注册。该文件位于覆盖率 `exclude` 列表（`ui-tool/src/*`）,因此覆盖率运行不度量它。
 
 fixture（`packages/client/connection/src/client/fixture.ts`）添加 turn 66（`web_search`）与 67（`web_fetch`）,内联撰写,因为客户端 fixture 无法 import web 工具:turn 66 的 result view 携带一个 answer 与三个 source,演练引用列表（一个带 snippet 与日期的有标题 source、一个无标题因而以主机名标注链接的 source、一个有日期无 snippet 的 source）并开启截断提示;turn 67 携带抓取的 URL 与一个 200 状态。两者都保留 generic pending call view,仅在 result 时添加 `web` 卡片,匹配约定的 result-only web 形状,且以真实工具命名,使其命中键控 `WebRow`。它们被排在 todo turn（重编号为 68）之前,理由与终端 turn 相同:待定计划在下一个 `turn/start` 退休,所以排在其后的 turn 会清空 dock 的 plan strip。这驱动 built-boot snapshot 与一个实时 `?fixture` 服务。
 

.agents/notes/implemented/feature/2026-07-30-web-search-card.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 .agents/notes/implemented/feature/2026-07-30-web-search-card.md
-2026-07-30-web-search-card.md: 23c89585770151551526223454e98d18716d1a44
-2026-07-30-web-search-card.zh.md: f92bd9f9231d947d4c70e283b462294c030e3f33
+2026-07-30-web-search-card.md: 930a705fc227d7961e9cb1a51b0b04774a62c6a4
+2026-07-30-web-search-card.zh.md: 83904c8f583af6a0ef3b24bbca2336c457644f6c

.agents/notes/implemented/feature/2026-07-30-web-search-card.md

@@ -54,9 +54,9 @@ Three sites consume the derivation, mirroring the terminal card's placement exac
 
 ## Testing
 
-`packages/client/ui-primitives/tests/search-block.spec.tsx` pins the component at per-file 100%: both kinds, the folded pre-cap total in the summary, the empty arm, per-file collapse/re-expand without touching neighbours, a file header counting as one capped row alongside its matches, the tail slice restoring its owning file header when the cut falls mid-file, the head/tail cap and its expand control across both shapes and the no-tail and default-cap edges, and the copy control writing the whole structured result on the accepted and refused clipboard paths.
+`packages/client/ui-primitives/tests/search-block.client.spec.tsx` pins the component at per-file 100%: both kinds, the folded pre-cap total in the summary, the empty arm, per-file collapse/re-expand without touching neighbours, a file header counting as one capped row alongside its matches, the tail slice restoring its owning file header when the cut falls mid-file, the head/tail cap and its expand control across both shapes and the no-tail and default-cap edges, and the copy control writing the whole structured result on the accepted and refused clipboard paths.
 
-`packages/client/ui-tool/tests/search-card.spec.tsx` pins the wiring at every render site: `searchCardModel`'s derivation for both kinds, the truncation signal, the replacement title, the recovery text surfaced only when capped, each null arm (running, no views, generic, terminal, unknown card, an uncompiled `kind`, and a known kind with a missing/malformed shape); the chat row's expand-gated matches and paths bodies through `GenericToolCard` (with the recovery footer) against the non-search args-JSON body; `SearchRow`'s resident card for both kinds, its recovery footer, its fallback body for both an errored search and a settled cardless result, its agreement with the summary row's run state, the replacement-title precedence, and the keyed registration under both `grep` and `glob` with one component; and the details panel's Output section for both kinds (with the recovery footer) against the non-search flattened form. `packages/client/ui-tool/src/*` sits on the coverage exclude list, so this file is written against no gate pressure. `packages/client/connection/src/client/fixture.ts` gains a `grep` turn emitting `kind: 'matches'` (three files, twelve rows over the row cap, `truncated` with a spill-recovery footer, so it exercises the head/tail cap and the recovery footer in the assembled snapshot) and a `glob` turn emitting `kind: 'paths'`, both driving the built-boot snapshot and the live `?fixture` server. `apps/web/tests/search-card.snapshot.ts` is the assembled-output check the repo contract asks for: it boots the real built `client.js` bundles through the keyless fixture transport, opens the fixture session, and pins the grep card's assembled shape — kind, truncation summary, the head/tail slice, and its expand control — under `apps/web/tests/snapshots/search-card/`, so a broken SearchRow registration or a dropped card fails a golden the built-boot smoke (boot-only by contract) cannot.
+`packages/client/ui-tool/tests/search-card.client.spec.tsx` pins the wiring at every render site: `searchCardModel`'s derivation for both kinds, the truncation signal, the replacement title, the recovery text surfaced only when capped, each null arm (running, no views, generic, terminal, unknown card, an uncompiled `kind`, and a known kind with a missing/malformed shape); the chat row's expand-gated matches and paths bodies through `GenericToolCard` (with the recovery footer) against the non-search args-JSON body; `SearchRow`'s resident card for both kinds, its recovery footer, its fallback body for both an errored search and a settled cardless result, its agreement with the summary row's run state, the replacement-title precedence, and the keyed registration under both `grep` and `glob` with one component; and the details panel's Output section for both kinds (with the recovery footer) against the non-search flattened form. `packages/client/ui-tool/src/*` sits on the coverage exclude list, so this file is written against no gate pressure. `packages/client/connection/src/client/fixture.ts` gains a `grep` turn emitting `kind: 'matches'` (three files, twelve rows over the row cap, `truncated` with a spill-recovery footer, so it exercises the head/tail cap and the recovery footer in the assembled snapshot) and a `glob` turn emitting `kind: 'paths'`, both driving the built-boot snapshot and the live `?fixture` server. `apps/web/tests/search-card.snapshot.ts` is the assembled-output check the repo contract asks for: it boots the real built `client.js` bundles through the keyless fixture transport, opens the fixture session, and pins the grep card's assembled shape — kind, truncation summary, the head/tail slice, and its expand control — under `apps/web/tests/snapshots/search-card/`, so a broken SearchRow registration or a dropped card fails a golden the built-boot smoke (boot-only by contract) cannot.
 
 ## Related
 

.agents/notes/implemented/feature/2026-07-30-web-search-card.zh.md

@@ -54,9 +54,9 @@ Status: implemented
 
 ## Testing
 
-`packages/client/ui-primitives/tests/search-block.spec.tsx` 以 per-file 100% 覆盖固定组件：两种 kind、折入摘要的截断前总数、空结果分支、逐文件折叠/再展开且不影响邻居、一个文件头与其匹配一起计为一个被截断行、切口落在文件中间时尾部切片恢复其所属文件头、跨两种形态的头/尾上限及其展开控件（含无尾与默认上限的边界），以及复制控件在接受与拒绝的剪贴板路径上写入整个结构化结果。
+`packages/client/ui-primitives/tests/search-block.client.spec.tsx` 以 per-file 100% 覆盖固定组件：两种 kind、折入摘要的截断前总数、空结果分支、逐文件折叠/再展开且不影响邻居、一个文件头与其匹配一起计为一个被截断行、切口落在文件中间时尾部切片恢复其所属文件头、跨两种形态的头/尾上限及其展开控件（含无尾与默认上限的边界），以及复制控件在接受与拒绝的剪贴板路径上写入整个结构化结果。
 
-`packages/client/ui-tool/tests/search-card.spec.tsx` 固定每个渲染点的接线：`searchCardModel` 对两种 kind 的推导、截断信号、替换标题、仅在截断时暴露的恢复文本，以及每个 null 分支（运行中、无视图、generic、terminal、未知卡片、本版本无法编译的 `kind`、以及一个形态缺失/错误的已知 kind）；通过 `GenericToolCard` 的展开门控 matches 与 paths body（含恢复脚注），对照非搜索的 args-JSON body；`SearchRow` 对两种 kind 的常驻卡片、它的恢复脚注、它对出错搜索与已结算无卡片结果两者的 fallback body、它与摘要行运行状态的一致、替换标题优先级，以及一个组件在 `grep` 与 `glob` 两个键下的 keyed 注册；以及 details panel 的 Output 段对两种 kind（含恢复脚注），对照非搜索的压平形态。`packages/client/ui-tool/src/*` 在覆盖排除清单上，因此该文件不受 gate 压力。`packages/client/connection/src/client/fixture.ts` 新增一个发出 `kind: 'matches'` 的 `grep` turn（三个文件、十二行超过行内上限、`truncated` 且带溢出恢复脚注，因此在组装快照里同时演练头/尾上限与恢复脚注）与一个发出 `kind: 'paths'` 的 `glob` turn，两者都驱动 built-boot snapshot 与实时 `?fixture` 服务。`apps/web/tests/search-card.snapshot.ts` 是仓库约定要求的组装输出检查：它通过 keyless fixture 传输启动真实构建的 `client.js` bundle，打开 fixture 会话，并把 grep 卡片的组装形态——kind、截断摘要、头/尾切片及其展开控件——固定在 `apps/web/tests/snapshots/search-card/` 下，因此一个损坏的 SearchRow 注册或被丢弃的卡片会让一个 golden 失败，而 built-boot smoke（按约定只测启动）无法捕获它。
+`packages/client/ui-tool/tests/search-card.client.spec.tsx` 固定每个渲染点的接线：`searchCardModel` 对两种 kind 的推导、截断信号、替换标题、仅在截断时暴露的恢复文本，以及每个 null 分支（运行中、无视图、generic、terminal、未知卡片、本版本无法编译的 `kind`、以及一个形态缺失/错误的已知 kind）；通过 `GenericToolCard` 的展开门控 matches 与 paths body（含恢复脚注），对照非搜索的 args-JSON body；`SearchRow` 对两种 kind 的常驻卡片、它的恢复脚注、它对出错搜索与已结算无卡片结果两者的 fallback body、它与摘要行运行状态的一致、替换标题优先级，以及一个组件在 `grep` 与 `glob` 两个键下的 keyed 注册；以及 details panel 的 Output 段对两种 kind（含恢复脚注），对照非搜索的压平形态。`packages/client/ui-tool/src/*` 在覆盖排除清单上，因此该文件不受 gate 压力。`packages/client/connection/src/client/fixture.ts` 新增一个发出 `kind: 'matches'` 的 `grep` turn（三个文件、十二行超过行内上限、`truncated` 且带溢出恢复脚注，因此在组装快照里同时演练头/尾上限与恢复脚注）与一个发出 `kind: 'paths'` 的 `glob` turn，两者都驱动 built-boot snapshot 与实时 `?fixture` 服务。`apps/web/tests/search-card.snapshot.ts` 是仓库约定要求的组装输出检查：它通过 keyless fixture 传输启动真实构建的 `client.js` bundle，打开 fixture 会话，并把 grep 卡片的组装形态——kind、截断摘要、头/尾切片及其展开控件——固定在 `apps/web/tests/snapshots/search-card/` 下，因此一个损坏的 SearchRow 注册或被丢弃的卡片会让一个 golden 失败，而 built-boot smoke（按约定只测启动）无法捕获它。
 
 ## Related
 

.agents/notes/implemented/feature/2026-08-01-windows-pwsh-default.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 .agents/notes/implemented/feature/2026-08-01-windows-pwsh-default.md
-2026-08-01-windows-pwsh-default.md: 4e681b32088954d870df86898e26fe2cae669f14
-2026-08-01-windows-pwsh-default.zh.md: a9d600f8a8e47db49c3733f33091e667e341c6a7
+2026-08-01-windows-pwsh-default.md: c66e289c24d6024b1df53cd60f25c27d46fafc5a
+2026-08-01-windows-pwsh-default.zh.md: b2ad45ec96d546d01436a383ed7d8884b978aa31

.agents/notes/implemented/feature/2026-08-01-windows-pwsh-default.md

@@ -12,9 +12,8 @@ The harness's shipped execution profile is bash-first on every platform. Windows
 
 Windows hosts booting a shipped profile (`dsh web`, `dsh --profile headless`, one-shot tasks) get the PowerShell stack by default; POSIX hosts are unchanged.
 
