Merge remote-tracking branch 'upstream/master' into feat/gui-full-access-confirmation

# Conflicts:
#	packages/client/ui-conversation/README.i18n.yaml

.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.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/2026-07-27-glob-sampling.md
+2026-07-27-glob-sampling.md: 67912cf290b127a96819d57f30387197af68323d
+2026-07-27-glob-sampling.zh.md: e339a5f87b483849df60feb726b061fe85074300

.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.md

@@ -0,0 +1,47 @@
+# Agent Note: Sample over-cap glob results across the tree
+
+Status: implemented
+
+English | [中文](2026-07-27-glob-sampling.zh.md)
+
+## Problem
+
+Asked what a workspace contained, an agent described one subfolder as if it were the whole project. The workspace held 22 top-level entries and 11,485 files. `glob {"pattern":"*"}` matched 10,030 paths, but all 100 inline paths sat under one recently unpacked subtree, so the model never saw the other 21 entries.
+
+Three individually valid behaviors composed into the false impression. A glob without `/` matches basenames at any depth, so `*` means every file in the tree rather than the shell's current-directory expansion. Ripgrep's `--sort=modified` is ascending, so an archive's restored old timestamps put that subtree first. The inline page then took the head of that order without saying that it represented only one concentrated slice.
+
+## Decision
+
+A result that fits within `globMaxResults` remains complete and byte-for-byte modification-time ordered. The required `sampleOverCapGlobResults` config has no fallback: `false` retains the modification-time head for an over-cap result, while `true` samples round-robin across the complete result's top-level entries. In sampling mode, every entry receives one slot before any receives a second, exhausted groups drop out, relative order remains stable within each group, and grouping is relative to the actual search root, including an explicit `path`.
+
+In sampling mode, the footer states that the page is a cross-entry sample rather than the modification-time head and reports how many top-level entries it reaches when that fact adds information. When more top-level entries exist than inline slots, it tells the model to narrow `path`. Head mode keeps the ordinary capped-result footer. When spill succeeds, both modes preserve the complete sorted list in the artifact.
+
+The prompt and schema state the configured over-cap ordering, that a pattern without `/` matches at any depth, and that glob returns files, never directory entries. The shipped CLI composition explicitly selects head mode; deployments that want representative capped pages select sampling mode. Directory orientation remains ordinary shell work in deployments that expose the model-facing bash tool: use `ls` for one directory, and glob for a named file-path pattern across the tree. `ctx.fs.listDir` remains an internal provider primitive used by skill discovery; this decision adds no model-facing `list` tool.
+
+## Alternatives considered
+
+**Keep the modification-time head as the only behavior.** Rejected after measuring the failure shape. Some deployments need the stable ordering, but a deployment that values workspace orientation can explicitly select representative data instead of asking the model to distrust the only paths it received.
+
+**Give the sampling choice a default.** Rejected. No product-wide evidence establishes either ordering as the implicit contract, so every composition selects one and misconfiguration fails at load.
+
+**Sample every result.** Rejected. A complete result loses nothing to truncation, so modification-time order remains useful for age-oriented questions. Sampling begins only when the head stops describing the whole.
+
+**Switch to newest-first order.** Rejected. It merely changes which concentrated subtree can dominate and removes the existing oldest-first contract without making a capped page representative.
+
+**Sample only past a skew threshold.** Rejected. No current evidence supports a deployment-wide threshold, and the model could not know which ordering contract applied. The existing cap is the explainable transition.
+
+**Balance recursively below the top level.** Deferred. First-segment balance fixes the observed failure; deeper balancing needs an unsupported depth-versus-breadth policy.
+
+**Add a model-facing `list` tool.** Rejected after implementation review. The default coding composition already exposes general bash and the model understands `ls`; a duplicate tool would add permanent schema/prompt tokens plus ordering, pagination, symlink, escaping, UI, and snapshot contracts without a distinct security or policy benefit. Thin deployments without a model-facing bash tool do not gain directory orientation from this change.
+
+**Reject `*` or silently anchor separator-free patterns.** Rejected. The same basename-at-any-depth behavior makes `*.ts` useful across a tree. Documenting the rule preserves working ripgrep semantics.
+
+## Consequences
+
+A sampling-mode over-cap page no longer answers age-order questions from its inline paths; its footer says so, and the spill artifact retains the complete sorted view. Sampling balances only the first segment beneath the search root, so a deeper hot subtree can still dominate within one top-level entry. Head mode retains the concentration risk as an explicit deployment trade-off.
+
+The tool surface does not grow. Every composition must set `sampleOverCapGlobResults`; changing it alters glob's prompt, schema description, and over-cap Native rendering. The canonical output keeps `root` so sampling mode can recover its grouping basis, while fitting results remain unchanged.
+
+## Testing
+
+Package tests pin the required config, both over-cap modes, their prompt and schema descriptions, concentrated and flat results, explicit roots, more groups than the JavaScript argument limit, exhausted groups, fewer slots than groups, and paths outside the workdir. The `fs-glob-sampling` ACP scenario explicitly enables sampling, boots a minimal real Loader/app/local-bash composition, and executes the real search plugin against a deterministic `rg` process fixture; its result spans four top-level entries instead of returning one subtree's head.

.agents/notes/implemented/bug-fix/2026-07-27-glob-sampling.zh.md

@@ -0,0 +1,47 @@
+# Agent Note: 跨目录树采样超出上限的 glob 结果
+
+Status: implemented
+
+[English](2026-07-27-glob-sampling.md) | 中文
+
+## 问题
+
+用户询问工作区包含什么内容时，一个 agent（智能体）把某个子文件夹描述成了整个项目。该工作区有 22 个顶层条目和 11,485 个文件。`glob {"pattern":"*"}` 匹配到 10,030 条路径，但内联显示的 100 条路径全部位于一棵近期解压的子树中，因此模型完全没有看到其余 21 个条目。
+
+三个单独看都合理的行为叠加后造成了错误印象。不含 `/` 的 glob 会匹配任意深度的文件名，因此 `*` 表示目录树中的每个文件，而不是 shell 对当前目录执行的展开。Ripgrep 的 `--sort=modified` 按升序排列，因此归档包还原出的旧时间戳会让该子树排在最前。随后，内联页面直接截取这一顺序的前部，却没有说明它只代表集中于一处的切片。
+
+## 决策
+
+未超过 `globMaxResults` 的结果仍保持完整，且按修改时间排序的内容逐字节不变。必填的 `sampleOverCapGlobResults` 配置没有回退值：`false` 会为超过上限的结果保留按修改时间排序的前部，`true` 则会在完整结果的顶层条目之间按轮转方式采样。采样模式下，每个条目都先获得一个位置，之后才有条目获得第二个位置；已经用尽的分组会退出轮转；各组内部的相对顺序保持稳定；分组以实际搜索根为基准，显式指定 `path` 时也如此。
+
+采样模式下，footer 会说明当前页面是跨条目的样本，而不是按修改时间排序的前部；当触达的顶层条目数能提供额外信息时，还会报告该数量。若顶层条目数量超过内联位置数，footer 会要求模型缩小 `path`。保留前部的模式沿用达到上限时的普通 footer。spill 成功时，两种模式都会在该产物中保留完整排序列表。
+
+提示词与 schema 会说明配置所指定的超限结果排序方式、不含 `/` 的模式会匹配任意深度，以及 glob 只返回文件而绝不返回目录条目。随产品交付的 CLI（命令行界面）组合显式选择保留前部的模式；希望达到上限的页面具有代表性的部署则选择采样模式。在向模型暴露 bash 工具的部署中，目录定位仍由普通 shell 操作完成：查看一个目录使用 `ls`，跨目录树按指定文件路径模式查找则使用 glob。skill（技能）发现流程仍将 `ctx.fs.listDir` 作为内部提供方原语使用；本决策不会新增面向模型的 `list` 工具。
+
+## 考虑过的替代方案
+
+**只保留按修改时间排序的前部。** 测量实际故障形态后否决。某些部署需要这种稳定排序；但重视工作区定位的部署可以显式选择具有代表性的数据，而不必要求模型怀疑自己拿到的唯一一批路径。
+
+**为采样选项提供默认值。** 否决。没有全产品范围的证据支持把任一排序作为隐式契约，因此每个组合都必须选择一种，配置错误则在加载时失败。
+
+**对所有结果采样。** 否决。完整结果没有因截断损失任何信息，因此按修改时间排序仍有助于回答关注新旧时间的问题。只有当截取前部已经无法描述整体时，才开始采样。
+
+**改为最新优先排序。** 否决。这只会改变哪一棵结果集中的子树可能占据主导；既取消了现有的最旧优先契约，也没有让受限页面更具代表性。
+
+**仅在偏斜超过阈值时采样。** 否决。目前没有证据支持适用于所有部署的统一阈值，模型也无法判断当前采用的是哪一种排序契约。现有上限是可以清楚解释的切换点。
+
+**在顶层以下递归平衡。** 暂缓。按第一路径段做平衡已经修复观测到的故障；更深层的平衡需要一套尚无依据的深度与广度取舍策略。
+
+**新增面向模型的 `list` 工具。** 实现评审后否决。默认编程组合已经提供通用 bash，模型也理解 `ls`；重复工具会永久增加 schema 与提示词所占的 token，并引入排序、分页、符号链接、转义、UI 与快照契约，却没有独立的安全或策略收益。不向模型提供 bash 工具的精简部署也不会因本次改动获得目录定位能力。
+
+**拒绝 `*`，或在不含分隔符的模式前静默加上根目录锚点。** 否决。同样的「在任意深度匹配文件名」行为使 `*.ts` 可以有效地跨目录树搜索。记录这条规则能够保留正常工作的 Ripgrep 语义。
+
+## 影响
+
+采样模式下，超过上限的 glob 页面无法再根据内联路径回答按时间判断新旧的问题；footer 会明确说明这一点，spill 产物仍保留完整的排序视图。采样只平衡搜索根下的第一路径段，因此某个顶层条目内部较深处、结果密集的子树仍可能占据主导。保留前部的模式则把集中风险作为显式部署取舍保留下来。
+
+工具接口不会扩大。每个组合都必须设置 `sampleOverCapGlobResults`；更改该值会改变 glob 的提示词、schema 描述以及超过上限时的 Native 渲染。规范输出保留 `root`，以便采样模式恢复其分组基准；未超过上限的结果保持不变。
+
+## 测试
+
+包测试锁定了必填配置、两种超过上限模式及其提示词和 schema 描述、结果集中与扁平两种情况、显式根目录、分组数超过 JavaScript 参数个数上限、分组耗尽、位置数少于分组数，以及工作目录以外的路径。`fs-glob-sampling` ACP（Agent Client Protocol）场景会显式启用采样，启动最小化的真实 Loader/app/local-bash 组合，并让真实搜索插件对接确定性的 `rg` 进程 fixture（测试前置数据）；其结果覆盖 4 个顶层条目，而不是只返回某棵子树的前部。

.agents/notes/implemented/bug-fix/2026-07-30-approval-panel-command-cap.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/2026-07-30-approval-panel-command-cap.md
+2026-07-30-approval-panel-command-cap.md: 941f7eda187f263f2d8af6aa643d493c92a3669b
+2026-07-30-approval-panel-command-cap.zh.md: 939a700934f6467947028d988da9a694169e203e

.agents/notes/implemented/bug-fix/2026-07-30-approval-panel-command-cap.md

@@ -0,0 +1,52 @@
+# Agent Note: The approval takeover shares the composer's text cap
+
+Status: implemented
+
+English | [中文](2026-07-30-approval-panel-command-cap.zh.md)
+
+## Problem
+
+The approval panel is a composer takeover: while a sandbox escalation waits, it replaces the InputBar in the composer seat with the model's justification, the paired command, and a refuse/allow row. Both texts are unbounded model output, and the card had no height cap. A long command — the realistic shape, since escalation happens on the command the sandbox just denied, and a denied command is often a long inline write — grew the card until the action row left the viewport. The user could read the request and not answer it: the buttons existed, off screen, in a sticky footer that had already used the whole column.
+
+The InputBar the panel replaces has always been capped (14 lines, then the textarea scrolls), so the takeover was also the one composer state that could grow without limit — the seat's height jumped on election and jumped back on answer.
+
+## Decision
+
+The panel's justification and command move into one scroll region (`data-approval-scroll`) capped at the same height as the composer's draft area; the amber strip and the action row sit outside it, so both buttons are in the card at every content length.
+
+The cap is one value with two consumers, declared as `--dsh-composer-text-max-height: 336px` on `ConversationRoot`'s `.composerSeat` — the composer chain's only shared ancestor, since the fallback InputBar and an elected takeover render as siblings. `InputBar`'s mirror and the panel's scroll region both read it, so the seat cannot cap its two states differently: what the designer asked for ("unify it with the input box's max height") is now a fact of the stylesheet rather than a number repeated in two files. The region is `box-sizing: border-box` so the cap is its outer height, the same box the composer's draft area occupies.
+
+The region is a tab stop (`tabIndex={0}`, named `role="group"`). Unlike the question composer's scroll body, whose option rows are focusable and pull the container along, this one holds nothing but text: without its own tab stop a keyboard-only user could reach the buttons and never the command's tail, and approve what they could not finish reading.
+
+The panel's card rebinds `--dsh-scrollbar-thumb{,-hover}` to the l2 pair, as every scrolling surface on an elevated background must ([scrollbar contract](../../../../packages/client/ui-theme/src/styles/scrollbar.css)).
+
+## Alternatives considered
+
+**Cap the whole card instead of the text region.** One declaration, no restructuring, and it reads as the literal "same max height as the input box". Rejected because the card holds the strip and the action row: at 336px total the justification and command would get ~250px, less room than the draft they replace, and the numbers would only agree by coincidence of the strip's height. Capping the text region makes both seats top out at the same text height, which is the property that keeps the footer from jumping.
+
+**Cap against the viewport like the question composer (`min(60vh, 520px)`).** The sibling takeover already does this, so it is the local precedent. Rejected because the designer's request was parity with the InputBar, and the two takeovers are not the same shape: the question composer's scroll content is a list of options the user must compare, which wants as much viewport as it can get, while the approval panel's is one command the user skims before deciding. A viewport-relative cap would also make the seat's height jump on election again, in the other direction.
+
+**Ellipsize or truncate the command.** No scroll region, no cap, and the buttons stay put. Rejected because the command is the thing being approved: hiding its tail asks the user to consent to text they cannot read. Truncation is also unrecoverable here — the panel is the whole approval UI, so there is no "show more" surface to fall back to.
+
+**Leave the action row inside the scroll region and cap the region.** Fewer moving parts than pinning the row. Rejected because it reproduces the defect inside the card: the buttons scroll out of the region, and the user has to discover a scrollbar to reach them.
+
+## Consequences
+
+- A long command scrolls inside the card and the refuse/allow buttons stay on screen. Measured on the built client at 900x1000 and 900x700: the region reports `scrollHeight` past `clientHeight`, and both buttons stay inside the card and inside the viewport.
+- Electing the takeover no longer changes how tall the composer seat can get, so the transcript above it does not reflow by hundreds of pixels when an approval arrives or resolves.
+- The InputBar's 14-line cap now resolves through a custom property inherited from `.composerSeat`. Rendering the bar outside that seat would drop the declaration (an unresolved `var()` with no fallback), so a future composer host has to carry the property — which is why it is declared on the shared seat rather than the app root.
+- The scenario's recorded command is a 200-token blob, far longer than a round trip needs. That cost is deliberate: the cap is unfalsifiable without content that passes it, and the model compresses any regular payload (the first recording turned "alpha 400 times" into `printf 'alpha %.0s' {1..400}`, a one-line command that proves nothing).
+
+## Verification
+
+`apps/web/tests/approval-composer.e2e.ts` drives the real composition: a read-only session, a denied write, the model's escalation retry, and the answer clicked through the panel. The geometry assertion runs on the live panel at two viewport heights and is guarded against holding vacuously — the region must actually be scrolling, and the measured cap must equal the composer's own, which the test reads off the live textarea before sending rather than hardcoding the px value.
+
+Confirmed both directions against the built client. With the cap reverted, the region reports `scrolls: false` and grows to the command's full height (1798px for the recorded blob at 900x1000, against 336px capped); at 900x700 the card is 680px tall against a 700px viewport and the action row's bottom lands at y=749 — below the fold, the designer's report exactly. With the cap restored the scenario passes in replay.
+
+Reproducing the off-screen buttons needs a card taller than the scrollport, not merely a tall card. The composer seat is `position: sticky; bottom: 0`, so while the card still fits it stays pinned to the viewport bottom and the buttons remain visible — at 900x1000 the uncapped card ate the whole transcript yet kept its action row on screen. Only once the card outgrows the scrollport does sticky stop being able to hold the bottom edge, and the row goes under.
+
+The geometry block and the golden are replay-only, so record mode reaches the fixture write instead of aborting on layout.
+
+The scenario keeps exactly one golden — the waiting panel — and asserts the answered state on the world instead (the decided outcome, the file the escalated command wrote, `DONE`, the panel gone, the composer re-enabled). An answered-transcript golden was recorded first and failed on Linux CI: the denied first attempt renders the OS's own refusal, and that text is platform-specific (`bash: notes.txt: Operation not permitted` on macOS against `bash: line 1: notes.txt: Read-only file system` on Linux). Any scenario whose transcript contains a sandbox-denied command inherits that, so the denial belongs in assertions, never in a golden.
+
+The panel ships as a client-module bundle: `pnpm run build:web` alone does not pick up a change to `ApprovalPanel.module.css` or a new `data-` hook in `ApprovalPanel.tsx` — the package build must run first, or the browser lane asserts against an older client than the tree.

.agents/notes/implemented/bug-fix/2026-07-30-approval-panel-command-cap.zh.md

@@ -0,0 +1,52 @@
+# Agent Note: 审批接管面板与输入框共用同一文本高度上限
+
+Status: implemented
+
+[English](2026-07-30-approval-panel-command-cap.md) | 中文
+
+## 问题
+
+审批面板是一次 composer 接管：当一次沙箱越权申请处于等待状态时，它在 composer 容器中取代 InputBar，展示模型给出的理由、与之配对的命令，以及一行拒绝／允许按钮。这两段文本都是长度不受限的模型输出，而卡片当时没有任何高度上限。命令一长——而这正是现实中的常见形态，因为越权申请针对的就是沙箱刚刚拒绝的那条命令，而被拒绝的命令往往是一次很长的内联写入——卡片就会一直变高，直到操作按钮行离开视口。用户能读到这次申请，却无法回应它：按钮存在，只是在屏幕之外，位于一个已经占满整列的吸底容器里。
+
+被它取代的 InputBar 一直是有上限的（14 行，之后由 textarea 自行滚动），因此这次接管也是 composer 唯一一个可以无限增高的状态——被选中时容器高度骤增，回应之后又骤降。
+
+## 决策
+
+面板的理由与命令移入同一个滚动区域（`data-approval-scroll`），其高度上限与 composer 的草稿区完全相同；琥珀色状态条与操作按钮行位于该区域之外，因此无论内容多长，两个按钮都留在卡片内。
+
+这个上限是一个值、两个消费者，以 `--dsh-composer-text-max-height: 336px` 声明在 `ConversationRoot` 的 `.composerSeat` 上——它是 composer 链唯一的共同祖先，因为兜底的 InputBar 与被选中的接管面板是兄弟节点。`InputBar` 的 mirror 与面板的滚动区域都读取它，于是同一个容器不可能给它的两种状态设出不同上限：设计同学要求的"可以跟输入框最大高度统一"，如今是样式表中的一个事实，而不是抄在两个文件里的一个数字。该区域取 `box-sizing: border-box`，因此上限指的是它的外框高度，与 composer 草稿区占据的是同一个盒子。
+
+该区域自身是一个 Tab 停靠点（`tabIndex={0}`，带名称的 `role="group"`）。提问 composer 的滚动体不需要这样做——它的选项行本身可聚焦，会把容器一起带过去；而这里除文本之外别无内容：没有自己的停靠点，仅用键盘的用户能走到按钮却走不到命令尾部，于是可能批准了自己没读完的东西。
+
+面板卡片把 `--dsh-scrollbar-thumb{,-hover}` 重新绑定到 l2 那一对，这是每一个位于高层表面上的滚动区域都必须做的（[滚动条约定](../../../../packages/client/ui-theme/src/styles/scrollbar.css)）。
+
+## 曾考虑的替代方案
+
+**给整张卡片设上限，而不是给文本区域设。** 一条声明，不需要重构结构，而且它读起来就是字面意义上的"与输入框相同的最大高度"。之所以否决：卡片还装着状态条和操作按钮行——总高 336px 时，理由与命令只能分到约 250px，比它们所取代的草稿区更矮，而且两边数字能对上纯属状态条高度的巧合。给文本区域设上限，才能让两种状态在同一文本高度处收住，而这正是让底部不再跳动的那条性质。
+
+**像提问 composer 那样按视口设上限（`min(60vh, 520px)`）。** 同为接管面板的兄弟组件已经这么做了，因此这是本地既有先例。之所以否决：设计同学的要求是与 InputBar 对齐，而两个接管面板形态并不相同——提问 composer 的滚动内容是一组需要用户互相比较的选项，能占多少视口就该占多少；审批面板的滚动内容则是一条命令，用户在决定之前扫读即可。按视口设上限还会让容器高度在被选中时再次跳动，只是方向相反。
+
+**对命令做省略号或截断处理。** 不需要滚动区域，不需要上限，按钮也不会移位。之所以否决：命令正是被审批的对象，隐去它的尾部等于要求用户为自己读不到的文本背书。在这里截断还是不可恢复的——面板就是审批的全部界面，没有"展开更多"的落脚处。
+
+**把操作按钮行留在滚动区域内，只给该区域设上限。** 比把按钮行固定住少动几处。之所以否决：这会把缺陷搬进卡片内部——按钮滚出该区域，用户得先发现有滚动条才能碰到它们。
+
+## 后果
+
+- 长命令在卡片内滚动，拒绝／允许按钮留在屏幕内。在构建产物客户端上于 900x1000 与 900x700 实测：该区域报告的 `scrollHeight` 超过 `clientHeight`，两个按钮都留在卡片内、也都留在视口内。
+- 选中接管面板不再改变 composer 容器能达到的高度，因此审批到来或解决时，上方的会话流不会有数百像素的重排。
+- InputBar 的 14 行上限现在通过一个自 `.composerSeat` 继承而来的自定义属性解析。把输入栏渲染到该容器之外会丢掉这条声明（一个没有兜底值的未解析 `var()`），因此未来的 composer 宿主必须带上这个属性——这也正是它声明在共享容器上、而不是应用根节点上的原因。
+- 该场景录制的命令是一段 200 个 token 的字符块，远超一次往返所需。这个代价是有意付出的：没有能越过上限的内容，这个上限无法被证伪，而模型会把任何规整的载荷压缩掉（第一次录制时，模型把"alpha 重复 400 次"写成了 `printf 'alpha %.0s' {1..400}`，一条什么也证明不了的单行命令）。
+
+## 验证
+
+`apps/web/tests/approval-composer.e2e.ts` 驱动的是真实组合：一个只读会话、一次被拒绝的写入、模型的越权重试，以及在面板上点击完成的回应。几何断言在两个视口高度上针对活动面板执行，并有守卫防止它空洞地成立——该区域必须确实处在滚动状态，且实测上限必须等于 composer 自身的上限，后者由测试在发送之前从活动 textarea 上读出，而不是把该像素值写死。
+
+在构建产物客户端上双向确认过。撤销上限后，该区域报告 `scrolls: false`，并长到命令的完整高度（900x1000 下，录制的字符块为 1798px，而设上限后为 336px）；在 900x700 下卡片高 680px、视口高 700px，操作按钮行底边落在 y=749——正在折叠之下，与设计同学的反馈完全一致。恢复上限后，该场景在回放模式下通过。
+
+要复现按钮跑到屏幕外，需要的是比滚动视口更高的卡片，而不只是一张很高的卡片。composer 容器为 `position: sticky; bottom: 0`，因此在卡片尚能容纳时它会一直吸附在视口底部，按钮仍然可见——在 900x1000 下，未设上限的卡片吃掉了整个会话流，却仍把操作按钮行留在屏幕内。只有当卡片长过滚动视口，sticky 才再也无法守住底边，按钮行随之沉入折叠之下。
+
+几何断言块与 golden 仅在回放模式下执行，这样录制模式才能走到写入 fixture 那一步，而不是在布局检查处中断。
+
+该场景只保留一份 golden —— 等待中的面板；回应之后的状态改为对世界作断言（决策结果、越权命令写出的那个文件、`DONE`、面板消失、输入框重新可用）。最初还录了一份"已回应会话流"的 golden，它在 Linux CI 上失败了：第一次被拒绝的尝试渲染的是操作系统自己的拒绝文本，而这段文本因平台而异（macOS 为 `bash: notes.txt: Operation not permitted`，Linux 为 `bash: line 1: notes.txt: Read-only file system`）。任何会话流中含有被沙箱拒绝命令的场景都会继承这一点，因此这类拒绝只能进断言，绝不能进 golden。
+
+该面板以客户端模组包的形式发布：单跑 `pnpm run build:web` 不会带上对 `ApprovalPanel.module.css` 的改动，也不会带上 `ApprovalPanel.tsx` 中新增的 `data-` 钩子——必须先执行包构建，否则浏览器测试通道会对着一个比工作树更旧的客户端做断言。

.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.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/2026-06-30-session-store-fork-api.md
-2026-06-30-session-store-fork-api.md: 5342deba8ca879026d32ee1420cb3c0fdf67c500
-2026-06-30-session-store-fork-api.zh.md: 51a3e0ce50aff10a9812c91d24dc6e78a56c43ba
+2026-06-30-session-store-fork-api.md: 69ff85e1f137f4f263bf951af0a3f655411c606a
+2026-06-30-session-store-fork-api.zh.md: 3304a6f384c9004b3572c95881f832a4aa21b77c

.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md

@@ -28,6 +28,12 @@ class SessionStore extends Service {
 
 An empty prefix is forkable; any non-empty boundary must be a safe existing sequence outside an open turn. Typed errors distinguish missing sources, stale objects, duplicate child ids, invalid boundaries, and prefixes ending during execution. Broader log validation and crash repair remain with their existing owners.
 
+### Host and browser adaptation
+
+The Host `session.fork` RPC accepts `atSeq` as an anchor within the desired turn rather than as the store's inclusive safe boundary. It selects the first `turn/end` at or after that anchor; an omitted or past-end anchor selects the last completed turn. An anchor already in the log but not followed by a matching `turn/end` returns `fork-unavailable` and never falls back to an earlier turn, so a message action cannot silently omit the clicked message.
+
+The Host creates the child through the agent registry with the selected seed and lineage, and pre-publication setup installs the latest logged provider, model, and reasoning target before the child can run. It then attaches the child to the source Workspace. An attachment failure returns `workspace-attach-failed` with the already-published child id; the client reconciles that child into its summary list before surfacing the error. The Session-row action uses the last completed turn, while a message action supplies its event seq; both open the child after success, and lineage expansion makes it visible beneath the source.
+
 ## Alternatives considered
 
 **Separate `ctx.sessionFork` service.** This was the first implementation, but review showed it overfit the capability-seam pattern. The code had no swappable backend, no extra event surface, no independent ownership lifecycle, and no durable behavior beyond `ctx.sessions.create({ seed, meta })`. Keeping a separate package would make callers discover and install a second service just to perform policy around a session-store primitive.
@@ -40,4 +46,4 @@ An empty prefix is forkable; any non-empty boundary must be a safe existing sequ
 
 The public surface stays small and discoverable: live session branching is part of `ctx.sessions`, next to `create({ seed })`, rather than a standalone service or a two-step helper pair. Persistence continues to work through existing `session/created` and `session/flush` behavior: a forked child starts life with seeded events, so existing backends persist that seed once and preserve `parentSession` / `seedLength` in the header.
 
-The v1 scope still excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has protocol and snapshot coverage; this Agent Note adds no ACP wire behavior, so no ACP snapshot is required. Fork-child replay remains covered by the existing [seed-boundary testing Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md), while this API gets focused `dsh-session` unit tests plus JSONL persistence coverage.
+The v1 scope still excludes ACP `session/fork`, unloaded persisted-session forking, model-facing tools, and subagent refactors. If a future ACP method is added, it should advertise the capability only after it has protocol and snapshot coverage; this Agent Note adds no ACP wire behavior, so no ACP snapshot is required. Fork-child replay remains covered by the existing [seed-boundary testing Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md); focused store, Host, carrier, and client tests pin the boundary and reconciliation contracts, while the real Chromium scenario pins the assembled message action and lineage tree.

