Merge remote-tracking branch 'origin/master' into codex/new-task

2026-07-31 00:10:46 +08:00
parent 1986de9ac1 33803240ad
commit edefdd96b9
281 changed files with 9154 additions and 909 deletions
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md
-2026-07-28-directory-picker-capability-seam.md: ad2aa904beddb2fe941883c3c1827702dbec9964
-2026-07-28-directory-picker-capability-seam.zh.md: 30e719ad9b4e8374496106b447e961a042c7d8b6
+2026-07-28-directory-picker-capability-seam.md: 495062f910785e1bb2f421dbb25c01c399d45567
+2026-07-28-directory-picker-capability-seam.zh.md: 62fc87212ab627ea8819dab55e3a769b4a5afc42
@@ -20,7 +20,7 @@ Placement and policy rulings folded into this decision:
 - **Dependency survey (hand-roll vs adopt).** Node's stdlib *is* the maintained cross-platform OS layer (`readdir(withFileTypes)`, `homedir`, path semantics); surveyed alternatives fail the dependency bar — file-manager packages (`node-file-manager`, `files-and-folders`, Syncfusion's provider) are whole HTTP apps (fit), drive-letter helpers (`drivelist` native addon, `windows-drive-letters` ~7y stale) fail health/proportionality. The browse backend is a thin adapter over stdlib.
 - **Hidden entries: return-and-flag.** The host stamps `hidden` (POSIX dot convention) and returns everything; the client filters. Display policy stays client-side, and the show-hidden toggle shipped as exactly that client-only change: a fixed-label footer toggle whose state lives in the pressed presentation (`aria-pressed` + check glyph), a dot-led path-draft prefix reveals the hidden entries it names, and the current selection is exempt from both the hidden and the prefix filter (it anchors the two-pane view). Windows' `FILE_ATTRIBUTE_HIDDEN` is not exposed by dirents — documented limitation until a native probe pays for itself.
 - **Path-editor cancel scope: the dialog card.** The browse client's path editor cancels on Escape and on focus leaving the card, both observed at a card-scope wrapper rather than the input — after Tab parks focus on a filtered row the input is off the event path, yet Escape must collapse the editor (not the dialog) and a later focus departure must still cancel. Non-cancel exemptions: window/tab focus loss, in-card focus moves, and pointer paths (rows and the toggle suppress focus steal on mousedown while editing). Separators for seeding and draft-tail filtering are inferred from `listing.home`; the wire-field alternative below records the deferred authoritative form. Combobox semantics between the editor and the list it filters (`aria-expanded`/`aria-controls`/active-descendant, result announcements) are likewise deferred — today they read to assistive tech as separate widgets.
- **Navigation lands selection-anchored, progressively.** Away from the display root (the same collapse the crumb header renders, so crumbs and pane shape never disagree), the browse client's navigate commits the target level the moment it arrives — the editor closes and loading ends on that first settlement, so an Enter-submitted navigation is never withdrawn waiting on more — and a parent leg then upgrades the landing in place: the target's actual parent-level entry re-selected (platform case folding on Windows), its children on the right, so a crumb jump reads as stepping back one pane rather than collapsing to a single column. The parent leg runs under the landing's supersession scope and is aborted on the wire by any newer intent; a failed parent leg, or a truncated parent window lacking the target, leaves the committed single-pane landing — the upgrade must never orphan the selection it exists to anchor.
+- **Navigation lands selection-anchored, quiet, and bounded.** Away from the display root (the same collapse the crumb header renders, so crumbs and pane shape never disagree), the landing is two-pane: the target's actual parent-level entry re-selected (platform case folding on Windows), its children on the right, so a crumb jump reads as stepping back one pane rather than collapsing to a single column. Target and parent legs land as **one frame** when the parent leg settles within the 200ms wait bound — the stale view keeps rendering until then, so navigation swaps the panes without an intermediate single-pane flash — and past the bound the target commits alone at once (an Enter-submitted navigation is never held hostage by a stalled parent) with the late parent leg upgrading the landing in place. The parent leg runs under the landing's supersession scope and is aborted on the wire by any newer intent (Escape inside the landing window therefore withdraws the whole navigation); a failed parent leg, or a truncated parent window lacking the target, leaves the single-pane landing — the upgrade must never orphan the selection it exists to anchor. The loading indicator follows the same quiet rule: it floats over the content's bottom-right corner (never a layout-shifting row; the truncated/error rows own the bottom left and keep rendering through a scan) and only once a scan outlives a 300ms silence window, so a local listing swaps with nothing shown at all. Row picks are deliberately exempt from the one-frame rule: a pick's immediate pane split is its selected-state feedback (aria-current, crumbs following), while a navigation has nothing to acknowledge the click but the swap itself. Both timing constants are calibrated for local enumeration; a remote deployment (one RPC per level, commonly 100–400ms) would sit inside the silence window with no pressed state on the crumbs — revisit the window or add pressed feedback when a remote consumer lands.
 - **Symlinks: follow for enterability.** `stat` probes symlinks (broken/cyclic → skipped); crumbs keep the logical path the operator navigated, and `workspace.create` already canonicalizes via realpath at adoption.
 - **Listing levels are bounded, and streamed.** One `list` call returns at most `maxEntries` rows (config, default 1000 — GitHub's web-UI directory-listing bound). The level streams via `opendir` into a name-sorted window of `maxEntries + 1` candidates, so memory stays O(maxEntries) and enterability probing touches only windowed candidates; the wire `DirectoryListing` carries a required `truncated` flag so the client states incompleteness instead of silently missing tail entries. A windowed broken symlink is not backfilled from beyond the window — the eviction already marks the level truncated. Window insertion is binary with an O(1) full-window tail rejection (an oversized level must not pay a window scan per dirent), and `list(path, signal)` threads the carrier's request signal so a scan of a stalled network directory cannot outlive a disconnected caller — every await in the scan (open, each read, each symlink probe) races the signal, an aborted exit abandons rather than awaits the close (Node queues close behind in-flight reads), and abandoned settlements are swallowed so cleanup can never surface as an unhandled rejection. An unbounded level is a memory/responsiveness hole for large or adversarial directories.
 - **Whole-filesystem scope, no roots config.** `workspace.create` accepts arbitrary paths and the API serves bash-driving methods, so a browse root would be UX scoping, not a boundary; configurability without a consumer fails the evidence bar. Deferred until a deployment needs it.
@@ -38,7 +38,7 @@ Placement and policy rulings folded into this decision:

 ## Consequences

- `cordis.yml` chooses the interaction; `apps/cli` mounts `-browse` (the shipped default — remote-capable picking out of the box), one row having swapped backend and UI together; `-native` remains the host-display alternative.
+- `cordis.yml` chooses the interaction; `apps/cli` mounts the [`-auto` chooser](../feature/2026-07-29-directory-picker-adaptive-default.md), which resolves the host's situation at boot and mounts `-native` or `-browse` itself, one row still swapping backend and UI together; composing a backend row directly pins the interaction.
 - The wire gains `host.listDirectory`/`host.createDirectory` and four error codes; the connection fixture serves a deterministic browse tree and a deterministic `pickDirectory` path for keyless assembled tests.
 - A future interaction (or an Electron provider of the `native` interaction) is one dual-face backend package — no gateway surgery, no ui-workspace edits.
 - `ApiProxyDefaults.pickDirectory` (test-only injection) is gone; tests provide a stub `ctx.directoryPicker` like any other service.
@@ -20,7 +20,7 @@ web GUI 的"打开本地文件夹"流程被焊死在一种交互上：`host.pick
 - **依赖调研（手写 vs 引入）。** Node 标准库本身就是维护中的跨平台 OS 层（`readdir(withFileTypes)`、`homedir`、路径语义）；调研过的替代品都过不了依赖门槛——文件管理器包（`node-file-manager`、`files-and-folders`、Syncfusion 的 provider）是整套 HTTP 应用（契合度不过），盘符工具（原生插件 `drivelist`、约七年未更的 `windows-drive-letters`）健康度／比例失当。browse 后端是标准库上的薄适配。
 - **隐藏条目：返回并打标。** 宿主标注 `hidden`（POSIX 点前缀约定）并返回全部条目；客户端过滤。展示策略留在客户端，"显示隐藏"开关正是作为这一纯客户端改动落地：标签固定的 footer 开关，其状态由按下态呈现承载（`aria-pressed` + 勾选符号）；以点开头的路径草稿前缀会显出它所指名的隐藏条目；当前选中项则不受隐藏与前缀两种过滤影响（它锚定着双栏视图）。Windows 的 `FILE_ATTRIBUTE_HIDDEN` 不被 dirent 暴露——记为限制，直到原生探测值回其成本。
 - **路径编辑器的取消范围：对话框卡片。** browse 客户端的路径编辑器在按 Escape 与焦点离开卡片时取消，两者都在卡片范围的包装层而非输入框上监听——Tab 把焦点停到某个过滤命中的行之后，输入框已不在事件路径上，但 Escape 仍须收起编辑器（而非对话框），其后的焦点离开也仍须取消。不取消的豁免：窗口／标签页失焦、卡片内焦点移动，以及指针路径（编辑期间行与开关在 mousedown 时抑制焦点夺取）。预填与草稿末段过滤所用的分隔符从 `listing.home` 推断；下文的线上字段替代方案记录了被延期的权威形态。编辑器与其过滤的列表之间的 combobox 语义（`aria-expanded`／`aria-controls`／active-descendant、结果播报）同样被延期——目前二者在辅助技术看来是彼此独立的控件。
- **导航以选中项为锚、渐进落地。** 在展示根之外（与 crumb 头部渲染的是同一塌缩，因此 crumb 与分栏形态永不相左），browse 客户端的导航在目标层级到达的那一刻即提交它——这次首个落定即关闭编辑器并结束加载，因此 Enter 提交的导航绝不会为等待更多内容而被撤回——随后父层级这一程就地升级这次落地：重新选中目标在父层级中的实际条目（Windows 上按平台惯例折叠大小写），右侧展示其子项，因此 crumb 跳转读作后退一栏，而不是塌缩成单列。父层级这一程在落地的 supersession 范围下运行，任何较新的意图都会在线上将其中止；父层级这一程失败，或被截断的父窗口缺少目标时，都保留已提交的单栏落地——升级的存在正是为了锚定选中项，绝不能反而让它悬空。
+- **导航以选中项为锚、安静且有界地落地。** 在展示根之外（与 crumb 头部渲染的是同一塌缩，因此 crumb 与分栏形态永不相左），落地即双栏：重新选中目标在父层级中的实际条目（Windows 上按平台惯例折叠大小写），右侧展示其子项，因此 crumb 跳转读作后退一栏，而不是塌缩成单列。父层级这一程在 200ms 等待上限内落定时，目标与父层级两程以**同一帧**落地——在此之前陈旧视图持续渲染，导航换栏时因此没有中间的单栏闪现——超出该上限则目标即刻单独提交（Enter 提交的导航绝不会被滞塞的父层级扣作人质），迟到的父层级这一程再就地升级这次落地。父层级这一程在落地的 supersession 范围下运行，任何较新的意图都会在线上将其中止（因此在落地窗口内按 Escape 即撤回整次导航）；父层级这一程失败，或被截断的父窗口缺少目标时，都保留单栏落地——升级的存在正是为了锚定选中项，绝不能反而让它悬空。加载指示器遵循同一安静规则：它浮于内容右下角（绝不是会挪动布局的一行；截断／错误行占据左下角，并在扫描期间持续渲染），且仅在扫描超出 300ms 静默窗口后才出现，因此本地列举切换时什么也不显示。行选取被刻意豁免于同一帧规则：选取后立即分栏本身就是其选中态反馈（aria-current、crumb 跟随），而导航除了换栏本身没有任何东西可确认这次点击。两个时序常量都按本地列举校准；远程部署（每层级一次 RPC，通常 100–400ms）会落在静默窗口之内、crumb 上却没有按下态——待远程消费方落地时，重新审视该窗口或补上按下反馈。
 - **符号链接：为可进入性而跟随。** 用 `stat` 探测符号链接（断链／循环→跳过）；面包屑保留操作者导航的逻辑路径，`workspace.create` 在接纳时本就做 realpath 规范化。
 - **列举层级有上限，且流式处理。** 单次 `list` 至多返回 `maxEntries` 行（配置项，默认 1000——GitHub 网页端目录列举的同一上限）。层级经 `opendir` 流入一个按名排序、容量 `maxEntries + 1` 的候选窗口，内存保持 O(maxEntries)，可进入性探测只触及窗口内候选；线上 `DirectoryListing` 携带必填的 `truncated` 标志，让客户端明示不完整而不是静默缺尾。窗口内的断链符号链接不从窗口外回填——发生过驱逐本身已把层级标记为截断。窗口插入为二分查找、满窗尾部单次比较即拒绝（超大层级不能为每个 dirent 付出一次全窗扫描），且 `list(path, signal)` 透传载体的请求信号，滞塞网络目录的扫描不会在调用方断连后继续存活——扫描中的每个 await（打开、每次读取、每次符号链接探测）都与信号赛跑，中止路径放弃而非等待 close（Node 会把 close 排在在飞读取之后），被放弃的 settlement 全部吞掉，清理不会以未处理拒绝的形式冒出。无上限的层级对超大或恶意构造的目录就是内存／响应性漏洞。
 - **全盘可浏览，不做 roots 配置。** `workspace.create` 接受任意路径且 API 本就提供驱动 bash 的方法，浏览根只会是 UX 范围而非边界；没有消费方的可配置性过不了证据门槛。等到有部署需要再做。
@@ -38,7 +38,7 @@ web GUI 的"打开本地文件夹"流程被焊死在一种交互上：`host.pick