-- **The platform layer is a data file, not a roster rewrite.** `@deepseek-ai/dsh-base` ships [`windows.cordis.patch.yml`](../../../../packages/bundle/base/windows.cordis.patch.yml) alongside its universal `cordis.patch.yml`. It disables the POSIX-only `bash-sandbox`/`tool-bash` rows and inserts `pwsh-sandbox`/`tool-pwsh`. The later [Windows ACL sandbox decision](2026-08-08-windows-acl-restricted-token-sandbox.md) filled the win32 runner chain and superseded this note's original unconfined roster: `sandbox`, `sandbox-policy`, `fs-sandbox`, `permission`/`ui-permission`, and `approval` now stay enabled exactly as on POSIX, while the ACL backend truthfully reports its Everyone and hard-link gaps as partial enforcement.
-- **The launcher injects the layer by platform.** `apps/cli/src/windows-shell.ts` resolves it from the base bundle layer's `packageDir` between the bundle layers and the user layers on `win32` hosts, in every composition path (boot, config-only HMR recomposition, config dumps). Overriding the shipped default is a composition decision: a Windows host that prefers the bash stack re-enables the bash rows and disables both pwsh rows through its profile or home `cordis.patch.yml`. Custom profiles without the base bundle are skipped (they own their shell stack); a base bundle that ships no Windows shell patch fails loud.
-- **Module resolution is restored for cold starts.** The profiles-rework CLI dropped the pwsh packages from `apps/cli`'s dependency closure, so `healProfilesModuleFallback` never linked them into `$DSH_HOME/profiles/node_modules` and a fresh Windows host could not resolve the inserted rows. `apps/cli` and `dsh-base` declare `dsh-pwsh-sandbox`/`dsh-tool-pwsh`; the executor's dependency chain supplies `dsh-pwsh-local`, and the base bundle lists every row plugin as a dependency by house style.
+- **The base patch gates both shell stacks on its own rows** (the [loader `disabled` interpolation](../architecture/2026-08-11-loader-entry-disabled-interpolation.md) note records the mechanism and the platform-layer fold): `bash-sandbox`/`tool-bash` carry `disabled: !!js process.platform === 'win32'` (bash has no Windows runner), and their twins `pwsh-sandbox`/`tool-pwsh` mount only on win32 with the inverted expression — one shared patch file, exactly one shell stack per host. The confined pwsh stack runs over the ACL restricted-token runner, and the permission surface stays exactly as on POSIX (the [Windows ACL restricted-token sandbox](2026-08-08-windows-acl-restricted-token-sandbox.md) note owns that roster). Overriding the shipped default is a composition decision: a Windows host that prefers the bash stack or an unconfined pwsh executor overrides these rows through its profile or home `cordis.patch.yml` (the bash-restore recipe must be complete: disable `pwsh-sandbox`/`tool-pwsh` AND re-enable `bash-sandbox`/`tool-bash` — both executor families register the same `bash` service, so an incomplete recipe fails loud at load) — composition config is the one override channel. The separate `windows.cordis.patch.yml` layer and the launcher's `apps/cli/src/windows-shell.ts` injection are deleted; the layer existed only because entry metadata was static.
+- **Module resolution is restored for cold starts.** The profiles-rework CLI dropped the pwsh packages from `apps/cli`'s dependency closure, so `healProfilesModuleFallback` never linked them into `$DSH_HOME/profiles/node_modules` and a fresh Windows host could not resolve the pwsh rows. `apps/cli` and `dsh-base` declare `dsh-pwsh-sandbox`/`dsh-tool-pwsh`, and the executor's dependency chain supplies `dsh-pwsh-local`; the base bundle lists every row plugin as a dependency by house style.
 
 The pwsh GUI rendering shipped earlier with the [pwsh UI presentation matches bash decision](2026-08-05-pwsh-ui-bash-parity.md); the [pwsh tool bash parity decision](2026-08-02-pwsh-tool-bash-parity.md) ships the tool's surface. Nothing in this decision changes POSIX behavior.
 
@@ -32,13 +31,13 @@ The pwsh GUI rendering shipped earlier with the [pwsh UI presentation matches ba
 
 ## Consequences
 
-- A Windows host running a shipped `dsh` surface gets `pwsh` as its shell tool and PowerShell as the `ctx.bash` executor without configuration; `bash` is absent from the model-visible roster there (its tool row is disabled).
+- A Windows host running a shipped `dsh` surface gets the confined `pwsh` as its shell tool and PowerShell as the `ctx.bash` executor without configuration; `bash` is absent from the model-visible roster there. On the Web surface the shell TOOL rows come from the session's preset (the [loader `disabled` interpolation](../architecture/2026-08-11-loader-entry-disabled-interpolation.md) note owns the one-plane mechanism): each shipped preset declares `tool-pwsh` gated by `process.platform !== 'win32'` and its `tool-bash` twin by the inverted expression, so the preset layer exposes exactly one shell tool per host.
 - Windows commands and fs operations share the sandbox policy, permission switcher, and approval service. The ACL runner confines writes but reports `enforcement: 'partial'`; explicit `danger-full-access` remains the approved bypass rather than the platform default.
-- POSIX hosts are unchanged: the platform layer never applies, and the bash stack remains the universal `cordis.patch.yml` rows.
-- Windows hosts that prefer the bash stack (e.g. with WSL/Git-Bash on PATH) override the shipped default through their profile or home `cordis.patch.yml` — disabling `pwsh-sandbox`/`tool-pwsh` and re-enabling `bash-sandbox`/`tool-bash` (both executors register the same `bash` service, so an incomplete recipe fails loud at load) — composition config is the one override channel.
+- POSIX hosts mount the bash stack as before; the pwsh rows sit disabled in their composition, because the one shared patch file lists both stacks and each row gates itself.
+- A Windows host that prefers the bash stack (e.g. with WSL/Git-Bash on PATH) overrides the shipped rows through its profile or home `cordis.patch.yml` — disabling `pwsh-sandbox`/`tool-pwsh` and re-enabling `bash-sandbox`/`tool-bash` (both executors register the same `bash` service, so an incomplete recipe fails loud at load) — composition config is the one override channel.
 
 ## Verification
 
-- Unit: `apps/cli/tests/windows-shell.spec.ts` pins the win32 default, custom-profile skip, missing-patch failure, cold-start dependency closure, and real composed roster; `packages/bundle/base/tests/base.spec.ts` pins that the Windows layer disables only the bash rows, inserts the confined pwsh rows, and leaves sandbox, permission, fs, and approval ownership untouched.
-- Keyless: a win32 `dsh --profile <name> --dump-config` shows the pwsh rows with `windows.cordis.patch.yml` provenance and the bash rows disabled; the POSIX dump (CI Linux) is unchanged.
+- Unit: `apps/cli/tests/windows-shell.spec.ts` composes the REAL shipped bundle layers (dsh-base + dsh-web-app resolved from the app installation) through the boot's patch algorithm and pins the effective per-platform roster — the win32 pwsh roster, the POSIX bash roster, and the base-only profile — plus the preset-level shell-tool gates (`tool-bash`/`tool-pwsh`) and the cold-start resolution closure; `packages/bundle/base/tests/base.spec.ts` pins the four shell rows' symmetric `!!js` platform gates and that no separate platform patch ships.
+- Keyless: a `dsh --profile <name> --dump-config` shows both stacks in the one shared patch layer, with each row's own `disabled` expression deciding the roster at mount.
 - The real-composition smoke boots the web profile on win32 with the pwsh stack mounted (the exact roster this note describes).

.agents/notes/implemented/feature/2026-08-01-windows-pwsh-default.zh.md

@@ -12,9 +12,8 @@ harness 交付的执行画像在每个平台都是 bash 优先。Windows 主机
 
 启动交付 profile（`dsh web`、`dsh --profile headless`、一次性任务）的 Windows 主机默认获得 PowerShell 栈；POSIX 主机不变。
 
-- **平台层是数据文件，不是清单重写。** `@deepseek-ai/dsh-base` 随通用 `cordis.patch.yml` 一起交付 [`windows.cordis.patch.yml`](../../../../packages/bundle/base/windows.cordis.patch.yml)。它禁用仅限 POSIX 的 `bash-sandbox`/`tool-bash` 行，并插入 `pwsh-sandbox`/`tool-pwsh`。后续的 [Windows ACL 沙箱决策](2026-08-08-windows-acl-restricted-token-sandbox.md)填充了 win32 runner 链，并取代了本笔记最初的不限权清单：`sandbox`、`sandbox-policy`、`fs-sandbox`、`permission`/`ui-permission` 与 `approval` 均与 POSIX 上一样保持启用，而 ACL 后端则如实把 Everyone 与硬链接缺口报告为部分强制执行。
-- **启动器按平台注入该层。** `apps/cli/src/windows-shell.ts` 在 `win32` 主机上从 base bundle 层的 `packageDir` 解析它，置于 bundle 层与用户层之间，覆盖所有组合路径（启动、config-only HMR 重组合、配置转储）。覆盖交付默认是组合决策：偏好 bash 栈的 Windows 主机通过其 profile 或 home 的 `cordis.patch.yml` 重新启用 bash 行，并禁用两个 pwsh 行。未挂 base bundle 的自定义 profile 被跳过（它们自己拥有 shell 栈）；base bundle 缺 `windows.cordis.patch.yml` 时 fail loud。
-- **冷启动的模块解析已恢复。** profiles 重构把 pwsh 包从 `apps/cli` 的依赖闭包中删掉了，`healProfilesModuleFallback` 因此从未把它们链接进 `$DSH_HOME/profiles/node_modules`，新 Windows 主机解析不到插入的行。`apps/cli` 与 `dsh-base` 声明 `dsh-pwsh-sandbox`/`dsh-tool-pwsh`；执行器的依赖链提供 `dsh-pwsh-local`，按仓库惯例，base bundle 把每个行插件都列为依赖。
+- **base patch 在自身行上按平台门控两个 shell 栈**（[loader `disabled` 插值](../architecture/2026-08-11-loader-entry-disabled-interpolation.md) note 记录了该机制与平台层折叠）：`bash-sandbox`/`tool-bash` 携带 `disabled: !!js process.platform === 'win32'`（bash 没有 Windows runner），它们的孪生行 `pwsh-sandbox`/`tool-pwsh` 以取反的表达式仅在 win32 挂载——同一份 patch 文件，每个宿主恰好挂载一个 shell 栈。受限 pwsh 栈运行在 ACL 受限令牌 runner 之上，权限面与 POSIX 完全一致（[Windows ACL 受限令牌沙箱](2026-08-08-windows-acl-restricted-token-sandbox.md) note 拥有该清单）。覆盖交付默认是组合决策：偏好 bash 栈或不限权 pwsh 执行器的 Windows 主机通过其 profile 或 home 的 `cordis.patch.yml` 覆盖这些行（bash 恢复配方必须完整：禁用 `pwsh-sandbox`/`tool-pwsh` 并重新启用 `bash-sandbox`/`tool-bash`——两个执行器家族注册同一个 `bash` 服务，配方不完整会在加载时 fail loud）——组合配置是唯一的覆盖通道。独立的 `windows.cordis.patch.yml` 层与启动器的 `apps/cli/src/windows-shell.ts` 注入已删除；该层只因条目元数据是静态的而存在。
+- **冷启动的模块解析已恢复。** profiles 重构把 pwsh 包从 `apps/cli` 的依赖闭包中删掉了，`healProfilesModuleFallback` 因此从未把它们链接进 `$DSH_HOME/profiles/node_modules`，新 Windows 主机解析不到 pwsh 行。`apps/cli` 与 `dsh-base` 声明 `dsh-pwsh-sandbox`/`dsh-tool-pwsh`，执行器的依赖链提供 `dsh-pwsh-local`；按仓库惯例，base bundle 把每个行插件都列为依赖。
 
 pwsh GUI 渲染已随 [pwsh UI 呈现与 bash 对齐决策](2026-08-05-pwsh-ui-bash-parity.md) 先行交付；[pwsh 工具与 bash 对齐决策](2026-08-02-pwsh-tool-bash-parity.md) 交付了工具表面。本决策不改变任何 POSIX 行为。
 