.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md

@@ -28,6 +28,12 @@ class SessionStore extends Service {
 
 空前缀可以被 fork；任何非空边界都必须是位于开放轮次之外且安全、已存在的序号。类型化的错误区分源缺失、对象陈旧、子 id 重复、边界无效和前缀结束于执行过程中等情况。更广泛的日志校验与崩溃恢复仍由其现有的负责方处理。
 
+### Host 与浏览器适配
+
+Host 的 `session.fork` RPC 接受 `atSeq`，并将其视为所需轮次内的锚点，而非 store 中包含该序号的安全边界。它选择该锚点处或其后的首个 `turn/end`；锚点省略或超过末尾时，选择最后一个已完成轮次。若锚点已在日志中，但从该锚点起找不到匹配的 `turn/end`，则返回 `fork-unavailable`，绝不回退到更早的轮次，因此消息操作不会静默遗漏所点击的消息。
+
+Host 通过 agent（智能体）注册表，以选定的种子和谱系创建子会话；发布前 setup 会先安装日志中最新的提供方、模型和推理（reasoning）目标，子会话才能运行。随后，Host 将子会话附加到源 Workspace。若附加失败，则返回 `workspace-attach-failed` 及已发布的子会话 id；客户端先将该子会话对账到摘要列表，再向调用方报告错误。Session 行操作使用最后一个已完成轮次，消息操作则提供其事件 seq；两者都会在成功后打开子会话，展开谱系后可在源会话下看到它。
+
 ## 曾考虑的替代方案
 
 **独立的 `ctx.sessionFork` 服务。** 这是最初的实现，但评审表明它过度套用了 capability-seam 模式。代码没有可替换的后端、没有额外的事件面、没有独立的所有权生命周期，也没有超出 `ctx.sessions.create({ seed, meta })` 的持久化行为。保留独立包会迫使调用方为了在会话存储原语之上执行一层策略而去发现并安装第二个服务。
@@ -40,4 +46,4 @@ class SessionStore extends Service {
 
 公开接口保持精简且易于发现：活跃会话分支是 `ctx.sessions` 的一部分，紧邻 `create({ seed })`，而非一个独立服务或一对两步辅助函数。持久化继续通过现有的 `session/created` 和 `session/flush` 行为运作：fork 出的子会话以种子事件开始生命，因此现有后端只需持久化该种子一次，并在 header 中保存 `parentSession`／`seedLength`。
 
-v1 范围仍然排除 ACP（Agent Client Protocol） `session/fork`、对未加载的已持久化会话的 fork、面向模型的工具，以及 subagent 重构。如果未来添加 ACP 方法，应在具备协议与快照覆盖后才广播该能力；本 Agent Note 不添加任何 ACP 协议行为，因此不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md) 覆盖，而本 API 则获得专门的 `dsh-session` 单元测试加 JSONL 持久化覆盖。
+v1 范围仍然排除 ACP（Agent Client Protocol） `session/fork`、对未加载的已持久化会话的 fork、面向模型的工具，以及 subagent 重构。如果未来添加 ACP 方法，应在具备协议与快照覆盖后才广播该能力；本 Agent Note 不添加任何 ACP 协议行为，因此不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md) 覆盖；store、Host、载体与客户端的专项测试固定边界和对账契约，真实 Chromium 场景则固定组装后的消息操作与谱系树。

.agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-2026-07-25-session-list-browsing-and-manual-order.md: 586995bf459aeaee88672863977f7acf2a7061a3
-2026-07-25-session-list-browsing-and-manual-order.zh.md: 432d5167a57d30bc04a0b4faf213e4341f07bd2f
+#   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: 831aa53e532a75392690c330837482bb0f9c32b1
+2026-07-25-session-list-browsing-and-manual-order.zh.md: 9ad074d59c13585aa4fca46ae4d40e2deb15cde6

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

@@ -12,14 +12,14 @@ Two existing mechanisms stood in the way. First, the host durably promoted the a
 
 ## Decision
 
-### Flat view and viewing state
+### Flat rows and viewing state
 
-The group-by menu offers two modes, WorkSpace / In one list. Flat mode renders every session (fork children included) as a top-level row, strictly newest-first by `updatedAt`, with no parent/child adjacency; the Intent placeholder renders as the first row. 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.
 
 ### Row interactions
 
 - Session rows show a detail card after a 500ms hover dwell (full title / relative time / status line; the status line has only running/idle until the wire grows a status field). The card and the row menu are mutually exclusive: no card while a menu is open or a drag is in flight.
-- Session-row … menu: Rename / Fork session / Delete session, visual-only this iteration; workspace-header … menu: Rename (wired) / Delete workspace (visual-only). Menus close when the pointer leaves them.
+- Session-row … menu: Rename / Fork session / Delete session; Rename and Fork are wired, while Delete remains visual-only. The workspace-header … menu's Rename / Delete workspace actions are both wired. Menus close when the pointer leaves them.
 - Supporting primitives: `Menu` gains label entries, danger rows, and `closeOnPointerLeave`; a new `HoverCard` (portaled placement, open delay, disabled guard).
 
 ### workspace.rename
@@ -30,7 +30,7 @@ The group-by menu offers two modes, WorkSpace / In one list. Flat mode renders e
 
 The `session/event` → `touchSession` activity-pinning chain is deleted wholesale; the workspace account order is now manually owned — new sessions prepend at attach, and explicit reordering goes through `workspace.insertSessionBefore({ workspaceId, sessionId, beforeSessionId? })` (DOM insertBefore semantics: with an anchor it inserts before it, omitted appends to the end). The entity throws a typed `WorkspaceMoveInvalidError` only for unaccounted session/anchor ids; the handler maps exactly that to the business code `workspace-move-invalid`, while storage failures stay internal.
 
-The UI is HTML5 drag on root rows inside a group (workspace grouping only, outside search; fork children ride with their parent and are not draggable). Order authority stays entirely host-side: drop only sends the RPC, the client performs zero local reordering, and the view refreshes from the response upsert and the changed frame; a failed move changes nothing. The client's upsert rejects snapshots older (`updatedAt`) than the installed projection so a late unary response cannot roll back a newer frame.
+The UI is HTML5 drag on session rows inside a group (workspace grouping only, outside search; fork children and their source sessions are ordered independently). Order authority stays entirely host-side: drop only sends the RPC, the client performs zero local reordering, and the view refreshes from the response upsert and the changed frame; a failed move changes nothing. The client's upsert rejects snapshots older (`updatedAt`) than the installed projection so a late unary response cannot roll back a newer frame.
 
 ### Shell/region split
 
@@ -46,15 +46,15 @@ ui-sidebar shrinks to the column-geometry shell: brand row, fold state machine,
 
 **Keep the rename dialog in ui-sidebar (smallest change)** — that is the problem itself: workspace-domain dialogs scattered in a borrowed slot, with each addition (the Delete confirmation is coming) repeating the cross-package wiring. Review first considered moving only the rename modal; the ruling was to give the whole browsing region to ui-workspace and leave the shell geometry-only.
 
-**Keep parent/child adjacency in flat mode** — contradicts strict recency (a child newer than its parent's sibling cannot slot adjacently), and the flat view's purpose is dropping the hierarchy; flattening fully and disabling drag in flat mode (no persistence carrier) is more consistent.
+**Nest sessions by fork lineage in WorkSpace mode** — nesting makes the current child visible only while its ancestors are expanded and limits in-group manual ordering to root nodes; `parentId` is lineage data, not a list-navigation structure. Flattening all sessions into peer rows lets each row be opened, searched, and ordered independently; In one list still disables drag because it has no workspace persistence carrier.
 
 ## 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.
 - 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 the three session-menu items and workspace Delete, and growing the wire status enum, remain future iterations.
+- Wiring session Delete and growing the wire status enum remain future iterations.
 
 ## Testing
 
-Package-level suites cover the derivations (deriveGroups/deriveFlat), row components, both apply registrations and passthroughs, host entity move semantics, and the rename/insertSessionBefore RPC implementations with their fixture stubs; the `apps/web` keyless snapshots regress the assembled application; delivery acceptance additionally runs a 12-item playwright (chromium headless) checklist (grouped default, flat switch and persistence, hover-card appearance and suppression, both menus, the full rename chain, drag persistence) and drives the real host over the wire for rename success / duplicate rejection / `workspace-move-invalid`.
+Package-level suites cover the derivations (deriveGroups/deriveFlat), peer session rows, both apply registrations and passthroughs, host entity move semantics, and the rename/insertSessionBefore RPC implementations with their fixture stubs; the `apps/web` keyless snapshots regress the assembled application and pin that a fork does not introduce session expansion controls.

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

@@ -12,14 +12,14 @@ Status: implemented
 
 ## Decision
 
-### 平铺视图与浏览态
+### 平铺行与浏览态
 
-group-by 菜单提供 WorkSpace / In one list 两种模式。平铺模式把所有 session(含 fork 子)一律作为顶层行,严格按 `updatedAt` 新→旧排序,不保持父子相邻;Intent 占位行渲染在列表首行。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。
 
 ### 行交互
 
 - session 行悬停 500ms 出详情卡(全名/相对时间/状态行;状态本期只有 running/idle 两态,枚举扩展待 wire 增补 status 字段)。卡片与行菜单互斥:菜单开启或拖拽进行中不出卡。
-- session 行 … 菜单:Rename / Fork session / Delete session,本期纯视觉;workspace 组头 … 菜单:Rename(已接线)/ Delete workspace(纯视觉)。菜单鼠标移出即关。
+- session 行 … 菜单:Rename / Fork session / Delete session，其中 Rename 与 Fork 已接线，Delete 仍为纯视觉；workspace 组头 … 菜单的 Rename / Delete workspace 均已接线。菜单鼠标移出即关。
 - 支撑件:`Menu` 新增 label 条目、danger 行、`closeOnPointerLeave`;新增 `HoverCard`(portal 定位、开启延时、disabled 守卫)。
 
 ### workspace.rename
@@ -30,7 +30,7 @@ group-by 菜单提供 WorkSpace / In one list 两种模式。平铺模式把所
 
 `session/event` → `touchSession` 活动置顶链整体删除;workspace 账本序改为纯手动拥有——新 session attach 时前插,显式重排走 `workspace.insertSessionBefore({ workspaceId, sessionId, beforeSessionId? })`(DOM insertBefore 语义:锚给了插锚前,缺省 append 到末尾)。实体只对不在账的 session/锚抛类型化的 `WorkspaceMoveInvalidError`,handler 仅把它映射为业务码 `workspace-move-invalid`,存储故障保持 internal。
 
-UI 为组内 root 行的 HTML5 拖拽(仅 workspace 分组、非搜索态;fork 子随父不单独拖)。顺序权威完全在 host:drop 只发 RPC,client 零本地重排,视图靠响应体 upsert 与 changed 帧刷新;失败即无事发生。client 的 upsert 拒绝比已装载投影更旧(`updatedAt`)的快照,防迟到的一元响应回滚更新的帧。
+UI 为组内 session 行的 HTML5 拖拽(仅 workspace 分组、非搜索态；fork 子与源会话一样独立排序)。顺序权威完全在 host:drop 只发 RPC,client 零本地重排,视图靠响应体 upsert 与 changed 帧刷新;失败即无事发生。client 的 upsert 拒绝比已装载投影更旧(`updatedAt`)的快照,防迟到的一元响应回滚更新的帧。
 
 ### 壳/区域切分
 
@@ -46,15 +46,15 @@ ui-sidebar 缩为列几何壳:品牌行、折叠状态机、New Session、Settin
 
 **rename 对话框留在 ui-sidebar(最小改动)** —— 正是问题本身:workspace 域的对话框散落在借来的坑里,每加一个(Delete 确认框将至)都重演跨包接线。评审中先议了「只挪 rename Modal」的中间态,最终裁定整个浏览区域归 ui-workspace,壳只留几何。
 
-**平铺模式保持父子相邻成组** —— 与「严格按时间」矛盾(子新于兄则插不进相邻位),且平铺本意就是取消层级;拉平并禁用平铺下的拖拽(无持久化载体)更一致。
+**WorkSpace 模式按 fork 谱系嵌套 session** —— 嵌套会让当前子会话依赖祖先展开态才能可见，也让组内手动序只能移动根节点；`parentId` 是 lineage 数据，不是列表导航结构。所有 session 拍平成同级行后，每行都可独立打开、搜索与排序；In one list 仍因没有 workspace 持久化载体而禁用拖拽。
 
 ## 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 契约随之改为手动序措辞。
 - 壳/区域两事实契约把 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 菜单三项与 workspace Delete 的功能接线、状态枚举扩 wire,留待后续迭代。
+- session Delete 的功能接线与状态枚举扩 wire,留待后续迭代。
 
 ## Testing
 
-包级用例覆盖派生(deriveGroups/deriveFlat)、行组件、两处 apply 注册与透传、host 实体移位语义、rename/insertSessionBefore 的 RPC 实现与 fixture 桩;`apps/web` keyless snapshot 回归覆盖装配后的应用;交付验收另以 playwright(chromium headless)过 12 项清单(分组默认、平铺切换与持久化、hover 卡出现与抑制、双菜单、rename 全链、拖拽落盘),并对真 host 直打 wire 验证 rename 成功/重名拒绝/`workspace-move-invalid` 三径。
+包级用例覆盖派生(deriveGroups/deriveFlat)、同级 session 行、两处 apply 注册与透传、host 实体移位语义、rename/insertSessionBefore 的 RPC 实现与 fixture 桩；`apps/web` keyless snapshot 回归覆盖装配后的应用，并钉住 fork 后没有 session 展开控件。

.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md
+2026-07-27-web-session-fork-actions.md: b5dc7e820de069a68b38ed87c7d29ffbdb4867bc
+2026-07-27-web-session-fork-actions.zh.md: 774cd74d69eb02d43ca01c8ec7ba1cf94c24b1dc

.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.md

@@ -0,0 +1,33 @@
+# Agent Note: Web session fork actions
+
+Status: implemented
+
+English | [中文](2026-07-27-web-session-fork-actions.zh.md)
+
+## Problem
+
+The Session store already provides a fork primitive that creates a child session from a completed-turn prefix, but the Web client has no unified interaction contract. The Session-row menu can express only “branch from the latest completed turn,” while message IconActions need to express “branch from the turn containing this message”; if the two entry points independently interpret the boundary, switching, and failure behavior, the same user action acquires two sets of semantics. Nesting a fork child beneath its source session also makes the newly selected child visible only while its ancestors are expanded and weakens the workspace manual-order model.
+
+## Decision
+
+The Web Session-row menu and message IconActions share the client runtime's `sessions.fork` action. A Session row passes `{ sessionId, increaseTitle: true }`, so it forks at the source session's last completed turn; a user message or settled assistant content message passes `{ sessionId, atSeq: node.seq, increaseTitle: true }`, so it forks at the turn containing that event. Only the client consumes `increaseTitle`: after adding the child session to its local list, the client increments a trailing `(N)` or `（N）` in the source session's persisted title without changing bracket style, appends ` (1)` to an unnumbered title, and skips the rename when no persisted title exists; the Host fork request still contains only `sessionId` and the optional `atSeq`. The caller opens the child only after the rename succeeds; a fork or rename failure leaves the source session and current selection unchanged, while a child created before a rename failure remains in the list.
+
+`forkAt(seq)` touches the session service only in ui-conversation's apply injection layer; message components report only the event `seq`. Session rows likewise initiate the operation only through ui-workspace's injected callback. Neither presentation package owns session mutation state or duplicates the host's boundary evaluation.
+
+Session lineage is not projected into a list hierarchy. WorkSpace mode displays source sessions and all fork children as peer rows in the manual order from `WorkspaceView.sessionIds`; every row can be opened, searched, and dragged independently. In one list mode continues to sort strictly by `updatedAt`; the Ungrouped group also sorts by recency when no workspace ledger is available. `parentId` remains available for lineage, tool presentation, and later queries, but does not control session-list visibility.
+
+## Alternatives considered
+
+**Wire only the Session-row menu.** Rejected: at a message, the user has already selected more precise context; forcing them back to the list can only degrade the boundary to the latest completed turn, while the visible message branch icon would remain non-responsive.
+
+**Allow branching only from user messages.** Rejected: settled assistant content also has a stable event `seq`, and the host places it in its containing completed turn; making only one of two visually identical branch buttons work would create an invisible behavioral difference.
+
+**Nest fork children beneath their source by `parentId`.** Rejected: lineage is not navigation ownership; nesting requires automatic ancestor expansion to reveal the current item and prevents children from participating in the workspace's peer manual order.
+
+**Call the session service directly from message components.** Rejected: client components must not touch `ctx` or business services; injected callbacks keep mutation in the apply world and leave components driven purely by props.
+
+## Consequences
+
+Users can create forks from Session rows, user messages, or settled assistant content messages; all three entry points ultimately use the same runtime/host operation. Message entry points preserve the exact event boundary, while the list entry point preserves the “latest completed turn” shortcut. Successive fork titles increment through `(1)`, `(2)`, and so on instead of repeatedly appending `(1)`; titles with fullwidth parentheses retain that style. Every fork child immediately appears as an ordinary peer row, so the list no longer needs session expansion state, recursive nodes, or twist controls.
+
+Fork and child-rename failures stay silent and preserve the source selection, preventing a derivation action from disrupting the current reading position; this tradeoff also means the UI does not yet expose a failure reason or retry entry point. Package tests separately pin the two message `seq` paths, title increments, and the peer-list derivation; `apps/web/tests/message-actions.e2e.ts` exercises assistant-message branching and Session-row menu branching through the assembled application.

.agents/notes/implemented/feature/2026-07-27-web-session-fork-actions.zh.md

@@ -0,0 +1,33 @@
+# Agent Note: Web session fork 操作
+
+Status: implemented
+
+[English](2026-07-27-web-session-fork-actions.md) | 中文
+
+## Problem
+
+Session store 已提供按完成轮前缀创建子会话的 fork 原语，但 Web 端没有一份统一的交互契约。Session 行菜单只能表达「从最新完成轮分支」，消息 IconActions 还需要表达「从这条消息所在轮分支」；如果两处各自解释边界、切换与失败行为，同一个用户动作会形成两套语义。把 fork 子会话嵌套在源会话下还会让新选中的子会话依赖祖先展开态才能看见，并削弱 workspace 的手动排序模型。
+
+## Decision
+
+Web 的 session 行菜单与消息 IconActions 共用 client runtime 的 `sessions.fork` 操作。Session 行传 `{ sessionId, increaseTitle: true }`，因此在源会话最后一个已完成轮次处分支；用户消息与已定稿 assistant 内容消息传 `{ sessionId, atSeq: node.seq, increaseTitle: true }`，因此在包含该事件的轮次处分支。`increaseTitle` 只由 client 消费：子会话进入本地列表后，client 把源会话持久化标题尾部的 `(N)` 或 `（N）` 递增并保留括号样式，无编号时追加 ` (1)`，没有持久化标题时不改名；Host fork 请求仍只有 `sessionId` 与可选的 `atSeq`。改名成功后调用方才打开子会话；fork 或改名失败时保持源会话与当前选择不变，改名失败时已创建的子会话仍留在列表中。
+
+`forkAt(seq)` 只在 ui-conversation 的 apply 注入层接触 session 服务，消息组件只回传事件 `seq`。Session 行同理只通过 ui-workspace 的注入回调发起操作；两个呈现包都不持有 session mutation 状态，也不复制 host 的边界求值。
+
+Session lineage 不投影成列表层级。WorkSpace 模式按 `WorkspaceView.sessionIds` 的手动序把源会话与所有 fork 子会话显示为同级行，每行都可独立打开、搜索和拖拽；In one list 模式继续按 `updatedAt` 严格排序；Ungrouped 组在没有 workspace 账本时也按 recency 排序。`parentId` 仍用于 lineage、工具呈现和后续查询，但不控制 session 列表可见性。
+
+## Alternatives considered
+
+**只接 session 行菜单。** 否决：用户在消息处已经选择了更精确的上下文，强迫其回到列表只能退化为最新完成轮，且已展示的消息分支图标会成为无响应控件。
+
+**只允许用户消息分支。** 否决：已定稿 assistant 内容同样有稳定事件 `seq`，host 会把它归入所属完成轮；让两个外观相同的分支按钮只有一个可用会制造不可见的行为差异。
+
+**按 `parentId` 把 fork 子会话嵌套在源会话下。** 否决：lineage 不是导航所有权；嵌套要求自动展开祖先才能看见当前项，并让子会话无法参与 workspace 的同级手动排序。
+
+**由消息组件直接调用 session 服务。** 否决：client 组件不得接触 `ctx` 或业务服务；注入回调让 mutation 留在 apply 世界，组件保持纯 props。
+
+## Consequences
+
+用户可从 session 行、用户消息或已定稿 assistant 内容消息创建分支，三处最终走同一个 runtime/host 操作；消息点位保留精确事件边界，列表点位保留「最新完成轮」快捷语义。连续 fork 的标题按 `(1)`、`(2)` 递增，而不是重复追加 `(1)`；全角括号标题保持全角样式。所有 fork 子会话立即作为普通同级行出现，列表不再需要 session 展开状态、递归节点或 twist 控件。
+
+Fork 与子会话改名失败都保持静默并保留源选择，避免一个派生操作破坏当前阅读位置；该取舍也意味着 UI 暂不提供失败原因或重试入口。Package tests 分别钉住两种消息 `seq`、标题递增与同级列表派生，`apps/web/tests/message-actions.e2e.ts` 通过装配后的应用执行 assistant 消息分支与 session 行菜单分支。

.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.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/2026-07-29-web-message-icon-actions-and-clock.md
-2026-07-29-web-message-icon-actions-and-clock.md: e79662056792c3ab413468ad038dec40455be767
-2026-07-29-web-message-icon-actions-and-clock.zh.md: 72d3b4e0cda19438f2f46fd402b3b76de3726ae5
+2026-07-29-web-message-icon-actions-and-clock.md: ccc9b127d2fcf276fa415ec0ede8b062e45f3df5
+2026-07-29-web-message-icon-actions-and-clock.zh.md: fb4b82a22478b2de38755368ec48a5dca420e79d

.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md

@@ -12,7 +12,7 @@ The web chat user bubble already had copy / branch / edit IconActions but no clo
 
 **User bubbles prepend a date-aware local clock to the existing IconActions row; finalized assistant *content* nodes (non-empty text blocks) append a copy / branch / clock row with `margin-top: 16px`; both seats stay visible whenever mounted and re-format at the next local midnight.**
 
-Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `AssistantMarkdown` places it after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content; Think-only nodes and the streaming tail omit the row. Copy writes joined text blocks. Branch stays a chrome stub. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`.
+Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `AssistantMarkdown` places it after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content; Think-only nodes and the streaming tail omit the row. Copy writes joined text blocks. Both message rows pass their event's `seq` to the same fork callback; [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the real mutation contract. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`.
 
 ## Alternatives considered
 
@@ -22,10 +22,10 @@ Both seats format `node.time` through `formatMessageClock`: same calendar day
 
 **Hover-reveal the action row on hover-capable pointers.** Rejected: once the row exists it should stay discoverable; opacity hiding made the chrome easy to miss and required parent hover selectors that duplicated the mount gate.
 
-**Wire branch to a real session fork.** Rejected for this change: same rationale as the archived [user IconActions note](../../archived/feature/2026-07-27-user-message-icon-actions.md) — the mutation path is unspecified; the button reserves the design seat.
+**Let the IconActions decision also define session fork semantics.** Rejected: this note owns only message chrome, clocks, and mount gating; boundary selection, failure behavior, and switching semantics belong to the separate [Web session fork actions](2026-07-27-web-session-fork-actions.md), keeping presentation components from becoming a second home for session mutation.
 
 **Publish the calendar day through a chat store or inject hook.** Rejected: the day tick is presentation-only local state with no cross-entry consumers; a component-local timeout matches the client rule that behavioral hooks may own state that does not subscribe to an external source.
 
 ## Consequences
 
-Settled assistant content answers expose copy and the event clock as soon as the row mounts; Think-only nodes stay chrome-free; branch stays a stub. User and assistant clocks share the same day/year widening rules and refresh after midnight without a message mutation. Per-message paging remains a deferred footer seat in the package README. Package tests pin the three clock shapes, the midnight widen, and the content-only assistant gate; the web e2e scenario pins the assembled IconActions chrome.
+Settled assistant content answers expose copy, branch, and the event clock as soon as the row mounts; Think-only nodes stay chrome-free. User and assistant clocks share the same day/year widening rules and refresh after midnight without a message mutation. Per-message paging remains a deferred footer seat in the package README. Package tests pin the three clock shapes, the midnight widen, the content-only assistant gate, and the respective event `seq` values passed by the user and assistant branch buttons; the web e2e scenario pins the assembled IconActions chrome.

.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md

@@ -12,7 +12,7 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有
 
 **用户气泡在既有 IconActions 行前追加感知日期的本地时钟；已定稿的 assistant *内容*节点（非空 text 块）在正文下追加带 `margin-top: 16px` 的复制／分支／时钟；两边只要挂载就保持可见，并在下一个本地午夜重新格式化。**
 
-两边都通过 `formatMessageClock` 格式化 `node.time`：同一日历日 → `HH:mm`，同年更早 → `M月D日 HH:mm`，跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度（定时到下一个本地午夜），因此 memo 行在日历日变化时会重渲染，且不新增框架 hook。`MessageItem` 把标签放在复制之前（figma `388:20051`）。`AssistantMarkdown` 把它放在分支之后（figma `43:32997`），且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染；纯 Think 节点与流式尾部省略该行。复制写入拼接后的 text 块。分支仍是 chrome stub。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装面由 `apps/web/tests/message-actions.e2e.ts`（冷 seed 历史 + aria golden）钉住；aria 归一化把每种时钟形态折叠为 `{{clock}}`。
+两边都通过 `formatMessageClock` 格式化 `node.time`：同一日历日 → `HH:mm`，同年更早 → `M月D日 HH:mm`，跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度（定时到下一个本地午夜），因此 memo 行在日历日变化时会重渲染，且不新增框架 hook。`MessageItem` 把标签放在复制之前（figma `388:20051`）。`AssistantMarkdown` 把它放在分支之后（figma `43:32997`），且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染；纯 Think 节点与流式尾部省略该行。复制写入拼接后的 text 块。两种消息行都把自己的事件 `seq` 交给同一个 fork 回调；真实 mutation 契约由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装面由 `apps/web/tests/message-actions.e2e.ts`（冷 seed 历史 + aria golden）钉住；aria 归一化把每种时钟形态折叠为 `{{clock}}`。
 
 ## 曾考虑的方案
 
@@ -22,10 +22,10 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有
 
 **在具备 hover 能力的指针上用 hover 才揭示操作行。** 否决：行一旦存在就应保持可发现；用 opacity 隐藏容易漏看，且需要父级 hover 选择器重复挂载门控。
 
-**把分支接到真实的会话 fork。** 本次否决：与已归档的[用户 IconActions 笔记](../../archived/feature/2026-07-27-user-message-icon-actions.md)同一理由——变更路径尚未规定；按钮只预留设计座位。
+**由 IconActions 决策同时定义 session fork 语义。** 否决：本笔记只拥有消息 chrome、时钟与挂载门控；边界选择、失败行为和切换语义属于独立的 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)，避免展示组件成为 session mutation 的第二正家。
 
 **通过 chat store 或 inject hook 发布日历日。** 否决：日刻度只是展示层本地状态，没有跨入口消费者；组件本地 timeout 符合「行为 hook 可拥有不订阅外部源的状态」这一客户端规则。
 
 ## 后果
 
-已定稿的 assistant 内容回答在行挂载后立刻暴露复制与事件时钟；纯 Think 节点不带 chrome；分支仍为 stub。用户与 assistant 时钟共用同一套跨天／跨年加宽规则，并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中的暂缓 footer 座位。包级测试钉住三种时钟形态、午夜加宽与 assistant 仅内容门控；Web e2e 场景钉住组装后的 IconActions chrome。
+已定稿的 assistant 内容回答在行挂载后立刻暴露复制、分支与事件时钟；纯 Think 节点不带 chrome。用户与 assistant 时钟共用同一套跨天／跨年加宽规则，并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中的暂缓 footer 座位。包级测试钉住三种时钟形态、午夜加宽、assistant 仅内容门控，以及 user/assistant 分支按钮各自传递的事件 `seq`；Web e2e 场景钉住组装后的 IconActions chrome。

.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md
+2026-07-30-plan-review-presentation-intent.md: aeab12aac308c24aa5c4b5953a60ae0f2cf6c5b5
+2026-07-30-plan-review-presentation-intent.zh.md: 4096018e374212c821675ce6ed3a2355df20edc9