 ## 后果

- `cordis.yml` 决定交互形态；`apps/cli` 挂 `-browse`（随附默认——开箱即得可远程的选取），一行同时切换了后端与 UI；`-native` 仍是宿主屏幕方案。
+- `cordis.yml` 决定交互形态；`apps/cli` 挂 [`-auto` 选择器](../feature/2026-07-29-directory-picker-adaptive-default.md)，它在启动时判定宿主处境并自行挂载 `-native` 或 `-browse`，一行仍同时切换后端与 UI；直接组合某个后端行即固定交互。
 - 协议新增 `host.listDirectory`／`host.createDirectory` 与四个错误码；connection fixture 提供确定性浏览树与确定性 `pickDirectory` 路径供无密钥组装测试使用。
 - 未来的新交互（或提供 `native` 交互的 Electron 实现）只是一个双面后端包——无需网关手术，也不动 ui-workspace。
 - `ApiProxyDefaults.pickDirectory`（仅测试注入）删除；测试像提供其他服务一样提供 stub `ctx.directoryPicker`。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-28-user-settings-seam.md
+2026-07-28-user-settings-seam.md: bf93f95168b1b6d0dec5a9fc2c9aac5531f0564a
+2026-07-28-user-settings-seam.zh.md: 8cd4dfcbb2facdd590b2c24d453ad79e9badda4d
@@ -0,0 +1,35 @@
+# Agent Note: user-settings seam (`ctx.settings`) and the file provider
+
+Status: implemented
+
+English | [中文](2026-07-28-user-settings-seam.zh.md)
+
+> Scope: the `packages/settings/` capability family — the abstract seam, the file-backed provider, and the composition boundary between user settings and `cordis.yml`. The [web config-tree note](2026-07-24-web-config-tree-boot-and-transport-layering.md) recorded "the profile write path" as a deferral; this seam is that write path's owner. Consumer migrations (theme, locale, default model route) and the web `settings.*` RPC surface are follow-ups, not part of this note's shipped scope.
+
+## Problem
+
+User-editable configuration had no owner: `dsh web` read a cwd-anchored profile json through a static whitelist with no write path, the TUI read `$DSH_HOME/config.yaml` raw loader patches, and both froze at boot. A personal-settings page (web GUI) needs one cross-surface user layer with schema validation, a write path, and hot propagation — and peer products (Codex, Claude Code, Kimi, OpenCode, Pi) all converged on separating user preferences from extension composition. Loader-reactive config updates cannot carry this: `fiber.update` swaps entry config in place, so a plugin that read config at construction observes nothing and no callback tells it otherwise.
+
+## Decision
+
+**Two planes with a litmus test.** `cordis.yml` (+ Include patches) stays the composition plane: which plugins exist, wiring, deployment config, owned by the orchestrator and upgraded with the product. A settings namespace carries only the user-editable subset; the test is "should the personal config page edit it?" Values live in both planes without ambiguity because layering is the contract: schema defaults, then the registrant's composition `base` (its entry-config subset), then the user document section.
+
+**Three-package seam mirroring `session-persistence/`.** `dsh-settings` owns the abstract `Settings` service: namespace registry, layered resolution, schema validation, per-namespace deep-equal change detection, and the `settings/updated` commit event. Providers implement only `writable`/`load()`/`persist(ns, section)` and push externally observed documents through the protected `publish(doc)` — so hot-update semantics are identical across providers, and a network configuration-center backend (nacos-style, possibly read-only) is a sibling package away. `dsh-settings-local` is the file provider: YAML/JSON under `resolveSpec` (explicit defaulting to `<DSH_HOME>/settings.yaml`), chokidar watch, read-modify-write persists under a cross-process writer lock with atomic `0600` tmp+rename commits, leaf-level diff patching of the written namespace (comments survive untouched nodes), and content-equality self-write suppression ([write-path integrity note](2026-07-30-settings-write-path-integrity.md)).
+
+**Registrations are caller-fiber effects.** `register()` runs through the service proxy, so `this.ctx` is the registrant's context and the registration rides `ctx.effect`: disposing the registrant removes the namespace and its watchers (proven by the HMR disposal test), while the user's section keeps living in storage for the next owner.
+
+**Fail loud at rest, last-good in motion.** Boot-time and registration-time validation throw (invalid stored section fails the registering plugin; an existing-but-unparsable document fails provider load). Once live, a bad external edit warns and keeps the last good state per namespace — a hot reload must never take the process down. This asymmetry mirrors `Include.refresh()` and Kimi's safe runtime reload.
+
+**Consumers stay optional-by-construction.** A consumer registers inside `ctx.inject(['settings'], …)`; without a mounted provider it keeps resolving entry config alone, so every existing composition, demo, and snapshot works unchanged and migration is per-plugin.
+
+## Alternatives considered
+
+- **Include write-back as the user layer** (per-plugin config pages writing loader entry files, cordis-webui style): write-back would target per-composition files, binding user preferences to one `cordis.yml`; a per-user layer must survive template upgrades and serve TUI and web from one document.
+- **Loader-reactive `fiber.update` as the propagation channel**: constructor-time reads observe nothing; the seam's explicit `watch()` makes hot-update a consumer contract instead of framework magic.
+- **A domain-aware settings service** (getters per product area): the coupling objection from design review stands; the service stores, validates, and publishes — domain meaning stays with the registrant that owns the schema.
+- **Multi-layer precedence now** (system/managed/project tiers à la Codex/Claude Code): deferred until a real second layer exists; the resolve step is the single place layering would extend.
+- **A cross-process lockfile now** (Pi's proper-lockfile): initially deferred as "atomic replace plus watcher convergence until real contention shows up" — review showed convergence loses unobserved sibling namespaces, so the deferral is superseded by the [write-path integrity note](2026-07-30-settings-write-path-integrity.md)'s hand-rolled writer lock.
+
+## Consequences
+
+Deferred, in dependency order: the web `settings.raw`/`settings.describe`/`settings.update` RPC surface (which must redact `role('secret')` fields before exposure); first consumer migrations (`ui-theme`, locale, api-gateway default route) retiring `PROFILE_MAPPINGS` and the profile json; `${env:VAR}` value indirection for secrets; provider-side layering. The keyless snapshot obligation lands with the first model- or product-user-visible consumer, not with this infrastructure step.
@@ -0,0 +1,35 @@
+# Agent Note：用户设置 seam（`ctx.settings`）与文件 provider
+
+Status: implemented
+
+[English](2026-07-28-user-settings-seam.md) | 中文
+
+> 范围：`packages/settings/` 能力族——抽象 seam、文件 provider，以及用户设置与 `cordis.yml` 的组合边界。[web config-tree note](2026-07-24-web-config-tree-boot-and-transport-layering.md) 曾把"profile 写路径"记为延后项；本 seam 就是该写路径的归属。消费者迁移（主题、语言、默认模型路由）与 web `settings.*` RPC 面是后续工作，不在本 note 已交付范围内。
+
+## 问题
+
+用户可编辑配置没有归属：`dsh web` 经静态白名单读 cwd 锚定的 profile json 且无写路径，TUI 读 `$DSH_HOME/config.yaml` 裸 loader patch，两者都在启动时冻结。个人设置页（web GUI）需要一个跨 surface 的用户层，带 schema 校验、写路径与热传导——同类产品（Codex、Claude Code、Kimi、OpenCode、Pi）也全部收敛于"用户偏好与扩展组合分离"。Loader 的 reactive 配置更新承载不了这件事：`fiber.update` 原地替换 entry config，构造期读过配置的插件毫无感知，也没有任何回调通知它。
+
+## 决策
+
+**两个面，一条判定。**`cordis.yml`（+ Include patches）仍是组合面：有哪些插件、接线、部署配置，归 orchestrator 所有并随产品升级。settings namespace 只承载用户可编辑子集；判定是"个人配置页应该能改它吗？"值可同时存在于两个面而不歧义，因为分层就是契约：schema 默认值，然后注册方的组合 `base`（其 entry 配置子集），最后用户文档分节。
+
+**镜像 `session-persistence/` 的三包 seam。**`dsh-settings` 拥有抽象 `Settings` 服务：namespace 注册表、分层解析、schema 校验、按 namespace 深相等变更检测，以及 `settings/updated` 提交事件。provider 只实现 `writable`/`load()`/`persist(ns, section)`，并通过受保护的 `publish(doc)` 推入外部观察到的文档——因此热更新语义对所有 provider 一致，网络配置中心后端（nacos 类，可能只读）只是一个平级包的距离。`dsh-settings-local` 是文件 provider：`resolveSpec` 显式默认到 `<DSH_HOME>/settings.yaml` 的 YAML/JSON、chokidar 监听、跨进程写锁下以 `0600` tmp+rename 原子提交的读-改-写 persist、对被写 namespace 的叶子级 diff 修补（未触碰节点的注释得以保留）、按内容相等抑制自写（[write-path integrity note](2026-07-30-settings-write-path-integrity.md)）。
+
+**注册是调用方 fiber 上的 effect。**`register()` 经服务代理调用，`this.ctx` 即注册方 context，注册挂在 `ctx.effect` 上：dispose 注册方即移除 namespace 及其观察者（HMR disposal 测试证明），而用户的分节继续留在存储中等待下一任 owner。
+
+**静止时响亮报错，运行中保留最后可用值。**启动期与注册期校验直接抛错（非法存量分节使注册插件加载失败；存在但不可解析的文档使 provider 加载失败）。运行中坏的外部编辑只告警并按 namespace 保留最后可用状态——热重载绝不拖垮进程。该不对称镜像 `Include.refresh()` 与 Kimi 的安全运行时重载。
+
+**消费者天然可选。**消费者在 `ctx.inject(['settings'], …)` 内注册；不挂 provider 时仍只按 entry 配置解析，因此所有既有组合、demo、snapshot 原样工作，迁移按插件渐进。
+
+## Alternatives considered
+
+- **以 Include 写回为用户层**（cordis-webui 式的按插件配置页写 loader entry 文件）：写回目标是按组合的文件，会把用户偏好绑死在某个 `cordis.yml` 上；用户层必须在模板升级中存活，并以同一文档服务 TUI 与 web。
+- **以 Loader reactive `fiber.update` 为传导通道**：构造期读取毫无感知；seam 的显式 `watch()` 把热更新变成消费者契约而非框架魔法。
+- **领域化的 settings 服务**（按产品域的 getter）：设计评审中的耦合反对成立；服务只做存储、校验、发布——领域含义留给拥有 schema 的注册方。
+- **现在就做多层优先级**（Codex/Claude Code 式 system/managed/project 层级）：延后到真实第二层出现；resolve 步骤是分层未来唯一的扩展点。
+- **现在就上跨进程锁**（Pi 的 proper-lockfile）：最初以"原子替换加 watcher 收敛，真实冲突出现再说"为由延后——评审发现收敛会丢失未观察到的同级 namespace，因此该延后已被 [write-path integrity note](2026-07-30-settings-write-path-integrity.md) 的手写写锁取代。
+
+## 后果
+
+按依赖顺序延后：web `settings.raw`/`settings.describe`/`settings.update` RPC 面（暴露前必须对 `role('secret')` 字段脱敏）；首批消费者迁移（`ui-theme`、语言、api-gateway 默认路由）并退役 `PROFILE_MAPPINGS` 与 profile json；面向密钥的 `${env:VAR}` 值间接引用；provider 侧分层。keyless snapshot 义务随第一个模型或产品用户可见的消费者落地，而非本基础设施步骤。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.md
+2026-07-30-settings-write-path-integrity.md: 07bd095162879c8e7866846cf562f6a13307e5fc
+2026-07-30-settings-write-path-integrity.zh.md: 5d02177073d482b61750d7bdfbbd0866bc227a6a
@@ -0,0 +1,35 @@
+# Agent Note: settings write-path integrity and observer lifecycle
+
+Status: implemented
+
+English | [中文](2026-07-30-settings-write-path-integrity.zh.md)
+
+> Scope: the third review round over `packages/settings/` — write-path data integrity in `dsh-settings-local` (operation chain, read-modify-write, cross-process writer lock, diff-shaped YAML edits) and observer lifecycle in `dsh-settings` (watch disposal, async listener containment, the JSON-shape write boundary). This note reverses one deferral recorded in the [user-settings seam note](2026-07-28-user-settings-seam.md): the cross-process lockfile now ships.
+
+## Problem
+
+Review found the provider's write path could destroy state it never observed, and the seam's observer lifecycle leaked past disposal. Concretely: watcher reloads and document writes ran on two independent promise chains while every write rendered the whole next document from the cached text, so an external edit still inside the debounce window was overwritten — and the follow-up reload no-oped because the post-rename content matched the cache, erasing the edit without a trace. The initial `load()` raced the watcher's own setup, leaving a startup window whose changes never fire an event. Two processes sharing a harness home rendered from independent caches, last writer winning whole namespaces. On the seam side, a `watch()` disposer only removed the observer from its set — an invocation already chained onto the watcher tail still ran after disposal, and nothing drained started invocations at service dispose; the `settings/updated` manual fan-out caught only synchronous throws, so an async listener's rejection escaped as an unhandled rejection; and `structuredClone` admitted Dates, Maps, BigInts, and cycles that YAML/JSON storage silently distorts on the reload round-trip (a Date lands as a timestamp string, a BigInt as a plain number). YAML writes replaced the whole namespace node, deleting every comment inside the section a comment-preserving provider had promised to keep.
+
+## Decision
+
+**One operation chain, and every write is a read-modify-write.** Watcher refreshes and persists from every namespace queue share a single settled chain, and `persistSection` begins by reconciling the on-disk text into the seam — publishing any unobserved difference first — before rendering against that fresh text. A write can no longer resurrect a stale document, and an on-disk document that turned invalid fails the write loud rather than being overwritten (the reload path keeps its warn-and-keep-last-good policy; the shared `reconcileFromDisk` throws and each caller picks its policy). The watcher's `ready` signal queues one extra reconcile, closing the startup gap between the initial load and the watcher becoming active.
+
+**Writes hold a `wx`-created `<file>.lock` sibling.** The read-render-rename cycle runs under a cross-process writer lock with exponential backoff, a 2 s acquisition deadline, and stale takeover after 5 s (a crashed holder, broken with a warning). Readers never lock — the rename commit is atomic — so contention is writer-only and resolves in milliseconds. The lock constants are protocol invariants, not config: a holder rewrites one small document, so the deadline and stale age derive from that bound, not from deployment taste.
+
+**Observer disposal is quiescent.** Watchers carry an `active` flag checked when a queued invocation would start, so a disposer that ran while the invocation waited prevents the start entirely; started invocations register in a service-level `pendingTails` set that the dispose drain awaits beside the write queues. The `settings/updated` fan-out contains a returned thenable's rejection through the same listener diagnostic as a sync throw, and the event contract now states that the `INVARIANT` rethrow serves synchronous listeners only — invariant companions must stay sync, which the shipped companion already is.
+
+**The write boundary admits JSON data only.** The call-time snapshot is a single `cloneJsonShaped` walk that detaches the patch and rejects any non-JSON value — Date, Map, BigInt, non-finite number, function, symbol, class instance, `undefined` array entry, circular reference — with its `$`-rooted path before anything persists. Object entries that are explicitly `undefined` still skip (the sparse-patch contract), now enforced at the boundary instead of inside `mergeLayers`.
+
+**YAML edits are leaf-level diffs.** `renderYaml` diffs the stored section against the next one and applies only `setIn` for changed values and `deleteIn` for removed keys, recursing through maps. Comments, anchors, and formatting survive on every untouched node and on the key node of every changed pair; arrays and other non-map values replace wholesale when unequal (`deepEqualJson` is the shared predicate), taking comments inside them along.
+
+## Alternatives considered
+
+- **`proper-lockfile` instead of a hand-rolled lock** — the dependency-over-hand-rolling policy was weighed: the library is barely maintained, its stale/retry policy is broader than this one-file protocol needs, and the shipped lock is ~40 lines with deterministic tests (including injected `EEXIST`/`stat` races). The policy favors dependencies that delete owned code; this one would replace 40 explained lines with an opaque peer.
+- **Revision/CAS instead of a lock** — rename cannot express compare-and-swap, so a CAS needs a version sidecar or content re-hash and a retry loop in every writer; the lock achieves the same serialization with one primitive and keeps readers free.
+- **Merging external edits into the in-flight write's own section** — the seam merges patches over the state visible at call time, so a same-namespace external edit racing a write still resolves last-write-wins; folding it in would need three-way merge semantics no consumer has asked for. The write publishes the external state first, so the loser is at least observed before being superseded.
+- **Declaring async `settings/updated` listeners unsupported** — the typed signature is `void` and lint flags misused promises, but an unlinted JS plugin can still register an async listener; a contract note cannot un-throw an unhandled rejection, so containment is the only defense that holds at runtime.
+- **Keeping `structuredClone` and validating in the provider** — the seam is the durable boundary's owner (every provider stores JSON-shaped documents), and rejecting at call time gives the caller the offending path; a provider-side check would reject after merge, blaming the merged section instead of the caller's value.
+
+## Consequences
+
+`update()` gained a documented failure mode (lock deadline, invalid on-disk document) and the rejection messages carry `$`-rooted paths. Remaining, documented in the provider README: same-namespace concurrent edits stay last-write-wins (no per-value merge or revision check), a watcher event the OS never delivers leaves the cache stale until the next signal or write, and comments inside replaced arrays or attached inline to changed scalar values go with the value they described. The [user-settings seam note](2026-07-28-user-settings-seam.md)'s deferred-lockfile alternative is superseded by this note. The same defect classes exist in `dsh-credentials-local` (two chains over one `.env`, cached whole-file write-back, post-persist emit) and in the `llm/adapters-updated` fan-out on the stacked branches; those fixes belong to the PRs that introduce the packages and follow this template on merge-up.
@@ -0,0 +1,41 @@
+# Agent Note: settings 写路径完整性与观察者生命周期
+
+Status: implemented
+
+[English](2026-07-30-settings-write-path-integrity.md) | 中文
+
+> 范围：对 `packages/settings/` 的第三轮评审——`dsh-settings-local` 的写路径数据完整性（操作链、读-改-写、跨进程写锁、diff 形态的 YAML 编辑）与 `dsh-settings` 的观察者生命周期（watch 的 dispose（资源释放）、异步监听器收容、JSON 形态写入边界）。本 note 推翻了[用户设置 seam note](2026-07-28-user-settings-seam.md)所记录的一项延后决定：跨进程锁文件现已交付。
+
+## 问题
+
+评审发现，提供方的写路径可能销毁它从未观察到的状态，而 seam 的观察者生命周期会泄漏到 dispose 之后。具体而言：watcher 重载与文档写入跑在两条相互独立的 promise 链上，而每次写入都从缓存文本渲染出完整的下一份文档，于是仍处于防抖窗口内的外部编辑会被覆盖——随后的重载又因 rename 后的内容与缓存一致而成为空操作，这次编辑就被无痕抹去。初始 `load()` 与 watcher 自身的建立过程存在竞态，留下一个启动窗口：落在这个窗口内的变更永远不会触发事件。共享同一 harness home 的两个进程各自从独立的缓存渲染，后写者以整个 namespace 为单位胜出。
+
+在 seam 一侧，`watch()` 的释放器只把观察者从集合中移除——已经接到 watcher 链尾的调用在 dispose 之后照常运行，服务 dispose 时也没有任何环节排空已启动的调用；`settings/updated` 的手动扇出只捕获同步抛错，异步监听器的 rejection 会以 unhandled rejection 的形式逃逸；`structuredClone` 则放行 Date、Map、BigInt 与循环引用，而 YAML/JSON 存储会在重载往返中悄悄扭曲这些值（Date 会变成时间戳字符串，BigInt 会变成普通数字）。
+
+YAML 写入则整体替换 namespace 节点，把分节内的每条注释都删掉——而这个保注释的提供方承诺过要保住它们。
+
+## 决策
+
+**单一操作链，且每次写入都是读-改-写。**watcher 的刷新与来自各 namespace 队列的持久化共享同一条结算链；`persistSection` 会先把磁盘上的文本对账进 seam——任何未被观察到的差异都先发布出去——然后才对照这份新鲜文本渲染。写入不再可能复活一份陈旧文档；磁盘上已变非法的文档会让写入响亮失败，而不是被覆盖（重载路径保持其“告警并保留最后可用值”策略；共享的 `reconcileFromDisk` 抛错，各调用方自选策略）。watcher 的 `ready` 信号会额外排入一次对账，弥合初始加载与 watcher 生效之间的启动缺口。
+
+**写入持有以 `wx` 创建的同目录 `<file>.lock`。**读-渲染-rename 循环在一把跨进程写锁下运行：指数退避、2 s 获取截止时间、5 s 后陈旧接管（持有者已崩溃；打破旧锁时给出告警）。读方从不加锁——rename 提交是原子的——因此竞争只发生在写方之间，毫秒级即可化解。锁的各项常量是协议不变式，不是配置：持有者只是重写一份小文档，截止时间与陈旧时限都从这一上界推得，而非出自部署偏好。
+
+**观察者 dispose 达到完全停稳。**watcher 携带一个 `active` 标志，排队的调用即将启动时先检查它，因此在调用等待期间已经运行过的释放器能让这次启动彻底不发生；已启动的调用会登记进服务级的 `pendingTails` 集合，dispose 排空除了等待各写队列，还会等待该集合。`settings/updated` 扇出会把监听器返回的 thenable 的 rejection 收容进与同步抛错相同的监听器诊断；事件契约现已写明 `INVARIANT` 重抛只服务同步监听器——不变式配套插件必须保持同步，而已交付的那个配套插件本就是同步的。
+
+**写入边界只放行 JSON 数据。**调用时刻的快照就是一次 `cloneJsonShaped` 遍历：它把 patch 从调用方分离出来，并在任何内容持久化之前拒绝一切非 JSON 值——Date、Map、BigInt、非有限数值、函数、symbol、类实例、值为 `undefined` 的数组元素、循环引用——拒绝时附带该值以 `$` 为根的路径。显式为 `undefined` 的对象条目仍会跳过（稀疏 patch 契约），这一契约如今在边界处强制执行，而不再放在 `mergeLayers` 内部。
+
+**YAML 编辑是叶子级 diff。**`renderYaml` 对比已存储分节与下一份分节，只对变化的值应用 `setIn`、对移除的键应用 `deleteIn`，并沿 map 递归。注释、锚点与格式在每个未触碰节点上、以及每个被改键值对的键节点上全部保留；数组等非 map 值在不相等时整体替换（`deepEqualJson` 是共享的判定谓词），其内部注释随之一并被带走。
+
+## 曾考虑的替代方案
+
+- **用 `proper-lockfile` 取代手写锁**——按“依赖优先于手写”政策做过权衡：该库几乎无人维护，其陈旧／重试策略比这个单文件协议所需的更宽泛，而已交付的锁约 40 行并带确定性测试（含注入的 `EEXIST`/`stat` 竞态）。该政策偏向能删除自有代码的依赖；这个依赖只会把 40 行带解释的代码换成一个不透明的等价物。
+- **用修订号/CAS 取代锁**——rename 表达不了 compare-and-swap，因此 CAS 需要一个版本伴随文件或内容重哈希，外加每个写方里的一个重试循环；锁用一个原语实现同样的串行化，还让读方完全免锁。
+- **把外部编辑合并进正在进行的写入自身的分节**——seam 是在调用时刻可见的状态之上合并 patch 的，因此与写入竞态的同 namespace 外部编辑仍按后写胜出解决；要把外部编辑并进来，需要三方合并语义，而没有任何消费方提出过这种需求。写入会先发布外部状态，落败一方至少在被取代之前被观察到。
+- **宣布不支持异步 `settings/updated` 监听器**——类型签名是 `void`，lint 也会标记误用的 promise，但未经 lint 的 JS 插件仍能注册异步监听器；契约里的一句说明无法收回已经抛出的 unhandled rejection，收容是唯一在运行时守得住的防线。
+- **保留 `structuredClone`、在提供方里做校验**——seam 才是持久化边界的所有者（每个提供方存储的都是 JSON 形态文档），而且在调用时刻拒绝能把违规值的路径给到调用方；提供方侧的检查要到合并之后才拒绝，归咎的是合并后的分节，而不是调用方传入的值。
+
+## 后果
+
+`update()` 有了成文的失败模式（锁截止时间到期、磁盘文档非法），rejection 消息携带以 `$` 为根的路径。仍然存在、且已记录在提供方 README 中的有：同 namespace 并发编辑仍是后写胜出（没有逐值合并，也没有修订号检查）；OS 从未投递的 watcher 事件会让缓存保持陈旧，直到下一个信号或下一次写入；被替换数组内部的注释、以及行内附着在被改标量值上的注释，会随其描述的值一起消失。
+
+[用户设置 seam note](2026-07-28-user-settings-seam.md)里“延后锁文件”那条替代方案已被本 note 取代。同类缺陷还存在于 `dsh-credentials-local`（两条链共用一个 `.env`、按缓存整文件写回、持久化之后才发事件）与堆叠分支上的 `llm/adapters-updated` 扇出；这些修复归引入相应包（package）的那些 PR（Pull Request）所有，向上合并时按本模板处理。
@@ -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
@@ -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.
@@ -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。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md
-2026-07-28-themed-scrollbars-and-reserved-gutter.md: 38228c868bb00210118e8110feb722fb81d0d56c
-2026-07-28-themed-scrollbars-and-reserved-gutter.zh.md: 9fafe1faa9303b5e2e23a1b3064904f71494026d
+2026-07-28-themed-scrollbars-and-reserved-gutter.md: b45f70b126d083916c756afb88a8b646a4e9bb85
+2026-07-28-themed-scrollbars-and-reserved-gutter.zh.md: 8afa36429ce7e6e061b014d63dcb20e5a642a84c
@@ -20,13 +20,13 @@ The rules sit on `body`, not `html`. `design-platform.css` declares the `--dsw-a

 The two renderings are mutually exclusive, and the exclusion is enforced rather than assumed. A non-`auto` `scrollbar-width` or `scrollbar-color` makes Chromium and Safari discard every `::-webkit-scrollbar*` rule for that element, `::-webkit-scrollbar-thumb:hover` included. Declaring both unconditionally therefore leaves the hover token rendering nowhere at all: the engines that implement the hover pseudo-element are exactly the ones the standard properties silence, and Firefox has no hover pseudo-element to fall back on. The standard properties consequently sit inside `@supports not selector(::-webkit-scrollbar)`, which is true only where the pseudo-element is unimplemented, so Firefox takes the standard path and WebKit-based engines take the pseudo-element path. The WebKit rules are not gated in turn: an engine without those pseudo-elements drops them as unknown selectors, so a gate would only restate what selector matching already does. An engine too old for the `selector()` function makes the condition invalid, which evaluates false and selects the pseudo-element path — the correct side for the pre-16.4 Safari that is the realistic case for that reading.