@@ -32,13 +31,13 @@ pwsh GUI 渲染已随 [pwsh UI 呈现与 bash 对齐决策](2026-08-05-pwsh-ui-b
 
 ## 后果
 
-- 运行交付版 `dsh` 表面的 Windows 主机无需配置即获得 `pwsh` 作为 shell 工具、PowerShell 作为 `ctx.bash` 执行器；那里的模型可见清单中没有 `bash`（其工具行被禁用）。
+- 运行交付版 `dsh` 表面的 Windows 主机无需配置即获得受限 `pwsh` 作为 shell 工具、PowerShell 作为 `ctx.bash` 执行器；那里的模型可见清单中没有 `bash`。在 Web 表面，shell 工具行来自会话的预设（[loader `disabled` 插值](../architecture/2026-08-11-loader-entry-disabled-interpolation.md) note 拥有 one-plane 机制）：每个 shipped 预设声明 `tool-pwsh`（以 `process.platform !== 'win32'` 门控）及其孪生行 `tool-bash`（取反表达式），因此预设层每台宿主恰好暴露一个 shell 工具。
 - Windows 命令与 fs 操作共用沙箱策略、权限切换器和 approval 服务。ACL runner 限制写入，但报告 `enforcement: 'partial'`；显式的 `danger-full-access` 仍是获准的绕过方式，而非平台默认。
-- POSIX 主机不变：平台层永不生效，bash 栈仍是通用 `cordis.patch.yml` 的行。
-- 偏好 bash 栈的 Windows 主机（例如 PATH 上有 WSL/Git-Bash 时）通过其 profile 或 home 的 `cordis.patch.yml` 覆盖交付默认——禁用 `pwsh-sandbox`/`tool-pwsh` 并重新启用 `bash-sandbox`/`tool-bash`（两个执行器注册同一个 `bash` 服务，配方不完整会在加载时 fail loud）——组合配置是唯一的覆盖通道。
+- POSIX 主机如常挂载 bash 栈；pwsh 行以其自身的门控表达式处于禁用状态——同一份共享 patch 文件列出两个栈，每个行自己决定挂载。
+- 偏好 bash 栈的 Windows 主机（例如 PATH 上有 WSL/Git-Bash 时）通过其 profile 或 home 的 `cordis.patch.yml` 覆盖交付行——禁用 `pwsh-sandbox`/`tool-pwsh` 并重新启用 `bash-sandbox`/`tool-bash`（两个执行器注册同一个 `bash` 服务，配方不完整会在加载时 fail loud）——组合配置是唯一的覆盖通道。
 
 ## 验证
 
-- 单元：`apps/cli/tests/windows-shell.spec.ts` 固定 win32 默认、自定义 profile 跳过、缺少 patch 时失败、冷启动依赖闭包和真实组合清单；`packages/bundle/base/tests/base.spec.ts` 固定 Windows 层仅禁用 bash 行、插入受限的 pwsh 行，并且不改变沙箱、权限、fs 与审批的归属。
-- Keyless：win32 上的 `dsh --profile <name> --dump-config` 显示带 `windows.cordis.patch.yml` 出处的 pwsh 行、被禁用的 bash 行；POSIX 转储（CI Linux）不变。
+- 单元：`apps/cli/tests/windows-shell.spec.ts` 通过启动所用的 patch 算法组合真实交付的 bundle 层（从应用安装解析的 dsh-base + dsh-web-app），固定每个平台的有效清单——win32 pwsh 清单、POSIX bash 清单与 base-only profile——外加预设级 shell 工具门控（`tool-bash`/`tool-pwsh`）与冷启动解析闭包；`packages/bundle/base/tests/base.spec.ts` 固定四个 shell 行的对称 `!!js` 平台门控，并断言不再交付独立的平台 patch。
+- Keyless：`dsh --profile <name> --dump-config` 在同一份共享 patch 层中显示两个栈，每个行以自己的 `disabled` 表达式在挂载时决定清单。
 - 真实组合冒烟在 win32 上启动 web profile，pwsh 栈挂载成功（即本笔记描述的确切清单）。

.agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.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 .agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.md
-2026-08-02-web-thinking-tail-scroll.md: 18e94b2e0075bf7099b9b48177de2e274896942a
-2026-08-02-web-thinking-tail-scroll.zh.md: 7bafeb0f64f05a41c502aba8f479e391c8b395f0
+2026-08-02-web-thinking-tail-scroll.md: b9aa47a01b4d8e22baddac1b03f52b3524250941
+2026-08-02-web-thinking-tail-scroll.zh.md: 34a0a39f88a9511a1c93d0b21b3ac13903848e98

.agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.md

@@ -28,4 +28,4 @@ The collapsed row now communicates provider cadence through content motion as we
 
 ## Testing
 
-`packages/client/ui-conversation/tests/reasoning-row.spec.tsx` pins the latest-line selection, the calculated right-edge scroll position, and the settlement reset to the first line and `scrollLeft = 0`. The keyless assembled Chromium scenario in `apps/web/tests/lifecycle-chrome.e2e.ts` replays real recorded reasoning chunks at observable pacing, narrows the viewport until the summary overflows, and asserts that the live collapsed Think row reaches its actual browser scroll extent. Its settled replay golden remains unchanged, proving the historical summary contract stays stable.
+`packages/client/ui-conversation/tests/reasoning-row.client.spec.tsx` pins the latest-line selection, the calculated right-edge scroll position, and the settlement reset to the first line and `scrollLeft = 0`. The keyless assembled Chromium scenario in `apps/web/tests/lifecycle-chrome.e2e.ts` replays real recorded reasoning chunks at observable pacing, narrows the viewport until the summary overflows, and asserts that the live collapsed Think row reaches its actual browser scroll extent. Its settled replay golden remains unchanged, proving the historical summary contract stays stable.

.agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.zh.md

@@ -28,4 +28,4 @@ Web Think 行在结算与流式 block 中都把 reasoning 首行渲染成折叠
 
 ## 测试
 
-`packages/client/ui-conversation/tests/reasoning-row.spec.tsx` 固定最新行选择、算出的右端滚动位置，以及结算后恢复首行和 `scrollLeft = 0`。`apps/web/tests/lifecycle-chrome.e2e.ts` 中的 keyless 完整 Chromium 场景以可观察节奏回放真实录制的 reasoning chunks，把视口收窄到摘要溢出，并断言实时折叠 Think 行到达真实浏览器的滚动边界。其结算态 replay golden 保持不变，证明历史摘要约定仍然稳定。
+`packages/client/ui-conversation/tests/reasoning-row.client.spec.tsx` 固定最新行选择、算出的右端滚动位置，以及结算后恢复首行和 `scrollLeft = 0`。`apps/web/tests/lifecycle-chrome.e2e.ts` 中的 keyless 完整 Chromium 场景以可观察节奏回放真实录制的 reasoning chunks，把视口收窄到摘要溢出，并断言实时折叠 Think 行到达真实浏览器的滚动边界。其结算态 replay golden 保持不变，证明历史摘要约定仍然稳定。

.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.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 .agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md
-2026-08-03-web-search-source-scroll.md: f6b118b91d3d2102e11fa7b6d068621e961a7674
-2026-08-03-web-search-source-scroll.zh.md: 58eae594bd18c58f7fb80322f6902abdbba49ba7
+2026-08-03-web-search-source-scroll.md: 3402f519e1974b99e1f5a87dcd53b4d94a1a8374
+2026-08-03-web-search-source-scroll.zh.md: 34ee46c6837cc81740d3f74df1f2c6eae689adf2

.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md

@@ -36,7 +36,7 @@ Every source the tool returned is always in the DOM, so no source the view carri
 
 ## Testing
 
-`packages/client/ui-primitives/tests/web-block.spec.tsx` drops the collapse cases (head/tail slice, expand-on-click, collapsed-tail numbering, expander-out-of-numbering, head-alone, default cap) and adds: a 30-source card renders all 30 `<li>` with no `[aria-expanded]` and no `<button>`, every `<ol>` child is a source `<li>`, and `<li value>` numbers 1..N contiguously. `packages/client/ui-tool/tests/web-card.spec.tsx` drops the `CHAT_WEB_MAX_SOURCES` cap assertion; the WebRow expansion test still asserts the card shows every source field. The `packages/web/tool-web` tests are unchanged — the model side did not move.
+`packages/client/ui-primitives/tests/web-block.client.spec.tsx` drops the collapse cases (head/tail slice, expand-on-click, collapsed-tail numbering, expander-out-of-numbering, head-alone, default cap) and adds: a 30-source card renders all 30 `<li>` with no `[aria-expanded]` and no `<button>`, every `<ol>` child is a source `<li>`, and `<li value>` numbers 1..N contiguously. `packages/client/ui-tool/tests/web-card.client.spec.tsx` drops the `CHAT_WEB_MAX_SOURCES` cap assertion; the WebRow expansion test still asserts the card shows every source field. The `packages/web/tool-web` tests are unchanged — the model side did not move.
 
 jsdom resolves no CSS Modules layout, so it reports `scrollHeight === clientHeight` for every element and cannot witness the scroll at all. The geometry is pinned in the assembled browser instead, by `apps/web/tests/web-search-round.e2e.ts`: its deterministic search double returns 12 provider results, each with a title, a citation snippet, and a date. That first pins the seam's cap end to end in a real composition — the shipped `searchMaxResults` keeps 8, the model-visible render text carries the 8 kept titles and none of the 4 dropped URLs plus `(Showing the first 8 sources. Refine the query for more.)`, and `meta.truncated` is true. A case after the aria golden then expands the `web_search` row and asserts on the card's `<ol>`: 8 `<li>`, no `<button>` anywhere in the card, the `来源列表已截断` indicator visible, and computed `max-height: 320px` with `overflow-y: auto` over `scrollHeight` 574 against `clientHeight` 320. A further case measures a `999. ` marker in the list's own inherited font and requires the computed `padding-left` to be at least that wide, so the marker room the scroll container cannot clip back is pinned against the widest marker rather than against one fixture's source count. Neither the recorded stream nor the aria golden moved: replay is a positional cursor over the fixture's `assistant/chunk` entries and the search double is a separate local endpoint the provider reaches by `fetch`, while the card is collapsed at capture time so its `<ol>` is out of the DOM and the summary row carries no source count.
 