.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.md

@@ -0,0 +1,55 @@
+# Agent Note: Plan review as a decision, not a question
+
+Status: implemented
+
+English | [中文](2026-07-30-plan-review-presentation-intent.zh.md)
+
+## Problem
+
+`exit_plan_mode` presents a finished plan for review through `ctx.userInteraction.ask()`, the same seam `ask_user_question` uses. On the Web GUI that made a plan review render as the generic question flow of [the ask-question Web presentation](2026-07-29-ask-question-web-presentation.md): a `1 / 1` pager, the plan as a question's supporting detail, the two verdicts as numbered radio rows with descriptions, an "Other — enter a custom answer" row, and `Skip this question` / `Submit` in the footer.
+
+Every one of those affordances is wrong for the surface. Reviewing a plan is one decision over one document, and the quiz chrome told the user they were being examined rather than asked to approve work — reported as "让人很困惑以为在做题". The paging controls page a set of one. Skipping is not an outcome the tool accepts (it folds into keep-planning). Worst, the surface gave no hint that this was the plan gate at all, while the adjacent waiting-approval takeover already had exactly the right shape for a decision: a tinted strip naming what is being decided, the subject as the body, and a right-aligned action row.
+
+## Decision
+
+A question may declare a **presentation intent**, and the Web composer renders a declared intent as its own surface. `AskUserQuestionItem` gains `intent?: AskUserQuestionIntent`, a tagged shape whose one member is `{ kind: 'plan-review', approve: string }`; `plan-mode` sets it on the review question, naming `Approve` as the label that approves.
+
+An intent shapes presentation only. The answer protocol is untouched: a UI honouring the intent answers with the same option labels a generic UI would send, so `exit_plan_mode` reads one answer shape regardless of which surface collected it, and a UI that does not know a tag renders the generic flow with nothing lost but the layout.
+
+`approve` names the affirmative option instead of relying on option order, so no UI infers a verdict from a position. Two assertions an intent makes are beyond the types, and `UserInteractionService.ask()` rejects both as `BAD_INTENT` at the asker: an `approve` naming none of that question's own options — before any UI can answer a choice never offered — and an intent on a question with no `detail`, the thing it declares itself a review of, which would ask the user to approve something invisible. On the wire the intent is a discriminated union, so an unrecognised tag is a rejected frame rather than a silently generic render.
+
+`ui-question` renders the intent as `PlanReviewPanel`, in the waiting-approval card language: the amber strip carries `Plan review`, the plan is the scrolling markdown body, and the decision row holds three actions — `Chat about it`, `Refuse`, `Approve`. The question text becomes the card's accessible name rather than a headline, because the buttons already say what the decision is. Approve and Refuse answer with the asker's own option labels and keep the asker's descriptions as tooltips; `Chat about it` cancels the request, which returns the composer so the user can simply say what they want. All copy is bilingual under the existing `question` namespace.
+
+Routing lives inside the single composer entry (`QuestionComposer` chooses the shape) rather than in a second chain registration, and `planReviewOf` claims a request only when the card can send every answer that request allows: one question declaring the intent, the plan as its `detail`, the named approve label offered, and a binary single choice — at most one option besides approve, and not multi-select. A third option or a multi-select batch has answers two buttons cannot express, so the generic flow keeps it, and keeps anything else the card cannot render. "Presentation only" is therefore literal: an intent never costs the user a reachable answer, and the client — downstream of a wire boundary — leaves every request answerable.
+
+Dismissal became its own model-facing outcome. `ASK_CANCELLED` previously reached the model as "the user cancelled ask_user_question", naming a tool it never called; `exit_plan_mode` now reports that the user dismissed the review to speak instead and to stay in plan mode and wait. Every other ask failure — an abort from turn cancel or provider teardown, where no user is coming — keeps its own message.
+
+## Alternatives considered
+
+**Make plan review its own pending kind (`plan-review/requested`).** Rejected as the wrong size for a presentation problem. It buys an honest response shape (approve / decline / discuss instead of an answer batch) at the cost of a third `PendingKind`, new requested/resolved frames and schemas, an api-proxy registry and respond branch, client session and baseline-replay handling, and a new three-package capability seam for a decision the question protocol already expresses. Worth revisiting only if plan review grows outcomes the answer shape cannot carry.
+
+**Route the card on the question's `id` or `header` (`plan-review` / `Plan review`).** Rejected: string-sniffing a foreign package's copy across a wire boundary, which any wording change silently breaks. The intent is the declaration that makes the routing legible.
+
+**Order the options and let the card read position 0 as approve.** Rejected: a positional contract at a package seam, invisible in both the type and the wire frame, and unenforceable — a producer that reorders its options would invert a user's verdict. Naming the label costs one string.
+
+**Register a second composer-chain entry for the plan card.** Rejected: two entries would select over the same pending question carrier, making the surface depend on chain priority and on whether the plan package's client half is composed at all. One entry that picks its own shape cannot race itself, and the generic flow is the built-in fallback.
+
+**Put the panel in `ui-plan` beside the plan chip.** Rejected: the panel's whole behavior is the question carrier's answer encoding (`PendingQuestion`), which `ui-question` owns; the intent is a question-protocol field, not plan-mode's private channel. Rendering declared intents belongs to the package that owns question rendering, as tool render intents belong to the tool renderer.
+
+**Extract a shared takeover card with `ui-conversation`'s `ApprovalPanel`.** Not done: the two takeovers agree on tokens and geometry but not on content — this body is scrolling markdown, that one a headline plus a command line — and the shared shell would be two elements wide. They are kept in step by token, not by component.
+
+**Give `Chat about it` its own protocol outcome.** Rejected: dismissing a request is a verb the generic flow already has (the `×` that cancels the batch). Promoting it to a labelled button is presentation; inventing a fourth wire outcome for it is not.
+
+## Consequences
+
+The question protocol now carries a presentation axis. Adding a second intent is a tag on the union, a producer that sets it, a schema member, and a panel — no new frame, service, or answer shape. The cost is that the question seam knows presentation exists at all, and that `ui-question` knows the word "plan"; both are the price of one entry owning every question surface.
+
+The plan gate reads as a plan gate: the plan is the card's content, the verdict is two labelled buttons, and taking the turn back is a third. The generic flow is untouched for every other question, and its committed goldens did not move.
+
+A deployment whose client half predates this change still shows the quiz layout — correct, answerable, and merely unstyled — because the intent is additive and the fallback is the generic flow.
+
+## Testing
+
+`ui-question` tests pin the narrowing (single-question batch, intent present, plan as detail, named approve label offered, binary single choice, decline absent when only approve is offered) and the panel (strip, markdown plan, accessible name, absence of pager/radio/skip/custom, approve and decline answering with the asker's labels, dismissal cancelling, one-shot latch with re-arm and message on a rejected receipt, tooltips present and absent, both locales). `user-interaction` tests pin both `BAD_INTENT` rejections and intent pass-through; `plan-mode` tests pin the declared intent against its own option list and both failure messages; the apiproxy schema test pins wire acceptance and an unknown tag's rejection.
+
+The `plan-review` Web e2e lane records `/plan` entering plan mode for real, the model calling `exit_plan_mode`, the decision card taking the composer (asserting the generic flow did **not** claim the request), and the card's own Approve completing the turn — two keyless goldens, the waiting card and the approved transcript.

.agents/notes/implemented/feature/2026-07-30-plan-review-presentation-intent.zh.md

@@ -0,0 +1,55 @@
+# Agent Note：计划审阅是一次决定，不是一道题
+
+Status: implemented
+
+[English](2026-07-30-plan-review-presentation-intent.md) | 中文
+
+## 问题
+
+`exit_plan_mode` 通过 `ctx.userInteraction.ask()` 把写好的计划交给用户审阅，而这正是 `ask_user_question` 使用的同一个 seam。在 Web GUI 上，这导致计划审阅渲染为[ask-question Web 呈现](2026-07-29-ask-question-web-presentation.md)里的通用问题流程：一个 `1 / 1` 分页器、计划作为问题的补充说明、两个裁决作为带描述的编号单选行、一行"其他，请填写自定义答案"，以及底部的 `跳过本题` / `提交`。
+
+这些可交互元素对这个界面而言无一正确。审阅一份计划是对一份文档做一次决定，而做题式的界面告诉用户他正在被考试，而不是被请求批准一份工作 —— 实际反馈是"让人很困惑以为在做题"。分页控件在给只有一项的集合分页。跳过并不是该工具接受的结果（它会折叠成继续规划）。最糟的是，这个界面完全没有暗示这就是计划关口，而旁边的等待审批接管早就具备了一次决定该有的形状：一条带色条带说明正在决定什么、主体是决定的对象、右对齐的操作行。
+
+## 决定
+
+一个问题可以声明**呈现意图（presentation intent）**，Web 输入区把已声明的意图渲染为它自己的界面。`AskUserQuestionItem` 新增 `intent?: AskUserQuestionIntent`，一个带标签的形状，目前唯一成员是 `{ kind: 'plan-review', approve: string }`；`plan-mode` 在审阅问题上设置它，并指明 `Approve` 是表示批准的标签。
+
+意图只塑造呈现。回答协议不变：遵循意图的 UI 回答的仍是通用 UI 会发送的那些选项标签，因此无论由哪个界面收集，`exit_plan_mode` 读到的都是同一种回答形状；而不认识某个标签的 UI 渲染通用流程，除布局之外一无所失。
+
+`approve` 指名肯定选项，而不依赖选项顺序，因此没有任何 UI 会从位置推断裁决。意图作出的两项断言超出类型的表达能力，`UserInteractionService.ask()` 都以 `BAD_INTENT` 在提问方一侧拒绝：`approve` 未命中该问题自身的任一选项 —— 早于任何 UI 回答一个从未被提供过的选择；以及意图落在没有 `detail` 的问题上，而 `detail` 正是它自称在审阅的东西，那会让用户去批准一件看不见的事。在协议格式（wire format）上意图是可辨识联合，因此无法识别的标签是被拒绝的帧，而不是静默退回通用渲染。
+
+`ui-question` 把该意图渲染为 `PlanReviewPanel`，沿用等待审批卡片的语言：琥珀色条带写着 `Plan review`，计划是可滚动的 markdown 主体，决定行放三个操作 —— `Chat about it`、`Refuse`、`Approve`。问题文本成为卡片的无障碍名称而非标题，因为按钮已经说明了这次决定是什么。Approve 与 Refuse 用提问方自己的选项标签回答，并把提问方的描述保留为 tooltip；`Chat about it` 取消该请求，从而让输入区归位，用户直接说他想说的话即可。所有文案在既有 `question` 命名空间下双语。
+
+路由住在单一输入区条目内部（由 `QuestionComposer` 选择形状），而不是第二个链式注册；`planReviewOf` 仅在卡片能够发出该请求允许的每一个答案时才接管：只有一个问题且声明了意图、以 `detail` 承载计划、提供了被指名的批准标签，且是二元单选 —— 除批准外最多一个选项，且非多选。出现第三个选项或多选批次时，其答案是两个按钮无法表达的，通用流程保留它，也保留其他任何卡片渲染不了的请求。因此"只塑造呈现"是字面意义上的：意图绝不让用户失去一个可达的答案，而位于协议边界下游的客户端让每个请求都保持可回答。
+
+放弃审阅成为面向模型的独立结果。`ASK_CANCELLED` 以前传到模型的是"the user cancelled ask_user_question"，指名了一个它从未调用的工具；现在 `exit_plan_mode` 报告用户放弃审阅是为了改用说话，并要求留在 plan mode 中等待。其余每一种 ask 失败 —— 轮次取消或提供方拆卸导致的中止，那里并没有用户会来 —— 保留它们自己的消息。
+
+## 备选方案
+
+**让计划审阅成为自己的待处理种类（`plan-review/requested`）。** 否决：对一个呈现问题来说尺寸不对。它换来的是诚实的响应形状（approve / decline / discuss 而非一批回答），代价是第三个 `PendingKind`、新的 requested/resolved 帧与 schema、一个 api-proxy 注册表与响应分支、客户端会话与基线重放处理，以及为一个问题协议已能表达的决定新增一个三包能力 seam。只有当计划审阅长出回答形状承载不了的结果时才值得重新考虑。
+
+**按问题的 `id` 或 `header`（`plan-review` / `Plan review`）路由卡片。** 否决：这是跨协议边界嗅探另一个包的文案字符串，任何措辞改动都会静默破坏它。意图才是让路由可读的那个声明。
+
+**约定选项顺序，让卡片把第 0 个位置读作批准。** 否决：这是包边界上的位置约定，在类型和协议帧里都看不见，也无法强制 —— 生产方一旦重排选项，就会颠倒用户的裁决。指名标签只花一个字符串。
+
+**为计划卡片注册第二个输入区链条目。** 否决：两个条目会对同一个待回答问题载体做选择，使界面取决于链优先级、以及计划包的客户端半边是否被组合。一个自己挑形状的条目不会和自己抢，而通用流程正是内建的回退。
+
+**把面板放在 `ui-plan` 里、紧挨计划状态标签。** 否决：面板的全部行为就是问题载体的回答编码（`PendingQuestion`），那是 `ui-question` 拥有的；意图是问题协议的字段，不是 plan-mode 的私有通道。渲染已声明的意图属于拥有问题渲染的那个包，正如工具渲染意图属于工具渲染方。
+
+**与 `ui-conversation` 的 `ApprovalPanel` 抽出共享的接管卡片。** 未做：两个接管在 token 和几何上一致，但内容不一致 —— 这边的主体是可滚动 markdown，那边是一行标题加一行命令 —— 共享外壳只会剩两个元素宽。它们靠 token 保持一致，而不是靠组件。
+
+**给 `Chat about it` 自己的协议结果。** 否决：放弃一个请求是通用流程已有的动词（取消整批的 `×`）。把它提升为带标签的按钮属于呈现；为它发明第四种协议结果不属于。
+
+## 结果
+
+问题协议从此带有一个呈现轴。新增第二个意图 = 联合上的一个标签、一个设置它的生产方、一个 schema 成员、一个面板 —— 不需要新的帧、服务或回答形状。代价是问题 seam 从此知道"呈现"这件事存在，且 `ui-question` 知道"plan"这个词；两者都是由单一条目拥有全部问题界面所要付的价钱。
+
+计划关口读起来就像计划关口：计划是卡片的内容，裁决是两个带标签的按钮，把轮次拿回来是第三个。通用流程对其他每个问题都未受影响，其已提交的 golden 也没有变动。
+
+客户端半边早于本次改动的部署仍然显示做题式布局 —— 正确、可回答、只是没有专门样式 —— 因为意图是增量的，而回退就是通用流程。
+
+## 测试
+
+`ui-question` 测试钉住收窄（单问题批、意图存在、计划作为 detail、被指名的批准标签确实被提供、二元单选、只提供批准时 decline 缺席）与面板（条带、markdown 计划、无障碍名称、无分页/单选/跳过/自定义、批准与拒绝用提问方的标签回答、放弃触发取消、一次性闭锁在回执被拒时重新武装并给出消息、tooltip 有与无、两种语言）。`user-interaction` 测试钉住两种 `BAD_INTENT` 拒绝与意图透传；`plan-mode` 测试钉住已声明的意图与其自身选项列表的一致、以及两条失败消息；apiproxy schema 测试钉住协议接受与未知标签的拒绝。
+
+`plan-review` Web e2e 通道录制了 `/plan` 真实进入 plan mode、模型调用 `exit_plan_mode`、决定卡片接管输入区（并断言通用流程**没有**接管该请求）、以及卡片自身的 Approve 完成该轮 —— 两份无密钥 golden：等待中的卡片与批准后的会话记录。

.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.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/2026-07-30-cordis-config-source-plane-resolution-gate.md
+2026-07-30-cordis-config-source-plane-resolution-gate.md: f9070d39559948ef27f96df5afccd7c4e076f131
+2026-07-30-cordis-config-source-plane-resolution-gate.zh.md: fac6c4047d334d7dd0685aa270234fee3d15dba8

.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.md

@@ -0,0 +1,27 @@
+# Agent Note: verify-cordis-config gates source-plane resolution of configured plugins
+
+Status: implemented
+
+English | [中文](2026-07-30-cordis-config-source-plane-resolution-gate.zh.md)
+
+## Problem
+
+`apps/cli/config/tui.cordis.yml` gained the `@deepseek-ai/dsh-tui/prompt` entry without a matching tsconfig `paths` mapping. The generic `@deepseek-ai/dsh-*` wildcard substitutes `tui/prompt` whole into its `<group>/*/src` candidates, none of which exist, so the [tsx source launch](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md) fell back to package `exports` and resolved `lib/prompt.js` — an artifact-plane file. Every environment with a built `lib/` (developer trees after `pnpm build`) booted fine, and the e2e workflow runs the keyless TUI PTY smoke in `lib` mode (`DSH_EXAMPLE_MODE=lib`, built bin under plain Node) so CI never exercises the source vector at all — while every clean checkout failed `pnpm dsh` at startup with `plugin(s) failed to load: @deepseek-ai/dsh-tui/prompt`. No gate checked the source plane, so the breakage shipped silently and surfaced only in fresh worktrees.
+
+## Decision
+
+`scripts/verify-cordis-config.ts` (`validateSourcePlaneResolution`) requires every configured specifier of a local workspace package — harness packages and vendored Cordis alike — to resolve through the `tsconfig.base.json` `paths` facade to a `.ts`/`.tsx` source file, using `ts.resolveModuleName` from the repository root. A failed resolution or a `.d.ts` hit (the `exports` fallback into built `lib/types`) fails `verify-cordis-config`, naming the config files and the specifier. The missing `@deepseek-ai/dsh-tui/prompt` mapping is added next to the other explicit subpath entries; removing it reproduces the gate failure.
+
+## Alternatives considered
+
+**Rely on the keyless TUI PTY smoke.** In default source mode it boots the real tree through the source vector and does catch the failure — but only on a clean tree. CI's e2e workflow runs it exclusively in `lib` mode (the built bin resolving real package `exports`), so no CI line runs the source vector, and developer trees with a stale `lib/` stay masked locally. Adding a source-mode CI smoke proves one composition per run; the static gate covers every shipped and example config.
+
+**Broaden the `dsh-source-launch-smoke` compat test to full boot.** The node-compat smoke asserts only the TTY refusal, which happens before plugin loading. A full keyless boot per matrix line duplicates the PTY smoke at higher cost and, like it, proves one composition rather than every shipped and example config.
+
+**A `@deepseek-ai/dsh-*/prompt`-style wildcard mapping.** Fixes this one subpath but not the class; the next single-file subpath export (`/surface`, `/message`, …) regresses identically. The static gate covers all current and future configured specifiers.
+
+## Consequences
+
+- A configured workspace specifier that resolves only through built `lib/` is now a red `verify-cordis-config` (in `hygiene` and CI) instead of a clean-tree-only startup crash.
+- New single-file subpath exports referenced from a cordis.yml need an explicit `tsconfig.base.json` `paths` entry at introduction time; the gate message says so.
+- The gate resolves with `tsconfig.base.json` options only; a specifier needing client-only compiler options to resolve would fail it, which matches the facade's role as the single resolution surface for tsx and vitest.

.agents/notes/implemented/process/2026-07-30-cordis-config-source-plane-resolution-gate.zh.md

@@ -0,0 +1,27 @@
+# Agent Note: verify-cordis-config 对配置中插件的源码面解析实施门禁
+
+Status: implemented
+
+[English](2026-07-30-cordis-config-source-plane-resolution-gate.md) | 中文
+
+## 问题
+
+`apps/cli/config/tui.cordis.yml` 新增了 `@deepseek-ai/dsh-tui/prompt` 配置项，却没有对应的 tsconfig `paths` 映射。通用的 `@deepseek-ai/dsh-*` 通配符会把 `tui/prompt` 整体代入其 `<group>/*/src` 候选路径，而这些路径全都不存在，因此 [tsx 源码启动](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)会回退到包（package）的 `exports`，解析出产物面文件 `lib/prompt.js`。任何带有已构建 `lib/` 的环境（开发者目录树运行 `pnpm build` 后）都能正常启动，而 e2e 工作流以 `lib` 模式（`DSH_EXAMPLE_MODE=lib`，构建产物 bin 在普通 Node 下运行）执行无密钥 TUI PTY 冒烟测试，因此 CI 根本不会经过源码启动向量——与此同时，所有干净检出环境中的 `pnpm dsh` 都会在启动时失败，并报错 `plugin(s) failed to load: @deepseek-ai/dsh-tui/prompt`。当时没有门禁检查源码面，因此该故障未被发现便进入发布版本，仅在新的 worktree 中暴露。
+
+## 决策
+
+`scripts/verify-cordis-config.ts`（`validateSourcePlaneResolution`）要求配置中凡是引用本地 workspace 包的模块说明符（包括 harness 包与纳入 vendor 的 Cordis）都必须通过 `tsconfig.base.json` 的 `paths` 外观层（facade）解析到 `.ts`/`.tsx` 源文件；解析以仓库根目录为起点，调用 `ts.resolveModuleName` 完成。解析失败或命中 `.d.ts`（即经 `exports` 回退到构建出的 `lib/types`）都会使 `verify-cordis-config` 失败，并列出配置文件与模块说明符。缺失的 `@deepseek-ai/dsh-tui/prompt` 映射已添加在其他显式子路径条目旁；删除该映射即可复现门禁失败。
+
+## 备选方案
+
+**依赖无密钥 TUI PTY 冒烟测试。** 在默认源码模式下，该测试通过源码向量启动真实目录树，确实能捕获这个故障，但仅限干净目录树。CI 的 e2e 工作流只以 `lib` 模式运行它（构建产物 bin 通过真实的包 `exports` 解析），因此没有任何 CI 环节执行源码向量，而带有过期 `lib/` 的开发者目录树在本地也仍被掩盖。为 CI 增加一个源码模式冒烟测试，每次也只能证明一种组合；静态门禁则覆盖所有随产品发布的配置与示例配置。
+
+**将 `dsh-source-launch-smoke` 兼容性测试扩展为完整启动。** node-compat 冒烟测试只断言 TTY 拒绝，而该拒绝发生在插件加载之前。每条矩阵版本线都执行一次完整的无密钥启动，会以更高成本重复 PTY 冒烟测试，而且同样只能验证一种组合，无法覆盖所有随产品发布的配置与示例配置。
+
+**使用类似 `@deepseek-ai/dsh-*/prompt` 的通配符映射。** 这能修复当前子路径，却不能杜绝这一类问题；下一个单文件子路径导出（`/surface`、`/message` 等）仍会以同样方式复发。静态门禁覆盖当前及未来配置中引用的所有模块说明符。
+
+## 结果
+
+- 配置中的 workspace 模块说明符若只能通过构建后的 `lib/` 解析，现在会导致 `verify-cordis-config` 门禁失败（在 `hygiene` 和 CI 中执行），而不再成为只在干净目录树中出现的启动崩溃。
+- cordis.yml 中引用新的单文件子路径导出时，必须同步为 `tsconfig.base.json` 添加显式 `paths` 条目；门禁消息会明确提示这一要求。
+- 门禁只使用 `tsconfig.base.json` 的选项执行解析；如果某个模块说明符需要仅客户端可用的编译器选项才能解析，门禁就会失败。这符合该外观层作为 tsx 与 vitest 唯一解析入口的定位。

.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.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/testing/2026-07-24-web-gui-browser-e2e-lane.md
-2026-07-24-web-gui-browser-e2e-lane.md: 898b8b5fe1b8d65b108b4afa95b782a1ce1e5c71
-2026-07-24-web-gui-browser-e2e-lane.zh.md: 966a9854aee8f3b63b2ae8f1362f91a40b9ba894
+2026-07-24-web-gui-browser-e2e-lane.md: 107dbddbfde8ad29e22d9cba04ce2b83c1d01383
+2026-07-24-web-gui-browser-e2e-lane.zh.md: e4132b2ebb3f30a9d540f47cf9416a13bc4aa9f3

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

@@ -16,7 +16,7 @@ The web GUI ships as a real assembled chain — chromium page → client plugin
 
 A plain shared-fixture module (the [testing-policy sanctioned shape](../../../../docs/testing.md)), not a package: the gate-worthy logic — replay derivation, session parsing, log scrubbing, persistence — lives in the gated packages `dsh-llm-replay`, `dsh-acp-snapshot`, and `dsh-session-persistence-jsonl`; what remains is boot wiring and browser glue, and chromium-driving code cannot hold per-file 100% coverage on the browserless coverage runners.
 
-`launchWebScaffold()` boots the real web composition from the shipped `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` through the vendored Loader's include mechanism — the same tree and mechanism `AppCLIEntry` drives for `dsh web`. Divergences ride include patches over that tree, the ACP `cordis.snapshot.yml` pattern expressed in-process: temp `persistenceRoot`, `workspace-context` disabled (recorded fixtures must not embed this repo's AGENTS.md), `session-title-llm` disabled (its fire-and-forget title call would race the loop for the session's replay cursor), the webserver row pinned to port 0 with the built dist, and in keyless modes `llm-deepseek` disabled. A patch id that stops matching a row fails the boot sweep loudly instead of drifting. The boot runs `chdir`'d to the temp workspace so the api-gateway's `process.cwd()` session default, tool cwds, and fixtures agree; the `dsh web` bin's own glue (argv, profile json, AppCLIEntry) stays held by the keyless CLI smokes in `smoke-real.e2e.ts`. Setup rollback and ordinary close both dispose the Cordis tree before removing the two owned temp roots, attempt every cleanup independently, and report cleanup failures without masking the setup failure.
+`launchWebScaffold()` boots the real web composition from the shipped `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` through the vendored Loader's include mechanism — the same tree and mechanism `AppCLIEntry` drives for `dsh web`. Divergences ride include patches over that tree, the ACP `cordis.snapshot.yml` pattern expressed in-process: temp `persistenceRoot`; every host-level `skill-local` root (`dshHome`, `agentsHome`, and `bundledSkillDir`) pinned beneath the temp workspace with watching disabled, because ambient skill catalogs are model-visible input; `workspace-context` disabled (recorded fixtures must not embed this repo's AGENTS.md); `session-title-llm` disabled (its fire-and-forget title call would race the loop for the session's replay cursor); the webserver row pinned to port 0 with the built dist; and in keyless modes `llm-deepseek` disabled. A patch id that stops matching a row fails the boot sweep loudly instead of drifting. The boot runs `chdir`'d to the temp workspace so the api-gateway's `process.cwd()` session default, tool cwds, and fixtures agree; the `dsh web` bin's own glue (argv, profile json, AppCLIEntry) stays held by the keyless CLI smokes in `smoke-real.e2e.ts`. Setup rollback and ordinary close both dispose the Cordis tree before removing the two owned temp roots, attempt every cleanup independently, and report cleanup failures without masking the setup failure.
 
 Keyless model displacement is the disabled adapter row plus `installLlmReplay` filling the open seam on the settled root ctx in providers-catalog mode — never catch-all: with the adapter row disabled no adapter exists, so catch-all would leave `resolveModelInfo` unroutable and `compact-basic`'s post-step pressure check would warn every step instead of being provably inert (the published 128k `contextWindow` keeps it inert for small fixtures). The direct install rather than an inserted replay plugin row is deliberate: it returns the `ReplayHandle` the teardown consumption check needs. A scenario with no fixture leaves the seam empty, so a stray stream fails loud with NO_ADAPTER.
 
@@ -76,7 +76,7 @@ Surveyed AI-chat/agent web UIs and mocking layers (LibreChat, vercel/ai-chatbot
 
 ## Testing
 
-`pnpm run test:web` builds and runs the lane keylessly; `test:web:built` runs it against existing build artifacts. `DSH_SNAPSHOT=record pnpm exec vitest run --config vitest.web.config.ts apps/web/tests/<spec>` records a prompting scenario against the live model, and `DSH_SNAPSHOT=refresh pnpm run test:web` rewrites aria goldens keylessly. CI explicitly selects replay mode. `dsh-llm-replay` unit coverage pins pacing, cancellation, consumption diagnostics, sidecar validation, indexed replacement, and the single append position.
+`pnpm run test:web` builds and runs the lane keylessly; `test:web:built` runs it against existing build artifacts. `DSH_SNAPSHOT=record pnpm exec vitest run --config vitest.web.config.ts apps/web/tests/<spec>` records a prompting scenario against the live model, and `DSH_SNAPSHOT=refresh pnpm run test:web` rewrites aria goldens keylessly. CI explicitly selects replay mode. The scaffold hermeticity scenario populates distinct entries in all three ambient skill roots and requires none to enter the assembled catalog. `dsh-llm-replay` unit coverage pins pacing, cancellation, consumption diagnostics, sidecar validation, indexed replacement, and the single append position.
 