-Both paths read one indirection pair, `--dsh-scrollbar-thumb` and `--dsh-scrollbar-thumb-hover`, bound on `body` to the l1 (base-surface) tokens. **This is the rebinding contract, and it is the part the CSS alone does not state**: an elevated surface sets `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` and `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)` on its own container, and that one rebind reaches the standard properties and the WebKit pseudo-elements together. The pair is rebound as a pair; rebinding the resting thumb alone leaves the hover state on the base-surface token. Eight surfaces rebind today: the command popup, the slash menu, the model-select panel, the settings panel, the shared `ui-primitives` menu card, the composer input card, the question composer card, and the todo panel. Most declare it on the elevated card rather than on the scrolling descendant, because the elevation is a property of the surface and custom properties inherit down to whichever child actually scrolls.
+Both paths read one indirection pair, `--dsh-scrollbar-thumb` and `--dsh-scrollbar-thumb-hover`, bound on `body` to the l1 (base-surface) tokens. **This is the rebinding contract, and it is the part the CSS alone does not state**: an elevated surface sets `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` and `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)` on its own container, and that one rebind reaches the standard properties and the WebKit pseudo-elements together. The pair is rebound as a pair; rebinding the resting thumb alone leaves the hover state on the base-surface token. The mechanically discoverable subset is owned by `packages/client/ui-theme/tests/scrollbar-styles.spec.ts`: any sheet that both scrolls and paints an elevated surface must rebind, so this note no longer maintains a complete surface inventory. Most declare the pair on the elevated card rather than on the scrolling descendant, because elevation belongs to the surface and custom properties inherit to whichever child actually scrolls.

-The last four were missed in the first implementation and found in review, which is why the rebinding contract is now checked mechanically rather than by inspection: a sheet that scrolls somewhere and paints an elevated surface somewhere must rebind.
+Four surfaces — `Menu`, `InputBar`, `QuestionComposer`, and `TodoPanel` — were missed in the first implementation and found in review, which is why the per-sheet rebinding contract is checked mechanically rather than by inspection.

 The elevated set is resolved from the palette's own dark elevation ladder — the surface tokens whose dark value lands on `bg-layer-2` or `bg-layer-3`, which is the step the l1/l2 split encodes. Deriving it instead from the sheets that already rebind was the first attempt and is unsound: such a set can only confirm what someone already remembered, and a surface nobody has rebound yet — exactly the case the check exists for — defines itself as unelevated. `--dsw-specific-tip` proved it, resolving to the menu surface's rung while the todo panel scrolled on it unrebound and the derived check stayed green.

-Scope is by token family, not by geometry: only `--dsw-alias-bg-*` and `--dsw-specific-*` name a surface. `--dsw-alias-button-*`, `--dsw-alias-interactive-*`, and `--dsw-alias-markdown-*` reach the same rungs while naming a control or an inline span that no scroll container renders its bar against. Shape cannot make that call, since a floating button legitimately carries a radius, a shadow, and a fixed size. The check is per sheet rather than per rule because the card and the descendant that scrolls are separate rules, and CSS text does not express which contains which.
+Scope is by token family, not by geometry: only `--dsw-alias-bg-*` and `--dsw-specific-*` name a surface. `--dsw-alias-button-*`, `--dsw-alias-interactive-*`, and `--dsw-alias-markdown-*` reach the same rungs while naming a control or an inline span that no scroll container renders its bar against. Shape cannot make that call, since a floating button legitimately carries a radius, a shadow, and a fixed size. The check is per sheet rather than per rule because the card and the descendant that scrolls are separate rules. That approximation cannot detect a scrolling component embedded in an elevated card painted by another package's stylesheet, as `DirectoryBrowser` inside `Modal` demonstrated; cross-sheet composition remains a review and assembled-UI responsibility.

 The track and the corner stay transparent, so the thumb reads against whatever surface scrolls under it; only the thumb and its hover state carry a token color.

@@ -20,13 +20,13 @@ Status: implemented

 两种渲染互斥，而这种互斥是被强制的，不是假定的。`scrollbar-width` 或 `scrollbar-color` 只要取非 `auto` 值，Chromium 与 Safari 就会丢弃该元素上的全部 `::-webkit-scrollbar*` 规则，`::-webkit-scrollbar-thumb:hover` 也在其中。因此无条件地同时声明会让 hover token 在任何地方都得不到渲染：实现了 hover 伪元素的引擎，恰恰就是被标准属性静音的那些，而 Firefox 没有 hover 伪元素可作退路。于是标准属性写在 `@supports not selector(::-webkit-scrollbar)` 之内，该条件只在伪元素未被实现处为真，因此 Firefox 走标准属性路径，WebKit 系引擎走伪元素路径。WebKit 规则不再反向加门禁：不实现这些伪元素的引擎会把它们当作未知选择器丢弃，因此加门禁只是重述选择器匹配本身已经做的事。对于旧到不支持 `selector()` 函数的引擎，该条件无效，从而求值为假并选中伪元素路径——对于这条判断下现实存在的 16.4 之前的 Safari，这正是正确的一侧。

-两条路径都读取同一组间接变量 `--dsh-scrollbar-thumb` 与 `--dsh-scrollbar-thumb-hover`，它们在 `body` 上绑定到 l1（基础表面）token。**这就是重新绑定契约，也是单看 CSS 无法得知的部分**：抬升表面在自己的容器上设置 `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` 与 `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)`，这一次重新绑定同时作用于标准属性和 WebKit 伪元素。这组变量必须成对重新绑定；只改静止态滑块会让 hover 状态仍留在基础表面的 token 上。目前有八处抬升表面做了重新绑定：命令浮层、斜杠菜单、模型选择面板、设置面板、`ui-primitives` 共用菜单卡片、输入条卡片、提问组件卡片与待办面板。多数把声明写在抬升卡片上而非滚动的后代元素上，因为抬升层级是这个表面的属性，而自定义属性会继承到真正滚动的那个子元素。
+两条路径都读取同一组间接变量 `--dsh-scrollbar-thumb` 与 `--dsh-scrollbar-thumb-hover`，它们在 `body` 上绑定到 l1（基础表面）token。**这就是重新绑定契约，也是单看 CSS 无法得知的部分**：抬升表面在自己的容器上设置 `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` 与 `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)`，这一次重新绑定同时作用于标准属性和 WebKit 伪元素。这组变量必须成对重新绑定；只改静止态滑块会让 hover 状态仍留在基础表面的 token 上。可由机械检查发现的子集归 `packages/client/ui-theme/tests/scrollbar-styles.spec.ts` 所有：任何既滚动又绘制抬升表面的样式表都必须重新绑定，因此本 note 不再维护完整的表面清单。多数把这组变量声明在抬升卡片上而非滚动的后代元素上，因为抬升层级属于这个表面，而自定义属性会继承到真正滚动的那个子元素。

-后四处在最初的实现里被漏掉、由评审发现，因此重新绑定契约现在由机械检查把关，而不再依赖人工审阅：一张样式表只要在某处滚动、又在某处绘制抬升表面，就必须重新绑定。
+`Menu`、`InputBar`、`QuestionComposer` 与 `TodoPanel` 这四个表面在最初的实现里被漏掉、由评审发现，因此逐样式表的重新绑定契约由机械检查而非人工审阅把关。

 抬升表面集合是从调色板自身的暗色抬升阶梯解析出来的——暗色取值落在 `bg-layer-2` 或 `bg-layer-3` 上的那些表面 token，而这一档正是 l1/l2 之分所编码的层级差。最初的做法是从已经做了重新绑定的样式表反向推导，那是不成立的：这样得到的集合只能确认别人已经记得的部分，而尚无人重新绑定的表面——恰恰就是这项检查存在的理由——会把自己定义成「非抬升」。`--dsw-specific-tip` 证明了这一点：它解析到与菜单表面相同的那一档，待办面板在它上面滚动却没有重新绑定，而推导式的检查依然是绿的。

-判定范围依据 token 家族而非几何形状：只有 `--dsw-alias-bg-*` 与 `--dsw-specific-*` 表述的是表面。`--dsw-alias-button-*`、`--dsw-alias-interactive-*` 与 `--dsw-alias-markdown-*` 会落到相同档位，但它们表述的是控件或行内片段，没有任何滚动容器会把滚动条画在它们之上。形状无法做这个判断，因为悬浮按钮本来就会带圆角、阴影和固定尺寸。这项检查以样式表为粒度而非以规则为粒度，因为卡片与真正滚动的后代元素是两条不同的规则，而 CSS 文本无法表达谁包含谁。
+判定范围依据 token 家族而非几何形状：只有 `--dsw-alias-bg-*` 与 `--dsw-specific-*` 表述的是表面。`--dsw-alias-button-*`、`--dsw-alias-interactive-*` 与 `--dsw-alias-markdown-*` 会落到相同档位，但它们表述的是控件或行内片段，没有任何滚动容器会把滚动条画在它们之上。形状无法做这个判断，因为悬浮按钮本来就会带圆角、阴影和固定尺寸。这项检查以样式表为粒度而非以规则为粒度，因为卡片与真正滚动的后代元素是两条不同的规则。这种近似检查无法检测嵌在由另一个包的样式表绘制的抬升卡片中的滚动组件，`Modal` 内的 `DirectoryBrowser` 就证明了这一点；跨样式表的组合仍需在评审和组装后 UI 层面把关。

 轨道与两条滚动条相交的角落保持透明，因此滑块是以其下滚动的任何表面为背景被看到；只有滑块及其 hover 状态带 token 颜色。

@@ -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/2026-07-29-human-transcript-append-origin.md
+2026-07-29-human-transcript-append-origin.md: a296b93d538d9c28bd61ee8fd0530863b4bfd878
+2026-07-29-human-transcript-append-origin.zh.md: 96e0cd1038fe8904dfd4c1eceaae9b25339c5dca
@@ -0,0 +1,53 @@
+# Agent Note: The human transcript projects append-origin events
+
+Status: implemented
+
+English | [中文](2026-07-29-human-transcript-append-origin.zh.md)
+
+## Problem
+
+The terminal and the host history gateway both treated the model-visible surface as the human transcript. A successful compaction replaces a surface range with one checkpoint node, so the moment that replacement landed the terminal dropped every message it shadowed — conversation the user had already read — and re-ran that destructive rebuild on any later replacement. The same confusion reached pagination: `maxMessages` counted every `user/message`, `assistant/message`, and `steering/message` in the window, so a model-only replacement copy consumed a page slot the human never filled, and the cut could land between a compaction's log-only provenance and the replacement that cites it.
+
+Nothing was lost from the log. `Session.events` still held every original message and full tool result; the surface only decides what the model is sent next. The defect was entirely in the projection.
+
+## Decision
+
+Model and human projections are separate, and the event's own marker decides which one an event belongs to. `dsh-session` exports the marker split `isAppendSurfaceEvent(event)` and `isReplacementSurfaceEvent(event)` over the two `SurfaceOp` variants, from the browser-safe `surface` module. Append-origin events are the durable source for a transcript; replacement copies stay model-only. Everything that must send exactly what the model sees — `deriveMessages`, token accounting, the compaction backends, tool pairing, injected-context liveness, cross-session reference projection — keeps reading `session.surface`.
+
+The terminal replays the transcript from append-origin surface events and keeps a shadowed step's tool cards paired through `transcriptToolCallIds`, which reads the append-origin `assistant/message` rather than surface membership. A landed compaction contributes one dim `… earlier context was compacted …` row at its own log position: the marker reports where the model stopped seeing that history instead of erasing it. The framed checkpoint payload never renders, and both paths classify a surface event by the same marker, so a compaction that arrives live and the same log replayed after resume produce the same transcript. Only replay re-derives `tool/call` pairing: a call event carries no marker of its own and inherits membership from the `assistant/message` that advertised it, which the live listener has necessarily just rendered.
+
+A checkpoint is recognized through the compaction seam's own contract — `isCompactCheckpointSource`, the backend-independent marker `CompactService` requires on the replacement user message — so the terminal depends on the declared vocabulary, not on the shape of the replacement. `dsh-session-reference` already consumes that predicate to project another session's log; this is the same question asked by a different reader. Other replacements are silent: a pruned `tool/result` and a regenerated `assistant/message` rewrite one node for the model and mark no boundary in the conversation.
+
+`session.history` counts only append-origin messages toward `maxMessages`. Each page remains one contiguous raw event range, so a compaction's `compact/summary` provenance stays on the page of the replacement that cites it.
+
+No persisted event, RPC envelope, compaction transaction, or model-visible surface changed, and no migration is required.
+
+## Deferred
+
+The browser client still builds its conversation from the model surface through `FoldAdapter`, so compaction still collapses web history to a single context row. The same predicate is the fix there, together with an append-order transcript projection and a marker component; that work is a separate change against `packages/client/runtime` and `packages/client/ui-conversation`.
+
+That work must handle a page whose checkpoint cites a `surfaceOp.start` outside the window: pagination no longer spends quota on the checkpoint, so it never cuts on the checkpoint's provenance group, and `FoldAdapter` pads absent events with a non-surface sentinel — so `SurfaceManager` rejects the range and `nodes()` falls back to `degradedSeqs()` with a logged error. The hole predates this change (counting could already run past a checkpoint into the range it shadows), but the old rule accidentally covered the case where the checkpoint was the oldest counted message and pulled the whole shadowed range onto its page. `degradedSeqs()` — every surface-eligible event in append order — is already close to the transcript projection A2 needs, which is the shape to build deliberately rather than reach as a degradation. Rendering compaction *progress* — a terminal indicator while a compaction runs — needs the bracket-first ordering that the queued manual `/compact` work introduces, and is likewise out of scope here. The marker also carries no scale: the checkpoint's `sourceEventSeqs` already hold the shadowed count, so a count or range would tell a reader how much each row folded. That belongs with progress, where the reader meets the other half of the same information. Whoever takes it should fold the terminal's two replacement branches — replay and the live listener, textually identical and 600 lines apart — into one `renderReplacement(event)` first, so the marker's content has a single home.
+
+## Alternatives considered
+
+**Recognize a checkpoint by shape (a replacement `user/message`).** Rejected: it reads a coincidence of today's producers instead of a declared contract, and any future producer that replaces a range with a user message would silently inherit the compaction marker. The seam already publishes `COMPACT_CHECKPOINT_SOURCE` precisely so consumers can recognize a checkpoint independently of the backend.
+
+**Keep rendering the checkpoint as an injected-context card.** Rejected: the framed checkpoint is an instruction envelope written for the model, not human conversation content. Showing it while hiding the history it replaced inverts what the reader needs.
+
+**Persist a second display transcript.** Rejected: the append-only log already contains the authoritative source material, so a parallel record buys nothing and adds migration and consistency work.
+
+**Derive the marker from the `compact/*` bracket instead of the checkpoint.** Rejected for the transcript: the bracket is a pair of time-point markers around an operation, while the transcript needs the position where the surface actually changed. The bracket is the right source for progress and duration, which this change does not render.
+
+**Classify events by re-folding the log, as `session-query` does for search (`current` / `shadowed` / `log-only`).** Rejected: a fold answers a whole-log question, while a projection asks a per-event one that the event's own marker already answers in constant time.
+
+## Consequences
+
+Compaction no longer erases terminal history; a session compacted several times shows one marker per landed compaction, in log order. Pagination pages can carry more raw events than before, because quota is spent only on messages a human or model actually produced.
+
+`rebuildTranscript` now materializes a component per append-origin event in the whole log, and it runs on mount, on a terminal color-scheme change, and on every reasoning toggle. Compaction used to bound that work for exactly the long sessions compaction serves, so the cost now grows with session length instead of with the surface. That is the trade the fix exists to make — preserved history is the point — but a windowing or reuse strategy belongs to whoever first measures a slow rebuild, not to a later profiler wondering why the work grew.
+
+`dsh-tui` gains a dependency on the `dsh-compact` seam for one pure predicate, mirroring `dsh-session-reference`'s existing use. The terminal still needs no compaction backend at runtime.
+
+Two behaviors changed with their tests. The surface-replacement terminal test previously pinned erasure ("hides shadowed tool calls") and now pins preservation plus exactly one marker, including a pruned result copy, a regenerated assistant message, and a foreign plugin's replacement all rendering nothing. The compaction snapshot scenario wrote a `workspace-context` source while claiming to pin compaction; it now writes a real checkpoint source, and its three fixtures are re-recorded to show the preserved prompt, the full tool card, and the marker.
+
+The live/replay equivalence above is fixture-pinned, not only asserted here: `surface-replayed-compaction` mounts with the replacement already stored and records byte-identical to the live path's `surface-after-compaction-wide`. Changing either path breaks that equality, which is the point — the resume projection is what regressed for users, and the two fixtures must move together.
@@ -0,0 +1,53 @@
+# Agent Note: 人类可读记录投影追加来源的事件
+
+Status: implemented
+
+[English](2026-07-29-human-transcript-append-origin.md) | 中文
+
+## Problem
+
+终端与宿主历史网关都把模型可见的 surface 当作人类可读记录（transcript）。一次成功的压缩（compaction）会用一个检查点节点替换一段 surface 范围，因此该替换一落地，终端就丢弃了它所遮蔽的每条消息——那些是用户已经读过的对话——并在此后任何替换到来时重新执行这次破坏性重建。同样的混淆也波及分页：`maxMessages` 统计窗口内的每个 `user/message`、`assistant/message` 和 `steering/message`，于是仅供模型使用的替换副本占用了一个人类从未填充的页面额度，而切分点还可能落在压缩的仅日志溯源信息与引用它的替换之间。
+
+日志本身没有丢失任何内容。`Session.events` 仍保存着每条原始消息和完整的工具结果；surface 只决定接下来发送给模型的内容。缺陷完全在投影层。
+
+## Decision
+
+模型投影与人类投影是分开的，而事件属于哪一种由事件自身的标记决定。`dsh-session` 在浏览器安全的 `surface` 模块中导出按两种 `SurfaceOp` 变体划分的谓词 `isAppendSurfaceEvent(event)` 与 `isReplacementSurfaceEvent(event)`。追加来源的事件是记录的持久来源，替换副本仅供模型使用。凡是必须准确发送模型所见内容的部分——`deriveMessages`、token 记账、压缩后端、工具配对、注入上下文的存活判断、跨会话引用投影——都继续读取 `session.surface`。
+
+终端从追加来源的 surface 事件回放记录，并通过 `transcriptToolCallIds` 让被遮蔽步骤的工具卡片保持配对：该函数读取追加来源的 `assistant/message`，而不是 surface 成员关系。已落地的压缩会在其自身日志位置贡献一行暗色 `… earlier context was compacted …`：这行标记报告模型从何处起不再看到那段历史，而不是把它抹掉。带框的检查点载荷从不渲染，且两条路径都按同一个标记对 surface 事件分类，因此实时到达的压缩与恢复后回放同一份日志会产生相同的记录。只有回放会重新推导 `tool/call` 的配对关系：调用事件自身不携带标记，其归属继承自公布它的 `assistant/message`，而实时监听器必然刚刚渲染过后者。
+
+检查点通过压缩接缝自身的契约来识别——`isCompactCheckpointSource`，即 `CompactService` 要求替换用户消息携带的、与后端无关的标记——因此终端依赖的是已声明的词汇，而不是替换的形态。`dsh-session-reference` 已经在用该谓词投影另一个会话的日志；这里只是另一个读者提出同样的问题。其他替换保持静默：被裁剪的 `tool/result` 与重新生成的 `assistant/message` 只是为模型重写一个节点，并不在对话中标出边界。
+
+`session.history` 只把追加来源的消息计入 `maxMessages`。每一页仍是一段连续的原始事件区间，因此压缩的 `compact/summary` 溯源信息会与引用它的替换留在同一页。
+
+持久事件、RPC 信封、压缩事务与模型可见的 surface 都没有变化，也不需要迁移。
+
+## Deferred
+
+浏览器客户端仍通过 `FoldAdapter` 从模型 surface 构建会话，因此压缩在 Web 端仍会把历史折叠成一行上下文。那里的修复用的是同一个谓词，另需按追加顺序的记录投影与一个标记组件；该工作是针对 `packages/client/runtime` 与 `packages/client/ui-conversation` 的独立变更。
+
+该工作必须处理这样一页：其检查点引用的 `surfaceOp.start` 落在窗口之外。分页不再为检查点消耗额度，因此永远不会按检查点的溯源分组切分；而 `FoldAdapter` 会用一个非 surface 的哨兵事件填补缺失事件——于是 `SurfaceManager` 拒绝该范围，`nodes()` 退化为 `degradedSeqs()` 并记录一条错误。这个缺口早于本次变更（此前计数就可能越过检查点进入它所遮蔽的范围），但旧规则恰好覆盖了这样一种情形：检查点是最旧的被计数消息，其溯源分组把整段被遮蔽的范围一起拉到该页。`degradedSeqs()`——按追加顺序的每个 surface 可入事件——已经很接近 A2 所需的记录投影，因此那正是应当刻意构建的形态，而不是作为退化路径被动落到的结果。渲染压缩*进度*——压缩运行期间的终端指示——需要排队式手动 `/compact` 工作引入的“先开括号”顺序，同样不在本次范围内。标记同样不携带规模信息：检查点的 `sourceEventSeqs` 已经包含被遮蔽的数量，因此一个计数或区间可以告诉读者每一行折叠了多少内容。这件事属于进度那一侧，读者正是在那里遇到同一份信息的另一半。接手者应当先把终端里两处替换分支——回放与实时监听器，文本完全相同却相隔 600 行——合并为一个 `renderReplacement(event)`，让标记的内容只有一个归处。
+
+## Alternatives considered
+
+**按形态识别检查点（一个替换型 `user/message`）。** 被否决：那读取的是当前生产者的巧合而非已声明的契约，而未来任何用用户消息替换一段范围的生产者都会静默地继承压缩标记。接缝已经发布 `COMPACT_CHECKPOINT_SOURCE`，正是为了让消费方与后端无关地识别检查点。
+
+**继续把检查点渲染为注入上下文卡片。** 被否决：带框的检查点是为模型撰写的指令信封，不是人类对话内容。展示它却隐藏它替换掉的历史，正好颠倒了读者的需要。
+
+**持久化第二份展示用记录。** 被否决：仅追加的日志已经包含权威源材料，平行记录换不来任何东西，反而增加迁移与一致性工作。
+
+**用 `compact/*` 括号而不是检查点来推导标记。** 就记录而言被否决：括号是围绕一次操作的一对时间点标记，而记录需要的是 surface 真正发生变化的位置。括号适合作为进度与耗时的来源，而本次变更并不渲染这些。
+
+**像 `session-query` 为搜索所做的那样重新折叠日志来分类事件（`current`／`shadowed`／`log-only`）。** 被否决：折叠回答的是整份日志的问题，而投影问的是逐事件的问题，事件自身的标记已能以常数时间给出答案。
+
+## Consequences
+
+压缩不再抹掉终端历史；被压缩多次的会话会按日志顺序显示每次落地压缩对应的一行标记。分页的每一页可以携带比以前更多的原始事件，因为额度只花在人类或模型真正产生的消息上。
+
+`rebuildTranscript` 现在会为整份日志中的每个追加来源事件物化一个组件，并在挂载时、终端配色方案变化时以及每次切换 reasoning 时运行。压缩此前正好为压缩所服务的那些长会话限制了这项工作量，因此这份开销现在随会话长度增长，而不再随 surface 增长。这正是本次修复要做的取舍——保留历史才是目的——但窗口化或复用策略属于第一个真正测到重建变慢的人，而不属于日后某个疑惑工作量为何增长的性能分析者。
+
+`dsh-tui` 为一个纯谓词新增了对 `dsh-compact` 接缝的依赖，与 `dsh-session-reference` 现有用法一致。终端在运行时仍然不需要任何压缩后端。
+
+两项行为随其测试一起改变。表层替换的终端测试此前钉住的是抹除（“隐藏被遮蔽的工具调用”），现在钉住的是保留加恰好一行标记，其中被裁剪的结果副本、重新生成的 assistant 消息以及来自其他插件的替换都不渲染任何内容。压缩快照场景此前声称钉住压缩，却写入了 `workspace-context` 来源；现在它写入真实的检查点来源，并重新录制三份 fixture，以显示被保留的提示、完整的工具卡片和那行标记。
+
+上文的实时／回放等价性由 fixture 钉住，而不只是在此断言：`surface-replayed-compaction` 在挂载时替换已经存在，其录制结果与实时路径的 `surface-after-compaction-wide` 逐字节一致。改动任一路径都会破坏这项相等——这正是要点：回放投影才是当初对用户造成回归的部分，两份 fixture 必须一起变动。
@@ -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
@@ -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.
@@ -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。
@@ -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/2026-07-17-dedicated-full-screen-tui-front-door.md
-2026-07-17-dedicated-full-screen-tui-front-door.md: 10564b110cc2e56615bde86830c0d39d5a7cee38
-2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 4624a4db3db598793eee257f829a080f4d7ad711
+2026-07-17-dedicated-full-screen-tui-front-door.md: c011a0284ea0efe59693785c038f814a866068ac
+2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 5aea4ac0c5a3b29c098c297e514fab49caf643ff
@@ -20,7 +20,7 @@ The selected front door receives the exact generated or resumed `SessionId` used