.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.zh.md

@@ -36,7 +36,7 @@ Status: implemented
 
 ## 测试
 
-`packages/client/ui-primitives/tests/web-block.spec.tsx` 删去折叠相关用例（首尾切片、点击展开、折叠尾部编号、展开器不计入编号、仅首部、默认上限），并新增：一张含 30 条来源的卡片渲染出全部 30 个 `<li>`，无 `[aria-expanded]`、无 `<button>`，每个 `<ol>` 子元素都是一条来源 `<li>`，且 `<li value>` 从 1 到 N 连续编号。`packages/client/ui-tool/tests/web-card.spec.tsx` 删去 `CHAT_WEB_MAX_SOURCES` 上限断言；WebRow 展开测试仍断言卡片展示每一个来源字段。`packages/web/tool-web` 的测试不变——模型侧没有改动。
+`packages/client/ui-primitives/tests/web-block.client.spec.tsx` 删去折叠相关用例（首尾切片、点击展开、折叠尾部编号、展开器不计入编号、仅首部、默认上限），并新增：一张含 30 条来源的卡片渲染出全部 30 个 `<li>`，无 `[aria-expanded]`、无 `<button>`，每个 `<ol>` 子元素都是一条来源 `<li>`，且 `<li value>` 从 1 到 N 连续编号。`packages/client/ui-tool/tests/web-card.client.spec.tsx` 删去 `CHAT_WEB_MAX_SOURCES` 上限断言；WebRow 展开测试仍断言卡片展示每一个来源字段。`packages/web/tool-web` 的测试不变——模型侧没有改动。
 
 jsdom 不解析 CSS Modules 布局，对任何元素都报 `scrollHeight === clientHeight`，因此它根本无从见证这次滚动。几何改由组装态浏览器钉住，位于 `apps/web/tests/web-search-round.e2e.ts`：其确定性 search double 返回 12 条提供方结果，每条带标题、引用摘录与日期。这首先在真实组合里端到端钉住 seam 的裁剪——出厂 `searchMaxResults` 保留 8 条，面向模型的 render 文本含这 8 条标题、不含被丢弃的 4 条 URL，并含 `(Showing the first 8 sources. Refine the query for more.)`，`meta.truncated` 为 true。随后位于 aria golden 之后的一个用例展开 `web_search` 行，对卡片的 `<ol>` 断言：8 个 `<li>`、卡片内任何位置都没有 `<button>`、`来源列表已截断` 指示可见，以及计算样式 `max-height: 320px` 与 `overflow-y: auto`，`scrollHeight` 为 574、`clientHeight` 为 320。再后一个用例在列表自身继承的字体下量出 `999. ` 序号的宽度，要求计算后的 `padding-left` 不小于该宽度，从而把滚动容器无从滚回的那段序号空间钉在最宽序号上，而非钉在某一份 fixture（测试前置数据）的来源条数上。录制的模型流与 aria golden 都未变动：回放是对 fixture 中 `assistant/chunk` 条目的位置游标，而 search double 是提供方经 `fetch` 抵达的另一个本地端点；捕获时卡片处于折叠状态，其 `<ol>` 不在 DOM 中，摘要行也不携带来源数量。
 

.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.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 .agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md
-2026-08-04-pointer-revealed-sidebar-scrollbars.md: 997945d55f7294f56a30917b050b5455de74acdf
-2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md: 128d7f12ba3e5be1c87774e79b3278383f59bf0b
+2026-08-04-pointer-revealed-sidebar-scrollbars.md: 5c6fff378932d3e63bc92ed27e9b0341effaf6b8
+2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md: edfc6e34925ecb0526946c462f8cf4dc701275fd

.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md

@@ -50,9 +50,9 @@ Hiding no longer counts as elevating: only an l2 rebind exempts a sheet from "ev
 
 ## Testing
 
-`packages/client/ui-sidebar/tests/pointer-scrollbars.spec.tsx` drives the class through the transitions with fake timers: revealed on entry, still revealed one millisecond before the linger closes, quiet one millisecond after, and cancelled by a return within the window. Two more cover the geometric leave: a `pointermove` landing outside the column's box hides the bars without any DOM leave (the settings-panel shape), and one landing back inside cancels a pending hide. It also unmounts mid-linger and asserts no timer survives — a pending hide firing into a dead component is the failure this shape is prone to. The events are `pointerover`/`pointerout` carrying a `relatedTarget`, because React synthesizes enter and leave from those and ignores the raw ones.
+`packages/client/ui-sidebar/tests/pointer-scrollbars.client.spec.tsx` drives the class through the transitions with fake timers: revealed on entry, still revealed one millisecond before the linger closes, quiet one millisecond after, and cancelled by a return within the window. Two more cover the geometric leave: a `pointermove` landing outside the column's box hides the bars without any DOM leave (the settings-panel shape), and one landing back inside cancels a pending hide. It also unmounts mid-linger and asserts no timer survives — a pending hide firing into a dead component is the failure this shape is prone to. The events are `pointerover`/`pointerout` carrying a `relatedTarget`, because React synthesizes enter and leave from those and ignores the raw ones.
 
-`packages/client/ui-sidebar/tests/scrollbar-quiet-styles.spec.ts` reads the sheet: the rule states both halves of the pair — rebinding the resting thumb alone would leave the hover colour painting the moment the pointer reached the bar — and states no `scrollbar-gutter`, which belongs to the scrolling region.
+`packages/client/ui-sidebar/tests/scrollbar-quiet-styles.client.spec.ts` reads the sheet: the rule states both halves of the pair — rebinding the resting thumb alone would leave the hover colour painting the moment the pointer reached the bar — and states no `scrollbar-gutter`, which belongs to the scrolling region.
 
 `apps/web/tests/sidebar-scrollbar.e2e.ts` is where the two halves meet a real engine. It parks the pointer over the list before every colour reading, since a scenario that never moves the mouse would measure the quiet state throughout and read as vacuous green. Its own test then moves the pointer away, asserts the thumb is still drawn on the leave itself, polls until it resolves to `rgba(0, 0, 0, 0)`, re-measures the geometry there to prove the reservation held while the bar was hidden, and scrolls the list programmatically — what a keyboard or a touch drag does — to pin that a pointerless scroll draws nothing. The committed golden records the thumb at both pointer positions in both palettes.
 

.agents/notes/implemented/feature/2026-08-04-pointer-revealed-sidebar-scrollbars.zh.md

@@ -50,9 +50,9 @@ Status: implemented
 
 ## 测试
 
-`packages/client/ui-sidebar/tests/pointer-scrollbars.spec.tsx` 用假定时器把这个类走过各次跃迁：进入时显示，拖尾结束前 1 毫秒仍然显示，结束后 1 毫秒转为静默，以及窗口内折返会取消隐藏。另有两条覆盖几何判定的离开：落在列盒子之外的 `pointermove` 会在没有任何 DOM leave 的情况下隐藏滚动条（即设置面板那种形态），落回盒子之内的则取消待触发的隐藏。它还在拖尾进行中卸载组件并断言没有定时器存活——待触发的隐藏落到已销毁的组件上，正是这种写法容易犯的错。事件用的是带 `relatedTarget` 的 `pointerover`／`pointerout`，因为 React 由它们合成 enter 与 leave，而会忽略原生的那两个事件。
+`packages/client/ui-sidebar/tests/pointer-scrollbars.client.spec.tsx` 用假定时器把这个类走过各次跃迁：进入时显示，拖尾结束前 1 毫秒仍然显示，结束后 1 毫秒转为静默，以及窗口内折返会取消隐藏。另有两条覆盖几何判定的离开：落在列盒子之外的 `pointermove` 会在没有任何 DOM leave 的情况下隐藏滚动条（即设置面板那种形态），落回盒子之内的则取消待触发的隐藏。它还在拖尾进行中卸载组件并断言没有定时器存活——待触发的隐藏落到已销毁的组件上，正是这种写法容易犯的错。事件用的是带 `relatedTarget` 的 `pointerover`／`pointerout`，因为 React 由它们合成 enter 与 leave，而会忽略原生的那两个事件。
 
-`packages/client/ui-sidebar/tests/scrollbar-quiet-styles.spec.ts` 直接读样式表：该规则必须写出这组变量的两半——只重新绑定静止态滑块，会让指针一碰到滚动条就露出 hover 颜色——并且不得出现 `scrollbar-gutter`，那属于滚动区域自己。
+`packages/client/ui-sidebar/tests/scrollbar-quiet-styles.client.spec.ts` 直接读样式表：该规则必须写出这组变量的两半——只重新绑定静止态滑块，会让指针一碰到滚动条就露出 hover 颜色——并且不得出现 `scrollbar-gutter`，那属于滚动区域自己。
 
 `apps/web/tests/sidebar-scrollbar.e2e.ts` 是两半在真实引擎里汇合的地方。它在每次读取颜色前先把指针停在列表上，因为一个从不移动鼠标的场景全程测到的都是静默状态，会在未实际验证目标行为的情况下通过。随后它自己的用例把指针移开，断言在 leave 当下滑块仍在绘制，轮询直到它解析为 `rgba(0, 0, 0, 0)`，在该状态下重新测量几何以证明滚动条隐藏期间那份预留依然生效，并以编程方式滚动列表——键盘或触摸拖动所做的事——来钉住无指针滚动不绘制任何滑块。提交的 golden 记录了两套调色板下、两个指针位置上的滑块颜色。
 

.agents/notes/implemented/feature/2026-08-06-manager-owned-subagent-settlement-delivery.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 .agents/notes/implemented/feature/2026-08-06-manager-owned-subagent-settlement-delivery.md
-2026-08-06-manager-owned-subagent-settlement-delivery.md: e06fe2b4ca7dd9a975f70524979de09d13cdcf79
-2026-08-06-manager-owned-subagent-settlement-delivery.zh.md: 77e8b5e4bae9b05e08bf2c4a4bf997b688cd1157
+2026-08-06-manager-owned-subagent-settlement-delivery.md: 11669d4603e658d1478557f81c2d2b4d5495bca7
+2026-08-06-manager-owned-subagent-settlement-delivery.zh.md: f3684777ccb3800226803e998438147ebc1dbf16

.agents/notes/implemented/feature/2026-08-06-manager-owned-subagent-settlement-delivery.md

@@ -16,7 +16,7 @@ The signal already existed. `subagent/end` has carried `stopReason` and `lastAss
 
 The continuation manager delivers the account itself, from inside the disposal transaction that ends the Activation.
 
-When a resident Activation settles, `notifySettlement()` resolves the child's durable direct parent and sends it one user-role message: the epoch's outcome as a sentence the parent can act on, then the child's final assistant content, or a statement that it produced none. Delivery is unconditional for every child whose id a caller actually received. It does not consult whether the child reported, and it keeps no bookkeeping that could make the promise conditional — that unconditionality is what lets `tool-subagent` tell the model "you are told when it finishes, so never poll or wait on it" and have that be true. A materialization rolled back before its first accepted message stays silent, because the caller was told that child was not established.
+When a resident Activation settles, `notifySettlement()` resolves the child's durable direct parent and sends it one user-role message: the epoch's outcome as a sentence the parent can act on, then the child's final assistant content, or a statement that it produced none. Delivery is unconditional for every child whose id a caller actually received. It does not consult whether the child reported, and it keeps no bookkeeping that could make the promise conditional — that unconditionality is what lets `tool-subagent` promise a runtime notice containing the outcome and any final assistant message. A materialization rolled back before its first accepted message stays silent, because the caller was told that child was not established.
 