 ## Deferred
 

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

@@ -16,7 +16,7 @@ Web GUI 以一条真实组装链交付——chromium 页面 → client 插件 bu
 
 一个普通的共享 fixture 模块（[测试政策认可的形态](../../../../docs/testing.md)），不是包：值得门禁把守的逻辑——回放推导、会话解析、日志脱敏、持久化——都在已受门禁的包 `dsh-llm-replay`、`dsh-acp-snapshot`、`dsh-session-persistence-jsonl` 中；剩下的只是启动接线和浏览器胶水，而驱动 chromium 的源码在无浏览器的覆盖率 runner 上无法诚实保持逐文件 100% 覆盖率。
 
-`launchWebScaffold()` 通过 vendored Loader 的 include 机制，从交付的 `apps/cli/config/base.cordis.yml` 与 `apps/cli/config/web.cordis.yml` 启动真实 web 组合——与 `AppCLIEntry` 为 `dsh web` 驱动的是同一棵树、同一套机制。差异全部经 include patch 覆盖在这棵树上，即 ACP `cordis.snapshot.yml` 模式的进程内表达：临时 `persistenceRoot`；禁用 `workspace-context`（录制的 fixture 不得嵌入本仓库的 AGENTS.md）；禁用 `session-title-llm`（其发后不管的标题调用会与循环争抢会话的回放游标）；webserver 行钉到端口 0 加已构建 dist；无密钥模式下禁用 `llm-deepseek`。patch 的 id 一旦不再匹配任何行，boot 扫描会大声失败而不是漂移。boot 在临时工作区 `chdir` 下运行，使 api-gateway 的 `process.cwd()` 会话默认值、工具 cwd 与 fixture 一致；`dsh web` bin 自身的胶水（argv、profile json、AppCLIEntry）仍由 `smoke-real.e2e.ts` 中的无密钥 CLI 冒烟把守。初始化回滚和正常关闭都会先对 Cordis 树执行 dispose（资源释放），再删除 scaffold 持有的两个临时根目录；每项清理都会独立尝试，并会报告清理失败而不掩盖初始化失败。
+`launchWebScaffold()` 通过 vendored Loader 的 include 机制，从交付的 `apps/cli/config/base.cordis.yml` 与 `apps/cli/config/web.cordis.yml` 启动真实 web 组合——与 `AppCLIEntry` 为 `dsh web` 驱动的是同一棵树、同一套机制。差异全部经 include patch 覆盖在这棵树上，即 ACP `cordis.snapshot.yml` 模式的进程内表达：临时 `persistenceRoot`；每个主机级 `skill-local` 根目录（`dshHome`、`agentsHome` 和 `bundledSkillDir`）都钉在临时工作区下并禁用监听，因为环境 skill（技能）目录是模型可见输入；禁用 `workspace-context`（录制的 fixture 不得嵌入本仓库的 AGENTS.md）；禁用 `session-title-llm`（其发后不管的标题调用会与循环争抢会话的回放游标）；webserver 行钉到端口 0 加已构建 dist；无密钥模式下禁用 `llm-deepseek`。patch 的 id 一旦不再匹配任何行，boot 扫描会大声失败而不是漂移。boot 在临时工作区 `chdir` 下运行，使 api-gateway 的 `process.cwd()` 会话默认值、工具 cwd 与 fixture 一致；`dsh web` bin 自身的胶水（argv、profile json、AppCLIEntry）仍由 `smoke-real.e2e.ts` 中的无密钥 CLI 冒烟把守。初始化回滚和正常关闭都会先对 Cordis 树执行 dispose（资源释放），再删除 scaffold 持有的两个临时根目录；每项清理都会独立尝试，并会报告清理失败而不掩盖初始化失败。
 
 无密钥的模型替换 = 禁用适配器行的 patch 加 `installLlmReplay` 在停稳的根 ctx 上以提供方目录（providers-catalog）模式填充开放的 seam——绝不用 catch-all：适配器行被禁用后不存在任何适配器，catch-all 会让 `resolveModelInfo` 无路由可走，`compact-basic` 的步后压力检查将步步告警，而不是被可证明地闲置（发布的 128k `contextWindow` 使该路径对小 fixture 保持闲置）。选择直接安装而非插入回放插件行是刻意的：直接安装返回收尾消费检查所需的 `ReplayHandle`。没有 fixture 的场景让 seam 保持空置，任何离群的流式调用都会以 NO_ADAPTER 大声失败。
 
@@ -76,7 +76,7 @@ Web GUI 以一条真实组装链交付——chromium 页面 → client 插件 bu
 
 ## Testing
 
-`pnpm run test:web` 构建并无密钥运行该车道；`test:web:built` 基于现有构建产物运行。`DSH_SNAPSHOT=record pnpm exec vitest run --config vitest.web.config.ts apps/web/tests/<spec>` 对真实模型录制一个发起提示的场景，`DSH_SNAPSHOT=refresh pnpm run test:web` 则无密钥重写 aria 预期输出。CI 显式选择回放模式。`dsh-llm-replay` 单元覆盖率钉住节奏控制、取消、消费诊断、sidecar 校验、按索引替换与唯一的追加位置。
+`pnpm run test:web` 构建并无密钥运行该车道；`test:web:built` 基于现有构建产物运行。`DSH_SNAPSHOT=record pnpm exec vitest run --config vitest.web.config.ts apps/web/tests/<spec>` 对真实模型录制一个发起提示的场景，`DSH_SNAPSHOT=refresh pnpm run test:web` 则无密钥重写 aria 预期输出。CI 显式选择回放模式。scaffold 环境隔离场景会在全部 3 个环境 skill 根目录中分别填入不同条目，并要求这些条目都不得进入组装后的目录。`dsh-llm-replay` 单元覆盖率钉住节奏控制、取消、消费诊断、sidecar 校验、按索引替换与唯一的追加位置。
 
 ## 暂缓
 

apps/cli/config/base.cordis.yml

@@ -102,6 +102,8 @@
 
 - id: tool-fs-search
   name: '@deepseek-ai/dsh-tool-fs-search'
+  config:
+    sampleOverCapGlobResults: false
 
 - id: workspace-context
   name: '@deepseek-ai/dsh-workspace-context'

apps/web/tests/approval-composer.e2e.ts

@@ -0,0 +1,181 @@
+// Web e2e scenario: the composer-takeover approval panel under a long
+// command. The shipped composition confines bash through the sandbox policy
+// and routes its escalation through the approval seam, so a read-only session
+// asked to write a file produces a REAL pending approval — the panel renders
+// in the browser, the test measures its geometry, answers through it, and the
+// escalated command then runs. Replay is deterministic: the denial, the
+// escalation retry and its command text arrive from replayed chunks, and the
+// answer click is the test's own gesture (the same sanctioned reaction to
+// model content as the question composer: the turn cannot complete without it).
+//
+// Geometry is the point of the scenario. The command is unbounded model text,
+// and before the cap a long one grew the card until the refuse/allow buttons
+// left the viewport — an approval the user could see and not answer.
+import { readFile } from 'node:fs/promises'
+import { fileURLToPath } from 'node:url'
+import { join } from 'node:path'
+import type { Browser, Page } from 'playwright'
+import { chromium } from 'playwright'
+import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+// Empty type import: carries the approval package's session-event merge, so
+// the decided-outcome assertion below type-checks against the real union.
+import type {} from '@deepseek-ai/dsh-user-approval'
+import {
+  assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
+  launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/approval-composer', import.meta.url))
+const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
+// The scenario's one golden: the waiting panel. Everything the answered state
+// proves is asserted directly — see the world-state block at the end.
+const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
+const MODE = webSnapshotMode()
+
+// Irreducible payload: the command has to be long enough to pass the card's
+// height cap, which is the only shape that reproduces an action row pushed off
+// screen. Unrelated tokens, not a repeated word — a repeated word is what the
+// model compressed into `printf 'alpha %.0s' {1..400}` while recording, and a
+// short command proves nothing here. The formula keeps the source small; the
+// model receives the expanded literal it has to put in the command.
+const TOKENS = Array.from({ length: 220 }, (_, index) => `tok${((index + 1) * 7919 % 99991).toString(36)}`).join(' ')
+const PROMPT = `Write a file named notes.txt in the workspace containing exactly this text on one line: ${TOKENS}. Use one bash command with the literal text inline. Then reply with the single word DONE and stop.`
+
+/** Draft used to measure the composer's own text cap: enough lines to pass it. */
+const CAP_PROBE = Array.from({ length: 40 }, (_, index) => `line ${index}`).join('\n')
+
+describe('web e2e: approval takeover keeps its actions reachable', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+  const sessionEvents: SessionEvent[] = []
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold(MODE === 'record' ? {} : { replayFixture: FIXTURE, paceMs: 15 })
+    scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { sessionEvents.push(event) })
+    browser = await chromium.launch()
+    page = await newEnglishPage(browser)
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await connectFreshWorkspace(page)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('caps the long command, answers through the panel, and runs the escalated command', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-approval'))
+    if (MODE !== 'record') {
+      expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([PROMPT])
+    }
+    const input = page.locator('textarea').first()
+    await input.waitFor({ timeout: 10_000 })
+
+    // The composer's own text cap, measured on the live textarea before the
+    // takeover replaces it. The panel's scroll region must stop at the same
+    // height (the designer's requirement: one cap for the composer seat), and
+    // measuring it here keeps the assertion free of the px value itself.
+    await input.fill(CAP_PROBE)
+    const composerCap = await input.evaluate(el => el.clientHeight)
+    expect(composerCap).toBeGreaterThan(0)
+    await input.fill('')
+
+    // Read-only: the mode whose denial the model escalates from. Switched
+    // through the shipped access-mode chip, not a test-only seam.
+    await page.locator('[aria-label^="Access mode"]').click()
+    await page.getByRole('menuitem', { name: 'Read Only' }).click()
+    await expect.poll(
+      () => page.locator('[aria-label="Access mode, current: Read Only"]').count(),
+      { timeout: 15_000 },
+    ).toBe(1)
+
+    const settled = scaffold.whenTurnSettled(MODE === 'record' ? 240_000 : 60_000)
+    await input.fill(PROMPT)
+    await input.press('Enter')
+
+    // The panel takes over the input area while the tool blocks. Its presence
+    // is a STABLE waiting state (it stays until answered), so waitFor is
+    // race-free.
+    const panel = page.locator('[data-approval-key]')
+    await panel.waitFor({ timeout: MODE === 'record' ? 180_000 : 60_000 })
+    const scroll = panel.locator('[data-approval-scroll]')
+    await expect.poll(() => scroll.getByText(/tok/).count(), { timeout: 15_000 }).toBeGreaterThan(0)
+
+    if (MODE !== 'record') {
+      // This golden owns the stable waiting surface; the answered golden below
+      // owns the resulting transcript.
+      const snapshot = await captureStableAria(page, '[data-approval-key]', scaffold.workspaceCwd)
+      await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
+
+      // The regression this scenario exists for: an uncapped card grew with
+      // the command until the action row left the viewport. Measured at the
+      // lane baseline and at a short viewport, on the live panel.
+      const original = page.viewportSize() ?? { width: 1680, height: 1000 }
+      for (const height of [1000, 700]) {
+        await page.setViewportSize({ width: 900, height })
+        const geometry = await panel.evaluate((root) => {
+          const region = root.querySelector<HTMLElement>('[data-approval-scroll]')
+          const card = region?.parentElement ?? null
+          // Role/text, not the CSS-module class names: the built client hashes those.
+          const buttons = [...root.querySelectorAll<HTMLElement>('button')]
+          const rows = buttons.map(button => button.getBoundingClientRect())
+          return {
+            buttons: buttons.length,
+            capped: region === null ? 0 : region.clientHeight,
+            // A scrolling region proves the cap is genuinely engaged; without
+            // it every assertion below would hold vacuously.
+            scrolls: region === null ? false : region.scrollHeight > region.clientHeight,
+            cardBottom: card === null ? Number.NaN : card.getBoundingClientRect().bottom,
+            actionsTop: Math.min(...rows.map(rect => rect.top)),
+            actionsBottom: Math.max(...rows.map(rect => rect.bottom)),
+            viewport: window.innerHeight,
+          }
+        })
+        expect(geometry.buttons).toBe(2)
+        expect(geometry.scrolls).toBe(true)
+        // One cap for the seat: the panel's text region stops where the
+        // composer draft does (sub-pixel tolerance for the shared padding).
+        expect(Math.abs(geometry.capped - composerCap)).toBeLessThan(1)
+        // Both buttons stay inside the card AND inside the viewport — the
+        // answerable state the cap exists to guarantee.
+        expect(geometry.actionsTop).toBeGreaterThan(0)
+        expect(geometry.actionsBottom).toBeLessThanOrEqual(geometry.viewport)
+        expect(geometry.actionsBottom).toBeLessThanOrEqual(geometry.cardBottom)
+      }
+      await page.setViewportSize(original)
+    }
+
+    await panel.getByRole('button', { name: '允许一次' }).click()
+
+    const sessionId = await settled
+    if (MODE === 'record') {
+      await recordFixture(scaffold, sessionId, FIXTURE)
+      return
+    }
+    // World state: the granted escalation is what let the command run, and the
+    // panel leaves with the regular composer restored. Asserted on the world
+    // and the DOM rather than through a transcript golden — the denied first
+    // attempt renders the OS's own refusal ("Operation not permitted" on
+    // macOS, "Read-only file system" on Linux), so the answered transcript is
+    // not a platform-neutral golden surface.
+    expect(JSON.stringify(sessionEvents.filter(e => e.type === 'approval/decided').at(-1)))
+      .toContain('allowed-once')
+    const written = await readFile(join(scaffold.workspaceCwd, 'workspace', 'notes.txt'), 'utf8')
+    expect(written).toContain(TOKENS.slice(0, 64))
+    await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 20_000 }).toBeGreaterThanOrEqual(1)
+    expect(await page.locator('[data-approval-key]').count()).toBe(0)
+    await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  }, 300_000)
+
+  it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
+    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'ui.expected.md'])
+  })
+})

apps/web/tests/message-actions.e2e.ts

@@ -8,6 +8,7 @@ import { fileURLToPath } from 'node:url'
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import { SessionId } from '@deepseek-ai/dsh-session'
 import {
   assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
   launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold,
@@ -19,6 +20,7 @@ const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/message-actions', import
 // a new recording (workspace-management / sidebar-scrollbar pattern).
 const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
 const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
+const FORK_EXPECTED = join(SNAPSHOT_DIR, 'fork.expected.md')
 const MODE = webSnapshotMode()
 const SEED_ID = 'message-actions-web-e2e'
 
@@ -85,9 +87,58 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
     await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
   })
 
+  it.skipIf(MODE === 'record')('forks through the settled-message and session-row actions', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-message-fork'))
+    // Exercise the assistant action specifically; package coverage pins the
+    // user action separately at its own event seq.
+    await page.getByRole('button', { name: '在新对话中分支' }).last().click()
+    await expect.poll(
+      () => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SEED_ID)),
+      { timeout: 15_000 },
+    ).toBeDefined()
+    await expect.poll(
+      () => page.locator('[role="treeitem"]').count(),
+      { timeout: 10_000 },
+    ).toBe(3)
+    await expect.poll(
+      () => page.locator('[role="treeitem"][aria-selected="true"]').count(),
+      { timeout: 10_000 },
+    ).toBe(1)
+    // The row action owns a distinct ui-workspace injection from the message
+    // action above, so exercise both through the loaded app before capture.
+    const sourceRow = page.locator('[role="treeitem"][aria-selected="true"]')
+    const rowBox = await sourceRow.boundingBox()
+    if (rowBox === null) throw new Error('fork source row has no layout box')
+    const actionButton = sourceRow.locator('button[aria-label^="Session actions for "]')
+    await sourceRow.hover({ position: { x: rowBox.width - 16, y: rowBox.height / 2 } })
+    await expect.poll(() => actionButton.isVisible(), { timeout: 2_000 }).toBe(true)
+    const buttonBox = await actionButton.boundingBox()
+    if (buttonBox === null) throw new Error('fork source row action has no layout box')
+    await page.mouse.click(buttonBox.x + buttonBox.width / 2, buttonBox.y + buttonBox.height / 2)
+    await page.getByRole('menuitem', { name: 'Fork session' }).click()
+    await expect.poll(
+      () => scaffold.ctx.agents.list().filter(agent => agent.session.header.parentSession !== undefined).length,
+      { timeout: 15_000 },
+    ).toBe(2)
+    await expect.poll(
+      () => page.locator('[role="treeitem"]').count(),
+      { timeout: 10_000 },
+    ).toBe(4)
+    await expect.poll(
+      () => page.locator('[role="treeitem"][aria-selected="true"]').count(),
+      { timeout: 10_000 },
+    ).toBe(1)
+    const tree = await captureStableAria(
+      page,
+      '[role="tree"][aria-label="Sessions"]',
+      scaffold.workspaceCwd,
+    )
+    await compareOrRefreshGolden(FORK_EXPECTED, tree, MODE)
+  })
+
   it.skipIf(MODE === 'record')('issued zero model calls and kept a closed inventory', async () => {
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
-    await assertFixtureInventory(SNAPSHOT_DIR, ['ui.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['fork.expected.md', 'ui.expected.md'])
   })
 })

apps/web/tests/plan-review.e2e.ts

@@ -0,0 +1,113 @@
+// Web e2e scenario: the plan-review takeover. The shipped composition mounts
+// plan mode and its client seat, so `/plan <task>` enters plan mode for real
+// and the recorded turn ends on exit_plan_mode blocking against the live
+// userInteraction seam. The composer is then occupied by the plan decision
+// card — not the generic question flow — and approving it through the card
+// completes the turn with the approval in the log.
+// Replay is deterministic: the plan content arrives from replayed chunks, the
+// review wait is real, and the approve click is the test's own gesture (the
+// turn cannot complete without it, in record and replay alike).
+import { readFile } from 'node:fs/promises'
+import { fileURLToPath } from 'node:url'
+import { join } from 'node:path'
+import type { Browser, Page } from 'playwright'
+import { chromium } from 'playwright'
+import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import {
+  assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
+  launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/plan-review', import.meta.url))
+const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
+// The waiting golden owns the decision card; the approved golden owns the
+// transcript the approval leaves behind — the state the card cannot see.
+const REVIEW_EXPECTED = join(SNAPSHOT_DIR, 'review.expected.md')
+const APPROVED_EXPECTED = join(SNAPSHOT_DIR, 'approved.expected.md')
+const MODE = webSnapshotMode()
+
+// One command line: /plan enters plan mode and submits the rest as the turn's
+// message. The task is deliberately self-contained (nothing to explore in a
+// fresh workspace) so the recorded turn is a plan and its review, and the
+// approved continuation is one word.
+const TASK = 'Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. '
+  + 'Call exit_plan_mode with a short plan of at most five bullet points. '
+  + 'Once the plan is approved, reply with the single word DONE and stop.'
+const LINE = `/plan ${TASK}`
+
+describe('web e2e: plan review takeover round trip', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+  const sessionEvents: SessionEvent[] = []
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold(MODE === 'record' ? {} : { replayFixture: FIXTURE, paceMs: 15 })
+    scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { sessionEvents.push(event) })
+    browser = await chromium.launch()
+    // English page: the decision copy is the surface under test, and the
+    // golden pins one language.
+    page = await newEnglishPage(browser)
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await connectFreshWorkspace(page)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('reviews the plan on a decision card and approves through it', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-plan-review'))
+    if (MODE !== 'record') {
+      expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([TASK])
+    }
+    const input = page.locator('textarea').first()
+    await input.waitFor({ timeout: 10_000 })
+    const settled = scaffold.whenTurnSettled(MODE === 'record' ? 180_000 : 30_000)
+    await input.fill(LINE)
+    await input.press('Enter')
+
+    // The card takes over the input area while exit_plan_mode blocks. Its
+    // presence is a STABLE waiting state (it stays until answered), so a plain
+    // waitFor is race-free.
+    const card = page.locator('[data-plan-review-key]')
+    await card.waitFor({ timeout: MODE === 'record' ? 120_000 : 30_000 })
+    // The plan-review request must NOT land on the generic question flow.
+    expect(await page.locator('[data-question-key]').count()).toBe(0)
+    await expect.poll(() => card.getByText('Plan review').count(), { timeout: 10_000 }).toBeGreaterThan(0)
+
+    if (MODE !== 'record') {
+      const snapshot = await captureStableAria(page, '[data-plan-review-key]', scaffold.workspaceCwd)
+      await compareOrRefreshGolden(REVIEW_EXPECTED, snapshot, MODE)
+    }
+
+    await card.getByRole('button', { name: 'Approve' }).click()
+
+    const sessionId = await settled
+    if (MODE === 'record') {
+      await recordFixture(scaffold, sessionId, FIXTURE)
+      return
+    }
+    // World state: the approval reached the tool, and plan mode is left behind.
+    const results = sessionEvents.filter(e => e.type === 'tool/result')
+    expect(JSON.stringify(results.at(-1))).toContain('Plan approved')
+    await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
+    // Card gone; regular input restored.
+    expect(await page.locator('[data-plan-review-key]').count()).toBe(0)
+    await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true)
+    const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(APPROVED_EXPECTED, snapshot, MODE)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  }, 200_000)
+
+  it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
+    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'review.expected.md', 'approved.expected.md'])
+  })
+})

apps/web/tests/scaffold-hermetic.e2e.ts

@@ -0,0 +1,57 @@
+import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { expect, it } from 'vitest'
+import type {} from '@deepseek-ai/dsh-skill'
+import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
+
+async function writeSkill(root: string, name: string): Promise<void> {
+  const bundle = join(root, name)
+  await mkdir(bundle, { recursive: true })
+  await writeFile(join(bundle, 'SKILL.md'), `---
+name: ${name}
+description: Must not enter the Web replay scaffold
+---
+
+Ambient host state.
+`)
+}
+
+it('isolates replay skill discovery from every ambient host root', async () => {
+  const ambient = await mkdtemp(join(tmpdir(), 'dsh-web-ambient-skills-'))
+  const dshHome = join(ambient, 'dsh-home')
+  const agentsHome = join(ambient, 'agents-home')
+  const bundled = join(ambient, 'bundled')
+  await Promise.all([
+    writeSkill(join(dshHome, 'skills'), 'ambient-dsh'),
+    writeSkill(join(agentsHome, 'skills'), 'ambient-agents'),
+    writeSkill(bundled, 'ambient-bundled'),
+  ])
+
+  const originalDshHome = process.env.DSH_HOME
+  const originalAgentsHome = process.env.DSH_AGENTS_HOME
+  const originalBundled = process.env.DSH_BUNDLED_SKILL_DIR
+  process.env.DSH_HOME = dshHome
+  process.env.DSH_AGENTS_HOME = agentsHome
+  process.env.DSH_BUNDLED_SKILL_DIR = bundled
+  let scaffold: WebScaffold | undefined
+  try {
+    scaffold = await launchWebScaffold()
+    const names = (await scaffold.ctx.skills.list({ cwd: scaffold.workspaceCwd })).map(skill => skill.name)
+    expect(names).not.toContain('ambient-dsh')
+    expect(names).not.toContain('ambient-agents')
+    expect(names).not.toContain('ambient-bundled')
+  } finally {
+    try {
+      await scaffold?.close()
+    } finally {
+      if (originalDshHome === undefined) delete process.env.DSH_HOME
+      else process.env.DSH_HOME = originalDshHome
+      if (originalAgentsHome === undefined) delete process.env.DSH_AGENTS_HOME
+      else process.env.DSH_AGENTS_HOME = originalAgentsHome
+      if (originalBundled === undefined) delete process.env.DSH_BUNDLED_SKILL_DIR
+      else process.env.DSH_BUNDLED_SKILL_DIR = originalBundled
+      await rm(ambient, { recursive: true, force: true })
+    }
+  }
+})

apps/web/tests/scaffold.ts

@@ -9,12 +9,13 @@
 // from live session memory), refresh (keyless replay that rewrites goldens).
 //
 // Composition divergences from `dsh web`, all deliberate, all via include
-// patches after the shipped surface overlay: temp persistenceRoot;
-// workspace-context disabled (recorded fixtures must not embed this repo's
-// AGENTS.md); session-title-llm disabled (its fire-and-forget title call
-// would race the loop for the session's replay cursor); webserver pinned to
-// port 0 with the built dist; keyless modes disable llm-deepseek and fill
-// the open llm seam post-boot with installLlmReplay on the settled root ctx
+// patches after the shipped surface overlay: temp persistenceRoot; local skill
+// roots confined to the temp workspace; workspace-context disabled (recorded
+// fixtures must not embed this repo's AGENTS.md); session-title-llm disabled
+// (its fire-and-forget title call would race the loop for the session's replay
+// cursor); webserver pinned to port 0 with the built dist; keyless modes
+// disable llm-deepseek and fill the open llm seam post-boot with
+// installLlmReplay on the settled root ctx
 // (the plugin-row path discards the ReplayHandle; the direct install keeps
 // assertConsumed for the teardown fixture-consumption check).
 import { existsSync } from 'node:fs'
@@ -172,6 +173,19 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
     // per write; the scaffold restores the original cwd after boot, so the
     // row gets an absolute temp root (removed with the workspace at close).
     { id: 'storage-json', config: { root: join(workspaceCwd, '.dsh-storages') } },
+    // Skill discovery is model-visible input. Pin every host-level root inside
+    // the owned temp world so ~/.dsh, ~/.agents, and a bundled-root env setting
+    // cannot change replay requests or conversation goldens. Project roots stay
+    // enabled against the same empty temp workspace, preserving the real seam.
+    {
+      id: 'skill-local',
+      config: {
+        dshHome: join(workspaceCwd, '.dsh-home'),
+        agentsHome: join(workspaceCwd, '.agents-home'),
+        bundledSkillDir: join(workspaceCwd, '.bundled-skills'),
+        watch: false,
+      },
+    },
     // fs/bash cwd default to process.cwd(); the gateway injects the same
     // value into session.cwd — chdir below anchors all three to the temp
     // workspace, keeping the composition untouched.

apps/web/tests/snapshots/approval-composer/ui.expected.md

@@ -0,0 +1,4 @@
+- text: 等待审批
+- group "审批详情": "escalate sandbox to workspace-write: Need to write the notes.txt file as requested by the user. echo 'tok63z tokc7y tokibx tokofw tokujv tok10nu tok16rt tok1cvs tok1izr tok1p3q tok1v7p tok21bo tok2a4 tok8e3 tokei2 tokkm1 tokqq0 tokwtz tok12xy tok191x tok1f5w tok1l9v tok1rdu tok1xht tok23ls tok4k8 tokao7 tokgs6 tokmw5 tokt04 tokz43 tok1582 tok1bc1 tok1hg0 tok1njz tok1tny tok1zrx tokqd tok6uc tokcyb tokj2a tokp69 tokva8 tok11e7 tok17i6 tok1dm5 tok1jq4 tok1pu3 tok1vy2 tok2221 tok30h tok94g tokf8f toklce tokrgd tokxkc tok13ob tok19sa tok1fw9 tok1m08 tok1s47 tok1y86 tok24c5 tok5al tokbek tokhij toknmi toktqh tokzug tok15yf tok1c2e tok1i6d tok1oac tok1ueb tok20ia tok1gq tok7kp tokdoo tokjsn tokpwm tokw0l tok124k tok188j tok1eci tok1kgh tok1qkg tok1wof tok22se tok3qu tok9ut tokfys tokm2r toks6q tokyap tok14eo tok1ain tok1gmm tok1mql tok1suk tok1yyj tok252i tok60y tokc4x toki8w tokocv tokugu tok10kt tok16os tok1csr tok1iwq tok1p0p tok1v4o tok218n tok273 tok8b2 tokef1 tokkj0 tokqmz tokwqy tok12ux tok18yw tok1f2v tok1l6u tok1rat tok1xes tok23ir tok4h7 tokal6 tokgp5 tokmt4 toksx3 tokz12 tok1551 tok1b90 tok1hcz tok1ngy tok1tkx tok1zow toknc tok6rb tokcva tokiz9 tokp38 tokv77 tok11b6 tok17f5 tok1dj4 tok1jn3 tok1pr2 tok1vv1 tok21z0 tok2xg tok91f tokf5e tokl9d tokrdc tokxhb tok13la tok19p9 tok1ft8 tok1lx7 tok1s16 tok1y55 tok2494 tok57k tokbbj tokhfi toknjh tokktng tokzrf tok15ve tok1bzd tok1i3c tok1o7b tok1uba tok20f9 tok1dp tok7ho tokdln tokjpm tokptl tokvxk tok121j tok185i tok1e9h tok1kdg tok1qhf tok1wle tok22pd tok3nt tok9rs tokfvr toklzq toks3p toky7o tok14bn tok1afm tok1gjl tok1mnk tok1srj tok1yvi tok24zh tok5xx tokc1w toki5v toko9u tokudt tok10hs tok16lr tok1cpq tok1itp tok1oxo tok1v1n tok215m tok242 tok881 tokec0 tokfz tokqjy tokwnx' > notes.txt"
+- button "拒绝"
+- button "允许一次"

apps/web/tests/snapshots/message-actions/fork.expected.md

@@ -0,0 +1,7 @@
+- tree "Sessions":
+  - treeitem "Ungrouped 3 sessions" [expanded]:
+    - img
+    - text: Ungrouped 3 sessions
+  - treeitem "Use the read tool twice (2) now" [selected]
+  - treeitem "Use the read tool twice (1) now"
+  - treeitem "Use the read tool twice 1min"

apps/web/tests/snapshots/plan-review/approved.expected.md

@@ -0,0 +1,51 @@
+- banner:
+  - navigation "Session hierarchy":
+    - 'button "Plan a small change: add" [disabled]'
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- img
+- text: "/plan Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. Plan mode on. Use /plan off to leave. Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. {{clock}}"
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- button "编辑":
+  - img
+- 'button "Think The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."':
+  - img
+  - img
+  - text: "Think The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."
+- paragraph:
+  - text: Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with
+  - code: exit_plan_mode
+  - text: .
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- text: {{clock}}
+- button:
+  - img
+  - img
+- text: "Tool call exit_plan_mode · # Add `--greeting` flag to CLI"
+- 'button "Think The plan was approved. The user''s last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."':
+  - img
+  - img
+  - text: "Think The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."
+- paragraph: DONE
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- text: {{clock}}
+- textbox "Message the agent"
+- button "Add attachment":
+  - img
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 51% Input 10.2K tok · Output 346 tok

apps/web/tests/snapshots/plan-review/review.expected.md

@@ -0,0 +1,44 @@
+- region "Approve this plan and leave plan mode?":
+  - text: Plan review
+  - heading "Add --greeting flag to CLI" [level=1]:
+    - text: Add
+    - code: "--greeting"
+    - text: flag to CLI
+  - list:
+    - listitem:
+      - strong: Locate the CLI entry point
+      - text: (e.g.,
+      - code: cli.py
+      - text: ","
+      - code: main.go
+      - text: ","
+      - code: index.js
+      - text: etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).
+    - listitem:
+      - strong: Register a new optional string argument
+      - text: named
+      - code: "--greeting"
+      - text: with a short alias (
+      - code: "-g"
+      - text: if available) and a sensible default value (e.g.,
+      - code: "\"Hello\""
+      - text: ).
+    - listitem:
+      - strong: Thread the parsed value
+      - text: through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).
+    - listitem:
+      - strong: Update the help text
+      - text: so
+      - code: "--help"
+      - text: or
+      - code: "-h"
+      - text: shows the new flag with its description.
+    - listitem:
+      - strong: No tests or config changes
+      - text: unless they already exist and directly validate the flag's presence.
+  - status
+  - button "Chat about it":
+    - img
+    - text: Chat about it
+  - button "Refuse"
+  - button "Approve"