 ### Session projection and interaction

-The TUI rebuilds the transcript from the active `session.surface` and reprojects it whenever an event carries a `surfaceOp`, so resumed and compacted history matches the model-visible conversation. It renders Markdown text and reasoning, including fenced code with hidden Markdown markers, a dim optional language label, and a code-colored body, token totals, the latest `todo/write` plan, and tool cards produced through each tool definition's `presentCall` and `presentResult` methods. Long card bodies retain a configurable head/tail preview with the hidden-line count; one terminal control expands or collapses every card. Pending chunks and tool calls update the same components that completed events settle.
+The TUI rebuilds the transcript from the append-origin session events, so resumed history keeps every message the reader already saw; a compacted range stays readable behind one marker instead of matching the model-visible conversation ([append-origin transcript](../bug-fix/2026-07-29-human-transcript-append-origin.md)). It renders Markdown text and reasoning, including fenced code with hidden Markdown markers, a dim optional language label, and a code-colored body, token totals, the latest `todo/write` plan, and tool cards produced through each tool definition's `presentCall` and `presentResult` methods. Long card bodies retain a configurable head/tail preview with the hidden-line count; one terminal control expands or collapses every card. Pending chunks and tool calls update the same components that completed events settle.

 Editor input calls `agent.send()` while idle and `agent.steer()` while a turn is running. Cancellation, reasoning visibility, tool-card expansion, redraw, transcript clearing, and exit are terminal-only controls. `/exit` and `/quit` share the same exit path: they cancel an active turn, wait for idle, and then restore and close the terminal. The idle footer derives context occupancy from `tokenMeter` and shows the selected model and explicit reasoning effort; during a run, elapsed activity and the Escape interrupt hint replace that summary. `/status` remains available in either state and appends a detailed terminal-only snapshot: session identity and timestamps, selected model, reasoning effort/default state and reasoning visibility, lifecycle counts folded from the event log, the same deduplicated usage buckets and KV-cache rate as the footer, and context use from `tokenMeter` plus the selected model's advertised capacity. The plugin registers the shared `userInteraction` provider and presents queued questions in a wide bottom-left keyboard panel with batch progress, numbered options, and aligned descriptions; the panel's controls hint lists only actions meaningful for the current option count, omitting navigation when exactly one option is shown; agent behavior and answer logging remain owned by their existing services.

@@ -47,6 +47,6 @@ The implemented [TUI terminal-state snapshot Agent Note](../testing/2026-07-18-t

 - Interactive terminal work has a stateful Markdown, card, plan, and question interface with no second terminal protocol to keep aligned.
 - The TUI carries a pi-tui dependency and a strict TTY requirement; non-TTY deployments use the Headless app or a structured protocol.
- Session projection makes resume and compaction consistent with the durable conversation, but one configured session owns the transcript and editor.
+- Session projection makes resume consistent with the durable conversation, but one configured session owns the transcript and editor.
 - Tool packages extend terminal cards through their existing presentation methods without adding tool-specific branches to the TUI.
 - Model and reasoning-effort selection use adapter-advertised metadata without turning catalog membership into request validation; unused selections are not durable state.
@@ -20,7 +20,7 @@ DeepSeek Harness 将 [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README

 ### 会话投影与交互

-TUI 从活跃的 `session.surface` 重建 transcript（文本记录），并在事件携带 `surfaceOp` 时重新投影，因此恢复或压缩后的历史与模型可见会话保持一致。TUI 渲染 Markdown 文本与推理（其中围栏代码块隐藏 Markdown 标记、保留一个暗色的可选语言标签，并使用代码配色的正文）、token 用量、最新 `todo/write` 计划，以及各工具定义通过 `presentCall` 和 `presentResult` 方法生成的工具卡片。较长的工具卡片正文会保留可配置的头尾预览，并显示隐藏行数；一个终端控制可以展开或收起全部卡片。进行中的分片与工具调用会更新同一组组件，随后由完成事件收束状态。
+TUI 从追加来源的会话事件重建 transcript（文本记录），因此恢复后的历史会保留读者已经看到的每条消息；被压缩的范围不再与模型可见会话保持一致，而是留在一行标记之后仍可阅读（[追加来源的 transcript](../bug-fix/2026-07-29-human-transcript-append-origin.md)）。TUI 渲染 Markdown 文本与推理（其中围栏代码块隐藏 Markdown 标记、保留一个暗色的可选语言标签，并使用代码配色的正文）、token 用量、最新 `todo/write` 计划，以及各工具定义通过 `presentCall` 和 `presentResult` 方法生成的工具卡片。较长的工具卡片正文会保留可配置的头尾预览，并显示隐藏行数；一个终端控制可以展开或收起全部卡片。进行中的分片与工具调用会更新同一组组件，随后由完成事件收束状态。

 agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调用 `agent.steer()`。取消、推理显隐、工具卡片展开、重绘、清空 transcript 和退出都只是终端控制。`/exit` 和 `/quit` 共用同一条退出路径：先取消进行中的轮次，等待 agent 空闲，然后恢复并关闭终端。空闲态页脚根据 `tokenMeter` 得出上下文占用率，并显示所选模型和显式选定的推理强度；agent 运行期间，该摘要会替换为带已用时长的活动指示和 Escape 中断提示。`/status` 在这两种状态下均可用，并会追加一份仅在终端显示的详细快照，其中包括会话标识与时间戳、所选模型、推理强度（或默认状态）及推理显隐状态、从事件日志归并得出的生命周期计数、与页脚一致的去重用量分项和 KV 缓存命中率，以及 `tokenMeter` 给出的上下文用量和所选模型公布的容量。插件注册共享的 `userInteraction` 提供方，在左下角宽幅键盘操作面板中呈现排队的问题，面板显示批次进度、带编号的选项和对齐的描述；面板的操作提示只列出在当前选项数量下有意义的操作，仅有一个选项时不显示导航项；agent 行为和答案日志仍由既有服务负责。

@@ -47,6 +47,6 @@ agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调

 - 交互式终端拥有带状态的 Markdown、卡片、计划和提问界面，无需再对齐第二套终端协议。
 - TUI 会引入 pi-tui 依赖并严格要求 TTY；非 TTY 部署使用 Headless app 或结构化协议。
- 会话投影使恢复和压缩与持久会话保持一致，但只有一个已配置会话拥有 transcript 和编辑器。
+- 会话投影使恢复与持久会话保持一致，但只有一个已配置会话拥有 transcript 和编辑器。
 - 工具包通过既有呈现方法扩展终端卡片，无需在 TUI 中增加工具专用分支。
 - 模型和推理强度选择使用适配器公布的元数据，但不会把目录成员关系变成请求校验；未使用的选择不属于持久化状态。
@@ -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
@@ -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.
@@ -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。
@@ -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
@@ -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.
@@ -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。
@@ -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-addressable-queue-operations.md
-2026-07-29-addressable-queue-operations.md: 78a7d346163bb7e5e76c989c6e93576b4a6cee64
-2026-07-29-addressable-queue-operations.zh.md: 050b9755ad4ebe70e2bdcafb711ef279331e27af
+2026-07-29-addressable-queue-operations.md: 7a08b889c958e583dc430d33a1855fe3725f3d48
+2026-07-29-addressable-queue-operations.zh.md: 701b028c7494fd7cb608d05a5d170c9075b155d7
@@ -18,7 +18,7 @@ The Web queue rendered pending messages but could not edit or delete one row. `M

 **Queue addresses require a live Agent.** `session.updateQueue` queries only the mounted Agent registry and never resumes a cold session: an `InboxItemId` is process-local and cannot name work after restart or disposal. A missing Agent and a driver-claimed occurrence both return `queue-item-not-found`.

-**Web actions address Queue only.** The Host excludes pending steering from `session/queue`; steering retains its existing durable transcript path after consumption. QueueDock exposes edit and delete, but no send-now control. The UI derives queue row and mutation types from the runtime `SessionFace` contract rather than importing the connection plugin, so plugin cooperation continues through services and snapshots. Edit is available only when all content blocks are text; the editor cannot silently drop non-text blocks. An editing row exposes only save and cancel, with Enter and Escape as their keyboard equivalents. Delete removes the exact occurrence.
+**Web actions address Queue only.** The Host excludes pending steering from `session/queue`; steering retains its existing durable transcript path after consumption. QueueDock hides while empty, renders one pending occurrence directly, and defaults two or more occurrences to a collapsed `"<n> 条排队消息"` header that expands or collapses the complete list. The header exposes `aria-expanded` and `aria-controls`; the expanded list scrolls within a 180px height bound. An active edit or mutation keeps its rows visible, and emptying the queue restores the collapsed default for the next queue. Visible rows expose edit and delete, but no send-now control. The UI derives queue row and mutation types from the runtime `SessionFace` contract rather than importing the connection plugin, so plugin cooperation continues through services and snapshots. Edit is available only when all content blocks are text; the editor cannot silently drop non-text blocks. An editing row exposes only save and cancel, with Enter and Escape as their keyboard equivalents. Delete removes the exact occurrence.

 ## Alternatives considered

@@ -34,7 +34,7 @@ The Web queue rendered pending messages but could not edit or delete one row. `M

 ## Verification

-AgentLoop contract tests hold prompt admission while editing and removing exact queued occurrences, reject mutations of steering occurrences, and verify the resulting independent turn and terminal lifecycle events. Host schema and proxy tests cover queued-only authoritative snapshots, synchronous re-entrant mutation order, reconnect, cold-Agent rejection, typed not-found errors, and the RPC transport. Client runtime and QueueDock tests cover non-optimistic projection, text-only editing, save and cancel affordances, removal, retirement races, and disabled mixed-content editing. Keyless browser scenarios drive the exposed edit and delete actions through the built Web composition and real HTTP/SSE wire.
+AgentLoop contract tests hold prompt admission while editing and removing exact queued occurrences, reject mutations of steering occurrences, and verify the resulting independent turn and terminal lifecycle events. Host schema and proxy tests cover queued-only authoritative snapshots, synchronous re-entrant mutation order, reconnect, cold-Agent rejection, typed not-found errors, and the RPC transport. Client runtime and QueueDock tests cover non-optimistic projection, single-row presentation, default multi-row collapse, interaction-forced visibility, reset after emptying, expansion, text-only editing, save and cancel affordances, removal, retirement races, and disabled mixed-content editing. Keyless browser scenarios capture the default collapsed header before expanding the queue and driving its exposed edit and delete actions through the built Web composition and real HTTP/SSE wire.