 ### Provenance
 
@@ -44,7 +44,7 @@ Delivery never blocks or fails teardown. A rejected send is logged and dropped,
 
 ### The epoch's own log is the whole account
 
-`epochStopReason()` reads the epoch's outcome from its own log, because teardown succeeding says nothing about whether the model errored, hit its ceiling, or was stopped. Reading turns alone got that wrong twice, in the same shape both times: a turn stopped before its first step leaves a `turn/end` indistinguishable from the balanced no-op turns a rejection or an emptied claim produces, so the filter that skipped those also skipped real endings and answered with the previous turn's clean completion. The durability checkpoint (`dsh-session-checkpoint-policy`, in every shipped profile) and prompt assembly both run at that boundary and both propagate, and `Inbox.claim()` has already taken the messages by then — so the parent was told a child finished while the delivery it was waiting on had been swallowed. Under a promise that says "you are told when it finishes, so never poll", that is the one failure a parent cannot detect and will not retry.
+`epochStopReason()` reads the epoch's outcome from its own log, because teardown succeeding says nothing about whether the model errored, hit its ceiling, or was stopped. Reading turns alone got that wrong twice, in the same shape both times: a turn stopped before its first step leaves a `turn/end` indistinguishable from the balanced no-op turns a rejection or an emptied claim produces, so the filter that skipped those also skipped real endings and answered with the previous turn's clean completion. The durability checkpoint (`dsh-session-checkpoint-policy`, in every shipped profile) and prompt assembly both run at that boundary and both propagate, and `Inbox.claim()` has already taken the messages by then — so the parent was told a child finished while the delivery it was waiting on had been swallowed. Under the advertised automatic settlement notice, that is the one failure a parent cannot detect and will not retry.
 
 The missing fact was never the turn's; it was the inbox's. `Inbox` logs every mutation with `removedCount` and marks a cancellation `outcome: 'canceled'`, which separates a turn claiming its input from work being dropped unrun. `foldConsumedWork()` in `dsh-agent` folds both vocabularies into one answer: the latest turn that accounts for consumed work — stepped, or claimed-then-failed, stopped, or rejected — and whether accepted work was cancelled after it with no turn opening over it. A `blocked` end over claimed input is an account too: the pre-step rejection that produced it — a hook deny, a policy plugin — discarded the messages the turn claimed, so the notice says the child declined rather than finished. Only a `blocked` turn that claimed nothing stays invisible.
 
@@ -60,7 +60,7 @@ Three assembled ACP scenarios cover the notice: a child that never reports, a ch
 
 `subagent-continuable` is the one that pins a failure. Its child's last turn dies on the forced durability checkpoint without entering a step, so that transcript is where the stop-reason rule above is visible end to end: the notice says the child *failed*, carries the earlier `SECOND_OK` as its last content rather than as a result, and the parent's own acknowledgement turn reaches the ACP client.
 
-A keyless headless Loader snapshot covers the user-visible path end to end. Its replay parent starts one continuable child with `run_in_background: true`, never calls `list_agents`, `send_message`, or Task tools, consumes the manager-authored `subagent-settled` notice, and produces its final answer. The child never calls `report`, so the transcript cannot pass through the cooperative report path. A test-only Loader fence holds the parent's post-spawn request until the real manager notice enters its inbox, removing platform scheduling from the transcript without synthesizing the notice.
+A keyless headless Loader snapshot covers the user-visible path end to end. Its replay parent omits `run_in_background` to exercise the continuable background default, never calls `list_agents`, `send_message`, or Task tools, consumes the manager-authored `subagent-settled` notice, and produces its final answer. The child never calls `report`, so the transcript cannot pass through the cooperative report path. A test-only Loader fence holds the parent's post-spawn request until the real manager notice enters its inbox, removing platform scheduling from the transcript without synthesizing the notice.
 
 `subagent-report` needed one more concession. With the shipped waking report default, that scenario has two independent parent wakes — the report and the settlement — and whether the second extends the first's turn or opens its own is a genuine coin flip that measured 50/50 across runs. No authored transcript can hold both orders. Its overlay therefore pins `reportDelivery: quiet`, leaving settlement as the only wake, and a snapshot-only pre-step fence holds the child until the parent's spawn turn ends so that wake opens one deterministic turn claiming both messages. The waking report default keeps its coverage in the report package's own tests.
 

.agents/notes/implemented/feature/2026-08-06-manager-owned-subagent-settlement-delivery.zh.md

@@ -16,7 +16,7 @@ Status: implemented
 
 继续执行管理器自己投递这份记账，就在结束 Activation 的那笔 dispose 事务内部完成。
 
-当驻留 Activation 结算时，`notifySettlement()` 解析该 child 持久化的直接父级，并向它发送一条用户角色消息：先是父级可据以行动的一句结果说明，然后是 child 的最终 assistant 内容，或一句说明它没有产出内容。对每个调用方真正拿到过 id 的 child，投递都是无条件的。它不查询 child 是否上报过，也不保留任何可能让这项承诺变成有条件的记账——正是这种无条件性，才让 `tool-subagent` 能够告诉模型「它结束时你会被告知，因此绝不要轮询或等待它」并且这句话为真。在第一条消息被接受之前就回滚的物化保持静默，因为调用方已被告知该 child 未建立。
+当驻留 Activation 结算时，`notifySettlement()` 解析该 child 持久化的直接父级，并向它发送一条用户角色消息：先是父级可据以行动的一句结果说明，然后是 child 的最终 assistant 内容，或一句说明它没有产出内容。对每个调用方真正拿到过 id 的 child，投递都是无条件的。它不查询 child 是否上报过，也不保留任何可能让这项承诺变成有条件的记账——正是这种无条件性，才让 `tool-subagent` 能够承诺一条包含结局与可能存在的最终 assistant 消息的运行时通知。在第一条消息被接受之前就回滚的物化保持静默，因为调用方已被告知该 child 未建立。
 
 ### 来源信息
 
@@ -44,7 +44,7 @@ Status: implemented
 
 ### epoch 自己的日志就是全部交代
 
-`epochStopReason()` 从 epoch 自己的日志读取结局，因为拆卸成功与否，对「模型是否报错、是否撞到上限、是否被停下」什么也没说明。只读轮次这件事已经错了两次，而两次的形状相同：在第一个 step 之前被停下的轮次，其 `turn/end` 与「拒绝」或「被清空的认领」产生的平衡空转轮次长得一模一样，于是那道用来跳过后者的过滤，也把真实的结局一起跳过了，转而用上一个轮次的干净收尾作答。持久化检查点（`dsh-session-checkpoint-policy`，存在于每个随附 profile 中）与提示词组装都运行在这个边界上、且都会向外传播，而此时 `Inbox.claim()` 已经把消息取走了——于是父级被告知 child 已完成，而它正在等待的那条投递已被吞掉。在「你会在它完成时被告知，所以永远不要轮询」这一承诺之下，这恰恰是父级无法察觉、也不会重试的那一种失败。
+`epochStopReason()` 从 epoch 自己的日志读取结局，因为拆卸成功与否，对「模型是否报错、是否撞到上限、是否被停下」什么也没说明。只读轮次这件事已经错了两次，而两次的形状相同：在第一个 step 之前被停下的轮次，其 `turn/end` 与「拒绝」或「被清空的认领」产生的平衡空转轮次长得一模一样，于是那道用来跳过后者的过滤，也把真实的结局一起跳过了，转而用上一个轮次的干净收尾作答。持久化检查点（`dsh-session-checkpoint-policy`，存在于每个随附 profile 中）与提示词组装都运行在这个边界上、且都会向外传播，而此时 `Inbox.claim()` 已经把消息取走了——于是父级被告知 child 已完成，而它正在等待的那条投递已被吞掉。在已公布的自动结算通知约定下，这恰恰是父级无法察觉、也不会重试的那一种失败。
 
 缺失的事实从来不属于轮次，而属于 inbox。`Inbox` 会把每次改动连同 `removedCount` 一起记入日志，并给取消标记 `outcome: 'canceled'`，这就把「某个轮次认领了它的输入」与「工作被丢弃且从未运行」区分开来。`dsh-agent` 中的 `foldConsumedWork()` 把两套词汇折叠成一个答案：能为已消费工作作出交代的最新轮次——进入过 step 的，或认领后失败、被停下或被拒绝的——以及此后是否有已接受的工作被取消、而没有任何轮次为它开启过。认领过输入、以 `blocked` 结束的轮次同样是一份交代：产生它的 pre-step 拒绝——hook deny、策略插件——把该轮次认领的消息一并丢弃了，因此通知会说 child 拒绝了任务，而不是完成了任务。只有没认领任何输入的 `blocked` 轮次保持不可见。
 
@@ -60,7 +60,7 @@ Status: implemented
 
 `subagent-continuable` 是其中固定失败结局的那个。它的 child 最后一个轮次在被强制的持久化检查点上死亡，且未进入任何 step，因此该 transcript 正是上面那条终止原因规则的端到端可见之处：通知说该 child **失败**，把此前的 `SECOND_OK` 作为它最后产出的内容而非结果携带，而父级自己的确认轮次会到达 ACP 客户端。
 
-另有一个无密钥的 headless Loader 快照端到端覆盖用户可见路径。其重放父级通过 `run_in_background: true` 启动一个可继续 child，从不调用 `list_agents`、`send_message` 或 Task 工具，消费管理器写入的 `subagent-settled` 通知，并给出最终答案。child 从不调用 `report`，因此该 transcript 不可能经由协作式上报路径通过。一个仅用于测试的 Loader 栅栏会把父级启动后的请求保持到真实管理器通知进入其 inbox 为止，从 transcript 中排除平台调度差异，但不会伪造该通知。
+另有一个无密钥的 headless Loader 快照端到端覆盖用户可见路径。其重放父级省略 `run_in_background` 以覆盖可继续后台默认路径，从不调用 `list_agents`、`send_message` 或 Task 工具，消费管理器写入的 `subagent-settled` 通知，并给出最终答案。child 从不调用 `report`，因此该 transcript 不可能经由协作式上报路径通过。一个仅用于测试的 Loader 栅栏会把父级启动后的请求保持到真实管理器通知进入其 inbox 为止，从 transcript 中排除平台调度差异，但不会伪造该通知。
 
 `subagent-report` 还需要多做一步让步。在随附的唤醒上报默认值下，该场景有两个互相独立的父级唤醒——上报与结算——而第二个究竟是延长第一个的轮次还是另开一个轮次，是一枚真正的硬币，多次运行实测约为五五开。任何手写 transcript 都无法同时容纳两种顺序。因此它的 overlay 固定 `reportDelivery: quiet`，使结算成为唯一唤醒；另一个仅用于快照的 pre-step 栅栏会把 child 保持到父级启动轮次结束，使这次唤醒开启一个确定轮次并同时认领两条消息。唤醒上报默认值的覆盖则保留在 report 包自身的测试中。
 