apps/web/tests/snapshots/plan-review/session.jsonl

@@ -0,0 +1,39 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785406804293,"cwd":"{{cwd}}/workspace"}
+{"type":"command/run","seq":0,"time":1785406804350,"data":{"commandId":"cmd-228a60ef-1","name":"plan","args":" Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop.","source":{"kind":"user"}}}
+{"type":"plan/mode","seq":1,"time":1785406804350,"data":{"active":true}}
+{"type":"command/done","seq":2,"time":1785406804352,"data":{"commandId":"cmd-228a60ef-1","kind":"success","text":"Plan mode on. Use /plan off to leave."}}
+{"type":"turn/start","seq":3,"time":1785406804353,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":4,"time":1785406804353,"data":{"content":[{"type":"text","text":"Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"a22bd0d2-15dc-4bfb-b978-0d5961459e57"},"surfaceOp":"append"}
+{"type":"session/title","seq":5,"time":1785406804354,"data":{"title":"Plan a small change: add","messageSeqs":[4],"source":{"kind":"fallback"}}}
+{"type":"step/start","seq":6,"time":1785406804355,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":7,"time":1785406804356,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"assistant/chunk","seq":8,"time":1785406805697,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"reasoning-chunks","seq0":9,"time0":1785406805698,"data":{"turn":1,"step":1,"index":0,"dt":[151,31,0,0,0,0,18,1,0,0,0,31,1,0,0,0,1,23,0,0,0,19,0,0,37,1,0,0,0,0,12,1,0,0,28,0,1,0,24,1,0,0,0,0,26,1,0,0,26,1,22],"texts":["The"," user"," wants"," me"," to"," plan"," a"," small"," change"," to"," add"," a"," `","--","gre","eting","`"," flag"," to"," a"," CLI","."," They"," explicitly"," told"," me"," not"," to"," read"," or"," write"," any"," files",","," and"," to"," call"," exit","_","plan","_mode"," with"," a"," short"," plan","."," Let"," me"," do"," that"," directly","."]}}
+{"type":"assistant/chunk","seq":61,"time":1785406806155,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
+{"type":"text-chunks","seq0":62,"time0":1785406806156,"data":{"turn":1,"step":1,"index":1,"dt":[0,20,0,34,23,26,0,1,0,0,28,0,0,0,32,0,15,1,0,30,1,0,0,23,1,0,24,0,0,0],"texts":["Since"," the"," user"," has"," explicitly"," asked"," me"," not"," to"," read"," or"," write"," any"," files"," and"," to"," go"," straight"," to"," planning",","," I","'ll"," proceed"," with"," `","exit","_","plan","_mode","`."]}}
+{"type":"assistant/chunk","seq":93,"time":1785406806493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":2,"blockType":"tool-call"}}}
+{"type":"tool-call-chunks","seq0":94,"time0":1785406806493,"data":{"turn":1,"step":1,"index":2,"dt":[27,1,0,0,0,24,0,0,29,1,0,0,0,1,20,0,27,1,0,21,28,0,0,31,1,23,0,0,1,23,0,0,0,23,1,0,28,20,26,28,1,0,29,1,0,0,21,28,0,0,25,1,26,1,0,0,24,1,0,26,0,0,0,1,23,1,0,0,22,29,0,31,1,1,0,21,1,0,0,0,0,20,0,32,25,0,0,22,0,0,27,0,1,0,31,0,1,0,0,20,1,0,0,0,0,24,0,1,0,26,1,29,1,26,1,0,25,30,1,18,0,30,0,0,30,21,1,28,0,21,1,0,0,23,1,23,36,0,0,1,0,13,1,28,27,0,0,25,1,45,1,11,0,21,0,0,0,0,23,0,0,32,1,0,0,0,16,28,0,27,1,0,22,31,1,24,1,21,32,1,0,24,1,0,24],"id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","args":["","{","\"","plan","\"",": ","\"","#"," Add"," `","--","gre","eting","`"," flag"," to"," CLI","\\n\\n","-"," **","Loc","ate"," the"," CLI"," entry"," point","**"," (","e",".g",".,"," `","cli",".py","`,"," `","main",".go","`,"," `","index",".js","`"," etc",".)"," and"," find"," the"," argument"," parser"," definition"," (","arg","parse",","," click",","," cob","ra",","," y","args",","," or"," similar",").\\n","-"," **","Register"," a"," new"," optional"," string"," argument","**"," named"," `","--","gre","eting","`"," with"," a"," short"," alias"," (`","-","g","`"," if"," available",")"," and"," a"," sensible"," default"," value"," (","e",".g",".,"," `","\\\"","Hello","\\\"","`",").\\n","-"," **","Thread"," the"," parsed"," value","**"," through"," the"," main"," handler"," function"," so"," it"," is"," passed"," where"," the"," greeting"," string"," is"," used"," (","e",".g",".,"," the"," welcome","/","response"," message",").\\n","-"," **","Update"," the"," help"," text","**"," so"," `","--","help","`"," or"," `","-","h","`"," shows"," the"," new"," flag"," with"," its"," description",".\\n","-"," **","No"," tests"," or"," config"," changes","**"," unless"," they"," already"," exist"," and"," directly"," validate"," the"," flag","'s"," presence",".","\"","}"]}}
+{"type":"assistant/chunk","seq":280,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."}}}}
+{"type":"assistant/chunk","seq":281,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."}}}}
+{"type":"assistant/chunk","seq":282,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":2,"block":{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}}}}
+{"type":"assistant/chunk","seq":283,"time":1785406808319,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52}}}}
+{"type":"assistant/chunk","seq":284,"time":1785406808319,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":285,"time":1785406808324,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."},{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."},{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"b9e18116-68f6-4442-b5a5-a33277ef526c"},"usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52}},"sourceEventSeqs":[8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284],"surfaceOp":"append"}
+{"type":"tool/call","seq":286,"time":1785406808325,"data":{"turn":1,"step":1,"callId":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}}
+{"type":"tool/result","seq":287,"time":1785406808720,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_TPh5fH8x5kRezK115kgx8155"},"content":[{"type":"tool-result","toolCallId":"call_00_TPh5fH8x5kRezK115kgx8155","content":[{"type":"text","text":"Plan approved — plan mode exited; carry out the plan starting with your next step."}],"isError":false}],"role":"user","id":"e7cf1f9f-e143-48df-b975-440a9d61a538"}},"sourceEventSeqs":[286],"surfaceOp":"append"}
+{"type":"step/end","seq":288,"time":1785406808721,"data":{"turn":1,"step":1}}
+{"type":"plan/mode","seq":289,"time":1785406808721,"data":{"active":false}}
+{"type":"step/start","seq":290,"time":1785406808723,"data":{"turn":1,"step":2}}
+{"type":"request/header","seq":291,"time":1785406808723,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
+{"type":"assistant/chunk","seq":292,"time":1785406809855,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"reasoning-chunks","seq0":293,"time0":1785406809855,"data":{"turn":1,"step":2,"index":0,"dt":[133,28,1,0,0,17,0,28,1,0,0,29,0,0,0,0,0,21,0,0,0,35,0,0,0,0,0,14,1,37,1,0,1,17,0,0,0,0,1],"texts":["The"," plan"," was"," approved","."," The"," user","'s"," last"," instruction"," says",":"," \"","Once"," the"," plan"," is"," approved",","," reply"," with"," the"," single"," word"," D","ONE"," and"," stop",".\""," So"," I"," should"," just"," reply"," with"," D","ONE"," and"," stop","."]}}
+{"type":"assistant/chunk","seq":333,"time":1785406810252,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":334,"time":1785406810253,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
+{"type":"assistant/chunk","seq":335,"time":1785406810253,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
+{"type":"assistant/chunk","seq":336,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."}}}}
+{"type":"assistant/chunk","seq":337,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
+{"type":"assistant/chunk","seq":338,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}}}}
+{"type":"assistant/chunk","seq":339,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":340,"time":1785406810257,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"2d9da552-d236-4166-9d06-dffa9bace4cd"},"usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}},"sourceEventSeqs":[292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339],"surfaceOp":"append"}
+{"type":"step/end","seq":341,"time":1785406810258,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":342,"time":1785406810258,"data":{"turn":1,"reason":{"kind":"completed"}}}

apps/web/tsconfig.json

@@ -23,8 +23,11 @@
   // cannot see both sides of the cordis Context merges).
   "exclude": [
     "tests/scaffold.ts",
+    "tests/scaffold-hermetic.e2e.ts",
     "tests/live-interactions.e2e.ts",
     "tests/question-composer.e2e.ts",
+    "tests/approval-composer.e2e.ts",
+    "tests/plan-review.e2e.ts",
     "tests/steering.e2e.ts",
     "tests/navigation-panes.e2e.ts",
     "tests/lifecycle-chrome.e2e.ts",

docs/config-catalog.md

@@ -1682,8 +1682,10 @@ Source: [`packages/fs/tool-fs/src/index.ts:24`](../packages/fs/tool-fs/src/index
 Requires: `tools` · `systemPrompt` · `bash`
 
 ```ts config-catalog
-/** Plugin config (all optional — `Config` supplies the defaults). */
+/** Plugin config; over-cap glob sampling is an explicit deployment choice and the remaining fields have defaults. */
 export interface Config {
+  /** Whether an over-cap `glob` page is sampled across top-level entries instead of taking the modification-time head. */
+  sampleOverCapGlobResults: boolean
   /** Max paths one `glob` call retains inline; later paths go to the formatted spill file. */
   globMaxResults?: number
   /** Max flat matches one `grep` call retains inline; later matches go to the formatted spill file. */

docs/cordis-catalog/services.md

@@ -908,7 +908,7 @@ set(agent: Agent, active: boolean): 'committed' | 'queued' | 'cancelled' | 'noop
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/plan/plan-mode/src/index.ts:179`](../../packages/plan/plan-mode/src/index.ts)
+Source: [`packages/plan/plan-mode/src/index.ts:182`](../../packages/plan/plan-mode/src/index.ts)
 
 ## `ctx.pty` — `PtyService`
 
@@ -2340,7 +2340,7 @@ async ask(request: AskUserQuestionRequest): Promise<AskUserQuestionAnswer>
 
 Types: [AskUserQuestionAnswer](../core-data-structures/user-interaction.md) · [AskUserQuestionRequest](../core-data-structures/user-interaction.md) · [UserInteractionProvider](../core-data-structures/user-interaction.md)
 
-Source: [`packages/ui/user-interaction/src/index.ts:50`](../../packages/ui/user-interaction/src/index.ts)
+Source: [`packages/ui/user-interaction/src/index.ts:51`](../../packages/ui/user-interaction/src/index.ts)
 
 ## `ctx.web` — `WebService`
 

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

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-user-interaction.md: 798a9790f424683775284a98421be08e6e1399e3
-user-interaction.zh.md: 12bfcffe4fe4caaacb54e90126eac55e333d64a5
+#   pnpm run verify-translation-pairing --write docs/core-data-structures/user-interaction.md
+user-interaction.md: 2483382eee07d379b13d456149096c8afab70e4b
+user-interaction.zh.md: 57f57277975597fff712705cc741ae8e78643642

docs/core-data-structures/user-interaction.md

@@ -20,6 +20,30 @@ interface AskUserQuestionOption {
 }
 ```
 
+## Presentation intent
+
+`AskUserQuestionIntent` is the optional declaration that a question IS a decision of a known shape. It is tagged on `kind` so intents can be added; a UI that does not recognise a tag renders the generic option list. An intent shapes presentation only — a UI honouring it answers with the same option labels a generic UI would send, so the caller reads one answer shape either way. `approve` names the affirmative option instead of relying on option order. `ask()` rejects the two assertions no type can carry: an `approve` naming none of its own question's options, and an intent on a question with no `detail`.
+
+```ts type-equiv
+/**
+ * A caller-declared presentation intent: the question IS a decision of this
+ * shape, so a UI that recognises the tag may present it as such instead of as a
+ * generic option list. Tagged so further intents can be added; a UI that does
+ * not know a tag renders the generic flow, and the answer encoding is identical
+ * either way — an intent shapes presentation only, never the protocol.
+ */
+type AskUserQuestionIntent = {
+  /** A plan submitted for review: `detail` is the plan markdown `ask()` requires, and the decision approves or declines it. */
+  kind: 'plan-review'
+  /**
+   * The option label that approves the plan; every other option declines it.
+   * Named rather than positional so no UI infers the verdict from option order.
+   * An `approve` naming no option of its own question is rejected at `ask()`.
+   */
+  approve: string
+}
+```
+
 ## Question item
 
 `AskUserQuestionItem` is one question in a request. The caller supplies a stable `id`, which is echoed back with the answer so batched questions remain routable. Optional `detail` carries supporting text that providers render with the question but keep out of selectable option labels.
@@ -39,6 +63,8 @@ interface AskUserQuestionItem {
   options?: AskUserQuestionOption[]
   /** Whether more than one option may be selected. Defaults to single-select. */
   multiSelect?: boolean
+  /** Optional presentation intent for capable UIs; absent asks for the generic option list. */
+  intent?: AskUserQuestionIntent
 }
 ```
 

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

@@ -20,6 +20,30 @@ interface AskUserQuestionOption {
 }
 ```
 
+## 呈现意图
+
+`AskUserQuestionIntent` 是一项可选声明：某个问题本身就是一次已知形状的决定。它按 `kind` 打标签，因此意图可以扩充；不认识某个标签的 UI 渲染通用选项列表。意图只塑造呈现 —— 遵循它的 UI 回答的仍是通用 UI 会发送的那些 option label，因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名肯定选项，而不依赖选项顺序。有两项断言是任何类型都承载不了的，`ask()` 会拒绝它们：`approve` 未命中该问题自身的任一选项，以及意图落在没有 `detail` 的问题上。
+
+```ts type-equiv
+/**
+ * A caller-declared presentation intent: the question IS a decision of this
+ * shape, so a UI that recognises the tag may present it as such instead of as a
+ * generic option list. Tagged so further intents can be added; a UI that does
+ * not know a tag renders the generic flow, and the answer encoding is identical
+ * either way — an intent shapes presentation only, never the protocol.
+ */
+type AskUserQuestionIntent = {
+  /** A plan submitted for review: `detail` is the plan markdown `ask()` requires, and the decision approves or declines it. */
+  kind: 'plan-review'
+  /**
+   * The option label that approves the plan; every other option declines it.
+   * Named rather than positional so no UI infers the verdict from option order.
+   * An `approve` naming no option of its own question is rejected at `ask()`.
+   */
+  approve: string
+}
+```
+
 ## 问题条目
 
 `AskUserQuestionItem` 是请求中的一个问题。调用方提供稳定的 `id`，它会随答案原样返回，使批量问题仍可路由。可选的 `detail` 携带辅助文本；提供方会将其随问题渲染，但不会放入可选 option label。
@@ -39,6 +63,8 @@ interface AskUserQuestionItem {
   options?: AskUserQuestionOption[]
   /** Whether more than one option may be selected. Defaults to single-select. */
   multiSelect?: boolean
+  /** Optional presentation intent for capable UIs; absent asks for the generic option list. */
+  intent?: AskUserQuestionIntent
 }
 ```
 

docs/tool-catalog.md

@@ -23,7 +23,7 @@ This table connects model-visible tool names to the plugin package and service s
 | `@deepseek-ai/dsh-tool-bash-persistent` | `bash` | `ctx.tools`, `ctx.pty`, `an owning Agent at execution time` | `tool/call`, `PTY shell state`, `tool/result` | - | One owner-isolated persistent bash tool; deployment composition supplies the PTY backend and may override the model-facing environment description. |
 | `@deepseek-ai/dsh-tool-str-replace-editor` | `str_replace_editor` | `ctx.tools`, `ctx.fs` | `tool/call`, `fs/observed after successful file operations`, `tool/result` | - | Standalone view/create/unique literal replace/line insert tool over the filesystem seam; it composes with any shell or terminal surface. |
 | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. |
-| `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. |
+| `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. |
 | `@deepseek-ai/dsh-tool-pty` | `terminal_close`, `terminal_list`, `terminal_open`, `terminal_read`, `terminal_send`, `terminal_signal` | `ctx.tools`, `ctx.pty`, `ctx.systemPrompt`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The six terminal tools are opt-in and complement one-shot bash/filesystem tools. `terminal_send(run_in_background: true)` registers with `ctx.tasks`; TUI, named key sequences, BEL, resize, auto-start, and cross-agent sharing are absent from the schema. |
 | `@deepseek-ai/dsh-tool-goal` | `create_goal`, `get_goal`, `update_goal` | `ctx.tools`, `ctx.agents`, `ctx.goals`, `ctx.systemPrompt`, `a calling Agent in an authorized open turn` | `tool/call`, `user/message goal snapshot for mutations`, `tool/result` | - | create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds. |
 | `@deepseek-ai/dsh-tool-lsp` | `lsp` | `ctx.tools`, `ctx.lsp`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | The lsp tool keeps provider selection and language-server subprocesses behind ctx.lsp, so its model-visible schema stays stable across providers. Requires a registered provider (e.g. `@deepseek-ai/dsh-lsp-local`) at runtime; without one, a query returns the structured `LSP_UNAVAILABLE` error rather than changing the schema. |
@@ -472,7 +472,7 @@ The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `
 
 ### `glob`
 
-Find files whose paths match a glob pattern. Returns matching paths sorted by modification time, including hidden and ignored files (VCS metadata directories are excluded). Returns the first 100 paths inline; a capped result reports where the complete list was saved.
+Find files whose paths match a glob pattern. Returns matching file paths — never directories — including hidden and ignored files (VCS metadata directories are excluded). Up to 100 paths come back in modification-time order; a larger result instead returns 100 paths sampled across top-level entries, says so, and reports where the complete sorted list was saved. This tool does not enumerate directory entries.
 
 ```json
 {
@@ -480,7 +480,7 @@ Find files whose paths match a glob pattern. Returns matching paths sorted by mo
   "properties": {
     "pattern": {
       "type": "string",
-      "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\")."
+      "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth."
     },
     "path": {
       "type": "string",
@@ -524,7 +524,7 @@ Search file contents with a ripgrep regular expression. Returns matching lines w
 
 Source: [`packages/fs/tool-fs-search/src/index.ts`](../packages/fs/tool-fs-search/src/index.ts)
 
-glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.
+glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.
 
 ## `@deepseek-ai/dsh-tool-pty`
 

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

@@ -43,6 +43,8 @@ const RETRY_CONFIG = fileURLToPath(new URL('../retry.cordis.yml', import.meta.ur
 const SESSION_TITLE_CONFIG = fileURLToPath(new URL('../session-title.cordis.yml', import.meta.url))
 const LSP_CONFIG = fileURLToPath(new URL('./lsp.cordis.yml', import.meta.url))
 const WEB_CONFIG = fileURLToPath(new URL('../web.cordis.yml', import.meta.url))
+const FS_SEARCH_CONFIG = fileURLToPath(new URL('./fs-search.cordis.yml', import.meta.url))
+const FS_SEARCH_BIN = fileURLToPath(new URL('./fixtures/fs-search-bin', import.meta.url))
 const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
 const PACKED_CHUNKS_SOURCE = 'hook-cc-pretool-deny'
 
@@ -147,6 +149,19 @@ const SCENARIOS: Scenario[] = [
     hasModelTurn: true,
     recorded: true,
   },
+  // The real Loader/app/bash path executes a deterministic rg stand-in at the
+  // external-process seam, pinning over-cap glob sampling without depending on
+  // a host-installed ripgrep binary.
+  {
+    name: 'fs-glob-sampling',
+    hasModelTurn: true,
+    recorded: false,
+    pinsHeader: true,
+    headerClass: 'fs-search',
+    configPath: FS_SEARCH_CONFIG,
+    env: { PATH: `${FS_SEARCH_BIN}:${process.env.PATH ?? ''}` },
+    posixOnly: true,
+  },
   { name: 'fs-read', hasModelTurn: true, recorded: true },
   { name: 'fs-write', hasModelTurn: true, recorded: true },
   { name: 'fs-edit', hasModelTurn: true, recorded: true },

examples/acp-agent/tests/fixtures/fs-search-bin/rg

@@ -0,0 +1,10 @@
+#!/bin/sh
+printf '%s\n' \
+  'archive/a.ts' \
+  'archive/b.ts' \
+  'archive/c.ts' \
+  'old\one' \
+  'old\two' \
+  'src/index.ts' \
+  'docs/guide.md' \
+  'test/spec.ts'

examples/acp-agent/tests/fs-search.cordis.snapshot.yml

@@ -0,0 +1,35 @@
+# Minimal keyless composition: real app, bash, and search tool; replayed model.
+- id: llm-replay
+  name: '@deepseek-ai/dsh-llm-replay'
+  config:
+    providers:
+      - id: deepseek
+        name: DeepSeek
+        models:
+          - id: deepseek-v4-pro
+
+- id: subprocess
+  name: '@deepseek-ai/dsh-subprocess-local'
+
+- id: bash
+  name: '@deepseek-ai/dsh-bash-local'
+
+- id: acp-agent
+  name: '@deepseek-ai/dsh-acp-demo'
+  config:
+    provider: deepseek
+    model: deepseek-v4-pro
+    persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+    persistenceCompression: none
+    workspaceContext: false
+    skills:
+      enabled: false
+    toolTasks: false
+    goals: false
+    persona: You are a concise snapshot agent working in {{cwd}}.
+
+- id: tool-fs-search
+  name: '@deepseek-ai/dsh-tool-fs-search'
+  config:
+    sampleOverCapGlobResults: true
+    globMaxResults: 4

examples/acp-agent/tests/fs-search.cordis.yml

@@ -0,0 +1,33 @@
+# Minimal live counterpart for the glob-sampling snapshot composition.
+- id: llm-deepseek
+  name: '@deepseek-ai/dsh-llm-deepseek'
+  config:
+    apiKey: !!js process.env.DEEPSEEK_API_KEY
+    baseURL: !!js process.env.DEEPSEEK_BASE_URL
+    models:
+      - id: deepseek-v4-pro
+
+- id: subprocess
+  name: '@deepseek-ai/dsh-subprocess-local'
+
+- id: bash
+  name: '@deepseek-ai/dsh-bash-local'
+
+- id: acp-agent
+  name: '@deepseek-ai/dsh-acp-demo'
+  config:
+    provider: deepseek
+    model: deepseek-v4-pro
+    persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+    workspaceContext: false
+    skills:
+      enabled: false
+    toolTasks: false
+    goals: false
+    persona: You are a concise snapshot agent working in {{cwd}}.
+
+- id: tool-fs-search
+  name: '@deepseek-ai/dsh-tool-fs-search'
+  config:
+    sampleOverCapGlobResults: true
+    globMaxResults: 4

examples/acp-agent/tests/snapshots/fs-glob-sampling/input.json

@@ -0,0 +1,7 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "Call glob exactly once with pattern * and no path. Then reply with exactly GLOB_SAMPLED and nothing else." }
+  ]
+}

examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl

@@ -0,0 +1,24 @@
+{"type":"session","version":0,"id":"f5a99d52-3eaa-4ce7-858d-61d4fd77df2a","createdAt":1785218400000,"cwd":"{{cwd}}","delegationDepth":0}
+{"type":"turn/start","seq":0,"time":1785218400001,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":1,"time":1785218400002,"data":{"content":[{"type":"text","text":"Call glob exactly once with pattern * and no path. Then reply with exactly GLOB_SAMPLED and nothing else."}],"source":{"kind":"user"},"role":"user","id":"4b397774-ea1a-445a-8116-d25647bf32e6"},"surfaceOp":"append"}
+{"type":"session/title","seq":2,"time":1785218400003,"data":{"title":"Call glob exactly once with","messageSeqs":[1],"source":{"kind":"fallback"}}}
+{"type":"step/start","seq":3,"time":1785218400004,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":4,"time":1785218400005,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"assistant/chunk","seq":5,"time":1785218400006,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":6,"time":1785218400007,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"glob-sampling-call","name":"glob","argumentsDelta":"{\"pattern\":\"*\"}"}}}
+{"type":"assistant/chunk","seq":7,"time":1785218400008,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}}}}
+{"type":"assistant/chunk","seq":8,"time":1785218400009,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}}
+{"type":"assistant/chunk","seq":9,"time":1785218400010,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":10,"time":1785218400011,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-pro"},"id":"d8c174b5-2f08-49b3-80d5-a69aabefbd7a"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
+{"type":"tool/call","seq":11,"time":1785218400012,"data":{"turn":1,"step":1,"callId":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}}
+{"type":"tool/result","seq":12,"time":1785218400013,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"glob-sampling-call"},"content":[{"type":"tool-result","toolCallId":"glob-sampling-call","content":[{"type":"text","text":"archive/a.ts\nold\\one\nold\\two\nsrc/index.ts\n\n(Showing 4 of 8 paths, sampled across 4 of the 6 top-level entries this pattern matched instead of taken in modification-time order. Narrow path to inspect a specific subtree. The complete result could not be saved; narrow pattern or path to see more.)"}],"isError":false}],"role":"user","id":"e9711775-0ea5-4383-a562-76a6b49a4742"}},"sourceEventSeqs":[11],"surfaceOp":"append"}
+{"type":"step/end","seq":13,"time":1785218400014,"data":{"turn":1,"step":1}}
+{"type":"step/start","seq":14,"time":1785218400015,"data":{"turn":1,"step":2}}
+{"type":"assistant/chunk","seq":15,"time":1785218400016,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":16,"time":1785218400017,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"GLOB_SAMPLED"}}}
+{"type":"assistant/chunk","seq":17,"time":1785218400018,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GLOB_SAMPLED"}}}}
+{"type":"assistant/chunk","seq":18,"time":1785218400019,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}}
+{"type":"assistant/chunk","seq":19,"time":1785218400020,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":20,"time":1785218400021,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"GLOB_SAMPLED"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-pro"},"id":"6f8b4c32-baad-405b-9957-435dc5c855b2"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
+{"type":"step/end","seq":21,"time":1785218400022,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":22,"time":1785218400023,"data":{"turn":1,"reason":{"kind":"completed"}}}

examples/acp-agent/tests/snapshots/fs-glob-sampling/stdout.expected.jsonl

@@ -0,0 +1,4 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GLOB_SAMPLED"}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}

examples/acp-agent/tests/snapshots/fs-glob-sampling/system-prompt.expected.md

@@ -0,0 +1,9 @@
+You are an AI agent powered by the DeepSeek Harness SDK.
+
+You are a concise snapshot agent working in {{cwd}}.
+
+Use the glob tool — not shell find — to discover files by path pattern. A pattern with no "/" matches basenames at any depth, so "*" matches every file in the tree rather than its top level. Results are files only, never directories, and include hidden and ignored files: a result that fits comes back in modification-time order, while a larger one is sampled across top-level entries, so it spans the tree instead of one subtree.
+
+Use the grep tool — not shell grep or rg — to search file contents. Use read on a matched file when you need surrounding context.
+
+Check the [exit code: N] marker on every bash result; investigate failures before moving on.

examples/acp-agent/tests/snapshots/fs-glob-sampling/tool-schemas.expected.json

@@ -0,0 +1,82 @@
+{
+  "initial": [
+    {
+      "name": "bash",
+      "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "description": "The bash command to execute."
+          },
+          "description": {
+            "type": "string",
+            "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
+          },
+          "timeoutMs": {
+            "type": "number",
+            "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
+          },
+          "workdir": {
+            "type": "string",
+            "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
+          },
+          "run_in_background": {
+            "type": "boolean",
+            "description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."
+          }
+        },
+        "required": [
+          "command",
+          "description"
+        ]
+      }
+    },
+    {
+      "name": "glob",
+      "description": "Find files whose paths match a glob pattern. Returns matching file paths — never directories — including hidden and ignored files (VCS metadata directories are excluded). Up to 4 paths come back in modification-time order; a larger result instead returns 4 paths sampled across top-level entries, says so, and reports where the complete sorted list was saved. This tool does not enumerate directory entries.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "pattern": {
+            "type": "string",
+            "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth."
+          },
+          "path": {
+            "type": "string",
+            "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it."
+          }
+        },
+        "required": [
+          "pattern"
+        ]
+      }
+    },
+    {
+      "name": "grep",
+      "description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns the first 250 matches inline; a capped result reports where the complete match list was saved. Use read on a matched file for surrounding context.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "pattern": {
+            "type": "string",
+            "description": "Regular expression to search for (ripgrep syntax)."
+          },
+          "path": {
+            "type": "string",
+            "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it."
+          },
+          "include": {
+            "type": "string",
+            "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported."
+          }
+        },
+        "required": [
+          "pattern"
+        ]
+      }
+    }
+  ],
+  "changes": []
+}