 ## Consequences

@@ -18,7 +18,7 @@ Web 队列能够渲染待处理消息，但无法编辑或删除其中某一行

 **Queue 寻址要求 Agent 存活。** `session.updateQueue` 只查询已挂载的 Agent 注册表，绝不恢复冷会话：`InboxItemId` 属于进程本地标识，无法在重启或资源释放后继续指向工作。Agent 缺失和单次入队项已被驱动器认领这两种情况都返回 `queue-item-not-found`。

-**Web 操作只面向 Queue。** Host 从 `session/queue` 中排除待处理 steering；steering 消费后仍沿用既有的持久 transcript（文本记录）路径。QueueDock 暴露编辑和删除，不提供立即发送控件。UI 从运行时 `SessionFace` 契约派生队列行与变更类型，而不是导入连接插件，因此插件仍通过服务和快照协作。仅当所有内容块都是文本时才提供编辑功能；编辑器不能静默丢弃非文本块。编辑中的行只展示保存和取消操作，对应的键盘操作分别是 Enter 和 Escape。删除会移除对应的精确入队项。
+**Web 操作只面向 Queue。** Host 从 `session/queue` 中排除待处理 steering；steering 消费后仍沿用既有的持久 transcript（文本记录）路径。QueueDock 在队列为空时隐藏，只有一个待处理项时直接渲染该行，存在两个或更多待处理项时则默认收起为可展开或收起完整列表的 `"<n> 条排队消息"` 表头。表头暴露 `aria-expanded` 和 `aria-controls`；展开后的列表以 180px 为高度上限，并可滚动。存在进行中的编辑或变更时，列表行会保持可见；队列清空后，下一次出现队列时会恢复默认收起状态。可见行暴露编辑和删除操作，不提供立即发送控件。UI 从运行时 `SessionFace` 契约派生队列行与变更类型，而不是导入连接插件，因此插件仍通过服务和快照协作。仅当所有内容块都是文本时才提供编辑功能；编辑器不能静默丢弃非文本块。编辑中的行只展示保存和取消操作，对应的键盘操作分别是 Enter 和 Escape。删除会移除对应的精确入队项。

 ## 考虑过的替代方案

@@ -34,7 +34,7 @@ Web 队列能够渲染待处理消息，但无法编辑或删除其中某一行

 ## 验证

-AgentLoop 契约测试会在编辑和移除精确 queued 入队项时阻塞提示词接纳，拒绝对 steering 入队项的变更，并验证所得独立轮次及终态生命周期事件。Host schema 与代理测试覆盖仅含 queued 项的权威快照、同步可重入变更顺序、重连、拒绝冷 Agent、类型化 not-found 错误和 RPC 传输。客户端运行时和 QueueDock 测试覆盖非乐观投影、仅文本编辑、保存与取消入口、移除、退役竞态，以及禁用混合内容编辑。无密钥浏览器场景会通过构建后的 Web 组合和真实 HTTP／SSE 协议操作公开的编辑和删除。
+AgentLoop 契约测试会在编辑和移除精确 queued 入队项时阻塞提示词接纳，拒绝对 steering 入队项的变更，并验证所得独立轮次及终态生命周期事件。Host schema 与代理测试覆盖仅含 queued 项的权威快照、同步可重入变更顺序、重连、拒绝冷 Agent、类型化 not-found 错误和 RPC 传输。客户端运行时和 QueueDock 测试覆盖非乐观投影、单行呈现、多行默认收起、交互期间强制保持可见、清空后重置、展开、仅文本编辑、保存与取消入口、移除、退役竞态，以及禁用混合内容编辑。无密钥浏览器场景会先捕获默认收起的表头，再展开队列，并通过构建后的 Web 组合和真实 HTTP／SSE 协议操作其公开的编辑和删除。

 ## 后果

@@ -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/2026-07-29-directory-picker-adaptive-default.md
+2026-07-29-directory-picker-adaptive-default.md: 7ff6529bb8e445f63343b1019ac520f56b19d5e4
+2026-07-29-directory-picker-adaptive-default.zh.md: a2a2d8ec4c91a347eedfc3aa3413b091ee847934
@@ -0,0 +1,30 @@
+# Agent Note: Adaptive default for the directory-picker interaction
+
+Status: implemented
+
+English | [中文](2026-07-29-directory-picker-adaptive-default.zh.md)
+
+## Problem
+
+The [directory-picker seam](../architecture/2026-07-28-directory-picker-capability-seam.md) made the interaction a `cordis.yml` swap point, but the shipped composition still had to pin one backend: `-browse` everywhere meant a local operator never got the OS chooser, `-native` everywhere breaks every remote deployment. The right default depends on facts only the running host knows — where the server binds, whether the process was launched over SSH, whether a display session exists — so no static row is correct for all deployments.
+
+## Decision
+
+A third sibling package, **`dsh-host-directory-picker-auto`**: a node-half-only *chooser* that owns no picking code and no UI. Its `apply` samples the host facts exactly once at boot — bind host from the injected `httpServer` (a new `host` getter mirrors the existing `port`), `SSH_CONNECTION`/`SSH_TTY`, platform, `DISPLAY`/`WAYLAND_DISPLAY`, and a `PATH` probe for a Linux chooser binary (zenity/kdialog) — resolves them through one exported pure function, and mounts the chosen dual-face backend with `ctx.loader.create({name})` into the Loader's **in-memory root tree**; the effect's disposer removes the entry and joins the backend fiber's teardown (`remove()` alone only starts it), so unloading the chooser settles only after the backend quiesced. `native` requires every attended-and-servable signal: loopback bind ∧ no SSH markers ∧ a display session the native backend can drive — assumed on darwin/win32, requiring `DISPLAY`/`WAYLAND_DISPLAY` plus a chooser binary on linux, and never true elsewhere (the native backend supports exactly darwin/win32/linux). Anything ambiguous resolves to `browse`, which works everywhere. `apps/cli` now mounts `-auto` as its `directory-picker` row; composing `-native` or `-browse` directly remains the pin.
+
+Why entry-level mounting is the load-bearing mechanism: the client module table (`dsh-client-modules`) reconciles **Loader entries** reactively over `internal/plugin`, so a backend mounted as a real entry gets its browser half discovered exactly as a config-row's would be — the seam's one-row-swaps-both-faces invariant survives adaptivity with zero duplicated client code. The dev HMR row (`AppCLIEntry`) is the mechanism precedent. Root-tree targeting matters: the root tree's `write()` is a no-op, so the resolved row can never be persisted back into `cordis.yml` (the Include subtree *does* write).
+
+## Alternatives considered
+
+- **Boot-glue resolution in `AppCLIEntry`** (ship both rows with static `disabled`, patch `disabled` from a `--directory-picker=auto|native|browse` flag). Works — `PatchOptions` patches metadata, and the modules scan skips disabled rows — but leaves the decision app-private where every future composition re-implements it; the chooser plugin gives any `cordis.yml` the same one-row adaptivity. Reintroduce the flag only when a deployment needs to *force* a backend without editing its yml.
+- **One merged plugin branching per call** (client tries `pick`, falls back to the browse dialog on `directory-picker-unavailable`). Rejected: the client would need both flows in one bundle — the bundle-purity gate forbids cross-plugin value imports and jscpd forbids copying the dialog — and per-call probing pays a doomed RPC on every open of a browse host.
+- **Resurrecting the wire advertisement** so both client flows mount and branch on the host's kind. Rejected: reverses the seam note's deletion for no consumer the chooser doesn't already serve, and collides with the `single` directory-flow holes.
+- **Per-connection adaptivity** (native for a loopback browser, browse for a remote one, same server). Deferred: needs a per-client capability, the advertisement above, and both flows mounted; no deployment serves both operator shapes at once today.
+
+## Consequences
+
+- The shipped web GUI adapts out of the box: attended local host → OS chooser; SSH launch, all-interfaces bind, headless host, unsupported platform, or Linux without a chooser binary → in-app browser. Detection infers operator location from launch context, which no launch-side signal can prove: a detached tmux session loses `SSH_*`; a non-Aqua darwin process still counts as displayed; and the `ssh -L` shape (a workstation-local launch later reached through a forwarded port, arriving from `127.0.0.1`) resolves `native` and opens the chooser on the unattended workstation — per-connection adaptivity could not fix that last case either. A wrong `native` choice degrades to the backend's existing retryable failure dialog; deployments in these shapes compose `-browse` directly.
+- The chooser mounts backends by runtime string (`BACKEND_PACKAGES`, exported), which yml-row scanning cannot see; `verify-cordis-config` therefore requires every composition mounting `-auto` to declare both backends as dependencies, so keyless Linux CI (which only ever resolves `browse`) cannot hide a dropped `-native` dependency. The shipped-tree web e2e/snapshot lane (`apps/web/tests/scaffold.ts`) pins `-browse` by disable+insert patch — its goldens are interaction-specific and must not depend on the host running the suite.
+- One resolution per boot keeps the seam's capability-stability contract; per-connection shapes remain out of scope until a deployment demands them.
+- Mounting the chooser **and** a backend row together fails loud (duplicate `directoryPicker` service; duplicate flow in the `single` holes).
+- The host typecheck aggregate now references the two backend projects (declarations only, node entries carry no client merge) so the chooser's REAL-composition test can mount them — the mirror of the client aggregate's `webserver` reference.
@@ -0,0 +1,30 @@
+# Agent Note：目录选择交互的自适应默认值
+
+状态：已实现
+
+[English](2026-07-29-directory-picker-adaptive-default.md) | 中文
+
+## 问题
+
+[目录选择 seam](../architecture/2026-07-28-directory-picker-capability-seam.md)把交互形态做成了 `cordis.yml` 的切换点，但随附的组合仍必须固定一个后端：处处用 `-browse` 意味着本地操作者永远得不到 OS 选择器，处处用 `-native` 则弄坏所有远程部署。正确的默认值取决于只有运行中的宿主才知道的事实——服务器绑定在哪里、进程是否经 SSH 启动、是否存在显示会话——因此没有哪一静态行对所有部署都正确。
+
+## 决策
+
+第三个同级包 **`dsh-host-directory-picker-auto`**：一个只有 node 半侧的*选择器*，不持有任何选取代码，也没有 UI。它的 `apply` 在启动时恰好采样一次宿主事实——从注入的 `httpServer` 读绑定宿主（新增的 `host` getter 与既有的 `port` 对称）、`SSH_CONNECTION`／`SSH_TTY`、平台、`DISPLAY`／`WAYLAND_DISPLAY`、以及对 Linux 选择器二进制（zenity／kdialog）的一次 `PATH` 探查——经由一个导出的纯函数判定，再用 `ctx.loader.create({name})` 把选中的双面后端挂进 Loader 的**内存根树**；该 effect 的 disposer 会移除该条目并汇入后端 fiber 的拆卸（单靠 `remove()` 只是启动拆卸），因此卸载选择器要到后端静止之后才落定。`native` 要求全部“有人值守且可服务”信号：回环绑定 ∧ 无 SSH 标记 ∧ native 后端能驱动的显示会话——darwin／win32 上视为存在，linux 上要求 `DISPLAY`／`WAYLAND_DISPLAY` 外加一个选择器二进制，其余平台一律不成立（native 后端恰好支持 darwin／win32／linux）。任何含糊情形都判定为处处可用的 `browse`。`apps/cli` 现在把 `-auto` 挂为它的 `directory-picker` 行；直接组合 `-native` 或 `-browse` 仍是固定交互的方式。
+
+条目级挂载之所以是承重机制：client 模块表（`dsh-client-modules`）基于 `internal/plugin` 对 **Loader 条目**做响应式协调，因此以真实条目挂载的后端，其 browser half 被发现的方式与配置行完全相同——seam 的“一行同时换两面”不变式在自适应下依然成立，且没有一行重复的 client 代码。开发环境的 HMR 行（`AppCLIEntry`）是该机制的先例。瞄准根树很关键：根树的 `write()` 是 no-op，因此判定出的行绝不会被持久化回 `cordis.yml`（Include 子树*会*写回）。
+
+## 曾考虑的替代方案
+
+- **在 `AppCLIEntry` 里做启动胶水判定**（随附两行并带静态 `disabled`，由 `--directory-picker=auto|native|browse` 标志修补 `disabled`）。可行——`PatchOptions` 能修补元数据，模块扫描也会跳过禁用行——但把决策留成应用私有，此后每个组合都要重新实现；选择器插件让任何 `cordis.yml` 都获得同样的一行自适应。只有当某个部署需要不改自己的 yml 就*强制*指定后端时，才重新引入该标志。
+- **合并成一个按调用分支的插件**（client 先试 `pick`，收到 `directory-picker-unavailable` 再回退到浏览对话框）。否决：client 得把两套流程装进同一个 bundle——bundle 纯净门禁禁止跨插件的值导入，jscpd 禁止复制对话框——而且按调用探测让 browse 宿主每次打开都付出一次注定失败的 RPC。
+- **复活 wire 广播**，让两套 client 流程都挂载并按宿主的 kind 分支。否决：推翻 seam Agent Note 的那次删除，却服务不了任何选择器尚未服务的消费方，还与 `single` 目录流洞相冲突。
+- **按连接自适应**（同一台服务器，回环浏览器用 native、远程浏览器用 browse）。延期：需要按客户端的能力对象、上述广播，以及同时挂载两套流程；今天没有部署同时服务两种操作者形态。
+
+## 后果
+
+- 随附的 web GUI 开箱即自适应：有人值守的本地宿主 → OS 选择器；SSH 启动、全网卡绑定、无头宿主、不支持的平台，或没有选择器二进制的 Linux → 应用内浏览器。探测是从启动上下文推断操作者位置，而任何启动侧信号都无法证明这一点：脱离的 tmux 会话会丢失 `SSH_*`；非 Aqua 的 darwin 进程仍被算作有显示；而 `ssh -L` 形态（在工作站本地启动、之后经转发端口访问，从 `127.0.0.1` 到达）会判定 `native`，把选择器弹在无人值守的工作站上——即便按连接自适应也修不了最后这一情形。错误的 `native` 选择会退化为后端既有的可重试失败对话框；处于这些形态的部署直接组合 `-browse`。
+- 选择器按运行时字符串（已导出的 `BACKEND_PACKAGES`）挂载后端，yml 行扫描看不到这一点；因此 `verify-cordis-config` 要求每个挂载 `-auto` 的组合把两个后端都声明为依赖，使无密钥的 Linux CI（它永远只会判定出 `browse`）无法掩盖被丢掉的 `-native` 依赖。随附树的 web e2e／快照通道（`apps/web/tests/scaffold.ts`）以 disable+insert 补丁固定 `-browse`——其 golden 是交互特定的，绝不能依赖运行该套件的宿主。
+- 每次启动只判定一次，维持 seam 的能力稳定性契约；按连接的形态在有部署提出需求前仍不在范围内。
+- 同时挂载选择器**和**某个后端行会大声失败（重复的 `directoryPicker` 服务；`single` 洞中的重复流程）。
+- host 类型检查聚合现在引用两个后端项目（仅声明，node 入口不携带 client 合并），使选择器的 REAL-composition 测试能挂载它们——与 client 聚合对 `webserver` 的引用互为镜像。
@@ -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
@@ -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.
@@ -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。
@@ -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
@@ -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.
@@ -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。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md
-2026-07-22-evidence-based-larger-hosted-runners.md: 983d5520bd73fc3cf82c37bf0d4a9ff1c6e6f51c
-2026-07-22-evidence-based-larger-hosted-runners.zh.md: a86dcf2c60d7b950e7557e84ef6993e712a2ce09
+2026-07-22-evidence-based-larger-hosted-runners.md: d46b8291ec05e997728da76354354f9e36bd2fb4
+2026-07-22-evidence-based-larger-hosted-runners.zh.md: e05ad30a713258ed7bc3d8099f8d6fab3d7c0c5d
@@ -18,9 +18,9 @@ The required primary path depends on those enterprise pools. Standard GitHub-hos

 The former gate-level and coarse primary shard jobs are absent from the workflow. Their static, lint, coverage, snapshot, and scenario shard selectors are also absent from the repository, so an unused diagnostic path cannot preserve a second CI architecture.

-Linux primary work uses three independent 32-core jobs. Coverage runs alone with its own worker bound, and the static scheduler runs alone so its result has no post-build consumer tail. After static gates finish, that job publishes its emitted `apps/*/lib`, `packages/*/*/lib`, and `vendor/*/lib` tree as a run-scoped artifact. The third job restores that exact tree, then starts lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers without repeating the build. Generated NodeNext consumer directories are excluded from Oxlint discovery because the artifact check removes them while these processes overlap. The pnpm store is restored without putting cache uploads on the pull-request critical path; Oxlint has no repository-managed result cache. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time.
+Linux primary work uses three independent 32-core jobs. Coverage runs alone with its own worker bound, and the static scheduler owns source and documentation gates that do not consume emitted output. The third job owns the single Linux build, then starts lint, Node 24 runtime compatibility, build-backed snapshots, documentation typechecking, and all artifact consumers against that tree. This [independent consumer build](2026-07-30-independent-ci-consumer-build.md) lets all three jobs request runners immediately without duplicating compilation or transferring a run-scoped artifact. Generated NodeNext consumer directories are excluded from Oxlint discovery because the artifact check removes them while these processes overlap. The pnpm store is restored without putting cache uploads on the pull-request critical path; Oxlint has no repository-managed result cache. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time.

-The gate dependencies remain explicit. Coverage consumes source and does not wait for build. Documentation typechecking builds its complete project-reference graph once. Snapshot replay and publication consumers wait for emitted output, while Node-version compatibility jobs exercise runtime-sensitive source loading without repeating the primary source-graph typecheck. PTY and subprocess suites keep their bounded inner concurrency rather than inheriting the runner's core count.
+The gate dependencies remain explicit. Coverage consumes source and does not wait for build. Documentation typechecking consumes the consumer lane's complete project-reference output. Snapshot replay and publication consumers wait for emitted output, while Node-version compatibility jobs exercise runtime-sensitive source loading without repeating the primary source-graph typecheck. PTY and subprocess suites keep their bounded inner concurrency rather than inheriting the runner's core count.

 The artifact boundary remains explicit. `scripts/publint-all.ts` calls publint's supported API against an in-memory publication view formed from each manifest's declared files plus npm's mandatory metadata, avoiding one package-manager pack process per package. `scripts/verify-built-package-invariants.mjs` stages the declared `lib/` files below the real package and imports its compiled self-reference through plain Node and Cordis Loader normalization; a runtime chunk omitted from the publication contract still fails.

@@ -68,7 +68,7 @@ An additional serial Linux reference runs on the in-house self-hosted pool (`vm-

 **Keep build behind typecheck.** This orders independent compiler invocations and turns snapshot replay into a three-stage critical chain. Build output has its own success dependency, so only snapshot and publication consumers wait for it.

-**Keep static gates and post-build consumers on one runner.** Reusing one workspace avoids a setup wave and artifact transfer, but build-duration variance delays every consumer and leaves their lint and snapshot tails after the static result. A run-scoped built tree preserves one exact build while independent jobs keep both complete paths within the observed target.
+**Publish the static job's build to post-build consumers.** A run-scoped artifact preserves one exact build, but the workflow can only consume it by waiting for the entire static job and then requesting another runner. The [independent consumer build](2026-07-30-independent-ci-consumer-build.md) assigns the single Linux build to its actual consumers instead.

 **Keep the complete required path on standard GitHub-hosted capacity.** This avoids repository-external runner configuration, but exact-head standard-runner runs remain materially slower and can spend longer queued behind shared capacity. Standard-hosted compatibility and serial references preserve portable evidence without making that slower topology the ordinary primary path.

@@ -80,7 +80,7 @@ An additional serial Linux reference runs on the in-house self-hosted pool (`vm-

 The required topology pays one setup wave per 32-core lane and retains no shard selectors. Every ordinary pull request consumes paid enterprise Linux and Windows minutes; manual benchmarks add other sizes only when remeasurement is useful.

-GitHub rounds each larger-runner execution up to a whole minute, so complete-job measurement exposes both billed time and workflow complexity. Splitting Linux repeats setup twice and transfers one built tree, but isolates coverage, static gates, and post-build consumers from each other's critical paths without repeating the build; consolidating Windows avoids repeating its slower setup.
+GitHub rounds each larger-runner execution up to a whole minute, so complete-job measurement exposes both billed time and workflow complexity. Splitting Linux repeats setup twice, but the consumer lane owns the only built tree and coverage, static gates, and post-build consumers enter runner allocation independently; consolidating Windows avoids repeating its slower setup.

 Performance targets are observations, not cancellation deadlines or correctness requirements. Manual all-size and serial suites remain available when image, dependency, scheduler, or pricing changes need remeasurement.