.agents/notes/implemented/feature/2026-08-11-background-first-continuable-delegation.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/2026-08-11-background-first-continuable-delegation.md
+2026-08-11-background-first-continuable-delegation.md: e90b0a97cd5eeb273c8084d231ced003a661b978
+2026-08-11-background-first-continuable-delegation.zh.md: b8f14e0c40c341fc91b2fd0dc8c3f00fc2e14b66

.agents/notes/implemented/feature/2026-08-11-background-first-continuable-delegation.md

@@ -0,0 +1,45 @@
+# Agent Note: Continuable delegation is background-first
+
+Status: implemented
+
+English | [中文](2026-08-11-background-first-continuable-delegation.zh.md)
+
+## Problem
+
+A continuable child already has a durable id, independent turns, follow-up messaging, and a manager-owned settlement notice. Treating an omitted `run_in_background` as foreground makes that lifecycle depend on the model restating `true` on every call. It also obscures the useful scheduling test: the parent should wait only when its next action requires the child's result.
+
+The child-scoped `report` prompt requires a self-contained final report, while [manager-owned settlement delivery](2026-08-06-manager-owned-subagent-settlement-delivery.md) independently sends the run outcome and closing message. A completed child can therefore wake its parent with a final report and again with settlement. Background-first scheduling must preserve both deliveries: the child-authored handoff remains mandatory guidance, while the manager-authored notice covers every terminal path regardless of model compliance.
+
+## Decision
+
+`tool-subagent` resolves an omitted `run_in_background` from the selected lifecycle policy. `backgroundMode: continuable` resolves omission to background and returns the durable child id immediately; explicit `false` selects foreground and waits for the result. `backgroundMode: one-shot` keeps its foreground default because background output still requires Task collection. `enableRunInBackground: false` continues to omit the parameter, reject forced `true`, and run in the foreground. No second default-selection config is added.
+
+The model-facing text divides responsibility by location:
+
+- the tool description states the call behavior, durable id, runtime settlement notice, follow-up through `send_message`, and the explicit foreground override;
+- the `run_in_background` parameter states the lifecycle-specific default and when to override it;
+- a `tool:<toolName>` system-prompt section tells the model to start independent delegations together, continue useful work while they run, and choose foreground only when the next action depends on the result. The section renders only when that tool remains visible in the assembly scope, so a child tool restriction removes the schema and its guidance together.
+
+The [continuable child report obligation](2026-08-06-continuable-child-report-obligation.md) remains unchanged: the child prompt requires one self-contained final report and earlier reports for findings that change the parent's next action. Manager-owned settlement remains unconditional and does not inspect whether a report arrived. The two messages may repeat final content, but they retain distinct authors and purposes: `report` is the child's explicit handoff, while settlement records how the run ended and preserves terminal output when the child cannot cooperate. `reportDelivery` remains deployment scheduling policy with `wakeup` as its default.
+
+The keyless headless `subagent-settlement` scenario omits `run_in_background`, receives the immediate child id, and reaches the final parent answer through the manager-authored settlement notice even though its fixture deliberately does not call `report`. Package tests separately pin explicit `false` as foreground, the parent scheduling text, and the child's mandatory-report prompt.
+
+## Alternatives considered
+
+**Replace the field with `run_in_foreground`.** Reversing the boolean makes the common case read positively, but creates a second vocabulary for the same scheduling choice and forces every existing caller and provider-facing transcript to change. Keeping `run_in_background` preserves one field and makes foreground the explicit exception.
+
+**Add a configurable background default.** A separate default can disagree with `backgroundMode`, the schema wording, and the installed prompt. The lifecycle policy already distinguishes a continuable activation from a one-shot Task, which is the distinction that determines whether background completion is delivered automatically.
+
+**Change only the prompt.** Prompt preference without runtime resolution still turns an omitted argument into foreground. The model must be able to rely on the advertised default rather than reproduce it perfectly on every tool call.
+
+**Suppress settlement after a final report arrives.** Conditional settlement reintroduces per-Activation bookkeeping and loses the unconditional runtime guarantee when a child reports progress and then fails. Settlement remains unconditional even when the resulting message overlaps a final report.
+
+**Use `report` only for progress before settlement.** This removes duplicate final content but also removes the explicit child-authored handoff from the child prompt. The final-report obligation remains, and runtime settlement remains its independent fallback and terminal record.
+
+## Consequences
+
+- An ordinary continuable call is non-blocking without spelling `run_in_background: true`; serialized delegation is an explicit `false` choice.
+- Independent subagent calls in one assistant message overlap under the tool loop's concurrency-safe dispatch, while dependent foreground calls can still be issued one at a time.
+- Parent guidance, tool schema, runtime resolution, and settlement delivery state the same default.
+- A compliant child reports one self-contained final result and may report important findings earlier. Every Activation also produces an unconditional settlement notice, so a completed run may deliver overlapping final content twice.
+- One-shot background Tasks and disabled-background tool instances retain their existing behavior.

.agents/notes/implemented/feature/2026-08-11-background-first-continuable-delegation.zh.md

@@ -0,0 +1,45 @@
+# Agent Note: 可继续委派采用后台优先
+
+Status: implemented
+
+[English](2026-08-11-background-first-continuable-delegation.md) | 中文
+
+## 问题
+
+可继续 child 已经具备持久化 id、独立轮次、后续消息以及由管理器负责的结算通知。如果把省略的 `run_in_background` 视为前台，模型就必须在每次调用时重复写出 `true`，才能得到这套生命周期。这样也会掩盖真正有用的调度判断：只有当 parent 的下一步动作需要 child 结果时，parent 才应等待。
+
+child 作用域的 `report` 提示词要求发送自包含的最终报告，而[由管理器负责的结算投递](2026-08-06-manager-owned-subagent-settlement-delivery.md)会独立发送本次运行的结束结果与收尾消息。已完成的 child 因而可能先用最终报告唤醒 parent，再用结算通知唤醒一次。后台优先调度会保留两次投递：由 child 编写的交接仍是强制提示词指引，由管理器生成的通知则不依赖模型是否遵循指令，覆盖每种终止路径。
+
+## 决策
+
+`tool-subagent` 根据选定的生命周期策略解析省略的 `run_in_background`。`backgroundMode: continuable` 会把省略解析为后台并立即返回持久化 child id；显式传入 `false` 会选择前台并等待结果。`backgroundMode: one-shot` 保留前台默认行为，因为它的后台输出仍需通过 Task 收集。`enableRunInBackground: false` 仍会省略该参数、拒绝强制传入的 `true` 并在前台运行。系统不增加第二个默认选择配置。
+
+面向模型的文本按位置划分职责：
+
+- 工具描述说明调用行为、持久化 id、运行时结算通知、通过 `send_message` 继续对话，以及显式前台覆盖；
+- `run_in_background` 参数说明具体生命周期的默认值以及何时覆盖；
+- `tool:<toolName>` 系统提示词 section 会告诉模型同时启动相互独立的委派、在它们运行时继续有用工作，并且仅当下一步动作依赖结果时选择前台。只有当该工具在组装作用域中仍可见时才会渲染这个 section，因此子级工具限制会同时移除 schema 与对应指引。
+
+[可继续 child 上报义务](2026-08-06-continuable-child-report-obligation.md)保持不变：child 提示词要求发送一份自包含的最终报告，并在发现会改变 parent 下一步动作的信息时提前报告。由管理器负责的结算仍然无条件执行，不检查报告是否已经到达。这两条消息可能重复最终内容，但作者和用途不同：`report` 是 child 的显式交接，结算则记录本次运行如何结束，并在 child 无法配合时保留终止输出。`reportDelivery` 仍是部署调度策略，默认值仍为 `wakeup`。
+
+无密钥 headless `subagent-settlement` 场景省略 `run_in_background`，收到立即返回的 child id；尽管 fixture（测试前置数据）有意不调用 `report`，它仍通过管理器生成的结算通知到达 parent 最终答案。包测试另行固定了显式 `false` 的前台语义、parent 调度文本以及 child 的强制报告提示词。
+
+## 考虑过的替代方案
+
+**把字段替换为 `run_in_foreground`。** 反转布尔值会让常见情形以肯定形式表达，却会为同一项调度选择创造第二套词汇，并迫使所有现有调用方与面向提供方的 transcript（文本记录）一起改变。保留 `run_in_background` 可以维持单一字段，并把前台作为显式例外。
+
+**增加可配置的后台默认值。** 独立默认值可能与 `backgroundMode`、schema 措辞和已安装提示词不一致。生命周期策略已经区分可继续 Activation 与一次性 Task，而这个区别正好决定了后台完成是否会自动投递。
+
+**只修改提示词。** 如果运行时解析不变，提示词偏好仍会让省略参数的调用进入前台。模型必须能够依赖公布的默认值，而不是在每次工具调用中完美复述它。
+
+**最终报告到达后抑制结算通知。** 条件结算会重新引入每次 Activation 的记账，并且当 child 先报告进度、随后失败时丢掉无条件运行时保证。即使生成的消息与最终报告重叠，结算仍然无条件执行。
+
+**只用 `report` 发送结算前的进度。** 这样可以消除重复的最终内容，但也会从 child 提示词中移除由 child 编写的显式交接。最终报告义务保持不变，运行时结算则继续作为它的独立后备和终止记录。
+
+## 后果
+
+- 普通可继续调用无需写出 `run_in_background: true` 即为非阻塞；串行委派需要显式选择 `false`。
+- 同一条 assistant 消息中的独立 subagent 调用会在工具循环的并发安全分发下重叠执行；有依赖的前台调用仍可逐个发出。
+- parent 指引、工具 schema、运行时解析和结算投递陈述同一个默认值。
+- 遵循指令的 child 会发送一份自包含的最终结果，也可以更早报告重要发现。每次 Activation 还会产生无条件结算通知，因此已完成的运行可能两次投递相互重叠的最终内容。
+- 一次性后台 Task 与禁用后台的工具实例保留现有行为。

.agents/notes/implemented/feature/2026-08-11-workspace-sidebar-order-and-folding.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/2026-08-11-workspace-sidebar-order-and-folding.md
+2026-08-11-workspace-sidebar-order-and-folding.md: 3a88a61ca25550f1ad803a79e171ae2a7b8d4820
+2026-08-11-workspace-sidebar-order-and-folding.zh.md: e3e710bb9f38bcefcc9eeb50983c866ec5bc2619

.agents/notes/implemented/feature/2026-08-11-workspace-sidebar-order-and-folding.md