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

@@ -1042,6 +1042,56 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
         const appended = logOf(sessionId).at(-1) as SessionEvent
         return ok(request, { title: normalized, seq: appended.seq })
       },
+      fork: (request) => {
+        const { sessionId, atSeq } = request.payload
+        const source = summaryOf(sessionId)
+        if (source === undefined) {
+          return err(request, {
+            code: 'session-not-found',
+            message: `no session ${sessionId}`,
+            details: { sessionId },
+          })
+        }
+        const log = logs.get(sessionId) ?? []
+        const lastSeq = log.at(-1)?.seq ?? -1
+        const anchoredBoundary = atSeq === undefined
+          ? undefined
+          : log.find(e => e.type === 'turn/end' && e.seq >= atSeq)
+        const boundary = anchoredBoundary
+          ?? (atSeq === undefined || atSeq > lastSeq
+            ? log.findLast(e => e.type === 'turn/end')
+            : undefined)
+        if (boundary === undefined) {
+          return err(request, {
+            code: 'fork-unavailable',
+            message: atSeq !== undefined && atSeq <= lastSeq
+              ? `session ${sessionId} has not completed the turn containing event ${String(atSeq)}`
+              : `session ${sessionId} has no completed turn`,
+            details: { sessionId },
+          })
+        }
+        let cut = boundary.seq + 1
+        while (cut < log.length && log[cut]?.type !== 'turn/start') cut++
+        const child: SessionSummary = {
+          sessionId: sid(`fx-${nextSession++}`), updatedAt: Date.now(), running: false, blank: false,
+          parentSessionId: sessionId,
+          ...source.cwd === undefined ? {} : { cwd: source.cwd },
+        }
+        logs.set(child.sessionId, log.slice(0, cut))
+        sessions.push(child)
+        emitHost({
+          type: 'host/session-added', sessionId: child.sessionId, blank: false,
+          parentSessionId: sessionId,
+          ...source.cwd === undefined ? {} : { cwd: source.cwd },
+        })
+        const workspace = workspaces.find(w => w.sessionIds.includes(sessionId))
+        if (workspace !== undefined) {
+          workspace.sessionIds = [child.sessionId, ...workspace.sessionIds]
+          workspace.updatedAt = new Date().toISOString()
+          emitHost({ type: 'host/workspace-changed', workspace: { ...workspace } })
+        }
+        return ok(request, { sessionId: child.sessionId })
+      },
       history: async (request) => {
         const log = logs.get(request.payload.sessionId) ?? []
         // Snapshot at request time, deliver after the transit delay (mirrors a real host under latency).
@@ -1591,6 +1641,7 @@ export class FixtureApiClient extends AbstractApiClient {
       case 'session.models': return this.api.sessions.models(request)
       case 'session.selectModel': return this.api.sessions.selectModel(request)
       case 'session.rename': return this.api.sessions.rename(request)
+      case 'session.fork': return this.api.sessions.fork(request)
       case 'session.prompt': return this.api.sessions.prompt(request)
       case 'session.updateQueue': return this.api.sessions.updateQueue(request)
       case 'session.cancel': return this.api.sessions.cancel(request)

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

@@ -46,6 +46,7 @@ export class FakeApiClient implements IApiClient {
   onList: (payload: unknown) => Promise<RpcResponse<{ items: never[] }>> = () => Promise.resolve(ok({ items: [] }))
   onCreate: (payload: unknown) => Promise<RpcResponse<{ sessionId: SessionId }>> = () => Promise.resolve(ok({ sessionId: 'fk-new' as SessionId }))
   onRename: (payload: unknown) => Promise<RpcResponse<{ title: string; seq: number }>> = () => Promise.resolve(ok({ title: 'fk-renamed', seq: 0 }))
+  onFork: (payload: unknown) => Promise<RpcResponse<{ sessionId: SessionId }>> = () => Promise.resolve(ok({ sessionId: 'fk-fork' as SessionId }))
   onHistory: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number })
   => Promise<RpcResponse<{ events: never[]; hasMore: boolean; modelTarget: ModelTarget }>> =
     () => Promise.resolve(ok({
@@ -99,6 +100,7 @@ export class FakeApiClient implements IApiClient {
     selectModel: (payload: ModelTarget & { sessionId: SessionId }) =>
       this.record('session.selectModel', payload, this.onSelectModel(payload)),
     rename: (payload: unknown) => this.record('session.rename', payload, this.onRename(payload)),
+    fork: (payload: unknown) => this.record('session.fork', payload, this.onFork(payload)),
     prompt: (payload: unknown) => this.record('session.prompt', payload, this.onPrompt(payload)),
     updateQueue: (payload: unknown) => this.record('session.updateQueue', payload, this.onUpdateQueue(payload)),
     cancel: (payload: unknown) => this.record('session.cancel', payload, this.onCancel(payload)),

packages/client/runtime/README.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 packages/client/runtime/README.md
-README.md: 766d8516225cd46cb1a3a80c832d1cf55e816140
-README.zh.md: 9b514afca91f604b3e895187de3b5532bf22a692
+README.md: b85deeec92fd4da1f342b5536757692f594853a5
+README.zh.md: 2dbb66c56ad5687fb299fe030d0abfe451004a62

packages/client/runtime/README.md

@@ -28,6 +28,10 @@ SlotsService gives the renderer separate bare observables for `useSessions` and
 
 `SessionManager` retains the latest validated `session/title` control snapshot independently of list and session-instance arrival. Newer event seqs replace older snapshots, title timestamps contribute to list recency, and a subscription baseline discards any retained title beyond its `lastSeq` before the optional folded title arrives. Explicit session removal also clears the retained title. The client-facing `SessionSummary.title` is therefore only the actual durable title; `displayTitle` is always present and falls back through the cwd basename and session id. A cold persisted session keeps that fallback until opening or resuming it causes the host to fold and project its log-backed title. `ISession.rename` settles the `title` projection cell directly from the unary response's `{title, seq}` under the same higher-seq-wins rule — the list row and every `useProjection('title')` reader update ahead of the push frame, whose later replay of the same seq is a no-op.
 
+## Session forking
+
+`ISessions.fork({sessionId, atSeq?, increaseTitle?})` resolves only after the child summary is locally addressable, carrying source lineage and cwd with `blank: false`; callers choose whether to open it. With `increaseTitle: true`, the client renames the child from the source session's persisted title: a trailing `(N)` or `（N）` is incremented without changing bracket style, while any other title gets ` (1)` appended; the rename is skipped when the source has no persisted title, and a rename failure rejects the promise but leaves the created child in place. This option is not sent in the Host fork request. A `workspace-attach-failed` response still identifies a child already published by the Host, so `SessionManager` reconciles that partial success before `SessionForkError` reaches the caller instead of making a retry create a duplicate child.
+
 ## Session model selection
 
 Each resident `Session` owns a `modelSelection` snapshot containing the current provider/model target, provider-grouped directory, provider-local failures, and the `idle`/`loading`/`ready`/`selecting`/`error` state. History establishes or refreshes the current target, opening a selector refreshes the directory, and selection failures preserve the last target and usable groups. Directory and selection operations share a monotonically increasing generation so an older response cannot overwrite a newer selection. A reconnect rebuild restores the target reported by the Host without replacing unchanged selection substructure.

packages/client/runtime/README.zh.md

@@ -28,6 +28,10 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸
 
 `SessionManager` 独立于列表和 Session 实例到达情况，保留最近一次通过验证的 `session/title` 控制快照。seq 更高的事件会替换旧快照，标题时间戳计入列表新近程度；订阅基线会先丢弃 seq 超过其 `lastSeq` 的任何已保留标题，再接收可选的折叠标题。显式移除 Session 也会清除已保留标题。因此，面向客户端的 `SessionSummary.title` 只包含实际的持久化标题；`displayTitle` 始终存在，并依次回退到 cwd basename 和 Session id。冷态持久化会话会保持该回退值，直到打开或恢复会话，促使主机折叠并投影由日志支撑的标题。`ISession.rename` 用 unary 响应中的 `{title, seq}` 直接结算 `title` 投影格，遵循同一 seq 高者胜规则——列表行和所有 `useProjection('title')` 读者在推送帧到达前即更新；推送帧随后重放同一 seq 时为无操作。
 
+## 会话 fork
+
+`ISessions.fork({sessionId, atSeq?, increaseTitle?})` 只在子会话摘要已能在本地寻址后才完成；该摘要携带源会话的谱系和 cwd，且 `blank: false`，由调用方决定是否打开。`increaseTitle: true` 会在 client 端把源会话的持久化标题改名到子会话：尾部 `(N)` 或 `（N）` 递增并保留括号样式，其余标题追加 ` (1)`；源会话没有持久化标题时跳过改名，改名失败时拒绝 promise 但保留已创建的子会话。该选项不会进入 Host fork 请求。即使响应为 `workspace-attach-failed`，其中仍会标识 Host 已发布的子会话，因此 `SessionManager` 会先将这一部分成功对账，再让 `SessionForkError` 到达调用方，避免重试创建重复的子会话。
+
 ## 会话模型选择
 
 每个常驻 `Session` 都拥有一个 `modelSelection` 快照，其中包含当前提供方/模型目标、按提供方分组的目录、逐提供方失败记录，以及 `idle`／`loading`／`ready`／`selecting`／`error` 状态。历史记录会建立或刷新当前目标，打开选择器会刷新目录；选择失败会保留上一个目标和可用分组。目录与选择操作共用单调递增的代次，因此较旧响应无法覆盖较新的选择。重连重建会恢复 Host 报告的目标，同时不替换未变化的选择子结构。

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

@@ -29,6 +29,17 @@ export interface ISessions {
   open(id: SessionId): void
   /** Clear the current selection into the no-session view state. */
   clear(): void
+  /**
+   * Fork a session from a completed-turn prefix of the source; on resolution
+   * the child is in the list store and `open()` can target it.
+   * @param opts - source session id, the optional event seq anchoring the
+   *   cut (the boundary is the first turn/end at or after it; an in-log
+   *   anchor in an open turn is unavailable rather than clipped backward),
+   *   and whether to increment an inherited durable title before resolving.
+   * @returns the child session id.
+   * @throws when the fork fails, or when a requested child-title rename fails after creation.
+   */
+  fork(opts: { sessionId: SessionId; atSeq?: number; increaseTitle?: boolean }): Promise<SessionId>
   /**
    * Register a per-session standard-props provider (hooks become `use<Name>`
    * selector hooks on the render side; props spread verbatim).

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

@@ -289,6 +289,40 @@ export class SessionManager {
     }
   }
 
+  /**
+   * Contract session.fork; on success merge the child into summaries
+   * immediately (same synchronous-addressability guarantee as create). The
+   * child carries the source's history, so it is never blank; lineage rides
+   * parentSessionId so the list nests it under its source. A child published
+   * before Workspace attachment fails is also reconciled into the list.
+   * @param opts - source session and the optional seq anchoring the cut.
+   * @returns the fork result (the child session id).
+   */
+  async fork(
+    opts: { sessionId: SessionId; atSeq?: number },
+  ): Promise<RpcResult<{ sessionId: SessionId }>> {
+    try {
+      const source = this.summaries.find(s => s.sessionId === opts.sessionId)
+      const { result } = await this.api.sessions.fork({
+        sessionId: opts.sessionId,
+        ...opts.atSeq === undefined ? {} : { atSeq: opts.atSeq },
+      })
+      const childId = result.ok
+        ? result.value.sessionId
+        : workspaceAttachSessionId(result.error)
+      if (childId !== undefined) {
+        this.recordMutation({ kind: 'upsert', summary: {
+          sessionId: childId, updatedAt: Date.now(), running: false, blank: false,
+          parentSessionId: opts.sessionId,
+          ...(source?.cwd !== undefined ? { cwd: source.cwd } : {}),
+        } })
+      }
+      return result
+    } catch (error) {
+      return transportError(error)
+    }
+  }
+
   /**
    * Insert-or-enrich a locally synthesized summary: a new id prepends; an
    * existing entry only gains fields it lacks (the session-added frame and the

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

@@ -81,6 +81,22 @@ export class SessionCreateError extends Error {
   }
 }
 
+/** Structured session-fork failure. */
+export class SessionForkError extends Error {
+  override readonly name = 'SessionForkError'
+
+  /**
+   * @param rpcError - Host business or folded transport error.
+   * @param sourceSessionId - the session the fork was cut from.
+   */
+  constructor(
+    readonly rpcError: RpcError,
+    readonly sourceSessionId: SessionId,
+  ) {
+    super(`session fork failed: ${rpcError.code}: ${rpcError.message}`)
+  }
+}
+
 /** Session assembly handle for SessionProvider/inject factories (identity-stable per session). */
 export interface SessionBinding {
   readonly sessionId: SessionId
@@ -121,6 +137,24 @@ function displayTitleOf(title: string | undefined, cwd: string | undefined, id:
   return id
 }
 
+/**
+ * Increment a trailing fork number while preserving its half-width or
+ * full-width parentheses; an unnumbered title starts with ` (1)`.
+ * @param title - source session's durable title.
+ * @returns the title assigned to the fork child.
+ */
+function increasedForkTitle(title: string): string {
+  const ascii = /^(.*?)\((\d+)\)$/u.exec(title)
+  if (ascii?.[1] !== undefined && ascii[2] !== undefined) {
+    return `${ascii[1]}(${BigInt(ascii[2]) + 1n})`
+  }
+  const fullWidth = /^(.*?)（(\d+)）$/u.exec(title)
+  if (fullWidth?.[1] !== undefined && fullWidth[2] !== undefined) {
+    return `${fullWidth[1]}（${BigInt(fullWidth[2]) + 1n}）`
+  }
+  return `${title} (1)`
+}
+
 interface ScopeRecord {
   fiber: Fiber
   ctx: Context
@@ -317,6 +351,42 @@ export class SessionsService implements ISessions {
     return result.value.sessionId
   }
 
+  /**
+   * Fork a session from a completed-turn prefix of the source (same
+   * synchronous-addressability guarantee as {@link SessionsService.create}:
+   * on resolution the child is in the list store and open() can target it).
+   * @param opts - source session id, the optional event seq anchoring the
+   *   cut (the boundary is the first turn/end at or after it; an in-log
+   *   anchor in an open turn is unavailable rather than clipped backward),
+   *   and whether to increment an inherited durable title before resolving.
+   * @returns the child session id.
+   * @throws {SessionForkError} with the source id.
+   * @throws {Error} when a requested child-title rename fails after creation.
+   */
+  async fork(opts: {
+    sessionId: SessionId
+    atSeq?: number
+    increaseTitle?: boolean
+  }): Promise<SessionId> {
+    const sourceTitle = opts.increaseTitle
+      ? this.list.getSnapshot().byId[opts.sessionId]?.title
+      : undefined
+    const result = await this.manager.fork({
+      sessionId: opts.sessionId,
+      ...(opts.atSeq === undefined ? {} : { atSeq: opts.atSeq }),
+    })
+    if (!result.ok) throw new SessionForkError(result.error, opts.sessionId)
+    this.projectList()
+    const childId = result.value.sessionId
+    if (sourceTitle !== undefined) {
+      const child = this.binding(childId)?.session
+      if (child === undefined) throw new Error(`fork child "${childId}" is not locally addressable`)
+      const renamed = await child.rename(increasedForkTitle(sourceTitle))
+      if (!renamed.ok) throw new Error(`fork child rename failed: ${renamed.error.code}: ${renamed.error.message}`)
+    }
+    return childId
+  }
+
   /**
    * Resolve an Agent-scoped context view (use-and-discard).
    * @param id - session id (the agent identity — 1:1 same axis).

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

@@ -64,6 +64,7 @@ export class FakeApiClient implements IApiClient {
   onCreate: (payload: unknown) => Promise<RpcResponse<{ sessionId: SessionId }>> = () => Promise.resolve(ok({ sessionId: 'fk-new' as SessionId }))
   readonly defaultModel: ModelTarget = { provider: 'deepseek', model: 'deepseek-v4-flash' }
   onRename: (payload: unknown) => Promise<RpcResponse<{ title: string; seq: number }>> = () => Promise.resolve(ok({ title: 'fk-renamed', seq: 0 }))
+  onFork: (payload: unknown) => Promise<RpcResponse<{ sessionId: SessionId }>> = () => Promise.resolve(ok({ sessionId: 'fk-fork' as SessionId }))
   onHistory: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number })
   => Promise<RpcResponse<{ events: never[]; hasMore: boolean }>> =
     () => Promise.resolve(ok({ events: [], hasMore: false }))
@@ -118,6 +119,7 @@ export class FakeApiClient implements IApiClient {
     selectModel: (payload: { provider: string; model: string }) =>
       this.record('session.selectModel', payload, this.onSelectModel(payload)),
     rename: (payload: unknown) => this.record('session.rename', payload, this.onRename(payload)),
+    fork: (payload: unknown) => this.record('session.fork', payload, this.onFork(payload)),
     prompt: (payload: unknown) => this.record('session.prompt', payload, this.onPrompt(payload)),
     updateQueue: (payload: unknown) => this.record('session.updateQueue', payload, this.onUpdateQueue(payload)),
     cancel: (payload: unknown) => this.record('session.cancel', payload, this.onCancel(payload)),

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

@@ -277,6 +277,23 @@ describe('remaining branches', () => {
     expect(manager.getListSnapshot().items[0]).not.toHaveProperty('cwd')
   })
 
+  it('reconciles a fork child published before workspace attachment fails', async () => {
+    const api = new FakeApiClient()
+    api.onFork = () => Promise.resolve(err({
+      code: 'workspace-attach-failed',
+      message: 'forked but unattached',
+      details: { sessionId: S2, workspaceId: 'w1' },
+    } as never))
+    const manager = new SessionManager(api)
+    const result = await manager.fork({ sessionId: S1 })
+    expect(result).toMatchObject({ ok: false, error: { code: 'workspace-attach-failed' } })
+    expect(manager.getListSnapshot().items).toEqual([expect.objectContaining({
+      sessionId: S2,
+      parentSessionId: S1,
+      blank: false,
+    })])
+  })
+
   it('reconciles a preallocated id after an ordinary transport failure', async () => {
     const api = new FakeApiClient()
     api.onCreate = () => Promise.reject(new Error('response lost'))

packages/client/runtime/tests/sessions-service.spec.ts

@@ -10,7 +10,7 @@ import { Context } from 'cordis'
 import { afterEach, describe, expect, it, vi } from 'vitest'
 import type { SessionId } from '@deepseek-ai/dsh-client-connection/client'
 import { SessionCreateError, SessionsService, scopeOf } from '../src/client/sessions/service.ts'
-import { FakeApiClient, deferred, ok } from './fake-api.ts'
+import { FakeApiClient, deferred, err, ok } from './fake-api.ts'
 
 const sid = (s: string): SessionId => s as SessionId
 
@@ -399,6 +399,69 @@ describe('create', () => {
   })
 })
 
+describe('fork', () => {
+  it.each([
+    ['Roadmap', 'Roadmap (1)'],
+    ['Roadmap (1)', 'Roadmap (2)'],
+    ['计划（1）', '计划（2）'],
+    ['计划 （9）', '计划 （10）'],
+  ])('increments the durable title %j after the child is published', async (sourceTitle, childTitle) => {
+    const b = bench()
+    b.svc.handleMuxEnvelope({
+      rpcId: 'source-title' as never,
+      payload: { type: 'session/projection', sessionId: sid('source'), key: 'title', value: sourceTitle, seq: 2 } as never,
+    })
+    await feedList(b, [{ id: 'source', cwd: '/work' }])
+    b.api.onFork = () => Promise.resolve(ok({ sessionId: sid('child') }))
+    b.api.onRename = (payload) => {
+      const { title } = payload as { title: string }
+      return Promise.resolve(ok({ title, seq: 3 }))
+    }
+
+    await expect(b.svc.fork({
+      sessionId: sid('source'), atSeq: 7, increaseTitle: true,
+    })).resolves.toBe('child')
+
+    expect(b.api.callsOf('session.fork')).toEqual([{ sessionId: 'source', atSeq: 7 }])
+    expect(b.api.callsOf('session.rename')).toEqual([{ sessionId: 'child', title: childTitle }])
+    await Promise.resolve()
+    expect(b.svc.list.getSnapshot().byId[sid('child')]).toMatchObject({
+      title: childTitle,
+      displayTitle: childTitle,
+      parentId: 'source',
+    })
+  })
+
+  it('does not rename without the title policy or a durable source title', async () => {
+    const b = bench()
+    await feedList(b, [{ id: 'source', cwd: '/work' }])
+    b.api.onFork = () => Promise.resolve(ok({ sessionId: sid('child') }))
+    await expect(b.svc.fork({ sessionId: sid('source'), increaseTitle: true })).resolves.toBe('child')
+    expect(b.api.callsOf('session.rename')).toEqual([])
+
+    b.api.onFork = () => Promise.resolve(ok({ sessionId: sid('child-2') }))
+    await expect(b.svc.fork({ sessionId: sid('source') })).resolves.toBe('child-2')
+    expect(b.api.callsOf('session.rename')).toEqual([])
+  })
+
+  it('rejects when child rename fails while keeping the published child addressable', async () => {
+    const b = bench()
+    b.svc.handleMuxEnvelope({
+      rpcId: 'source-title' as never,
+      payload: { type: 'session/projection', sessionId: sid('source'), key: 'title', value: 'Roadmap', seq: 2 } as never,
+    })
+    await feedList(b, [{ id: 'source' }])
+    b.api.onFork = () => Promise.resolve(ok({ sessionId: sid('child') }))
+    b.api.onRename = () => Promise.resolve(err({
+      code: 'title-invalid', message: 'rejected', details: { sessionId: sid('child') },
+    }))
+
+    await expect(b.svc.fork({ sessionId: sid('source'), increaseTitle: true }))
+      .rejects.toThrow('fork child rename failed: title-invalid: rejected')
+    expect(b.svc.binding(sid('child'))).toBeDefined()
+  })
+})
+
 describe('scope lifecycle rides the list mirror (entity parity: no client-side pre-birth)', () => {
   it('a session-added frame births the row (blank) and makes the scope resolvable; removal prunes it', async () => {
     const b = bench()

packages/client/test-runtime/src/sessions.ts

@@ -169,7 +169,7 @@ export class TestSessions implements ISessions {
   private readonly channel: SessionProvideChannel
 
   /** Calls observed on the service-level face (open/clear), newest last. */
-  readonly calls: { method: 'open' | 'clear'; args: unknown[] }[] = []
+  readonly calls: { method: 'open' | 'clear' | 'fork'; args: unknown[] }[] = []
 
   /**
    * @param stabilize - the owning runtime's act wrapper.
@@ -392,6 +392,17 @@ export class TestSessions implements ISessions {
     this.list.update((draft) => { draft.current = undefined })
   }
 
+  /**
+   * Recorded fork stub: no child materializes (benches asserting the full
+   * fork flow drive the production service; this face only proves the call).
+   * @param opts - source session id, optional cut anchor, and client title policy.
+   * @returns the source id (no child record is created).
+   */
+  fork(opts: { sessionId: SessionId; atSeq?: number; increaseTitle?: boolean }): Promise<SessionId> {
+    this.calls.push({ method: 'fork', args: [opts] })
+    return Promise.resolve(opts.sessionId)
+  }
+
   /**
    * The session face of a fixture (typed view for assertions; fixture
    * behavior methods are grafted onto it).

packages/client/test-runtime/tests/runtime.spec.tsx

@@ -201,7 +201,7 @@ describe('sessions', () => {
     await runtime.dispose()
   })
 
-  it('records service-face calls; open() moves the selection and clear() empties it', async () => {
+  it('records service-face calls; open() moves selection, clear() empties it, and fork() echoes the source', async () => {
     const runtime = await runtimeWithFrame()
     await runtime.sessions.add({ id: 's1' })
     await runtime.sessions.add({ id: 's2' })
@@ -211,9 +211,13 @@ describe('sessions', () => {
     runtime.sessions.clear()
     await runtime.flush()
     expect(runtime.sessions.list.getSnapshot().current).toBeUndefined()
+    await expect(runtime.sessions.fork({
+      sessionId: 's1' as SessionId, atSeq: 7, increaseTitle: true,
+    })).resolves.toBe('s1')
     expect(runtime.sessions.calls).toEqual([
       { method: 'open', args: ['s1'] },
       { method: 'clear', args: [] },
+      { method: 'fork', args: [{ sessionId: 's1', atSeq: 7, increaseTitle: true }] },
     ])
     await runtime.dispose()
   })

packages/client/ui-conversation/README.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 packages/client/ui-conversation/README.md
-README.md: d2e113138e331d54221e59732720a64b398f5c3f
-README.zh.md: 985fbc6e6d46f23e617452b53e8e521ba435b584
+README.md: baef52cb3a13bfd1ce0a62c19d5f231ec12e7c13
+README.zh.md: 5cee56366b9f4f98d11de4fea0b79b3d5fcb237f

packages/client/ui-conversation/README.md

@@ -40,7 +40,7 @@ None; this package neither assembles nor sends a provider request.
 
 - **Stats-line durations cover the in-window flow only** — LLM and tool wall times fold the snapshot's assistant `timing` and tool call/result pairs, so nodes outside the loaded event window (older history) are not counted.
 - **Details panel is the minimal form and currently has no entry point** — selected call args/result raw display; the Input/Output/Metadata switch, Prev/Next stepping, and See-in-trajectory deep link are deferred. Tool rows stopped being details-panel click targets and nothing replaced that gesture, so `ChatViewInjected.openDetails` is implemented but uncalled and the panel (including its terminal card) is unreachable in the assembled application; its rendering stays covered by mounting it with a selection directly.
-- **Assistant per-message paging is a reserved slot** — drawn in the design, not implemented. The finalized content IconActions row (copy / branch / clock) ships under text output only; branch remains a chrome stub.
+- **Assistant per-message paging is a reserved slot** — drawn in the design, not implemented. The finalized content IconActions row (copy / branch / clock) ships under text output only; branch forks through the turn containing that message, increments the inherited title on the client, and then opens the child, while a fork or rename failure leaves the source selected.
 - **The sparkle icon for the others tool row is a hand-drawn approximation** — the design glyph's vector geometry is not exportable locally; promotion into ui-primitives waits on an exact export.
 - **The approval panel's "Always allow this type" is deferred** — durable grants need a grant-storage design; only allow-once/reject answer today.
 - **TodoPanel truncates long item text to one ellipsized line** — the figma strip has no wrap or expand affordance; full text is not readable inline.

packages/client/ui-conversation/README.zh.md

@@ -38,9 +38,9 @@ todo 两个面就是在该形状上的两个注册项，都是普通注册方插
 
 ## 已知限制与暂缓事项
 
-- **统计行的耗时只覆盖窗口内消息流**：LLM 与工具墙钟时间由快照的 assistant `timing` 与工具 call/result 配对折算，落在已加载事件窗口之外的节点（更早的历史）不计入。
+- **统计行的耗时只覆盖窗口内消息流**：LLM（大语言模型）与工具墙钟时间由快照的 assistant `timing` 与工具 call/result 配对折算，落在已加载事件窗口之外的节点（更早的历史）不计入。
 - **详情面板是最小形态，且当前没有入口**：以原始形式显示已选择调用的参数／结果；Input/Output/Metadata 切换、Prev/Next 步进与 See-in-trajectory 深链接暂缓实现。工具行已不再是详情面板的点击目标，且没有任何手势接替它，因此 `ChatViewInjected.openDetails` 虽已实现却无人调用，该面板（含其终端卡片）在组装后的应用中不可达；其渲染仍由直接以选中态挂载它来覆盖。
-- **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在 text 输出下；分支仍是 chrome stub。
+- **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在 text 输出下；分支会 fork 到包含该消息的轮次末尾，在 client 端递增继承标题后打开子会话，而 fork 或改名失败时源会话保持选中。
 - **others 工具行的闪光图标是手绘近似版本**：无法在本地导出设计字形的矢量几何；等到存在精确导出后再将其提升到 ui-primitives。
 - **审批面板的「始终允许此类」暂缓**：持久授权需要授权存储设计；今天只能回答允许一次／拒绝。
 - **TodoPanel 将过长条目截成单行省略号**：figma 条没有换行或展开入口，完整文本无法在行内读完。

packages/client/ui-conversation/src/client/apply.ts

@@ -286,6 +286,13 @@ export function apply(ctx: Context): void {
           })
         },
         loadOlder: () => { void scoped.loadOlder() },
+        forkAt: (seq) => {
+          sessions.fork({ sessionId, atSeq: seq, increaseTitle: true })
+            .then((childId) => { sessions.open(childId) })
+            .catch(() => {
+              // Fork or child-rename failure keeps the source view untouched.
+            })
+        },
       }
     },
   }, ChatView)

packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx

@@ -23,6 +23,10 @@ export interface AssistantMarkdownProps {
   interrupted?: boolean | undefined
   /** Unix epoch ms for the finalized IconActions clock; omitted while streaming. */
   time?: number | undefined
+  /** Event sequence used as the fork boundary; omitted while streaming. */
+  seq?: number | undefined
+  /** Fork the session through the turn containing this finalized message. */
+  onFork?: ((seq: number) => void) | undefined
 }
 
 function firstLine(text: string): string {
@@ -60,7 +64,7 @@ function ThinkRow({ text, running }: { text: string; running: boolean }) {
 }
 
 export const AssistantMarkdown = memo(function AssistantMarkdown({
-  blocks, streaming, interrupted, time,
+  blocks, streaming, interrupted, time, seq, onFork,
 }: AssistantMarkdownProps) {
   const last = blocks.length - 1
   // Tool-call heads render as tool rows in the chat view's grouping pass, so
@@ -91,6 +95,7 @@ export const AssistantMarkdown = memo(function AssistantMarkdown({
           text={copyText(blocks)}
           time={time}
           clock="end"
+          onBranch={onFork === undefined || seq === undefined ? undefined : () => { onFork(seq) }}
           className={css.actions}
         />
       )}

packages/client/ui-conversation/src/client/chat/ChatView.tsx

@@ -230,7 +230,7 @@ function StreamingTail({ useSession, onGrow }: {
  * The chat view slot entry: pure component over the composed props (tool rows
  * render through the declared keyed hole's renderSlot share).
  */
-export function ChatView({ useSession, useSessions, useStore, renderSlot, sessionId, openFile, loadOlder }: ChatViewSlotProps) {
+export function ChatView({ useSession, useSessions, useStore, renderSlot, sessionId, openFile, loadOlder, forkAt }: ChatViewSlotProps) {
   const nodes = useSession(s => s.nodes)
   // Workspace root off the session list row: path summaries display relative to it.
   const cwd = useSessions(s => s.byId[sessionId]?.cwd)
@@ -377,6 +377,8 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio
           streaming={false}
           interrupted={node.interrupted}
           time={node.time}
+          seq={node.seq}
+          onFork={forkAt}
         />
       )
     }
@@ -385,7 +387,7 @@ export function ChatView({ useSession, useSessions, useStore, renderSlot, sessio
     }
     /* v8 ignore next -- tool-result never reaches here: deriveChatFlow folds them into groups. */
     if (node.kind === 'tool-result') return null
-    return <MessageItem key={item.key} node={node} />
+    return <MessageItem key={item.key} node={node} onFork={forkAt} />
   }
 
   return (

packages/client/ui-conversation/src/client/chat/MessageIconActions.tsx

@@ -1,5 +1,6 @@
-// Shared IconActions chrome for user and assistant messages: copy / branch
-// live (branch still a stub), date-aware clock, optional edit stub.
+// Shared IconActions chrome for user and assistant messages: copy live,
+// branch wired through onBranch, date-aware clock,
+// optional edit stub.
 