@@ -18,11 +18,11 @@ Status: implemented

 原有的门禁级和粗粒度主流程分片作业已从工作流中移除。相应的静态、lint、覆盖率、快照和场景分片选择器也已从仓库中移除，因此未使用的诊断路径无法继续维系第二套 CI 架构。

-Linux 主流程使用 3 个相互独立的 32 核作业。覆盖率单独运行，并设有自己的工作线程上限；静态调度器也单独运行，因此构建后的消费方不会拖延其结果。静态门禁完成后，该作业将其生成的 `apps/*/lib`、`packages/*/*/lib` 和 `vendor/*/lib` 目录树作为仅供本次运行使用的产物发布。第三个作业恢复完全相同的目录树，再让 lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方基于构建完成后的工作树启动，而不重复构建。生成的 NodeNext 消费方目录不会纳入 Oxlint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 会得到恢复，但缓存上传不会进入拉取请求关键路径；Oxlint 没有由仓库管理的结果缓存。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。
+Linux 主流程使用 3 个相互独立的 32 核作业。覆盖率单独运行，并设有自己的工作线程上限；静态调度器负责不消费生成输出的源码和文档门禁。第三个作业负责唯一一次 Linux 构建，随后让 lint、Node 24 运行时兼容性、依赖构建产物的快照、文档类型检查和所有产物消费方基于该目录树启动。这种[消费方独立构建](2026-07-30-independent-ci-consumer-build.md)使 3 个作业都能立即请求运行器，而无需重复编译或传输仅供本次运行使用的产物。生成的 NodeNext 消费方目录不会纳入 Oxlint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 会得到恢复，但缓存上传不会进入拉取请求关键路径；Oxlint 没有由仓库管理的结果缓存。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。

-门禁依赖关系保持显式。覆盖率消费源码，不等待构建。文档类型检查只构建一次完整的 project-reference 图。快照回放和发布消费方等待生成的输出，而 Node 版本兼容性作业会验证对运行时敏感的源码加载，且不重复主源码项目图的类型检查。PTY 和子进程套件继续使用自身有界的内部并发，不继承运行器的核心数。
+门禁依赖关系保持显式。覆盖率消费源码，不等待构建。文档类型检查以消费方通道的完整 project-reference 输出为输入。快照回放和发布消费方等待生成的输出，而 Node 版本兼容性作业会验证对运行时敏感的源码加载，且不重复主源码项目图的类型检查。PTY 和子进程套件继续使用自身有界的内部并发，不继承运行器的核心数。

-产物边界保持显式。`scripts/publint-all.ts` 对内存中的发布视图调用 publint 支持的 API；该视图由每个 manifest（元数据清单）声明的文件和 npm 强制要求的元数据组成，从而避免为每个包启动一次包管理器 pack 进程。`scripts/verify-built-package-invariants.mjs` 将已声明的 `lib/` 文件暂存到真实包下，并通过普通 Node 和 Cordis Loader 规范化导入其已编译的自身引用；发布契约只要遗漏一个运行时分片，检查仍会失败。
+产物边界保持显式。`scripts/publint-all.ts` 对内存中的发布视图调用 publint 支持的 API；该视图由每个 manifest（元数据清单）声明的文件和 npm 强制要求的元数据组成，从而避免为每个包（package）启动一次包管理器 pack 进程。`scripts/verify-built-package-invariants.mjs` 将已声明的 `lib/` 文件暂存到真实包下，并通过普通 Node 和 Cordis Loader 规范化导入其已编译的自身引用；发布契约只要遗漏一个运行时分片，检查仍会失败。

 Windows 以一次 32 核环境设置同时承载阻塞性构建、生产网站和观测性的构建产物契约。重复的 lint、覆盖率和快照清单由 Linux 承担，因为在 Windows 上运行这些观测性副本会延长付费关键路径，却不会新增任何阻塞性平台契约。

@@ -68,7 +68,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完

 **让构建继续等待类型检查。** 此方案会给相互独立的编译器调用排定先后顺序，并把快照回放变成 3 阶段关键链。构建输出本身有独立的成功依赖关系，因此只有快照和发布消费方需要等待它。

-**将静态门禁和构建后消费方保留在同一台运行器上。** 复用同一个工作区可以省去一轮设置和一次产物传输，但构建耗时的波动会延迟每个消费方，并使消费方的 lint 和快照尾段延续到静态结果之后。仅供本次运行使用的已构建目录树可以保留同一份构建结果，而相互独立的作业能让两条完整路径都保持在实测目标内。
+**将静态作业的构建发布给构建后消费方。** 仅供本次运行使用的产物能保留同一份构建结果，但工作流要消费它，只能先等待整个静态作业完成，再请求另一台运行器。[消费方独立构建](2026-07-30-independent-ci-consumer-build.md)则转而让实际消费方负责唯一一次 Linux 构建。

 **将完整必需路径保留在 GitHub 标准托管容量上。** 此方案可以避免依赖仓库外部的运行器配置，但标准运行器上的分支头精确运行仍明显更慢，也可能因共享容量而排队更久。标准托管兼容性作业和串行参考流程保留可移植证据，无需让这套较慢的拓扑成为普通主路径。

@@ -80,7 +80,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完

 必需拓扑中的每个 32 核通道只承担 1 轮设置开销，且不保留分片选择器。每个普通拉取请求都会消耗付费的企业级 Linux 和 Windows 运行器分钟数；只有在重新测量有价值时，手动基准测试才会加入其他规格。

-GitHub 会把每次大型运行器执行向上取整到整分钟计费，因此完整作业测量能同时呈现计费时长与工作流复杂度。拆分 Linux 会重复两轮设置并传输一份已构建目录树，但能使覆盖率、静态门禁与构建后消费方不再相互进入关键路径，且无需重复构建；合并 Windows 则避免重复其耗时更长的设置。
+GitHub 会把每次大型运行器执行向上取整到整分钟计费，因此完整作业测量能同时呈现计费时长与工作流复杂度。拆分 Linux 会重复两轮设置，但消费方通道拥有唯一一份已构建目录树，且覆盖率、静态门禁与构建后消费方分别进入运行器分配；合并 Windows 则避免重复其耗时更长的设置。

 性能目标是观测结果，而非取消截止时间或正确性要求。当映像、依赖、调度器或定价发生变化而需要重新测量时，仍可使用手动全规格和串行套件。

@@ -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
@@ -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.
@@ -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。
@@ -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-independent-ci-consumer-build.md
+2026-07-30-independent-ci-consumer-build.md: ea87d8051a30c282bdf57ddc3226072be8cb7f24
+2026-07-30-independent-ci-consumer-build.zh.md: 1b5faf73711bd522ddf0ae04f870e0401a481c0e
@@ -0,0 +1,35 @@
+# Agent Note: Independent CI consumer build
+
+Status: implemented
+
+English | [中文](2026-07-30-independent-ci-consumer-build.zh.md)
+
+## Problem
+
+The [larger-runner topology](2026-07-22-evidence-based-larger-hosted-runners.md) gave the static and built-consumer inventories separate jobs, but the static job owned their shared build. It uploaded the emitted tree only after every static gate completed, and the consumer job declared a job-level dependency before restoring that tree. Compiled-output snapshots and publication checks genuinely require a complete build; they do not require runtime-closure checks, documentation generation, module-graph verification, or Knip.
+
+That wider dependency made runner availability part of the required critical chain. In one failover run, static waited 8 minutes 1 second for a runner and ran for 1 minute 41 seconds; only then could consumers enter the same shared pool, where they waited another 10 minutes 34 seconds before running for 1 minute 58 seconds. Reusing the static build saved repository work but serialized two independent runner allocations.
+
+## Decision
+
+The three required Linux jobs enter runner allocation independently. Coverage remains source-only. Static owns source and documentation checks that do not consume emitted output. The consumer job owns the single Linux build together with documentation typechecking, compiled-output snapshots, publication checks, NodeNext checks, and built-bin smokes.
+
+The consumer's internal gate graph preserves the real dependency. Build and source-only Node compatibility start first; publint waits for build, built-package invariants validate that publication view, and every compiled-output consumer waits for that validation. Example and Web snapshots therefore continue to exercise current `lib/` output under plain Node, while no GitHub job waits for an unrelated job or transfers a built-tree artifact.
+
+Windows and serial reference aggregates retain their own build ownership. The change is confined to the required pull-request Linux topology; `all checks passed` still aggregates the same named jobs and fails for any unsuccessful dependency.
+
+## Alternatives considered
+
+**Keep publishing the static job's build.** This preserves one build but cannot express the actual step-level dependency: GitHub makes the consumer wait for the whole static job before it can request a runner. The saved build time is smaller than the repeated queue delay during failover saturation.
+
+**Build independently in both jobs.** Removing the job dependency while leaving build in static would restore parallel allocation, but every pull request would compile the same tree twice. Moving documentation typechecking and build ownership to the consumer preserves one build.
+
+**Add a dedicated build job.** A narrow producer would make the dependency name accurate, but it would add a fourth setup and runner-allocation stage before consumers. The consumer already owns every long-lived use of emitted output, so a separate producer has no second independent consumer.
+
+**Combine static and consumers only during failover.** One long job would avoid the second allocation, but conditional job inventories and result aggregation would create a second CI topology. Independent jobs preserve the same graph on hosted and failover pools.
+
+## Consequences
+
+Static and consumer queue delays overlap instead of accumulating. The consumer's active time includes the build, while the static job becomes shorter and artifact upload, download, compression, and extraction disappear. Total Linux build count remains one.
+
+A static failure no longer prevents the consumer inventory from producing its own evidence; the final verdict still fails. Build and documentation-typecheck failures appear under `node 24 / snapshots and artifacts` rather than `node 24 / static`, matching the job that owns their output dependency.
@@ -0,0 +1,35 @@
+# Agent Note: 消费方独立构建
+
+Status: implemented
+
+[English](2026-07-30-independent-ci-consumer-build.md) | 中文
+
+## 问题
+
+[大型运行器拓扑](2026-07-22-evidence-based-larger-hosted-runners.md)将静态门禁清单和构建后消费方清单分配给不同作业，但二者共用的构建由静态作业负责。静态作业要等所有静态门禁完成后才上传生成的目录树，消费方作业则在恢复该目录树前声明了作业级依赖。基于编译输出的快照与发布校验确实需要完整构建，但不依赖运行时依赖闭包检查、文档生成、模块图验证或 Knip。
+
+这项过宽的依赖使运行器可用性成为必需关键链的一环。一次故障切换运行中，静态作业等待运行器 8 分 1 秒，随后运行 1 分 41 秒；直到此时，消费方作业才能进入同一个共享池，它又等待 10 分 34 秒，随后运行 1 分 58 秒。复用静态作业的构建省去了部分仓库工作，却让两次原本相互独立的运行器分配串行发生。
+
+## 决策
+
+3 个必需 Linux 作业分别进入运行器分配。覆盖率仍只消费源码。静态作业负责无需消费生成输出的源码检查与文档检查。消费方作业负责唯一一次 Linux 构建，以及文档类型检查、基于编译输出的快照、发布校验、NodeNext 检查和 built-bin 冒烟测试。
+
+消费方内部的门禁图保留实际依赖关系。构建和只消费源码的 Node 兼容性检查率先启动；publint 等待构建完成，已构建包不变式检查会验证该发布视图，所有编译输出消费方都等待这项验证完成。因此，示例和 Web 快照仍会在普通 Node 下验证当前 `lib/` 输出；同时，没有任何 GitHub 作业需要等待无关作业或传输已构建目录树产物。
+
+Windows 与串行参考聚合流程仍各自负责自身构建。本变更仅涉及拉取请求的必需 Linux 拓扑；`all checks passed` 仍聚合同一批具名作业，任一依赖未成功时都会失败。
+
+## 曾考虑的替代方案
+
+**继续发布静态作业的构建。** 此方案只需构建一次，却无法表达实际的步骤级依赖：GitHub 会让消费方等到整个静态作业结束后才可请求运行器。故障切换池饱和时，再次排队的延迟超过了省下的构建时间。
+
+**在两个作业中分别独立构建。** 在静态作业中保留构建、同时移除作业依赖，可以恢复并行分配，但每个拉取请求都会对同一目录树编译两次。将文档类型检查和构建职责移给消费方，则仍只需构建一次。
+
+**新增专用构建作业。** 职责单一的生产方能让依赖名称与实际关系相符，但会在消费方之前新增第 4 个需要设置和分配运行器的阶段。所有需要持续使用生成输出的任务都已由消费方作业负责，因此单独增设生产方也没有第二个相互独立的消费方。
+
+**仅在故障切换期间合并静态作业与消费方作业。** 单个长作业可以避免第二次分配，但带条件分支的作业清单与结果聚合会形成第二套 CI 拓扑。独立作业能让托管池与故障切换池使用同一作业图。
+
+## 后果
+
+静态作业与消费方作业的排队延迟会相互重叠，不再累加。消费方的活动耗时包含构建；静态作业则变短，产物上传、下载、压缩和解压步骤全部消失。Linux 构建总次数仍为 1 次。
+
+静态作业失败不再阻止消费方清单生成自身证据；最终判定仍会失败。构建与文档类型检查失败会归入 `node 24 / snapshots and artifacts` 而非 `node 24 / static`，这一归类与输出依赖的实际归属一致。
@@ -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: fb28b7013550a853b92e50810f5bc34f2c02d2e4
-2026-07-24-web-gui-browser-e2e-lane.zh.md: b9a7d050031c3d08269a3b971cd1a84f082efba7
+2026-07-24-web-gui-browser-e2e-lane.md: 107dbddbfde8ad29e22d9cba04ce2b83c1d01383
+2026-07-24-web-gui-browser-e2e-lane.zh.md: e4132b2ebb3f30a9d540f47cf9416a13bc4aa9f3
@@ -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.

@@ -46,7 +46,7 @@ The lane covers three behavior families. Live-turn scenarios pin ordinary tool e

 ### CI stance

-The lane is a required compare-only gate for Linux pull requests under the [browser snapshot CI decision](2026-07-30-web-browser-snapshot-ci-gate.md). The static job publishes `apps/web/dist` with the package build artifacts; the `node 24 / snapshots and artifacts` consumer job installs the lockfile-selected Chromium, restores its OS-and-lockfile-keyed cache, and runs the lane with `DSH_SNAPSHOT=replay`. This is an intentional plane split: the host and specs use the [tsx source-launch contract](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md), while the browser consumes `apps/web/dist` and package `lib/client.js` artifacts, so the gate depends on `built-package-invariants` for those client artifacts. The hosted and self-hosted default-branch Linux serial jobs run the same gate; the hosted job produces the browser cache consumed by pull requests, while the persistent self-hosted pool needs no hosted cache. CI never records or refreshes goldens. Scenarios remain POSIX-oriented and stay outside the Windows and macOS matrices.
+The lane is a required compare-only gate for Linux pull requests under the [browser snapshot CI decision](2026-07-30-web-browser-snapshot-ci-gate.md). The `node 24 / snapshots and artifacts` consumer job owns the [single Linux build](../process/2026-07-30-independent-ci-consumer-build.md), installs the lockfile-selected Chromium, restores its OS-and-lockfile-keyed cache, and runs the lane with `DSH_SNAPSHOT=replay`. This is an intentional plane split: the host and specs use the [tsx source-launch contract](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md), while the browser consumes `apps/web/dist` and package `lib/client.js` artifacts, so the gate depends on `built-package-invariants` for those client artifacts. The hosted and self-hosted default-branch Linux serial jobs run the same gate; the hosted job produces the browser cache consumed by pull requests, while the persistent self-hosted pool needs no hosted cache. CI never records or refreshes goldens. Scenarios remain POSIX-oriented and stay outside the Windows and macOS matrices.

 ## Prior art

@@ -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

@@ -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。

@@ -46,7 +46,7 @@ Web GUI 以一条真实组装链交付——chromium 页面 → client 插件 bu

 ### CI 立场

-根据[浏览器快照 CI 决策](2026-07-30-web-browser-snapshot-ci-gate.md)，该车道是 Linux 拉取请求必需的只比较门禁。static 任务会把 `apps/web/dist` 与包构建产物一同发布；`node 24 / snapshots and artifacts` 消费方任务安装锁文件选定的 Chromium，恢复以操作系统和锁文件为键的缓存，并用 `DSH_SNAPSHOT=replay` 运行该车道。这是有意的平面切分：host 与 spec 使用 [tsx 源码启动契约](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)，浏览器则消费 `apps/web/dist` 和包的 `lib/client.js` 产物，因此门禁依赖 `built-package-invariants` 提供这些客户端产物。托管和自托管的默认分支 Linux 串行任务运行同一门禁；托管任务生成供 PR 消费的浏览器缓存，持久化自托管池则不需要托管侧缓存。CI 从不录制或刷新预期输出。场景仍面向 POSIX，并继续置于 Windows 和 macOS 矩阵之外。
+根据[浏览器快照 CI 决策](2026-07-30-web-browser-snapshot-ci-gate.md)，该车道是 Linux 拉取请求必需的只比较门禁。`node 24 / snapshots and artifacts` 消费方任务在[消费方独立构建](../process/2026-07-30-independent-ci-consumer-build.md)中负责唯一一次 Linux 构建，安装锁文件选定的 Chromium，恢复以操作系统和锁文件为键的缓存，并用 `DSH_SNAPSHOT=replay` 运行该车道。这是有意的平面切分：host 与 spec 使用 [tsx 源码启动契约](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)，浏览器则消费 `apps/web/dist` 和包的 `lib/client.js` 产物，因此门禁依赖 `built-package-invariants` 提供这些客户端产物。托管和自托管的默认分支 Linux 串行任务运行同一门禁；托管任务生成供 PR 消费的浏览器缓存，持久化自托管池则不需要托管侧缓存。CI 从不录制或刷新预期输出。场景仍面向 POSIX，并继续置于 Windows 和 macOS 矩阵之外。

 ## 业界先例

@@ -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

@@ -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/2026-07-30-web-browser-snapshot-ci-gate.md
-2026-07-30-web-browser-snapshot-ci-gate.md: 3f87bb0f3d936bcee7ba7c3d84ae808c6ede1a97
-2026-07-30-web-browser-snapshot-ci-gate.zh.md: af563f0e2a1c20f7b53d371e97e41b7ffa52a1d1
+2026-07-30-web-browser-snapshot-ci-gate.md: 14402485034cd85ec5781477ce67481165d47e62
+2026-07-30-web-browser-snapshot-ci-gate.zh.md: f214c524253d2ad8a43e8543dc65ddfcfd7c065c
@@ -12,7 +12,7 @@ The [keyless web browser e2e lane](2026-07-24-web-gui-browser-e2e-lane.md) runs

 For Linux PRs, the `node 24 / snapshots and artifacts` job must run the full web browser replay/compare suite. `scripts/run-gates.ts` registers `test:web:built` as a `ci-consumers` gate and explicitly injects `DSH_SNAPSHOT=replay`; CI never runs in `record` or `refresh` mode, so when the committed goldens disagree with the currently assembled application, the tests fail directly instead of silently rewriting them on the runner and then passing.

-The static CI job already builds all publishable artifacts; it puts `apps/web/dist` and the package `lib/` directories in the built-tree artifact, which the consumer job reuses without rebuilding the entire repository. On hosted runners, CI installs Chromium and its system dependencies at the Playwright version in the lockfile. On the persistent failover VM, the image owns the Linux system packages and CI installs only Chromium, avoiding per-run `apt` mutation. The hosted default-branch Linux serial job runs the suite and produces the operating-system-and-lockfile-keyed browser cache; pull requests restore it without paying compression and upload on the required path, with an operating-system prefix fallback across lockfile changes. The self-hosted standby runs the same comparison without hosted cache actions.
+The consumer job owns the [single Linux build](../process/2026-07-30-independent-ci-consumer-build.md), so `apps/web/dist` and the package `lib/` directories remain in its workspace for the browser suite. On hosted runners, CI installs Chromium and its system dependencies at the Playwright version in the lockfile. On the persistent failover VM, the image owns the Linux system packages and CI installs only Chromium, avoiding per-run `apt` mutation. The hosted default-branch Linux serial job runs the suite and produces the operating-system-and-lockfile-keyed browser cache; pull requests restore it without paying compression and upload on the required path, with an operating-system prefix fallback across lockfile changes. The self-hosted standby runs the same comparison without hosted cache actions.

 Local `pnpm run test:web` continues to build first and then run the full browser suite; `test:web:built` is the entry point for existing build artifacts. Developers explicitly run `DSH_SNAPSHOT=refresh pnpm run test:web` only after confirming that user-visible output changed intentionally, review every expected-output diff, and then verify again in replay mode that no files are written.

@@ -26,10 +26,10 @@ An observed self-hosted consumer run measured `web-snapshot` at 112.15 seconds a

 **Run CI in `refresh` mode and then check the working tree.** Rejected: checking after writing turns the assertion mechanism into a generator; if the working-tree check is wired incorrectly, it can turn a regression into a passing expected-output update. Replay compares the existing goldens directly and has a smaller failure surface.

-**Create a standalone browser job and rebuild the entire repository.** Rejected: it would duplicate dependency installation and the publishable build. The existing Linux consumer job already consumes the same built-tree artifact and is part of the unified required verdict.
+**Create a standalone browser job and rebuild the entire repository.** Rejected: it would duplicate dependency installation and the publishable build. The existing Linux consumer job already owns that build and is part of the unified required verdict.

 **Replace real Chromium with jsdom snapshots.** Rejected: jsdom does not cover the browser, HTTP/SSE carriage, or the composition of real client plugin bundles. It remains useful for fast lower-layer feedback, but cannot replace the assembled browser chain.