@@ -0,0 +1,56 @@
+# Agent Note: Workspace Sidebar Order and Folding
+
+Status: implemented
+
+English | [中文](2026-08-11-workspace-sidebar-order-and-folding.zh.md)
+
+## Problem
+
+A Workspace with many Sessions can consume the entire sidebar and push other Workspaces out of reach. A compact list needs a bounded default while preserving an explicit route to every Session. The sidebar also needs an activity-oriented order, but `WorkspaceView.sessionIds` is the durable manual account and must not be rewritten by Session activity.
+
+Workspace groups themselves had no user-controlled durable order. Browser-native drag additionally rejects a drop released outside the list and animates the row back even when the application still has a valid insertion marker. Expanded Workspace sections make header-only hit testing ambiguous because the visual boundary between two groups does not match either header's midpoint.
+
+## Decision
+
+### Workspace order
+
+The Workspace registry owns a durable `workspaceIds` order and exposes `insertBefore(id, beforeId?)` with DOM `insertBefore` semantics. The Host RPC `workspace.insertBefore` returns the complete committed order, and a pure order mutation emits `host/workspace-order-changed` with the same complete order. Unknown source or anchor ids reject as `workspace-not-found`; self-anchored and already-positioned moves do not write.
+
+The client installs a Workspace drag optimistically. Request and frame generations ensure that only the latest unary echo can replace local order and that a newer Host frame outranks an older response; a latest rejected request restores the last complete order accepted from a Host baseline, frame, or current unary echo. Every successful list baseline restores Host order so reconnects adopt durable changes made elsewhere.
+
+### Session folding and view order
+
+Each Workspace persists one browser-local open state: closed means zero Session rows and open means up to five. When more Sessions exist, **Show more** reveals the remainder only for the current mount; closing the whole Workspace clears this transient expansion, so reopening returns to five. The current Session's group opens automatically only when the user has not already stored an explicit state for that Workspace. Creating a Session from a Workspace row opens the target group before starting the Session, keeping the new row visible when state propagation completes. After a ready Workspace baseline changes, the browser removes expansion, order, and observed-timestamp records for ids absent from that baseline while retaining the Ungrouped and flat-list accounts.
+
+The combined view menu offers **Manual** and **Last updated** in grouped and flat presentation, with one browser-local persisted order per account. A real Workspace initializes from `WorkspaceView.sessionIds`; Ungrouped and the cross-Workspace flat list initialize from recency and have no Host Session account. Entering Last updated performs one complete recency sort; a later user prompt or steer promotes that Session once, and dragging may edit the resulting order. Returning to Manual preserves the current order and only disables later activity promotion. Manual-mode drags for a real Workspace also write the Host Session account, while Ungrouped and flat-list drags and activity promotion remain browser-local. Flat rows omit an empty leading status slot because they have no parent hierarchy, while a visible status retains its slot.
+
+### Drag and compact chrome
+
+Workspace hit testing uses the complete rendered group section, including visible Session rows. One insertion boundary is shared by the preceding group's lower half and the following group's upper half, and the indicator is an absolutely positioned line with a joined right-facing chevron that does not affect layout. A tree-body overlay draws the first boundary at the same negative offset outside the scrolling clip, so the leading chevron remains visible without moving the list. During a Workspace or Session drag, document-level `dragover` and `drop` handlers accept the native operation; if release occurs outside the Workspace list, `dragend` commits the last valid marker.
+
+Search is a header action while collapsed and expands across the title and trailing actions. An outside click collapses a query that is empty after trimming but retains a non-empty query. Compact Workspace and Session rows, a 24px bottom fade, and the absence of per-Workspace Session counts preserve vertical space without removing navigation affordances.
+
+## Alternatives considered
+
+**Write every activity promotion into `Workspace.sessionIds`.** A browser presentation preference would overwrite the shared Host account whenever a user submits a prompt.
+
+**Keep independent Manual and Last updated orders.** Switching modes would replace the visible list with stale positions from the other order, even though choosing Manual only means that later activity stops moving rows.
+
+**Always show every Session in an open Workspace.** One large Workspace would continue to crowd out the rest, and remembering only the whole-group open state would not bound its height.
+
+**Persist the expanded-remainder state.** A Workspace reopened much later could unexpectedly occupy the full sidebar. Only the zero-or-five state represents a stable navigation preference; revealing the remainder is a local inspection.
+
+**Use numeric drop indices or header-only hit testing.** Indices drift when rows change during a drag, while header midpoints disagree with the visible boundary when a Workspace is expanded. Anchor ids and full-section geometry remain stable under both conditions.
+
+**Let the browser reject an outside release.** The application would commit the last valid marker while the browser displays a rejected-drop animation, presenting contradictory feedback.
+
+## Consequences
+
+- Workspace order is durable and shared through the Host, while grouping, open state, per-account Session view order, and query state remain browser-local presentation preferences. Ungrouped and the flat list support the same drag and promotion rules, but their orders are browser-local because neither has one Workspace account.
+- Last updated performs a complete recency sort on entry, then preserves manual adjustments until a user prompt or steer advances one Session and moves it to the front. Returning to Manual preserves every current position.
+- Opening a Workspace never shows more than five Sessions without an explicit **Show more** gesture, and closing it resets only that transient gesture.
+- The Host Session account retains the manual-order meaning established by [Session List Browsing and Manual Workspace Order](2026-07-25-session-list-browsing-and-manual-order.md).
+
+## Testing
+
+Domain and Host tests cover durable Workspace moves, no-op and invalid anchors, restart recovery, full-order RPC responses, order frames, and one Workspace snapshot per Host-stream baseline. Runtime tests cover optimistic order, frame/response precedence, overlapping rejection rollback to Host-confirmed order, reconnect baselines, and New Session target priority. UI tests cover five-row folding, transient expansion reset, pruning persisted state after Workspace removal, order-preserving mode switches, one-time recent-update promotion, browser-local Ungrouped and flat-list drag persistence, hierarchy-free flat-row leading spacing, selected view indicators, expanded-section Workspace hit testing, an unclipped first insertion boundary, outside-list Workspace and Session drops, search collapse rules, and compact CSS dimensions.

.agents/notes/implemented/feature/2026-08-11-workspace-sidebar-order-and-folding.zh.md

@@ -0,0 +1,56 @@
+# Agent Note: Workspace 侧边栏顺序与折叠
+
+Status: implemented
+
+[English](2026-08-11-workspace-sidebar-order-and-folding.md) | 中文
+
+## 问题
+
+Session 很多的 Workspace 会占满整个侧边栏，把其他 Workspace 挤出可见范围。紧凑列表需要有界的默认高度，同时仍要提供到达每条 Session 的明确入口。侧边栏还需要面向活动时间的顺序，但 `WorkspaceView.sessionIds` 是持久的手动记账，不能被 Session 活动改写。
+
+Workspace 分组本身没有用户可控的持久顺序。浏览器原生拖拽还会把列表外松手判为拒绝，并把行弹回原位，即使应用仍持有有效插入标记。Workspace 展开后，若只按组头命中，两个分组之间的视觉边界也不再等于任一组头的中点。
+
+## 决策
+
+### Workspace 顺序
+
+Workspace 注册表持有持久 `workspaceIds` 顺序，并提供采用 DOM `insertBefore` 语义的 `insertBefore(id, beforeId?)`。Host RPC `workspace.insertBefore` 返回完整的已提交顺序；单纯顺序变更通过 `host/workspace-order-changed` 推送同一份完整顺序。未知来源或锚点 id 以 `workspace-not-found` 拒绝；以自身为锚点或移动到当前位置不会写入。
+
+客户端对 Workspace 拖拽进行乐观安装。请求代次与帧代次保证只有最新一元回声可以替换本地顺序，且更新的 Host 帧优先于旧响应；最新请求被拒时会恢复最近一份由 Host 基线、帧或当前一元回声确认的完整顺序。每次成功的列表基线都会恢复 Host 顺序，因此重连会接纳其他位置提交的持久变更。
+
+### Session 折叠与视图顺序
+
+每个 Workspace 持久化一项浏览器本地打开状态：关闭表示零条 Session 行，打开表示最多五条。存在更多 Session 时，**展开其余**只在当前挂载期间显示剩余项；关闭整个 Workspace 会清除此临时展开，因此重新打开时恢复为五条。只有在用户尚未为该 Workspace 存储明确状态时，当前 Session 所在分组才会自动打开。从 Workspace 行创建 Session 时会在启动 Session 前打开目标分组，使状态传播完成后新行保持可见。就绪的 Workspace 基线发生变化后，浏览器会移除基线中不存在 id 的展开状态、顺序和已观察时间戳记录，同时保留 Ungrouped 和单列表记账。
+
+组合视图菜单在分组和单列表呈现中都提供**手动排序**和**最近更新**，每个记账各自持有一份浏览器本地持久顺序。真实 Workspace 从 `WorkspaceView.sessionIds` 初始化；Ungrouped 和跨 Workspace 的单列表从最近更新时间顺序初始化，且没有 Host Session 记账。进入最近更新时会执行一次完整的时间排序；后续 user prompt 或 steer 会将对应 Session 置顶一次，拖拽仍可编辑所得顺序。返回手动排序会保留当前顺序，只停用后续活动置顶。真实 Workspace 在手动模式下的拖拽还会写入 Host Session 记账，而 Ungrouped 和单列表的拖拽与活动置顶保留在浏览器本地。单列表没有父级层次，因此不显示空的左侧状态槽；存在可见状态时仍保留该槽。
+
+### 拖拽与紧凑界面
+
+Workspace 命中测试使用完整渲染分组区段，包括可见 Session 行。前一分组的下半部与后一分组的上半部共享同一条插入边界，指示器是一条带有相连右向尖角且不影响布局的绝对定位横线。树主体覆盖层会在滚动裁切区外以相同的负偏移绘制第一条边界，因此左侧尖角保持可见，列表位置也不会改变。Workspace 或 Session 拖拽期间，文档级 `dragover` 与 `drop` 处理器会接受原生操作；若在 Workspace 列表外松手，`dragend` 会提交最后一个有效标记。
+
+搜索在折叠时是区头操作，展开后占据标题与尾部操作的空间。查询经清除首尾空白后为空时，点击外部会收起搜索；非空查询则会保留。紧凑的 Workspace 与 Session 行、24px 底部渐隐以及取消每个 Workspace 的 Session 数量共同节省纵向空间，同时保留导航入口。
+
+## 考虑过的替代方案
+
+**把每次活动置顶写入 `Workspace.sessionIds`。** 浏览器呈现偏好会在用户每次提交提示词时覆盖共享的 Host 记账。
+
+**为手动排序和最近更新分别保留独立顺序。** 切换模式会用另一份顺序中的旧位置替换可见列表，而选择手动排序只表示后续活动不再移动条目。
+
+**打开 Workspace 时始终显示全部 Session。** 大型 Workspace 仍会挤占其他分组；只记忆整个分组的打开状态无法限制其高度。
+
+**持久化展开剩余状态。** 很久以后重新打开 Workspace 时，它可能意外占满侧边栏。只有零条或五条状态属于稳定导航偏好；显示剩余项只是一次本地查看。
+
+**使用数字下标或只按组头命中拖拽。** 拖拽期间行发生变化会使下标漂移；Workspace 展开时，组头中点与可见边界不一致。锚点 id 与完整区段几何在两种情况下都保持稳定。
+
+**让浏览器拒绝列表外松手。** 应用会提交最后一个有效标记，而浏览器同时播放拒绝动画，形成相互矛盾的反馈。
+
+## 后果
+
+- Workspace 顺序通过 Host 持久并共享；分组方式、打开状态、每个记账的 Session 视图顺序和查询状态仍是浏览器本地呈现偏好。Ungrouped 和单列表支持相同的拖拽与置顶规则，但因没有单一 Workspace 记账，其顺序只保存在浏览器本地。
+- 最近更新模式会在进入时执行完整时间排序，随后保持手动调整，直到 user prompt 或 steer 推进某条 Session 并将其置顶。返回手动排序会保留所有当前位置。
+- 未执行明确的**展开其余**手势时，打开 Workspace 最多显示五条 Session；关闭分组只重置这项临时手势。
+- Host Session 记账继续采用[会话列表浏览与 Workspace 手动排序](2026-07-25-session-list-browsing-and-manual-order.md)确立的手动顺序含义。
+
+## 测试
+
+领域与 Host 测试覆盖持久 Workspace 移动、无操作与无效锚点、重启恢复、完整顺序 RPC 响应、顺序帧以及每条 Host stream 基线只读取一份 Workspace 快照。运行时测试覆盖乐观顺序、帧／响应优先级、重叠拒绝后恢复 Host 已确认顺序、重连基线以及 New Session 目标优先级。UI 测试覆盖五行折叠、临时展开重置、Workspace 移除后清理持久状态、保持顺序的模式切换、一次性最近更新置顶、浏览器本地 Ungrouped 与单列表拖拽持久化、无层级单列表行左侧间距、当前视图标记、展开区段的 Workspace 命中、未裁切的第一条插入边界、列表外 Workspace 与 Session 松手、搜索收起规则和紧凑 CSS 尺寸。