 import { useCallback } from 'react'
 import {
@@ -18,17 +19,19 @@ export interface MessageIconActionsProps {
   clock: 'start' | 'end'
   /** When true, append the stub edit control (user bubble). */
   edit?: boolean | undefined
+  /** Fork the session at this message. */
+  onBranch?: (() => void) | undefined
   /** Parent layout class composed onto the actions row. */
   className?: string | undefined
 }
 
 /**
  * Copy / branch (/ clock) IconActions row shared by user and assistant chrome.
- * @param props - Copy text, event time, clock side, optional edit, className.
+ * @param props - Copy text, event time, clock side, optional edit, branch callback, className.
  * @returns The actions row element.
  */
 export function MessageIconActions({
-  text, time, clock, edit, className,
+  text, time, clock, edit, onBranch, className,
 }: MessageIconActionsProps) {
   const day = useCalendarDay()
   const onCopy = useCallback(() => {
@@ -48,7 +51,7 @@ export function MessageIconActions({
         </button>
       </Tooltip>
       <Tooltip label="在新对话中分支" side="bottom">
-        <button type="button" className={css.action} aria-label="在新对话中分支">
+        <button type="button" className={css.action} aria-label="在新对话中分支" onClick={onBranch}>
           <IconBranchOutline16 />
         </button>
       </Tooltip>

packages/client/ui-conversation/src/client/chat/MessageItem.tsx

@@ -16,6 +16,8 @@ import css from './MessageItem.module.css'
 
 export interface MessageItemProps {
   node: UserMessageNode | SteeringMessageNode | ContextMessageNode | UnknownSurfaceNode
+  /** Fork the session through the turn containing this message (user-bubble branch action). */
+  onFork?: (seq: number) => void
 }
 
 function contentText(content: readonly unknown[]): { text: string; rest: unknown[] } {
@@ -61,7 +63,7 @@ function projectUserText(text: string): ReactNode {
   return <>{parts}</>
 }
 
-export const MessageItem = memo(function MessageItem({ node }: MessageItemProps) {
+export const MessageItem = memo(function MessageItem({ node, onFork }: MessageItemProps) {
   switch (node.kind) {
     case 'user': {
       const { text, rest } = contentText(node.content)
@@ -76,6 +78,7 @@ export const MessageItem = memo(function MessageItem({ node }: MessageItemProps)
             time={node.time}
             clock="start"
             edit
+            onBranch={onFork === undefined ? undefined : () => { onFork(node.seq) }}
             className={css.actions}
           />
         </div>

packages/client/ui-conversation/src/client/contract/slots.ts

@@ -421,6 +421,8 @@ export interface ChatViewInjected {
    */
   openFile: (path: string) => void
   loadOlder: () => void
+  /** Fork the session through the turn containing the message at `seq`, then open the child. */
+  forkAt: (seq: number) => void
 }
 
 /** Full chat-view component props: runtime share & the declared toolview/commandview holes' render share & store share & injected share. */

packages/client/ui-conversation/src/client/skeleton/ApprovalPanel.module.css

@@ -19,6 +19,13 @@
   border-radius: 20px;
   background: var(--dsw-specific-input-major);
   box-shadow: var(--dsw-shadow-lv2);
+  /* Elevated surface in dark, same as the menus: `.body` inside scrolls once
+     the justification or command passes the cap, so the thumb takes the l2
+     pair. Declared on the card because the elevation belongs to the surface,
+     and the custom properties inherit down to the region that actually
+     scrolls (see ui-theme styles/scrollbar.css for the rebinding contract). */
+  --dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2);
+  --dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2);
 }
 
 /* Tinted full-width header band. */
@@ -40,11 +47,22 @@
   background: var(--dsw-alias-state-warn-primary);
 }
 
+/* Scroll region: an agent's justification and its command are unbounded model
+   text (a one-line `cd` or a 40-line heredoc), and the seat sits in a
+   fixed-height column — uncapped, a long command pushed the action row past
+   the viewport and the approval could not be answered at all. The strip and
+   the action row stay outside, so the buttons are always on screen. */
 .body {
   display: flex;
   flex-direction: column;
   gap: 6px;
-  padding: 12px 16px 14px;
+  /* border-box so the cap is the region's OUTER height: the composer's draft
+     area counts its padding inside the same number, and the two seats are
+     only interchangeable if they occupy the same box. */
+  box-sizing: border-box;
+  max-height: var(--dsh-composer-text-max-height);
+  overflow-y: auto;
+  padding: 12px 16px 0;
 }
 
 /* The model's justification is the panel's message, not a footnote. */
@@ -63,11 +81,15 @@
   word-break: break-all;
 }
 
+/* Card-level row, not body content. Its padding reproduces the metrics the row
+   had inside the body: 14px above (the flex gap of 6 plus the row's 8px top
+   margin, neither of which reaches it out here) and the body's former 14px
+   bottom pad below, so the resting card is unchanged. */
 .actionRow {
   display: flex;
   justify-content: flex-end;
   gap: 8px;
-  margin-top: 8px;
+  padding: 14px 16px 14px;
 }
 
 .allow,

packages/client/ui-conversation/src/client/skeleton/ApprovalPanel.tsx

@@ -4,7 +4,11 @@
 // pending, this panel occupies the composer slot in place of the InputBar:
 // an amber "Waiting for approval" strip on the card top, the model's
 // justification as the headline, the paired command in muted code text, and
-// a right-aligned refuse/allow action row. One-shot: the buttons disable
+// a right-aligned refuse/allow action row. Justification and command are
+// unbounded model text, so they scroll inside the card at the shared composer
+// cap (`data-approval-scroll`) and the action row stays outside it — the
+// buttons must be reachable no matter how long the command is.
+// One-shot: the buttons disable
 // after a click and the panel leaves (the InputBar returns) on the broadcast
 // resolved frame. The draft's "Always allow this type" is deferred with
 // grant storage.
@@ -53,17 +57,20 @@ function ApprovalFlow({ pending, command }: { pending: PendingApproval; command?
     <div className={css.root} data-approval-key={pending.key}>
       <div className={css.card}>
         <div className={css.strip}><span className={css.dot} />等待审批</div>
-        <div className={css.body}>
+        {/* Tab stop: the region scrolls once the command passes the cap and
+            holds nothing focusable of its own, so without one a keyboard-only
+            user cannot reach the command's tail before answering. */}
+        <div className={css.body} data-approval-scroll="" tabIndex={0} role="group" aria-label="审批详情">
           <div className={css.headline}>{pending.reason ?? `工具 ${pending.toolName} 请求越权执行`}</div>
           {command !== undefined && <div className={css.command}>{command}</div>}
-          <div className={css.actionRow}>
-            <button type="button" className={css.reject} disabled={answered} onClick={() => { answer('rejected') }}>
-              拒绝
-            </button>
-            <button type="button" className={css.allow} disabled={answered} onClick={() => { answer('allowed-once') }}>
-              允许一次
-            </button>
-          </div>
+        </div>
+        <div className={css.actionRow}>
+          <button type="button" className={css.reject} disabled={answered} onClick={() => { answer('rejected') }}>
+            拒绝
+          </button>
+          <button type="button" className={css.allow} disabled={answered} onClick={() => { answer('allowed-once') }}>
+            允许一次
+          </button>
         </div>
       </div>
     </div>

packages/client/ui-conversation/src/client/skeleton/ConversationRoot.module.css

@@ -143,6 +143,14 @@
   display: flex;
   flex: none;
   flex-direction: column;
+  /* One cap for every scrolling text region a composer seat can hold: the
+     InputBar draft (figma Input 75:8208 max 14 lines × 24px line) and the
+     takeover panels' bodies top out at the same height, so electing a
+     takeover never grows the footer past the card it replaces. Declared on
+     the seat because it is the chain's only shared ancestor — fallback and
+     elected overlay are siblings — and custom properties inherit down to
+     whichever entry is mounted. */
+  --dsh-composer-text-max-height: 336px;
 }
 
 /* Active phase: header is ordinary column chrome above the scrollport (not

packages/client/ui-conversation/src/client/skeleton/InputBar.module.css

@@ -209,7 +209,9 @@
 .mirror {
   visibility: hidden;
   pointer-events: none;
-  max-height: 336px;
+  /* 14-line cap, shared with the composer takeovers (declared on
+     ConversationRoot .composerSeat). */
+  max-height: var(--dsh-composer-text-max-height);
   overflow: hidden;
 }
 

packages/client/ui-conversation/tests/apply-inject.spec.tsx

@@ -122,6 +122,13 @@ describe('conversation slot inject surface', () => {
     const chatView = b.chatViewSurface(ROOT)
     chatView.injected.loadOlder()
     expect(b.sessionFake.loadOlder).toHaveBeenCalledTimes(1)
+    chatView.injected.forkAt(17)
+    await vi.waitFor(() => {
+      expect(b.runtime.sessions.calls).toContainEqual({ method: 'open', args: [ROOT] })
+    })
+    expect(b.runtime.sessions.calls).toContainEqual({
+      method: 'fork', args: [{ sessionId: ROOT, atSeq: 17, increaseTitle: true }],
+    })
     await b.runtime.dispose()
   })
 

packages/client/ui-conversation/tests/chat-view.spec.tsx

@@ -94,6 +94,7 @@ function makeHarness(init?: Partial<ConversationSnapshot>) {
   const openDetails = vi.fn<(t: SelectionTarget) => void>()
   const openFile = vi.fn<(path: string) => void>()
   const loadOlder = vi.fn()
+  const forkAt = vi.fn()
   // Selection rides the REAL chat store (same construction path as
   // production; the view reads it through the PropsStore useStore share).
   // renderSlot stub renders the render-site fallback (an empty keyed ledger:
@@ -120,9 +121,10 @@ function makeHarness(init?: Partial<ConversationSnapshot>) {
     openDetails,
     openFile,
     loadOlder,
+    forkAt,
   }
   const setSelection = (next: SelectionTarget | null): void => { chat.actions.select(next) }
-  return { set, ChatView, props, openDetails, openFile, loadOlder, setSelection }
+  return { set, ChatView, props, openDetails, openFile, loadOlder, forkAt, setSelection }
 }
 
 describe('chat-flow derivation', () => {
@@ -194,6 +196,16 @@ describe('ChatView', () => {
     expect(view.getByText('run a')).toBeTruthy()
   })
 
+  it('forks from both user and finalized assistant message actions at their event seq', () => {
+    const h = makeHarness({ nodes: [user(1, 'question'), assistant(2, 'answer')] })
+    const view = render(<h.ChatView {...h.props} />)
+    const buttons = view.getAllByRole('button', { name: '在新对话中分支' })
+    expect(buttons).toHaveLength(2)
+    fireEvent.click(buttons[0]!)
+    fireEvent.click(buttons[1]!)
+    expect(h.forkAt.mock.calls).toEqual([[1], [2]])
+  })
+
   it('renders assistant Markdown across history, streaming, final, and interrupted states while user text stays literal', () => {
     const markdown = '# Rendered\n\n- **one**\n- `two`'
     const h = makeHarness({ nodes: [user(1, markdown), assistant(2, markdown)] })

packages/client/ui-question/README.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 packages/client/ui-question/README.md
-README.md: 0700375758774610fcd897b9a3e16484206a871d
-README.zh.md: d9e5eb22cef13e16ab1ce2cebba9e563bd9d08d9
+README.md: 5ebba2a1da6e6108b82e9deb235b84f987600345
+README.zh.md: 0aa6428a9b6472fc5b525c11b4716ebc50c378c3

packages/client/ui-question/README.md

@@ -6,6 +6,8 @@ Web `ask_user_question` feature plugin. Its host half mounts `dsh-tool-ask-user`
 
 The component renders one question at a time with progress navigation, single- and multi-select choices, recommendation badges derived from label suffixes, and custom answers. Question detail reuses the assistant-output `MarkdownText` primitive, including its GFM rendering and untrusted-content policy. The capped card keeps its title, navigation, and submission actions fixed while long detail and choices share an internal scroll region. Single-select choices advance immediately, and Enter submits once every question is answered or skipped; Enter during IME composition confirms the input candidate without advancing. It submits one structured answer batch for the whole request: “Skip this question” retains other drafts and emits the existing blank `{ selected: [] }` shape for that item, while close rejects the whole wait as `ASK_CANCELLED`.
 
+A request whose single question declares a presentation intent renders as that intent's own surface instead. `plan-review` — set by `dsh-plan-mode` on the `exit_plan_mode` review — takes the waiting-approval card shape: a `Plan review` strip, the plan as the scrolling markdown body, the question text as the card's accessible name, and one decision row of `Chat about it` / `Refuse` / `Approve`. Approve and Refuse answer with the asker's own option labels (the intent names which label approves, so the verdict never rides option order) and keep the asker's descriptions as tooltips; `Chat about it` rejects the wait as `ASK_CANCELLED`, returning the composer so the user can say what they want instead. The card claims a request only when it can send every answer that request allows: one question, the intent declared, the plan present as `detail`, the named approve label offered, and a binary single choice (at most one option besides approve, not multi-select). Anything else — no intent, a batch of several questions, a missing plan, an approve label naming no option, a third option, a multi-select decision — stays on the generic flow, which can express it. An intent changes the layout, never which answers are reachable.
+
 Selection state is local to a component keyed by the request rpcId. A replay with the same id preserves a still-mounted draft, while `question/resolved` from the host removes the composer. The host remains authoritative: successful HTTP delivery does not remove pending state locally.
 
 Composer chrome copy (pager, buttons, placeholders, validation feedback) is bilingual: the plugin registers zh/en dictionaries under the `question` namespace of `dsh-client-locale` and hands the entry its bound translator plus the locale snapshot source through the inject face, so a locale switch re-renders a mounted composer. Question and option text arrives from the model and renders verbatim; carrier failure messages also display untranslated.

packages/client/ui-question/README.zh.md

@@ -6,6 +6,8 @@ Web `ask_user_question` 功能插件。只有选择 Web 功能时，其主机侧
 
 组件每次渲染一个问题，提供进度导航、单选和多选选项、由标签后缀派生的推荐徽标，以及自定义答案。问题详情复用助手输出的 `MarkdownText` 原语，包括其 GFM 渲染与不受信内容策略。封顶卡片保持标题、导航与提交动作固定，超长的详情与选项共享内部滚动区。单选选项会立即前进；所有问题均已回答或跳过后，Enter 会提交；IME 输入法组合期间按 Enter 只会确认输入候选，不会前进。组件为整个请求提交一批结构化答案：「跳过此问题」会保留其他草稿，并为该项发出既有的空 `{ selected: [] }` 形状；关闭则以 `ASK_CANCELLED` 拒绝整个等待。
 
+若某个请求的唯一问题声明了呈现意图，则改为渲染该意图自己的界面。`plan-review` —— 由 `dsh-plan-mode` 在 `exit_plan_mode` 审阅上设置 —— 采用等待审批卡片的形状：一条 `Plan review` 条带、计划作为可滚动的 markdown 主体、问题文本作为卡片的无障碍名称，以及一行 `Chat about it` / `Refuse` / `Approve` 的决定操作。Approve 与 Refuse 用提问方自己的选项标签回答（意图指名哪个标签表示批准，因此裁决绝不依赖选项顺序），并把提问方的描述保留为 tooltip；`Chat about it` 以 `ASK_CANCELLED` 拒绝该等待，让编辑器归位，用户可以直接说出他想说的话。卡片只在能够发出该请求允许的每一个答案时才接管：只有一个问题、声明了意图、计划以 `detail` 存在、提供了被指名的批准标签，且是二元单选（除批准外最多一个选项，且非多选）。其他任何情形 —— 没有意图、一批含多个问题、缺少计划、批准标签未命中任何选项、出现第三个选项、多选决定 —— 都留在能够表达它的通用流程上。意图改变的只是布局，从不改变可达的答案。
+
 选择状态只存在于以请求 rpcId 为 key 的组件本地。使用相同 id 回放时，只要组件仍挂载，就会保留草稿；主机发出的 `question/resolved` 则会移除编辑器。主机仍具有最终决定权：HTTP 交付成功不会在本地移除待处理状态。
 
 编辑器外框文案（翻页器、按钮、占位符、校验提示）是双语的：插件在 `dsh-client-locale` 的 `question` 命名空间下注册 zh/en 词典，并通过 inject face 把绑定的翻译函数和 locale 快照源交给该配置项，因此切换语言会重新渲染已挂载的编辑器。问题与选项文本来自模型并原样渲染；载体失败消息也不经翻译直接显示。

packages/client/ui-question/src/client/PlanReviewPanel.module.css

@@ -0,0 +1,113 @@
+/* Plan-review takeover: the waiting-approval card language (amber strip on a
+   floating capsule, right-aligned actions) applied to a reviewed plan. Kept as
+   its own module rather than shared with ui-conversation's ApprovalPanel: the
+   two takeovers agree on tokens and geometry, not on content — this one's body
+   is scrollable markdown, that one's is a headline plus a command line. Warn
+   semantics ride the alias state tokens; no hardcoded colors. */
+
+/* Mirrors the question card's frame so the takeover is a content swap. */
+.frame {
+  display: flex;
+  justify-content: center;
+  padding: 6px 24px 10px;
+}
+
+.card {
+  display: flex;
+  overflow: hidden;
+  flex-direction: column;
+  width: 100%;
+  max-width: 776px;
+  /* Composer seat sits in a fixed-height conversation column (overflow
+     hidden): cap the card against the viewport and scroll the plan, so the
+     strip and the decision row stay reachable on a long plan. */
+  max-height: min(60vh, 520px);
+  border: 1px solid var(--dsw-alias-state-warn-secondary);
+  border-radius: 20px;
+  background: var(--dsw-specific-input-major);
+  box-shadow: var(--dsw-shadow-lv2);
+  color: var(--dsw-alias-label-primary);
+  /* Elevated surface in dark: the plan body inside scrolls once the card hits
+     the cap above, so the thumb takes the l2 pair (see ui-theme
+     styles/scrollbar.css for the rebinding contract). */
+  --dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2);
+  --dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2);
+}
+
+.card,
+.card * {
+  box-sizing: border-box;
+}
+
+/* Tinted full-width header band, as on the approval takeover. */
+.strip {
+  display: flex;
+  align-items: center;
+  flex-shrink: 0;
+  gap: 8px;
+  padding: 10px 16px;
+  background: var(--dsw-alias-state-warn-tertiary);
+  color: var(--dsw-alias-state-warn-primary);
+  font-size: 13px;
+  line-height: 18px;
+}
+
+.dot {
+  width: 8px;
+  height: 8px;
+  border-radius: 50%;
+  background: var(--dsw-alias-state-warn-primary);
+}
+
+/* The plan is the panel's message: it takes the whole body and the scroll. */
+.body {
+  flex: 1 1 auto;
+  min-height: 0;
+  overflow-y: auto;
+  overscroll-behavior: contain;
+  padding: 12px 16px 4px;
+  font-size: 14px;
+  line-height: 22px;
+}
+
+.footer {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  flex-shrink: 0;
+  gap: 12px;
+  padding: 8px 16px 12px;
+}
+
+.feedback {
+  min-height: 16px;
+  color: var(--dsw-alias-state-error-primary);
+  font-size: 11px;
+  line-height: 16px;
+}
+
+.actions {
+  display: flex;
+  align-items: center;
+  flex-shrink: 0;
+  gap: 8px;
+}
+
+@media (max-width: 720px) {
+  .frame {
+    padding: 6px 10px 10px;
+  }
+
+  .card {
+    border-radius: 16px;
+  }
+
+  .body {
+    padding: 10px 12px 4px;
+  }
+
+  .footer {
+    align-items: flex-end;
+    padding: 8px 12px 10px;
+  }
+}

packages/client/ui-question/src/client/PlanReviewPanel.tsx

@@ -0,0 +1,100 @@
+// PlanReviewPanel: the composer takeover for a question carrying the
+// `plan-review` presentation intent. A plan under review is one decision over
+// one body of markdown, so it takes the waiting-approval card shape — tinted
+// strip, content, right-aligned action row — instead of the generic question
+// flow's pager, numbered options, skip and custom-answer affordances, which
+// read as a quiz the user is being graded on.
+//
+// The three actions are the whole decision surface: approve and decline answer
+// the question with the option labels the asker offered (localised copy on the
+// buttons, the asker's descriptions as their tooltips), while "discuss"
+// dismisses the request so the composer returns and the user can simply say
+// what they want. Dismissal is the generic flow's own cancel verb, promoted to
+// a labelled button because in a two-outcome decision it is the third real
+// answer, not an escape hatch.
+
+import { useState } from 'react'
+import { Button, IconEditOutline16, MarkdownText } from '@deepseek-ai/dsh-client-ui-primitives'
+import type { PendingQuestion, PlanReview, QuestionComposerProps } from './contract/slots.ts'
+import css from './PlanReviewPanel.module.css'
+
+/** The panel's own props: the question domain face, the narrowed review, and the locale seat. */
+export type PlanReviewPanelProps =
+  { pending: PendingQuestion; review: PlanReview } & Pick<QuestionComposerProps, 't'>
+
+/**
+ * Optional-prop spread for a decision button's tooltip: `title` is optional on
+ * the DOM props, and exactOptionalPropertyTypes rejects an explicit undefined.
+ *
+ * @param description - the asker's option description, when it carries one.
+ * @returns The `title` prop to spread, or nothing.
+ */
+function tooltip(description: string | undefined): { title?: string } {
+  return description === undefined ? {} : { title: description }
+}
+
+/**
+ * Render a plan review as a decision card.
+ *
+ * @param props - the question domain face, the narrowed plan review, and `t`.
+ * @returns The plan-review takeover for this request.
+ */
+export function PlanReviewPanel({ pending, review, t }: PlanReviewPanelProps) {
+  // One-shot latch shaped like the approval takeover's: the panel leaves only
+  // when the host's resolved frame lands, so until then a second click must
+  // not re-fire. A failed send (rejected receipt / transport) re-arms it and
+  // shows why, since nothing else would tell the user the click was lost.
+  const [busy, setBusy] = useState(false)
+  const [error, setError] = useState<string | null>(null)
+  const settle = (send: () => Promise<void>): void => {
+    setBusy(true)
+    setError(null)
+    void send().catch((cause: unknown) => {
+      setBusy(false)
+      setError(cause instanceof Error ? cause.message : String(cause))
+    })
+  }
+  const decide = (label: string): void => {
+    settle(() => pending.answer({ answers: [{ id: review.id, selected: [label] }] }))
+  }
+  const decline = review.decline
+
+  return (
+    <div className={css.frame} data-plan-review-key={pending.key}>
+      <section className={css.card} aria-label={review.question}>
+        <div className={css.strip}>
+          <span className={css.dot} />
+          {t('plan.header')}
+        </div>
+        <div className={css.body} data-plan-review-scroll>
+          <MarkdownText text={review.plan} />
+        </div>
+        <div className={css.footer}>
+          <div className={css.feedback} role="status">{error}</div>
+          <div className={css.actions}>
+            <Button
+              size="sm" variant="ghost" icon={<IconEditOutline16 />}
+              disabled={busy} onClick={() => { settle(() => pending.cancel()) }}
+            >
+              {t('plan.discuss')}
+            </Button>
+            {decline !== undefined && (
+              <Button
+                size="sm" variant="outline" {...tooltip(decline.description)}
+                disabled={busy} onClick={() => { decide(decline.label) }}
+              >
+                {t('plan.decline')}
+              </Button>
+            )}
+            <Button
+              size="sm" variant="primary" {...tooltip(review.approve.description)}
+              disabled={busy} onClick={() => { decide(review.approve.label) }}
+            >
+              {t('plan.approve')}
+            </Button>
+          </div>
+        </div>
+      </section>
+    </div>
+  )
+}

packages/client/ui-question/src/client/QuestionComposer.tsx

@@ -5,9 +5,10 @@ import {
   IconCloseOutline16, IconEditOutline16, MarkdownText,
 } from '@deepseek-ai/dsh-client-ui-primitives'
 import {
-  PendingQuestion,
+  PendingQuestion, planReviewOf,
   type QuestionAnswer, type QuestionComposerProps,
 } from './contract/slots.ts'
+import { PlanReviewPanel } from './PlanReviewPanel.tsx'
 import css from './QuestionComposer.module.css'
 
 interface DraftAnswer {
@@ -46,14 +47,24 @@ function isComposing(event: KeyboardEvent<HTMLTextAreaElement | HTMLInputElement
 /**
  * Composer takeover boundary; the carrier key keys local drafts, so a
  * same-request replay (same key, new carrier object) preserves them.
+ *
+ * One takeover, two shapes: a request that declares a presentation intent this
+ * package renders takes that shape (a plan review is one decision over one
+ * plan, not a question set), and every other request takes the generic flow.
+ * The routing lives here, at the one entry that owns the composer seat, so
+ * neither shape can claim a request the other is already rendering.
+ *
  * @param props - the selector-matched pending question carrier plus the framework standard kit.
- * @returns The question flow for this request.
+ * @returns The question flow, or the intent's own surface, for this request.
  */
 export function QuestionComposer(props: QuestionComposerProps) {
   // Domain-face mint rides the carrier's stable identity (never minted in a
   // select/render dispatch — per-dispatch minting would churn memo identity).
   const question = useMemo(() => new PendingQuestion(props.matched), [props.matched])
-  return <QuestionFlow key={question.key} pending={question} t={props.t} />
+  const review = useMemo(() => planReviewOf(question.questions), [question])
+  return review === undefined
+    ? <QuestionFlow key={question.key} pending={question} t={props.t} />
+    : <PlanReviewPanel key={question.key} pending={question} review={review} t={props.t} />
 }
 
 function QuestionFlow({ pending, t }: { pending: PendingQuestion } & Pick<QuestionComposerProps, 't'>) {

packages/client/ui-question/src/client/contract/slots.ts

@@ -19,6 +19,71 @@ export type QuestionWait = PendingWait<'question'>
 /** One structured answer batch covering every question of the request. */
 export type QuestionAnswer = QuestionResponsePayload['answer']
 
+/** One question of the request, as the carrier payload carries it. */
+type QuestionItem = QuestionWait['payload']['questions'][number]
+
+/** One option the asker offered on a question. */
+type QuestionOption = NonNullable<QuestionItem['options']>[number]
+
+/**
+ * A request narrowed to the `plan-review` presentation intent: everything the
+ * decision card renders and answers with, so the panel never re-reads the
+ * request shape. `approve` and `decline` are the asker's own options — an
+ * answer must carry one of those labels verbatim — and `plan` is the markdown
+ * body under review.
+ */
+export interface PlanReview {
+  /** The reviewed question's id, echoed in the answer. */
+  id: string
+  /** The question text, kept as the card's accessible name. */
+  question: string
+  /** The plan markdown under review. */
+  plan: string
+  /** The option that approves the plan. */
+  approve: QuestionOption
+  /** The option that declines it; absent when the asker offered no other option. */
+  decline?: QuestionOption
+}
+
+/**
+ * Narrow a request to a renderable plan review, or return undefined to leave it
+ * to the generic question flow.
+ *
+ * The card is one decision over one plan, and it claims a request only when it
+ * can send every answer that request allows — an intent changes the layout,
+ * never which answers are reachable. So the batch must be a single question
+ * that declares the intent, carries the plan as its detail, offers the approve
+ * label the intent names, and is a binary single choice: at most one option
+ * besides approve, and not multi-select. A third option or a multi-select batch
+ * has answers two buttons cannot express, so the generic flow keeps it — as it
+ * keeps any request whose intent the asker's own service would have rejected,
+ * because the client sits downstream of a wire boundary and every request must
+ * stay answerable.
+ *
+ * @param questions - the request's whole question batch.
+ * @returns The narrowed review, or undefined when the generic flow owns it.
+ */
+export function planReviewOf(questions: readonly QuestionItem[]): PlanReview | undefined {
+  if (questions.length !== 1) return undefined
+  // Length-checked above; the index read is the narrowing tax, not a guess.
+  const question = questions[0] as QuestionItem
+  const intent = question.intent
+  if (intent?.kind !== 'plan-review' || question.detail === undefined) return undefined
+  if (question.multiSelect === true) return undefined
+  const options = question.options ?? []
+  if (options.length > 2) return undefined
+  const approve = options.find(option => option.label === intent.approve)
+  if (approve === undefined) return undefined
+  const decline = options.find(option => option.label !== intent.approve)
+  return {
+    id: question.id,
+    question: question.question,
+    plan: question.detail,
+    approve,
+    ...(decline === undefined ? {} : { decline }),
+  }
+}
+
 /**
  * Question domain face over the carrier: render identity and questions
  * transparently forwarded; answer/cancel own the wire encoding (the ok value

packages/client/ui-question/src/client/index.ts

@@ -5,6 +5,12 @@
  * question carrier (matched prop), and the whole behavior surface rides the
  * carrier (domain encoding in contract/slots.ts PendingQuestion); copy rides
  * the standard locale seat. Export discipline: packages/client/AGENTS.md.
+ *
+ * One entry, two shapes: the composer renders a request that declares a
+ * presentation intent as that intent's own surface (`plan-review` → the plan
+ * decision card) and every other request as the generic question flow. A
+ * separate chain entry per shape would race the same carrier, so the shape
+ * choice lives inside this entry — see QuestionComposer.
  */
 import type { ClientContext } from '@deepseek-ai/dsh-client-runtime/client'
 import type { ComposerChainProps } from '@deepseek-ai/dsh-client-ui-conversation/client'
@@ -15,7 +21,9 @@ import { QuestionComposer } from './QuestionComposer.tsx'
 import { en, zh, type QuestionKey } from './locales.ts'
 
 export { PendingQuestion } from './contract/slots.ts'
-export type { QuestionAnswer, QuestionComposerProps, QuestionWait } from './contract/slots.ts'
+export type {
+  PlanReview, QuestionAnswer, QuestionComposerProps, QuestionWait,
+} from './contract/slots.ts'
 export type { QuestionKey } from './locales.ts'
 
 declare module '@deepseek-ai/dsh-client-ui-slots' {

packages/client/ui-question/src/client/locales.ts

@@ -11,6 +11,10 @@ export const zh = {
   'custom.placeholder': '输入你的答案',
   'action.skip': '跳过本题',
   'action.next': '下一题',
+  'plan.header': '计划待审',
+  'plan.approve': '确认执行',
+  'plan.decline': '拒绝',
+  'plan.discuss': '去聊天里说',
 } satisfies Record<string, string>
 