 ## Consequences

-Before merge, every PR proves that the current web assembly matches all committed browser expected outputs, turning a missed refresh from an “unrelated change in a later PR” into a failure in the PR that introduced it. The cost is Chromium provisioning and one serial pass through the browser scenarios in the consumer job; built-artifact reuse and the browser cache avoid duplicate builds and downloads on reruns. The gate still makes no claim of cross-platform browser consistency, and if a Playwright/Chromium upgrade changes the ARIA format, the upgrade PR must explicitly refresh the expected outputs and review the churn.
+Before merge, every PR proves that the current web assembly matches all committed browser expected outputs, turning a missed refresh from an “unrelated change in a later PR” into a failure in the PR that introduced it. The cost is Chromium provisioning and one serial pass through the browser scenarios in the consumer job; the consumer-owned build and browser cache avoid duplicate builds and downloads on reruns. The gate still makes no claim of cross-platform browser consistency, and if a Playwright/Chromium upgrade changes the ARIA format, the upgrade PR must explicitly refresh the expected outputs and review the churn.
@@ -12,7 +12,7 @@ Status: implemented

 Linux PR 的 `node 24 / snapshots and artifacts` 必须运行完整 Web 浏览器 replay/compare。`scripts/run-gates.ts` 把 `test:web:built` 作为 `ci-consumers` 的一个 gate，并显式注入 `DSH_SNAPSHOT=replay`；CI 永不以 `record` 或 `refresh` 模式运行，因此提交的 golden 与当前组装应用不一致时测试直接失败，不会在 runner 内静默改写后通过。

-静态 CI job 已经构建全部发布产物；它把 `apps/web/dist` 和包的 `lib/` 目录放进 built-tree 产物，消费方 job 复用该产物而不重复全仓构建。在托管运行器上，CI 按锁文件中的 Playwright 版本安装 Chromium 及其系统依赖。在持久化故障切换 VM 上，镜像负责预装 Linux 系统软件包，CI 只安装 Chromium，避免每次运行都通过 `apt` 改动系统。托管的默认分支 Linux 串行 job 运行该套件，并生成以操作系统和锁文件为键的浏览器缓存；PR 恢复该缓存，使必需路径无需承担压缩和上传开销，并可在锁文件变化时按操作系统前缀回退。自托管热备运行相同的比较，但不执行托管缓存操作。
+消费方 job 在[消费方独立构建](../process/2026-07-30-independent-ci-consumer-build.md)中负责唯一一次 Linux 构建，因此 `apps/web/dist` 和包的 `lib/` 目录会保留在其工作区中，供浏览器套件使用。在托管运行器上，CI 按锁文件中的 Playwright 版本安装 Chromium 及其系统依赖。在持久化故障切换 VM 上，镜像负责预装 Linux 系统软件包，CI 只安装 Chromium，避免每次运行都通过 `apt` 改动系统。托管的默认分支 Linux 串行 job 运行该套件，并生成以操作系统和锁文件为键的浏览器缓存；PR 恢复该缓存，使必需路径无需承担压缩和上传开销，并可在锁文件变化时按操作系统前缀回退。自托管热备运行相同的比较，但不执行托管缓存操作。

 本地 `pnpm run test:web` 仍先构建再运行浏览器全集；`test:web:built` 是已有构建产物的执行入口。开发者只在确认用户可见输出有意变化后显式运行 `DSH_SNAPSHOT=refresh pnpm run test:web`，评审每一处 expected diff，再以 replay 模式复验不再写文件。

@@ -26,10 +26,10 @@ Linux PR 的 `node 24 / snapshots and artifacts` 必须运行完整 Web 浏览

 **让 CI 以 `refresh` 模式运行后检查工作树。** 已否决：写后比较把断言机制变成生成器，若工作树检查接线失效就会把回归更新成绿色；replay 直接比较已有 golden，失败面更小。

-**新建独立 browser job 并重新构建全仓。** 已否决：它会重复依赖安装和发布构建。现有 Linux consumer job 已消费同一 built-tree artifact，并已被统一的 required verdict 聚合。
+**新建独立 browser job 并重新构建全仓。** 已否决：它会重复依赖安装和发布构建。现有 Linux 消费方 job 已负责该构建，并已被统一的 required verdict 聚合。

 **用 jsdom 快照代替真实 Chromium。** 已否决：jsdom 不覆盖浏览器、HTTP/SSE 承载及真实 client plugin bundle 组合；它保留为快速的下层反馈，不能替代 assembled browser chain。

 ## 后果

-每个 PR 都在合并前证明当前 Web 组装与所有已提交的浏览器 expected 一致，漏刷从“后续 PR 的无关变化”变成引入 PR 自己的失败。成本是消费方 job 需要供给 Chromium，并串行运行一轮浏览器场景；built artifact 复用与浏览器缓存避免重跑时重复构建和下载。门禁仍不声称跨平台浏览器一致性，Playwright/Chromium 升级若改变 aria 格式，升级 PR 必须显式 refresh 并评审 churn。
+每个 PR 都在合并前证明当前 Web 组装与所有已提交的浏览器 expected 一致，漏刷从“后续 PR 的无关变化”变成引入 PR 自己的失败。成本是消费方 job 需要供给 Chromium，并串行运行一轮浏览器场景；消费方独立构建与浏览器缓存避免重跑时重复构建和下载。门禁仍不声称跨平台浏览器一致性，Playwright/Chromium 升级若改变 aria 格式，升级 PR 必须显式 refresh 并评审 churn。
@@ -27,9 +27,12 @@ env:

 jobs:

+  # FIXME: Re-enable the three hosted serial reference jobs before cutting a release.
+  # The self-hosted standby remains active on every master push.
+
  # Three enterprise jobs isolate coverage, static analysis, and the
-  # build-backed consumer tail. The static job publishes its exact build so
-  # consumers do not repeat the longest part of their critical path.
+  # build-backed consumer tail. The consumer job owns the only Linux build so
+  # all three jobs enter runner allocation independently.
  #
  # FAILOVER: each Linux enterprise job resolves its pool through the
  # DSH_CI_FAILOVER repository variable. Unset (normal), the expressions
@@ -47,7 +50,7 @@ jobs:
      ${{ vars.DSH_CI_FAILOVER == 'selfhosted'
          && github.event.pull_request.user.login != 'dependabot[bot]'
          && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]')
-          || 'dsh-enterprise-ubuntu-latest-32core-test' }}
+          || 'dsh-ubuntu-24-04-16core' }}
    name: node 24 / static
    env:
      DSH_GATE_CONCURRENCY: '8'
@@ -93,26 +96,13 @@ jobs:
          DSH_ARCHIVE_BASE_REF: ${{ github.event.pull_request.base.sha }}
        run: pnpm run check:ci:static

-      - name: Pack built tree
-        run: >-
-          tar -czf "$RUNNER_TEMP/node-24-built-tree.tar.gz"
-          apps/*/lib apps/web/dist packages/*/*/lib vendor/*/lib
-
-      - uses: actions/upload-artifact@v7
-        with:
-          name: node-24-built-tree
-          path: ${{ runner.temp }}/node-24-built-tree.tar.gz
-          if-no-files-found: error
-          retention-days: 1
-          compression-level: 0
-
  node-24-coverage:
    if: github.event_name == 'pull_request'
    runs-on: >-
      ${{ vars.DSH_CI_FAILOVER == 'selfhosted'
          && github.event.pull_request.user.login != 'dependabot[bot]'
          && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]')
-          || 'dsh-enterprise-ubuntu-24-04-32core-test' }}
+          || 'dsh-ubuntu-24-04-16core' }}
    name: node 24 / coverage
    env:
      # Failover shrinks the worker bound: the hosted 32-core runner is
@@ -120,9 +110,8 @@ jobs:
      # across six always-on runner instances, and the timing-sensitive
      # process suites have documented aggregate-contention failures.
      # 8 × 6 instances = 48 workers worst case on 64 cores.
-      DSH_COVERAGE_MAX_WORKERS: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && github.event.pull_request.user.login != 'dependabot[bot]' && '8' || '8' }}
+      DSH_COVERAGE_MAX_WORKERS: ${{ vars.DSH_CI_FAILOVER == 'selfhosted' && github.event.pull_request.user.login != 'dependabot[bot]' && '8' || '6' }}
      DSH_GATE_CONCURRENCY: '3'
-      NODE_OPTIONS: '--max-old-space-size=8192'
    steps:
      - uses: actions/checkout@v6
        with:
@@ -172,13 +161,12 @@ jobs:
        run: pnpm run check:ci:coverage

  node-24-consumers:
-    needs: node-24
    if: github.event_name == 'pull_request'
    runs-on: >-
      ${{ vars.DSH_CI_FAILOVER == 'selfhosted'
          && github.event.pull_request.user.login != 'dependabot[bot]'
          && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]')
-          || 'dsh-enterprise-ubuntu-latest-32core-test' }}
+          || 'dsh-ubuntu-24-04-16core' }}
    name: node 24 / snapshots and artifacts
    env:
      DSH_GATE_CONCURRENCY: '8'
@@ -192,14 +180,6 @@ jobs:
        with:
          persist-credentials: false

-      - uses: actions/download-artifact@v8
-        with:
-          name: node-24-built-tree
-          path: ${{ runner.temp }}
-
-      - name: Restore built tree
-        run: tar -xzf "$RUNNER_TEMP/node-24-built-tree.tar.gz"
-
      - uses: pnpm/action-setup@v4
        with:
          dest: ${{ runner.temp }}/setup-pnpm
@@ -225,8 +205,8 @@ jobs:
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-

-      # Pull requests restore the cache produced by serial-linux on master;
-      # they do not pay compression and upload on the required path.
+      # Pull requests restore the cache normally produced by serial-linux on
+      # master; they do not pay compression and upload on the required path.
      - uses: actions/cache/restore@v4
        if: vars.DSH_CI_FAILOVER != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]'
        with:
@@ -321,8 +301,9 @@ jobs:
  # The required pull-request Windows signal: the two blocking win32 surfaces
  # (workspace build, production site) execute with real, checksum-verified
  # Windows Node under Wine on standard hosted Linux. The master
-  # serial-windows job below keeps the complete native-kernel inventory —
-  # including the observational portability gates this lane does not run —
+  # serial-windows job below normally keeps the complete native-kernel
+  # inventory — including the observational portability gates this lane does
+  # not run —
  # on real windows-2025. This job only provisions runner state (caches,
  # apt); scripts/wine-windows-gates.sh owns the gate logic and is the same
  # script the optional local gate `pnpm run check:windows-wine` runs.
@@ -427,12 +408,12 @@ jobs:
          cp /var/cache/apt/archives/*.deb "$HOME/wine-debs/"
          du -sh "$HOME/wine-debs"

-  # Master pushes run only the serial reference jobs below.
-  # Each host executes the complete, unsharded primary Node aggregate with one
-  # gate worker, giving reviewers a simple cross-platform oracle for completeness
-  # and timing.
+  # The hosted reference jobs below are temporarily disabled; the self-hosted
+  # standby remains active. Each enabled host executes the complete, unsharded
+  # primary Node aggregate with one gate worker, giving reviewers a simple
+  # cross-platform oracle for completeness and timing.
  serial-linux:
-    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
+    if: false
    name: serial / linux
    runs-on: ubuntu-latest
    steps:
@@ -557,7 +538,7 @@ jobs:
        run: pnpm run check:ci:linux-primary

  serial-macos:
-    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
+    if: false
    name: serial / macos
    runs-on: macos-latest
    steps:
@@ -584,7 +565,7 @@ jobs:
        run: pnpm run check:ci

  serial-windows:
-    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
+    if: false
    name: serial / windows
    runs-on: windows-2025
    steps:
@@ -31,6 +31,7 @@ packages/    @deepseek-ai/dsh-<pkg> workspaces at packages/<group>/<pkg>/
  cordis/      self-referential toolset: the agent inspects/mounts plugins in its own runtime
  hooks/       Claude Code/Codex hook bridges + shared wire-protocol library
  session-persistence/  persistence seam + JSONL/SQLite backends
+  settings/    user-settings seam + file-backed provider
  acp/         automation-only Agent Client Protocol server
  ui/          TUI/JSON-RPC bridges; boot, approval, interaction plugins
  examples/    demo bundles (agent-spine + TUI/CLI/ACP/JSON-RPC bins) leaves load
@@ -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'
@@ -111,12 +111,15 @@
    - id: tool-todo
      name: '@deepseek-ai/dsh-tool-todo'

+    # Resolve bind host, SSH launch, and display once at boot, then mount the
+    # matching dual-face directory picker. Mount -native or -browse directly in
+    # an overlay to pin the interaction.
+    - id: directory-picker
+      name: '@deepseek-ai/dsh-host-directory-picker-auto'
+
    # The API gateway: the transport-agnostic dispatch face every client shape
    # shares. provider/model are the host default routing — the profile json's
    # mapping target (user config overrides these engineering defaults).
-    - id: directory-picker
-      name: '@deepseek-ai/dsh-host-directory-picker-browse'
-
    - id: api-gateway
      name: '@deepseek-ai/dsh-host-apiproxy'
      config:
@@ -58,7 +58,9 @@
    "@deepseek-ai/dsh-goal": "workspace:^",
    "@deepseek-ai/dsh-goal-session": "workspace:^",
    "@deepseek-ai/dsh-host-apiproxy": "workspace:^",
+    "@deepseek-ai/dsh-host-directory-picker-auto": "workspace:^",
    "@deepseek-ai/dsh-host-directory-picker-browse": "workspace:^",
+    "@deepseek-ai/dsh-host-directory-picker-native": "workspace:^",
    "@deepseek-ai/dsh-host-webserver": "workspace:^",
    "@deepseek-ai/dsh-invariants": "workspace:^",
    "@deepseek-ai/dsh-llm": "workspace:^",
@@ -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'])
  })
 })
@@ -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'])
+  })
+})
@@ -20,6 +20,7 @@ import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './suppor

 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/queue-actions', import.meta.url))
 const FIXTURE = fileURLToPath(new URL('./snapshots/live-interactions/session.jsonl', import.meta.url))
+const COLLAPSED_EXPECTED = join(SNAPSHOT_DIR, 'collapsed.expected.md')
 const EDITING_EXPECTED = join(SNAPSHOT_DIR, 'editing.expected.md')
 const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
 const MODE = webSnapshotMode()
@@ -80,6 +81,16 @@ describe('web e2e: queue row actions', () => {
      await input.fill(text)
      await input.press('Enter')
    }
+    const queueHeader = page.getByRole('button', { name: '2 条排队消息' })
+    await expect.poll(() => queueHeader.getAttribute('aria-expanded'), { timeout: 10_000 })
+      .toBe('false')
+    const collapsedSnapshot = await captureStableAria(
+      page,
+      '[class*="centerCol"]',
+      scaffold.workspaceCwd,
+    )
+    await compareOrRefreshGolden(COLLAPSED_EXPECTED, collapsedSnapshot, MODE)
+    await queueHeader.click()
    await expect.poll(
      () => page.getByRole('button', { name: '删除排队消息' }).count(),
      { timeout: 10_000 },
@@ -112,6 +123,9 @@ describe('web e2e: queue row actions', () => {
  }, 120_000)

  it.skipIf(MODE === 'record')('keeps its snapshot inventory closed', async () => {
-    await assertFixtureInventory(SNAPSHOT_DIR, ['editing.expected.md', 'ui.expected.md'])
+    await assertFixtureInventory(
+      SNAPSHOT_DIR,
+      ['collapsed.expected.md', 'editing.expected.md', 'ui.expected.md'],
+    )
  })
 })
@@ -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 })
+    }
+  }
+})
@@ -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'
@@ -172,12 +173,33 @@ 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.
    { id: 'workspace-context', disabled: true },
    { id: 'session-title-llm', disabled: true },
    { id: 'webserver', config: { host: '127.0.0.1', port: 0, distIndex: DIST_INDEX } },
+    // The shipped directory-picker row is the -auto chooser, which resolves
+    // the interaction from the RUNNING host (display, SSH launch, bind). The
+    // lane's goldens are interaction-specific (workspace-management drives
+    // the in-app browse dialog), so pin -browse deterministically on every
+    // host: patch `name` is an assertion, not an override, hence the
+    // disable+insert pair.
+    { id: 'directory-picker', disabled: true },
+    { insert: [{ id: 'directory-picker-browse', name: '@deepseek-ai/dsh-host-directory-picker-browse' }] },
    ...options.toolsMode === undefined ? [] : [{ id: 'tools', config: { mode: options.toolsMode } }],
    ...options.cordisTools === true
      ? [{ insert: [{ id: 'tool-cordis', name: 'cordis:tool-cordis' }] }]
@@ -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"
@@ -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
@@ -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"
@@ -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"}}}
@@ -0,0 +1,24 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- button "编辑":
+  - img
+- paragraph: partial
+- button "2 条排队消息"
+- 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 "Stop generating"
@@ -12,6 +12,7 @@
 - button "编辑":
  - img
 - paragraph: partial
+- button "2 条排队消息" [disabled] [expanded]
 - list:
  - listitem:
    - text: Queue item to remove
@@ -23,8 +23,10 @@
  // 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/plan-review.e2e.ts",
    "tests/steering.e2e.ts",
    "tests/navigation-panes.e2e.ts",
    "tests/lifecycle-chrome.e2e.ts",
@@ -38,6 +38,9 @@ flowchart LR
  pkg_tool_bash["tool-bash"]
  pkg_hooks_claude["hooks-claude"]
  pkg_hooks_codex["hooks-codex"]
+  pkg_settings["settings"]
+  svc_settings["ctx.settings<br/>User-settings seam"]
+  pkg_settings_local["settings-local"]
  pkg_session_telemetry["session-telemetry"]
  svc_telemetry["ctx.telemetry<br/>Session telemetry seam"]
  pkg_session_telemetry_otel["session-telemetry-otel"]
@@ -205,6 +208,8 @@ flowchart LR
  pkg_session_title --> svc_sessionTitle
  pkg_session_title_all_messages_llm --> svc_sessionTitle
  pkg_session_title_first_message_llm --> svc_sessionTitle
+  pkg_settings --> svc_settings
+  pkg_settings_local --> svc_settings
  pkg_skill --> svc_skills
  pkg_skill_local --> svc_skills
  pkg_spill --> svc_spillStore
@@ -341,6 +346,7 @@ flowchart LR
 | `ctx.invariants` | `core` | [`invariants`](../packages/support/invariants) | - | [`session`](../packages/core/session), [`agent`](../packages/core/agent), [`scope`](../packages/core/scope), [`agent-loop`](../packages/core/agent-loop) | - | Companion subpaths register owner-local checks; the service owns selection, uniqueness, child fibers, and package-attributed failures. |
 | `ctx.typert` | `core` | [`typert-registry`](../packages/typert/registry) | - | [`typert-loader`](../packages/typert/loader) | - | Plugins register live zod contributions directly or through dsh-typert-loader; runtime consumers query schemas and reflection metadata at their own edges. |
 | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`session-query`](../packages/session-query/session-query), [`session-query-sqlite`](../packages/session-query/session-query-sqlite) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
+| `ctx.settings` | `seam` | [`settings`](../packages/settings/settings) | [`settings-local`](../packages/settings/settings-local) | - | - | Plugins register namespace schemas and resolve layered values; providers store the raw document. No production consumer is migrated yet. |
 | `ctx.telemetry` | `seam` | [`session-telemetry`](../packages/telemetry/session-telemetry) | [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel) | - | - | The seam captures, redacts, and hands session records to one backend; nothing else consumes the service — its output leaves the process. |
 | `ctx.storage` | `seam` | [`storage`](../packages/storage/storage) | [`storage-json`](../packages/storage/storage-json), [`storage-sqlite`](../packages/storage/storage-sqlite) | [`storage-domain`](../packages/storage/storage-domain) | - | Backends register side by side under names; data forms (domain first) mount on the hub and translate typed operations into opaque KV-unit primitives. |
 | `ctx.storageDomain` | `core` | [`storage-domain`](../packages/storage/storage-domain) | - | [`workspace`](../packages/workspace/workspace) | - | Waits for every configured backend, then publishes the domain form as one lifecycle-bound service for typed durable state. |
@@ -1238,6 +1238,24 @@ Depends on: [`SessionTitleLlmConfig`](../packages/session-title/session-title-ll