.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.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 .agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md
-2026-07-04-doc-tiers-and-budgets.md: e7b3421d09a1ae5ab9a9373e8040832c1b0d4b97
-2026-07-04-doc-tiers-and-budgets.zh.md: 3bc04ae73a4d8c9c005e154a236772fc1845389e
+2026-07-04-doc-tiers-and-budgets.md: 3f263864b9b6ee9479d1133b908617f10073dd66
+2026-07-04-doc-tiers-and-budgets.zh.md: 63b0b2945e1ff3e3fdf6af3cddb80cf44cf448ee

.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md

@@ -12,6 +12,7 @@ Standing docs accumulated repeated rules, retold incidents, duplicated package m
 
 - **Structure follows the documentation tree.** [docs/AGENTS.md](../../../../docs/AGENTS.md) is the documentation standard: a document owns detail about its subject, summarizes only the purpose, responsibility, and high-level behavior of direct children, and links to deeper owners. [Agent Notes](../../README.md) remain outside this structural contract. Every human-facing document is a tutorial with an ordered outcome or a reference with an explicit lookup scope; a [postmortem](../../../../docs/postmortem/README.md) is an incident-scoped reference whose chronology records evidence. Tutorials introduce concepts in prerequisite order for the reader's starting knowledge.
 - **A tier taxonomy with one home per fact.** The standard assigns every Markdown tier one job, forbids restating a fact outside its home tier, and carries the slop checklist used when writing or reviewing any doc.
+- **One product onboarding path.** The root README owns the recommended package-run path, the source-run alternative, and compact `dsh plugin --profile` usage. The published user guide starts with tasks inside the running Web UI, then links to distinct tutorials or reference owners for other interfaces, plugin development, and advanced configuration instead of repeating Web startup.
 - **A narrow, hard budget gate.** [scripts/verify-doc-budgets.ts](../../../../scripts/verify-doc-budgets.ts) joins `doc-sync`: every doc listed in [scripts/doc-budgets.manifest.json](../../../../scripts/doc-budgets.manifest.json) must stay under its word ceiling (`wc -w` semantics, whole file), and a budgeted file that is missing fails the gate so a rename cannot silently orphan its budget. Scope is deliberately only the accretion-prone standing docs — the root and subtree `AGENTS.md` files, `architecture.md`, `packages/README.md`, and the standing policy docs they evict content into (`docs/testing.md`, `docs/defensive-patterns.md`). Reference docs, Agent Notes, and package READMEs are unbudgeted: length is legitimate there when every row is a fact, and review plus the slop checklist govern them.
 - **Ceilings are an enforcement frontier that ratchets.** A doc at or below its target keeps at least 5% headroom as its ceiling ratchets down; a doc above target keeps a frozen ceiling that prevents growth until it reaches the target (root `AGENTS.md` ≤ 1,600 words; `architecture.md` ≤ 1,800; subtree `AGENTS.md` ≤ 600 except `packages/AGENTS.md` ≤ 650 and `docs/AGENTS.md` ≤ 1,250; `packages/README.md` ≤ 600). When the gate goes red, relocate or condense; raise a ceiling only with explicit PR justification.
 - **A thin workflow skill, contracts in docs.** [.agents/skills/dsh-doc-standards](../../../skills/dsh-doc-standards/SKILL.md) carries the placement/audit/red-gate workflow and defers to the standard as its source of truth, the same split as [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) over the i18n contract.
@@ -20,11 +21,13 @@ Standing docs accumulated repeated rules, retold incidents, duplicated package m
 
 - **Skill and review discipline without a gate** — rejected: the accretion above happened while the current-state rule and reviewer attention already existed; a prose rule with no mechanical backstop demonstrably does not hold here, and this repo's own [quality-gates stance](2026-06-11-quality-gates.md) says invariants worth keeping are worth encoding.
 - **A broad gate over every doc tier** — rejected: a blanket ceiling punishes exactly the right kind of long doc (a feature matrix or type catalog where every row is a fact) and generates per-file override churn that trains contributors to rubber-stamp raises.
+- **Independent onboarding tutorials for each documentation entry point** — rejected: duplicated setup steps drift in command order, first outcome, and product identity. A short README path followed by task-focused guides keeps the transition explicit without maintaining competing tutorials.
 - **Housing the standard inside the skill** — rejected: contracts live in docs and workflows in skills; a standard packed into SKILL.md is invisible to an agent that edits docs without invoking the skill, and `docs/AGENTS.md` already loads as subtree instructions for anyone working under `docs/`.
 
 ## Consequences
 
 - Adding to a budgeted doc requires displacement: relocate the addition to its taxonomy home with a pointer, or condense existing prose to pay for it. Growth without pruning fails CI.
 - Structural review starts with ownership and document form before sentence-level editing, so lower-level detail moves to its owner instead of being polished in the wrong place.
+- Readers reach a running Web UI before encountering headless execution, SDK embedding, custom profiles, or direct settings files; those interfaces remain available from their reference owners.
 - Budgeted docs that remain above target cannot grow; reaching the target restores the 5% working headroom.
 - Word count is a crude proxy accepted deliberately: it cannot judge quality, but it forces the relocation decision at exactly the moment content is being added, which is when the author has the context to place it correctly.

.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.zh.md

@@ -12,6 +12,7 @@ Status: implemented
 
 - **结构遵循文档树。**[docs/AGENTS.md](../../../../docs/AGENTS.md) 是文档标准：文档负责承载其主题的详细内容，仅概述直接子项的目的、职责和高层行为，并链接到更深层内容的归属文档。[Agent Note](../../README.md) 仍不受这一结构约定约束。每份面向人的文档要么是按顺序引导读者达成结果的教程（tutorial），要么是查阅范围明确的参考文档（reference）；[事故复盘（postmortem）](../../../../docs/postmortem/README.md) 是范围限定于单起事故的参考文档，其时间线记录证据。教程结合读者的起始知识，按前置依赖顺序介绍概念。
 - **每项事实只归属一处的层级分类。**文档标准为每种 Markdown 层级分配单一职责，禁止在事实归属层级之外重复陈述，并包含编写或评审任何文档时使用的赘余检查清单。
+- **单一产品入门路径。**根 README 负责推荐的包运行路径、从源码运行的备选路径和简要的 `dsh plugin --profile` 用法。已发布的用户指南从运行中的 Web UI 内部任务开始，再链接到其他界面的独立教程或插件开发与进阶配置的参考文档归属处，而不会重复介绍 Web 启动步骤。
 - **范围窄且严格的预算门禁。**[scripts/verify-doc-budgets.ts](../../../../scripts/verify-doc-budgets.ts) 接入 `doc-sync`：[scripts/doc-budgets.manifest.json](../../../../scripts/doc-budgets.manifest.json) 列出的每份文档都必须低于其词数上限（采用 `wc -w` 语义，统计整个文件）；预算内文件缺失也会使门禁失败，使重命名无法悄然遗落其预算。范围刻意只涵盖容易膨胀的常设文档——根目录和子树中的 `AGENTS.md` 文件、`architecture.md`、`packages/README.md`，以及它们将内容移入的常设策略文档（`docs/testing.md`、`docs/defensive-patterns.md`）。参考文档、Agent Note 和包 README 不设预算：只要每一行都是事实，长度在这些位置就是合理的；评审和赘余检查清单负责约束它们。
 - **上限是只进不退的执行红线。** 达到或低于目标的文档在上限逐步下调时保留至少 5% 的余量；高于目标的文档则维持冻结的上限，在达到目标之前不得增长（根 `AGENTS.md` ≤ 1,600 词；`architecture.md` ≤ 1,800；子树 `AGENTS.md` ≤ 600，但 `packages/AGENTS.md` ≤ 650、`docs/AGENTS.md` ≤ 1,250；`packages/README.md` ≤ 600）。门禁变红时，迁移或压缩内容；只有在 PR（Pull Request）描述中给出明确理由时才提高上限。
 - **精简的工作流 skill（技能），约定归文档。**[.agents/skills/dsh-doc-standards](../../../skills/dsh-doc-standards/SKILL.md) 承载文档放置、审计和门禁失败处理工作流，并以文档标准为真源，与 [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) 和 i18n 约定之间的分工相同。
@@ -20,11 +21,13 @@ Status: implemented
 
 - **仅靠 skill 和评审纪律，不设门禁**：否决。上述膨胀正是在现行规则和评审注意力已经存在的情况下发生的；一条没有自动化保障的行文规则在此处已被证明无法维持，而本仓库自身的[质量门禁立场](2026-06-11-quality-gates.md)认为值得保持的不变式就值得编码。
 - **对所有文档层级全面设限**：否决。一刀切的上限恰好惩罚了那些正当的长文档（如功能矩阵或类型目录，每一行都是事实），并产生逐文件的例外变更，训练贡献者机械地批准提限。
+- **为每个文档入口维护独立入门教程**：否决。重复的设置步骤会在命令顺序、首个结果和产品定位上产生分歧。简短的 README 路径接上面向任务的指南，可明确衔接两者，且不需要维护相互竞争的教程。
 - **将标准放在 skill 内部**：否决。约定归文档，工作流归 skill；如果标准被塞进 SKILL.md，那些不调用该 skill 而直接编辑文档的 agent（智能体）就看不到它，而 `docs/AGENTS.md` 已经作为子树指令被任何在 `docs/` 下工作的人加载。
 
 ## 后果
 
 - 向受预算约束的文档添加内容需要腾挪空间：将新增内容迁移到其分类体系归属地并留下链接，或压缩现有行文来腾出空间。只增不减会导致 CI 失败。
 - 结构评审先检查归属关系和文档形式，再进行句子层面的编辑，使较低层级的细节迁移到其归属文档，而不是在错误的位置加以润色。
+- 读者会先进入可运行的 Web UI，再遇到 headless 执行、SDK 嵌入、自定义 profile 或直接 settings 文件；这些入口仍可从各自的参考文档归属处访问。
 - 仍高于目标的受预算约束文档不得增长；达到目标后，将恢复 5% 的工作余量。
 - 词数是一个粗糙的代理指标，这是有意接受的：它无法判断质量，但它在内容被添加的那一刻强制触发迁移决策，而那正是作者拥有足够上下文来正确放置内容的时刻。

.agents/notes/implemented/process/2026-08-12-face-named-client-test-files.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/process/2026-08-12-face-named-client-test-files.md
+2026-08-12-face-named-client-test-files.md: e83ebe4fda25218d96bab546af025b59064ca18f
+2026-08-12-face-named-client-test-files.zh.md: 7062c67f9c98d87f480e119df807955c1a10820a