 /** The question namespace key union. */
@@ -27,4 +31,8 @@ export const en = {
   'custom.placeholder': 'Type your answer',
   'action.skip': 'Skip this question',
   'action.next': 'Next',
+  'plan.header': 'Plan review',
+  'plan.approve': 'Approve',
+  'plan.decline': 'Refuse',
+  'plan.discuss': 'Chat about it',
 } satisfies Record<QuestionKey, string>

packages/client/ui-question/tests/plan-review-panel.spec.tsx

@@ -0,0 +1,228 @@
+// @vitest-environment jsdom
+// The plan-review takeover, driven through the composer entry that routes to
+// it: a request carrying the intent must reach the decision card and answer
+// with the asker's own option labels, and a request that does not (or cannot)
+// must keep the generic question flow.
+import { afterEach, describe, expect, it, vi } from 'vitest'
+import { cleanup, fireEvent, render, screen } from '@testing-library/react'
+import type {
+  ConversationSnapshot, SessionId, SessionListState, WorkspaceListState,
+} from '@deepseek-ai/dsh-client-runtime/client'
+import { PendingWait } from '@deepseek-ai/dsh-client-runtime/client'
+import type { RpcReceipt } from '@deepseek-ai/dsh-client-connection/client'
+import { RpcId } from '@deepseek-ai/dsh-client-connection/client'
+import type { SnapshotSelectorHook } from '@deepseek-ai/dsh-client-ui-slots'
+import { planReviewOf, type QuestionComposerProps, type QuestionWait } from '../src/client/contract/slots.ts'
+import { QuestionComposer } from '../src/client/QuestionComposer.tsx'
+import { en, zh } from '../src/client/locales.ts'
+import { en as commonEn } from '@deepseek-ai/dsh-client-locale/src/locales/en.ts'
+import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts'
+
+afterEach(cleanup)
+
+const SID = 's1' as SessionId
+
+/** Seat stub over a dictionary pair mirroring the real lookup chain: package dictionary, then common vocabulary, then the key. */
+const seatOver = (dict: Record<string, string>, common: Record<string, string>): QuestionComposerProps['t'] =>
+  (key => dict[key] ?? common[key] ?? key)
+
+/** Framework standard-kit stubs: the panel consumes only the locale seat. */
+const kit = {
+  sessionId: SID,
+  useSession: (() => { throw new Error('unused') }) as unknown as SnapshotSelectorHook<ConversationSnapshot>,
+  useSessions: (() => { throw new Error('unused') }) as unknown as SnapshotSelectorHook<SessionListState>,
+  useWorkspaces: (() => { throw new Error('unused') }) as unknown as SnapshotSelectorHook<WorkspaceListState>,
+  useProjection: (() => undefined) as never,
+  useInput: (() => { throw new Error('unused') }) as never,
+  inputActions: { setDraft: () => { throw new Error('unused') }, submit: () => { throw new Error('unused') } } as never,
+  t: seatOver(zh, commonZh),
+}
+
+const PLAN = '# Ship the picker\n\n- read the store\n- render the rows\n'
+
+/** The plan-mode request shape: one question, the plan as detail, approve named. */
+const questions = (): QuestionWait['payload']['questions'] => [{
+  id: 'plan-review',
+  header: 'Plan review',
+  question: 'Approve this plan and leave plan mode?',
+  detail: PLAN,
+  options: [
+    { label: 'Approve', description: 'Leave plan mode; the plan is carried out from the next step.' },
+    { label: 'Keep planning', description: 'Stay in plan mode; feedback goes back to the model.' },
+  ],
+  intent: { kind: 'plan-review', approve: 'Approve' },
+}]
+
+/** Carrier fixture over a scripted respond carrier. */
+function wait(
+  payload: QuestionWait['payload'] = { questions: questions() },
+  respond = vi.fn(() => Promise.resolve<RpcReceipt>({ accepted: true })),
+) {
+  return { carrier: new PendingWait('question', RpcId('q-1'), SID, payload, respond), respond }
+}
+
+/** The client-response envelope respond must have received for a decision. */
+function decidedEnvelope(label: string) {
+  return {
+    type: 'client-response', rpcId: RpcId('q-1'),
+    result: { ok: true, value: { sessionId: SID, answer: { answers: [{ id: 'plan-review', selected: [label] }] } } },
+  }
+}
+
+describe('planReviewOf', () => {
+  it('narrows a plan-review request to its decision, options included', () => {
+    expect(planReviewOf(questions())).toEqual({
+      id: 'plan-review',
+      question: 'Approve this plan and leave plan mode?',
+      plan: PLAN,
+      approve: { label: 'Approve', description: 'Leave plan mode; the plan is carried out from the next step.' },
+      decline: { label: 'Keep planning', description: 'Stay in plan mode; feedback goes back to the model.' },
+    })
+  })
+
+  it('leaves the decline absent when the asker offered approve alone', () => {
+    const [question] = questions()
+    const review = planReviewOf([{ ...question as object, options: [{ label: 'Approve' }] } as never])
+    expect(review?.approve).toEqual({ label: 'Approve' })
+    expect(review === undefined ? true : 'decline' in review).toBe(false)
+  })
+
+  it.each([
+    ['a batch of more than one question', () => [...questions(), ...questions()]],
+    ['no intent at all', () => [{ ...questions()[0] as object, intent: undefined }]],
+    ['an intent without the plan as detail', () => [{ ...questions()[0] as object, detail: undefined }]],
+    ['an intent whose approve names no option', () => [{
+      ...questions()[0] as object, intent: { kind: 'plan-review', approve: 'Ship it' },
+    }]],
+    ['an intent with no options at all', () => [{ ...questions()[0] as object, options: undefined }]],
+    // Two buttons cannot send a third label or a combination, and the generic
+    // flow can: an intent never costs the user a reachable answer.
+    ['a third option the card could not offer', () => [{
+      ...questions()[0] as object,
+      options: [{ label: 'Approve' }, { label: 'Keep planning' }, { label: 'Start over' }],
+    }]],
+    ['a multi-select decision', () => [{ ...questions()[0] as object, multiSelect: true }]],
+  ])('declines %s, leaving the request to the generic flow', (_case, build) => {
+    expect(planReviewOf(build() as never)).toBeUndefined()
+  })
+
+  it('declines an empty batch, which the generic flow reports as such', () => {
+    expect(planReviewOf([])).toBeUndefined()
+  })
+})
+
+describe('PlanReviewPanel', () => {
+  it('renders the plan under a review strip, with none of the quiz affordances', () => {
+    const { carrier } = wait()
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
+
+    expect(document.querySelector('[data-plan-review-key="q:q-1"]')).toBeTruthy()
+    expect(screen.getByText(zh['plan.header'])).toBeTruthy()
+    // The plan renders as markdown, so its heading is a heading.
+    expect(screen.getByRole('heading', { name: 'Ship the picker' })).toBeTruthy()
+    expect(screen.getByText('render the rows')).toBeTruthy()
+    // The question text stays as the card's accessible name rather than a title
+    // that reads like a test item.
+    expect(screen.getByLabelText('Approve this plan and leave plan mode?')).toBeTruthy()
+    // No pager, no numbered options, no skip, no custom answer.
+    expect(screen.queryByText('1 / 1')).toBeNull()
+    expect(screen.queryByRole('radio')).toBeNull()
+    expect(screen.queryByText(zh['action.skip'])).toBeNull()
+    expect(screen.queryByRole('textbox')).toBeNull()
+  })
+
+  it('answers with the asker\'s approve label and keeps its description as the tooltip', () => {
+    const { carrier, respond } = wait()
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
+
+    const approve = screen.getByRole('button', { name: zh['plan.approve'] })
+    expect(approve.getAttribute('title')).toBe('Leave plan mode; the plan is carried out from the next step.')
+    fireEvent.click(approve)
+    expect(respond).toHaveBeenCalledWith(decidedEnvelope('Approve'))
+    // One-shot: every action locks until the host's resolved frame lands.
+    expect(approve.hasAttribute('disabled')).toBe(true)
+    expect(screen.getByRole('button', { name: zh['plan.decline'] }).hasAttribute('disabled')).toBe(true)
+    fireEvent.click(approve)
+    expect(respond).toHaveBeenCalledTimes(1)
+  })
+
+  it('answers with the asker\'s decline label', () => {
+    const { carrier, respond } = wait()
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
+
+    fireEvent.click(screen.getByRole('button', { name: zh['plan.decline'] }))
+    expect(respond).toHaveBeenCalledWith(decidedEnvelope('Keep planning'))
+  })
+
+  it('dismisses the request so the composer returns for a plain message', () => {
+    const { carrier, respond } = wait()
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
+
+    fireEvent.click(screen.getByRole('button', { name: zh['plan.discuss'] }))
+    expect(respond).toHaveBeenCalledWith({
+      type: 'client-response', rpcId: RpcId('q-1'),
+      result: {
+        ok: false,
+        error: { code: 'cancelled', message: 'the user closed this question request', details: {} },
+      },
+    })
+  })
+
+  it('omits the tooltip for an option carrying no description', () => {
+    const { carrier } = wait({ questions: [{
+      ...questions()[0] as object,
+      options: [{ label: 'Approve' }, { label: 'Keep planning' }],
+    }] as never })
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
+
+    expect(screen.getByRole('button', { name: zh['plan.approve'] }).hasAttribute('title')).toBe(false)
+    expect(screen.getByRole('button', { name: zh['plan.decline'] }).hasAttribute('title')).toBe(false)
+  })
+
+  it('hides the decline action when the asker offered approve alone', () => {
+    const { carrier } = wait({ questions: [{
+      ...questions()[0] as object, options: [{ label: 'Approve' }],
+    }] as never })
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
+
+    expect(screen.queryByRole('button', { name: zh['plan.decline'] })).toBeNull()
+    expect(screen.getByRole('button', { name: zh['plan.approve'] })).toBeTruthy()
+  })
+
+  it('re-arms the actions and says why when the decision does not land', async () => {
+    const { carrier, respond } = wait(
+      { questions: questions() },
+      vi.fn(() => Promise.resolve<RpcReceipt>({ accepted: false, reason: 'not-pending' })),
+    )
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
+
+    fireEvent.click(screen.getByRole('button', { name: zh['plan.approve'] }))
+    const failure = await screen.findByText('question response rejected: not-pending')
+    expect(failure.getAttribute('role')).toBe('status')
+    // Re-armed for the retry: a lost click must not leave a dead card.
+    expect(screen.getByRole('button', { name: zh['plan.approve'] }).hasAttribute('disabled')).toBe(false)
+    fireEvent.click(screen.getByRole('button', { name: zh['plan.approve'] }))
+    expect(respond).toHaveBeenCalledTimes(2)
+  })
+
+  it('reports a non-Error transport failure as its stringified value', async () => {
+    // A non-Error rejection is the case under test: a carrier can reject with
+    // anything, and the panel must still show the user something.
+    // oxlint-disable-next-line typescript/prefer-promise-reject-errors
+    const { carrier } = wait({ questions: questions() }, vi.fn(() => Promise.reject('socket gone')))
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
+
+    fireEvent.click(screen.getByRole('button', { name: zh['plan.discuss'] }))
+    expect(await screen.findByText('socket gone')).toBeTruthy()
+  })
+
+  it('carries the same decision surface in English', () => {
+    const { carrier } = wait()
+    render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} t={seatOver(en, commonEn)} />)
+
+    expect(screen.getByText('Plan review')).toBeTruthy()
+    expect(screen.getByRole('button', { name: 'Approve' })).toBeTruthy()
+    expect(screen.getByRole('button', { name: 'Refuse' })).toBeTruthy()
+    expect(screen.getByRole('button', { name: 'Chat about it' })).toBeTruthy()
+  })
+})

packages/client/ui-workspace/README.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 packages/client/ui-workspace/README.md
-README.md: a1b58f4abe0925be3b426d10344777e46caa9ba0
-README.zh.md: a472507bc45549c8feb55a75d294cbd7b3138cc5
+README.md: 860c24b8a25a1e9968261f586c16163579131a1c
+README.zh.md: 5a8e88051fc6f4fd46c5f2f6dcdc185eb4559ac6

packages/client/ui-workspace/README.md

@@ -6,6 +6,8 @@ Shared Workspace picker plugin. `WorkspaceBrowser` is registered into the sideba
 
 The picker lists real Host Workspace entities through the global `useWorkspaces` hook. Selecting a Workspace invokes the slot owner's `onPick` callback to retarget the frontend Session object. Each registration declares a **directory-flow child hole** (`single` kind: `conversation.hero.workspace.directoryFlow` / `sidebar.workspaces.directoryFlow`) that the composed picker package's client half fills with its picking interaction — the [`-native`](../../host/directory-picker-native/README.md) backend's renderless OS-chooser driver today, an in-app browsing dialog under a `-browse` composition. The flat **Open local folder...** action renders only while the surface's hole is occupied (occupancy read per menu render; an empty hole means the composition has no picking affordance — the seam's documented no-flow default). This package owns the trigger and the adoption: the occupant reports one picked path per open through the hole's owner conversation (`open`/`busy`/`onPicked`/`onCancel`/`onError`), and the owner adopts it through the object layer, selecting the committed Workspace only after its list projection has refreshed; cancellation is silent, and errors land in the retryable folder dialog whose **Choose again** reopens the flow. **Create a new workspace** retains the name dialog and disables names already present in that list, while the Host remains authoritative for concurrent or non-UI callers. The runtime Session and Workspace services own materialization. The Workspace row's Delete action opens a confirmation that states the retention boundary, blocks duplicate submission, and keeps failures open; success removes the group while its Sessions remain under Ungrouped. The Session row's Rename action opens the same browser-owned dialog pattern prefilled with the row's display title: no client-side conflict rule exists (the host normalizes and may reject with `title-invalid`, rendered in the dialog alert), and confirming an unchanged title is deliberately allowed — it pins the current automatic title against regeneration.
 
+The Session row's Fork action forks at the source's last completed turn, increments the inherited persisted title on the client, and then opens the child; a trailing ASCII or fullwidth parenthesized number is incremented in the same style, while an unnumbered title gets ` (1)` appended. The source and child always appear as peer rows within a workspace group, with lineage retained only as session data. A fork or rename failure leaves the current selection unchanged; after a rename failure, the created child remains in the list.
+
 Both target slots are declared by other plugins, so `apply` registers through declaration-aware deferral and re-registers after a declaring slot is restored.
 
 ## Model Experience
@@ -18,5 +20,5 @@ None; this package neither assembles nor sends a provider request.
 
 ## Known Limitations and Deferred Work
 
-- **No Session deletion or fork control** — the Session menu's Fork and Delete rows remain visual-only (Rename is wired); Workspace registration deletion does not delete Sessions.
+- **No Session deletion control** — the Session menu's Delete row remains visual-only; Workspace registration deletion does not delete Sessions.
 - **Native folder selection depends on the local Host carrier** — under the `-native` composition, fixture-only or remote browser deployments cannot open a local operating-system dialog; platform failures are shown in a retryable modal. Remote-capable picking is the `-browse` composition's in-app flow.

packages/client/ui-workspace/README.zh.md

@@ -6,6 +6,8 @@
 
 该选择器通过全局 `useWorkspaces` hook 列出真实的 Host Workspace 实体。选择 Workspace 会调用 slot owner 的 `onPick` 回调，重新定位前端 Session 对象。每个注册各自声明一个**目录流子洞**（`single` kind：`conversation.hero.workspace.directoryFlow`／`sidebar.workspaces.directoryFlow`），由组合的选择器包 client half 填入其选取交互——今天是 [`-native`](../../host/directory-picker-native/README.md) 后端的无渲染 OS 选择器驱动，`-browse` 组合下则是应用内浏览对话框。平铺显示的 **打开本地文件夹…** 操作仅在本表层的洞被占用时渲染（每次菜单渲染读取占用状态；洞为空意味着该组合没有选目录能力——seam 文档化的无流程默认行为）。本包持有触发与接纳：占用者经洞的 owner 会话（`open`/`busy`/`onPicked`/`onCancel`/`onError`）每次打开上报一个所选路径，owner 通过对象层接纳它，并等待 Workspace 列表投影刷新后才选中已提交的 Workspace；取消操作不会显示提示，错误落入可重试的文件夹对话框，其 **重新选择** 会重新打开流程。**创建新工作区** 操作保留名称对话框，并禁用列表中已有的名称，而 Host 对并发或非 UI 调用方仍具有最终决定权。运行时 Session 与 Workspace 服务负责物化。Workspace 行内的 Delete 操作会打开确认框，说明保留边界、阻止重复提交，并在失败时保持打开；成功后，该分组会被移除，其 Session 则留在 Ungrouped 下。Session 行内的 Rename 操作打开同款浏览器持有的对话框，并以该行的显示标题预填：客户端不设名称冲突规则（host 负责规范化，可能以 `title-invalid` 拒绝，错误渲染在对话框告警区）；确认未修改的标题是有意允许的——这正是把当前自动标题钉住、不再被重新生成覆盖的手势。
 
+Session 行内的 Fork 操作在源会话最后一个已完成轮次处 fork，在 client 端递增继承的持久化标题后再打开子会话；尾部半角或全角括号编号会原样式递增，无编号标题追加 ` (1)`。源会话与子会话在 workspace 组内始终作为同级行展示，谱系只保留为 session 数据。Fork 或改名失败都不会改变当前选中项，改名失败时已创建的子会话仍会留在列表中。
+
 两个目标 slot 都由其他插件声明，因此 `apply` 通过声明感知的延迟机制完成注册，并在声明该 slot 的插件恢复后重新注册。
 
 ## 模型体验
@@ -18,5 +20,5 @@
 
 ## 已知限制与暂缓事项
 
-- **没有 Session 删除与 fork 控件**：Session 菜单的 Fork 与 Delete 行仍仅提供视觉效果（Rename 已接线）；删除 Workspace 注册记录不会删除 Session。
+- **没有 Session 删除控件**：Session 菜单的 Delete 行仍仅提供视觉效果；删除 Workspace 注册记录不会删除 Session。
 - **原生文件夹选择依赖本地 Host 载体**：在 `-native` 组合下，仅使用 fixture（测试前置数据）的部署或远程浏览器部署无法打开本地操作系统对话框；模态框会显示平台故障，并允许重试。可远程的选取是 `-browse` 组合的应用内流程。

packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx

@@ -83,7 +83,7 @@ interface DragState {
 
 type SessionTreeProps = Pick<
   WorkspaceBrowserProps,
-  'useSessions' | 'startSession' | 'open' | 'insertSessionBefore'
+  'useSessions' | 'startSession' | 'open' | 'forkSession' | 'insertSessionBefore'
 > & {
   workspaces: readonly WorkspaceView[]
   /** Live search filter owned by the browser root (the query outlives the tree). */
@@ -98,13 +98,12 @@ type SessionTreeProps = Pick<
 
 /** The scrolling session tree; unmounting at collapse settle drops the sessions subscription and expansion state. */
 function SessionTree({
-  useSessions, startSession, open, workspaces, query,
+  useSessions, startSession, open, forkSession, workspaces, query,
   onRenameRequest, onDeleteRequest, onSessionRename, insertSessionBefore,
 }: SessionTreeProps) {
   const list = useSessions(s => s)
   const current = list.current
   const [expandedProjects, setExpandedProjects] = useState<string[]>([])
-  const [expandedSessions, setExpandedSessions] = useState<string[]>([])
   // Transient drag viewing state (never store-bound; order truth stays Host-side).
   const [drag, setDrag] = useState<DragState | null>(null)
   const currentGroup = current === undefined
@@ -116,8 +115,8 @@ function SessionTree({
     setExpandedProjects(l => (l.includes(currentGroup) ? l : [...l, currentGroup]))
   }, [current, currentGroup])
   const groups = useMemo(
-    () => deriveGroups(list, workspaces, { expandedProjects, expandedSessions, query }),
-    [list, workspaces, expandedProjects, expandedSessions, query],
+    () => deriveGroups(list, workspaces, { expandedProjects, query }),
+    [list, workspaces, expandedProjects, query],
   )
   const now = Date.now()
 
@@ -128,7 +127,7 @@ function SessionTree({
           <div className={css.empty}>{query === '' ? 'No sessions yet' : 'No matches'}</div>
         )}
         {groups.map(group => (
-          // Group section: header row + expanded session subtree. The
+          // Group section: header row + expanded top-level session rows. The
           // inter-group breathing room (former flat-list batch separator)
           // is the section's own margin (WorkspaceBrowser.module.css).
           <div key={group.key} className={css.groupSection}>
@@ -152,7 +151,7 @@ function SessionTree({
                 }}
             />
             {group.sessions.map((node, index) => {
-              // Draggable: real-workspace group roots outside search. The drag
+              // Draggable: real-workspace session rows outside search. The drag
               // never leaves its group — rows of other groups show no markers
               // and reject drops (visual movement confined to this section).
               const draggable = group.workspaceId !== undefined && query === ''
@@ -170,15 +169,15 @@ function SessionTree({
                 drop: (half: 'before' | 'after') => {
                   /* v8 ignore next -- narrowing guard: Rows gates drop on `active`, which is false while the drag state is null. */
                   if (drag === null) return
-                  const roots = group.sessions
+                  const sessions = group.sessions
                   // Anchor = the row the insert line points at ('after' means
                   // the next root; end-of-list omits the anchor → append).
-                  const anchor = half === 'before' ? node.id : roots[index + 1]?.id
+                  const anchor = half === 'before' ? node.id : sessions[index + 1]?.id
                   setDrag(null)
                   if (anchor === drag.sessionId) return
                   // No-op when the drop lands back on the source position.
-                  const sourceIndex = roots.findIndex(r => r.id === drag.sessionId)
-                  const anchorIndex = anchor === undefined ? roots.length : roots.findIndex(r => r.id === anchor)
+                  const sourceIndex = sessions.findIndex(r => r.id === drag.sessionId)
+                  const anchorIndex = anchor === undefined ? sessions.length : sessions.findIndex(r => r.id === anchor)
                   if (sourceIndex !== -1 && (anchorIndex === sourceIndex || anchorIndex === sourceIndex + 1)) return
                   insertSessionBefore(drag.workspaceId, drag.sessionId, anchor).catch((reason: unknown) => {
                     console.warn('session reorder rejected:', reason)
@@ -190,12 +189,11 @@ function SessionTree({
                 <SessionNodeItem
                   key={node.id}
                   node={node}
-                  depth={0}
                   currentId={current}
                   now={now}
                   onOpen={open}
                   onRename={onSessionRename}
-                  onToggle={(id) => { setExpandedSessions(l => toggled(l, id)) }}
+                  onFork={forkSession}
                   drag={dragProps}
                 />
               )
@@ -209,7 +207,7 @@ function SessionTree({
 }
 
 /** The flat "In one list" body: every session a top-level row, newest-first. */
-function FlatList({ useSessions, open, onSessionRename, query }: Pick<SessionTreeProps, 'useSessions' | 'open' | 'onSessionRename' | 'query'>) {
+function FlatList({ useSessions, open, forkSession, onSessionRename, query }: Pick<SessionTreeProps, 'useSessions' | 'open' | 'forkSession' | 'onSessionRename' | 'query'>) {
   const list = useSessions(s => s)
   const rows = useMemo(() => deriveFlat(list, { query }), [list, query])
   const now = Date.now()
@@ -223,14 +221,11 @@ function FlatList({ useSessions, open, onSessionRename, query }: Pick<SessionTre
           <SessionNodeItem
             key={node.id}
             node={node}
-            depth={0}
             currentId={list.current}
             now={now}
             onOpen={open}
             onRename={onSessionRename}
-            /* v8 ignore next -- required-prop filler: flat rows render no twist, so it never fires. */
-            onToggle={() => {}}
-            flat
+            onFork={forkSession}
           />
         ))}
       </div>
@@ -254,6 +249,7 @@ export function WorkspaceBrowser({
   startSession,
   open,
   renameSession,
+  forkSession,
   renameWorkspace,
   deleteWorkspace,
   insertSessionBefore,
@@ -462,11 +458,12 @@ export function WorkspaceBrowser({
           itself is wide-only. */}
       <div className={css.listArea}>
         {wide && (groupBy === 'flat'
-          ? <FlatList useSessions={useSessions} open={open} onSessionRename={onSessionRename} query={query} />
+          ? <FlatList useSessions={useSessions} open={open} forkSession={forkSession} onSessionRename={onSessionRename} query={query} />
           : (
             <SessionTree
               useSessions={useSessions}
               onSessionRename={onSessionRename}
+              forkSession={forkSession}
               workspaces={workspaces}
               startSession={startSession}
               open={open}

packages/client/ui-workspace/src/client/contract/slots.ts

@@ -95,6 +95,8 @@ export type WorkspaceBrowserInjected = DirectoryPickingInjected & {
   open: (sessionId: SessionId) => void
   /** Rename a Session (explicit user title; resolves on host acceptance). */
   renameSession: (sessionId: SessionId, title: string) => Promise<void>
+  /** Fork a Session at its last completed turn and open the child. */
+  forkSession: (sessionId: SessionId) => void
   /** Rename a Host Workspace (rejects on name conflict; resolves on durability). */
   renameWorkspace: (workspaceId: WorkspaceId, title: string) => Promise<void>
   /** Delete only a Host Workspace registration; directory and Session logs remain. */

packages/client/ui-workspace/src/client/index.ts

@@ -59,6 +59,13 @@ export function apply(ctx: ClientContext): void {
       const result = await session.rename(title)
       if (!result.ok) throw new Error(result.error.message)
     },
+    forkSession: (sessionId) => {
+      ctx.sessions.fork({ sessionId, increaseTitle: true })
+        .then((childId) => { ctx.sessions.open(childId) })
+        .catch(() => {
+          // Fork or child-rename failure keeps the current selection.
+        })
+    },
     renameWorkspace: async (workspaceId, title) => { await ctx.workspaces.rename(workspaceId, title) },
     deleteWorkspace: async (workspaceId) => { await ctx.workspaces.delete(workspaceId) },
     insertSessionBefore: async (workspaceId, sessionId, beforeSessionId) => {

packages/client/ui-workspace/src/client/rows/Rows.module.css

@@ -39,9 +39,7 @@
   height: 20px;
 }
 
-/* Session cell (figma): pad 8, adjacent 16px twist + status slots, then a 4px
-   gap to the title — the slots butt together, so the row gap is zeroed and
-   the title carries its own margins. */
+/* Session cell (figma): pad 8, a 16px status slot, then a 4px title gap. */
 .sessionRow {
   height: 34px;
   gap: 0;
@@ -168,7 +166,7 @@
   background: var(--dsw-alias-interactive-bg-hover);
 }
 
-/* Drag reorder insert line (workspace-group roots): 2px accent above or
+/* Drag reorder insert line (workspace-group session rows): 2px accent above or
    below the hovered row, drawn with box-shadow so no layout shift. */
 .sessionRow.dropBefore {
   box-shadow: 0 -2px 0 0 var(--dsw-alias-state-business-primary);
@@ -233,33 +231,9 @@
   color: var(--dsw-alias-label-primary);
 }
 
-/* Session expand twist occupies the leading 16px slot; keep a spacer when absent
-   so titles align across sibling rows. Duplicates the .iconButton reset instead
-   of `composes:` — the tsdown CSS-modules pipeline drops composes mappings, which
-   left the raw UA button box showing. */
-.twist {
-  flex: none;
-  display: inline-flex;
-  align-items: center;
-  justify-content: center;
-  width: 16px;
-  height: 20px;
-  border: none;
-  border-radius: 4px;
-  padding: 0;
-  background: transparent;
-  cursor: pointer;
-}
-
-.twist:hover {
-  color: var(--dsw-alias-label-primary);
-}
-
-/* Chevrons and tree twists ride the caption grey (#ADB2B8); the folder glyph
-   stays one step darker (tertiary, #81858C) per the cell spec. Declared last
-   to win over the composed .iconButton color. */
-.chevron,
-.twist {
+/* Chevrons ride the caption grey (#ADB2B8); the folder glyph stays one step
+   darker (tertiary, #81858C) per the cell spec. */
+.chevron {
   color: var(--dsw-alias-label-caption);
 }