 Source: [`packages/session-title/session-title-first-message-llm/src/index.ts:15`](../packages/session-title/session-title-first-message-llm/src/index.ts)

+## `@deepseek-ai/dsh-settings-local`
+
+```ts config-catalog
+/** Plugin config: file location and hot-reload behavior. */
+export interface Config {
+  /** Settings document path; defaults to `settings.yaml` under the harness home. */
+  path?: string
+  /** Harness home used when `path` is omitted; defaults to `$DSH_HOME` or `~/.dsh`. */
+  dshHome?: string
+  /** Watch the document and hot-publish external edits; defaults to true. */
+  watch?: boolean
+  /** Watcher write-settle window in milliseconds; defaults to 100. */
+  debounceMs?: number
+}
+```
+
+Source: [`packages/settings/settings-local/src/index.ts:21`](../packages/settings/settings-local/src/index.ts)
+
 ## `@deepseek-ai/dsh-skill`

 ```ts config-catalog
@@ -1664,8 +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. */
@@ -2252,6 +2272,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co
 - `@deepseek-ai/dsh-commands` ([`packages/ui/commands/src/index.ts`](../packages/ui/commands/src/index.ts))
 - `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts))
 - `@deepseek-ai/dsh-goal-session` — requires `agents` · `goals` · `sessions` ([`packages/goal/goal-session/src/index.ts`](../packages/goal/goal-session/src/index.ts))
+- `@deepseek-ai/dsh-host-directory-picker-auto` — requires `httpServer` · `loader` ([`packages/host/directory-picker-auto/src/index.ts`](../packages/host/directory-picker-auto/src/index.ts))
 - `@deepseek-ai/dsh-host-directory-picker-native` ([`packages/host/directory-picker-native/src/index.ts`](../packages/host/directory-picker-native/src/index.ts))
 - `@deepseek-ai/dsh-llm` ([`packages/llm/llm/src/index.ts`](../packages/llm/llm/src/index.ts))
 - `@deepseek-ai/dsh-lsp` ([`packages/lsp/lsp/src/index.ts`](../packages/lsp/lsp/src/index.ts))
@@ -2282,6 +2303,7 @@ Abstract service classes — a deployment loads a concrete implementation packag
 - `@deepseek-ai/dsh-sandbox` — abstract `SandboxProvider` ([`packages/sandbox/sandbox/src/index.ts`](../packages/sandbox/sandbox/src/index.ts))
 - `@deepseek-ai/dsh-session-persistence` — abstract `SessionPersistence` ([`packages/session-persistence/session-persistence/src/index.ts`](../packages/session-persistence/session-persistence/src/index.ts))
 - `@deepseek-ai/dsh-session-query` — abstract `SessionQueryService` ([`packages/session-query/session-query/src/index.ts`](../packages/session-query/session-query/src/index.ts))
+- `@deepseek-ai/dsh-settings` — abstract `Settings` ([`packages/settings/settings/src/index.ts`](../packages/settings/settings/src/index.ts))
 - `@deepseek-ai/dsh-spill` — abstract `SpillStore` ([`packages/spill/spill/src/index.ts`](../packages/spill/spill/src/index.ts))
 - `@deepseek-ai/dsh-subprocess` — abstract `SubprocessService` ([`packages/subprocess/subprocess/src/index.ts`](../packages/subprocess/subprocess/src/index.ts))
 - `@deepseek-ai/dsh-tasks` — abstract `TaskService` ([`packages/tasks/tasks/src/index.ts`](../packages/tasks/tasks/src/index.ts))
@@ -659,6 +659,35 @@ Types: [Scoped](../core-data-structures/scope.md) · [Session](../core-data-stru

 Source: [`packages/core/session/src/index.ts:103`](../../packages/core/session/src/index.ts)

+## `settings/*`
+
+### `settings/updated` — emit
+
+Committed change to one registered namespace's resolved value. Emitted after the provider persisted (for `update`) or published (`provider`) the change; never emitted when the resolved value is deep-equal. Listener failures are contained and logged — a sync throw and an async rejection alike — except `INVARIANT`-coded failures, which rethrow after every listener ran; that rethrow reaches the emitter only from synchronous listeners, so invariant checks on this event must not be async functions.
+
+```ts cordis-catalog
+/**
+ * Committed change to one registered namespace's resolved value. Emitted
+ * after the provider persisted (for `update`) or published (`provider`)
+ * the change; never emitted when the resolved value is deep-equal.
+ * Listener failures are contained and logged — a sync throw and an async
+ * rejection alike — except `INVARIANT`-coded failures, which rethrow
+ * after every listener ran; that rethrow reaches the emitter only from
+ * synchronous listeners, so invariant checks on this event must not be
+ * async functions.
+ * @param ns - the namespace whose resolved value changed.
+ * @param next - the new resolved value.
+ * @param prev - the previous resolved value.
+ * @param source - whether the change entered through `update()` or the provider.
+ * @mode emit
+ */
+'settings/updated'(ns: SettingsNamespace, next: unknown, prev: unknown, source: SettingsUpdateSource): void
+```
+
+Types: [SettingsNamespace](../core-data-structures/settings.md) · [SettingsUpdateSource](../core-data-structures/settings.md)
+
+Source: [`packages/settings/settings/src/index.ts:108`](../../packages/settings/settings/src/index.ts)
+
 ## `skills/*`

 ### `skills/change` — emit
@@ -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`

@@ -1590,7 +1590,7 @@ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId):

 Types: [CreateSessionOptions](../core-data-structures/persistence.md) · [Session](../core-data-structures/session.md) · [SessionId](../core-data-structures/core.md)

-Source: [`packages/core/session/src/index.ts:713`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:714`](../../packages/core/session/src/index.ts)

 ## `ctx.sessionTitle` — `SessionTitleService`

@@ -1639,6 +1639,62 @@ Types: [Session](../core-data-structures/session.md) · [SessionTitleProvider](.

 Source: [`packages/session-title/session-title/src/index.ts:261`](../../packages/session-title/session-title/src/index.ts)

+## `ctx.settings` — `Settings` (abstract seam)
+
+Abstract settings service. Providers implement raw-document storage (`load`/`persist`) and push external changes through Settings.publish; the base class owns namespace registration, resolution, validation, change detection, and the `settings/updated` commit event.
+
+```ts cordis-catalog
+/**
+ * Register a namespace schema and receive its owner scope. The registration
+ * is an effect on the calling plugin's fiber: disposing that fiber removes
+ * the namespace and its observers. An invalid stored section fails the
+ * registration itself — the earliest point where the schema can judge it.
+ * @param ns - unique namespace; duplicate registration fails loud.
+ * @param schema - schemastery schema resolving this namespace's value.
+ * @param options - composition `base` layer and effect timing.
+ * @returns the owner scope for reads, observation, and updates.
+ */
+register<T>(ns: SettingsNamespace, schema: z<T>, options?: SettingsRegisterOptions<T>): SettingsScope<T>
+
+/**
+ * Describe every registered namespace for configuration surfaces.
+ * @returns one descriptor per registered namespace, in registration order.
+ */
+describe(): SettingsDescriptor[]
+
+/**
+ * Read one registered namespace's resolved value.
+ * @param ns - the namespace to read.
+ * @returns the resolved value, or `undefined` while unregistered.
+ */
+get(ns: SettingsNamespace): unknown
+
+/**
+ * Merge a patch into one registered namespace's user layer, validate the
+ * resolved candidate, persist through the provider, then commit and emit.
+ * A validation failure rejects before anything is persisted. Writes to one
+ * namespace are serialized: concurrent updates apply in call order, each
+ * merging over the previous write's committed section.
+ * @param ns - the registered namespace to update.
+ * @param patch - plain-object patch over the user section.
+ */
+async update(ns: SettingsNamespace, patch: object): Promise<void>
+
+/**
+ * Replace one registered namespace's user section wholesale, validate,
+ * persist, then commit and emit. Keys absent from `section` fall back to the
+ * composition `base` and schema defaults — this is the removal/reset path a
+ * merge-only patch cannot express (`replace({})` re-inherits everything).
+ * @param ns - the registered namespace to replace.
+ * @param section - the complete next user section.
+ */
+async replace(ns: SettingsNamespace, section: object): Promise<void>
+```
+
+Types: [SettingsDescriptor](../core-data-structures/settings.md) · [SettingsNamespace](../core-data-structures/settings.md) · [SettingsRegisterOptions](../core-data-structures/settings.md) · [SettingsScope](../core-data-structures/settings.md)
+
+Source: [`packages/settings/settings/src/index.ts:250`](../../packages/settings/settings/src/index.ts)
+
 ## `ctx.skills` — `SkillService`

 Registry of skill providers. It merges provider catalogs with stable first-wins duplicate handling, exposes sorted invocation-neutral summaries, and loads full skill bodies on demand.
@@ -2197,7 +2253,7 @@ The concrete provider retains pi-tui, focus, and terminal lifecycle state. Plugi
 abstract openOverlay(request: TuiOverlayRequest): TuiOverlaySession
 ```

-Source: [`packages/ui/tui/src/index.ts:240`](../../packages/ui/tui/src/index.ts)
+Source: [`packages/ui/tui/src/index.ts:241`](../../packages/ui/tui/src/index.ts)

 ## `ctx.typert` — `TypertRegistry`

@@ -2284,7 +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`

@@ -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 docs/core-data-structures/core.md
-core.md: dad533cee00646a40f57bd9097b2cceb8e9de9e2
-core.zh.md: 9e8afac0744fcf0df8c35dad5debce746d6614c6
+core.md: a12e96b4156b4ccd8f6f0c453224ed57d6040966
+core.zh.md: ac10c801bde8898ebd3393b05a94cc63627e1b89
@@ -24,6 +24,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
 | [commands.md](commands.md) | the human-command seam: definitions, adapter discovery, direct invocation, results, and parsing views |
 | [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, execution enclosure, and standalone events |
 | [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` |
+| [settings.md](settings.md) | the user-settings seam: `SettingsNamespace` registration, layered resolution (defaults → composition `base` → user document), owner scopes, hot commits |
 | [session-query.md](session-query.md) | logical records, bounded exact-event reads, relationship traces, semantic filters/documents, and full-text result pages |
 | [session-title.md](session-title.md) | durable title snapshots, source provenance, and the asynchronous provider contract |
 | [system-prompt.md](system-prompt.md) | per-assembly context, tool-provider results, prompt sections, and cooperative assembly |
@@ -24,6 +24,7 @@ harness 是一个微内核：一个极小的核心加上众多插件。大多数
 | [commands.md](commands.md) | 人类命令 seam：定义、适配器发现、直接调用、结果与解析视图 |
 | [session.md](session.md) | 完整的 `SessionEventMap` 变体目录、`TurnTrigger`/`TurnEndReason`、`deriveMessages()`、执行封闭与独立事件 |
 | [persistence.md](persistence.md) | 持久性 seam：`SessionPersistence`、JSONL + SQLite 后端、`session/flush`、崩溃恢复、`SessionHeader` |
+| [settings.md](settings.md) | 用户设置 seam：`SettingsNamespace` 注册、分层解析（默认值 → 组合 `base` → 用户文档）、owner scope、热提交 |
 | [session-query.md](session-query.md) | 逻辑记录、有界精确事件读取、关系追踪、语义筛选器/文档与全文检索结果页 |
 | [session-title.md](session-title.md) | 持久标题快照、来源 provenance 与异步提供方契约 |
 | [system-prompt.md](system-prompt.md) | 逐次组装的上下文、工具提供方结果、提示词段落与协作式组装 |
@@ -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 docs/core-data-structures/session.md
-session.md: 769d5db301e3e81664c732ab1685c859a00cceb2
-session.zh.md: 7af459949eda1b939596c20adf1c9e55f6d2b2b4
+session.md: 5389c2e2114094df5afdca25afd904b2cbbf8270
+session.zh.md: 29c4853213dfc886155e3f8d0991fa161e05c71a
@@ -269,7 +269,7 @@ interface SurfaceIntent {
 }
 ```

-Required for `SurfaceEventType` events — every message-producing event must declare how it joins the surface, the sole source of derived history. Non-surface types reject it at compile time.
+Required for `SurfaceEventType` events — every message-producing event must declare how it joins the surface, the sole source of derived model history. A human-facing transcript is the other projection and reads the log's append-origin events instead, because the surface deliberately shadows the ranges a replacement summarizes (`isAppendSurfaceEvent` in [dsh-session](../../packages/core/session/README.md)). Non-surface types reject it at compile time.

 The same provenance distinction applies here: only `assistant/message` may carry a present empty `sourceEventSeqs`; omission does not assert that its source stream was empty.

@@ -388,7 +388,8 @@ declare class Session {
   *   the ordered surface; `sourceEventSeqs` records provenance (the seq
   *   numbers of events this one derives from). REQUIRED for
   *   {@link SurfaceEventType} events (every message-producing event must
-   *   declare how it joins the surface, the sole source of derived history) and
+   *   declare how it joins the surface, the sole source of derived model
+   *   history) and
   *   rejected by the compiler for non-surface types like `turn/start` or
   *   `assistant/chunk`.
   * @returns the logged event — its assigned `seq`/`time` plus the SNAPSHOT of
@@ -271,7 +271,7 @@ interface SurfaceIntent {
 }
 ```

-对 `SurfaceEventType` 事件必填：每个产生消息的事件都必须声明它如何加入 surface（派生历史的唯一来源）。非 surface 类型在编译期拒绝此参数。
+对 `SurfaceEventType` 事件必填：每个产生消息的事件都必须声明它如何加入 surface（派生模型历史的唯一来源）。面向人类的记录（transcript）是另一个投影，读取的是日志中追加来源的事件，因为 surface 会有意遮蔽替换所概括的范围（见 [dsh-session](../../packages/core/session/README.md) 的 `isAppendSurfaceEvent`）。非 surface 类型在编译期拒绝此参数。

 此处适用相同的溯源区分：只有 `assistant/message` 可以携带存在但为空的 `sourceEventSeqs`；省略该字段并不表示其源流为空。

@@ -390,7 +390,8 @@ declare class Session {
   *   the ordered surface; `sourceEventSeqs` records provenance (the seq
   *   numbers of events this one derives from). REQUIRED for
   *   {@link SurfaceEventType} events (every message-producing event must
-   *   declare how it joins the surface, the sole source of derived history) and
+   *   declare how it joins the surface, the sole source of derived model
+   *   history) and
   *   rejected by the compiler for non-surface types like `turn/start` or
   *   `assistant/chunk`.
   * @returns the logged event — its assigned `seq`/`time` plus the SNAPSHOT of
@@ -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 docs/core-data-structures/settings.md
+settings.md: 381b36b3ff2f45a2090a2a2eac0f700bd00270c4
+settings.zh.md: bc6547db3b05c5a78f112462ae205d848f93da60
@@ -0,0 +1,99 @@
+# User Settings
+
+English | [中文](settings.zh.md)
+
+The user-settings seam of [dsh-settings](../../packages/settings/settings) holds one user-owned document of per-namespace sections and resolves each registered namespace as schema defaults, then the registrant's composition `base`, then the user section. Providers such as [dsh-settings-local](../../packages/settings/settings-local) store the raw document and push external edits; consumer plugins register a schema and read or observe the resolved value. Composition config stays in `cordis.yml` — a namespace carries only the user-editable subset.
+
+Source: [`packages/settings/settings/src/index.ts`](../../packages/settings/settings/src/index.ts)
+
+## Identity
+
+A namespace names one plugin-owned section of the user document. The brand keeps namespaces from mixing with other cross-boundary ids; construction validates the lowercase kebab-case shape.
+
+```ts type-equiv
+/** Nominal id of one registered settings namespace. */
+type SettingsNamespace = Branded<'SettingsNamespace'>
+```
+
+## Registration
+
+Registration binds a schemastery schema to a namespace on the calling plugin's fiber — disposing that fiber removes the namespace and its observers. The options carry the composition layer and the owner's effect timing.
+
+```ts type-equiv
+/** Registration options beyond the namespace schema. */
+interface SettingsRegisterOptions<T> {
+  /** Composition-layer values resolved below the user layer (entry-config subset). */
+  base?: Partial<T>
+  /** Owner's effect timing, surfaced to configuration UIs; defaults to `live`. */
+  applies?: SettingsApplies
+}
+```
+
+`applies` is a UI hint, not a mechanism: a `restart` owner simply never watches, so its value is read once at construction and configuration surfaces can badge the pending change.
+
+```ts type-equiv
+/** When a namespace's changes take effect for its owner. */
+type SettingsApplies = 'live' | 'restart'
+```
+
+## Owner scope
+
+The scope is the owner-facing handle. `update` merges a sparse patch over the user section only (never into `base`); `replace` sets the section wholesale, which is the removal/reset path — keys absent from the replacement re-inherit `base` and schema defaults. Writes to one namespace are serialized in call order, and resolved values are deep-frozen snapshots.
+
+```ts type-equiv
+/** Owner-facing handle for one registered namespace. */
+interface SettingsScope<T> {
+  /** Current resolved value: schema defaults, then `base`, then the user layer. */
+  get(): T
+  /**
+   * Observe committed changes to this namespace's resolved value. Invocations
+   * of one callback run asynchronously, one at a time, in commit order; a
+   * rejection is contained and logged like a sync throw. After the disposer
+   * returns, no further invocation starts — one already queued is skipped;
+   * one already started still settles, and service disposal waits for it.
+   * @param callback - invoked after each commit with the next and previous values.
+   * @returns the disposer removing this observer.
+   */
+  watch(callback: (next: T, prev: T) => void | Promise<void>): () => void
+  /**
+   * Merge a partial patch into this namespace's user layer and persist it.
+   * @param patch - plain-object patch over the user section; JSON-shaped data
+   * only (non-JSON values reject with their path before anything persists).
+   */
+  update(patch: object): Promise<void>
+  /**
+   * Replace this namespace's user section wholesale; absent keys re-inherit
+   * the composition `base` and schema defaults (`replace({})` resets all).
+   * @param section - the complete next user section; JSON-shaped data only,
+   * as for {@link update}.
+   */
+  replace(section: object): Promise<void>
+}
+```
+
+## Descriptors
+
+`describe()` serializes every registered namespace for configuration surfaces: the schemastery `toJSON()` envelope drives schema-rendered forms, and the resolved value fills them.
+
+```ts type-equiv
+/** One registered namespace as surfaced to configuration UIs. */
+interface SettingsDescriptor {
+  /** The registered namespace. */
+  ns: SettingsNamespace
+  /** Serialized schemastery schema (`schema.toJSON()`). */
+  schema: unknown
+  /** Current resolved value. */
+  value: unknown
+  /** Owner's declared effect timing. */
+  applies: SettingsApplies
+}
+```
+
+## Change commits
+
+Every committed change — an in-process write or an externally observed provider edit — emits `settings/updated (ns, next, prev, source)` after the new value is authoritative, and never when the resolved value is deep-equal. The source tag separates the two entry paths.
+
+```ts type-equiv
+/** Origin of one committed settings change. */
+type SettingsUpdateSource = 'update' | 'provider'
+```
@@ -0,0 +1,99 @@
+# 用户设置
+
+[English](settings.md) | 中文
+
+[dsh-settings](../../packages/settings/settings) 的用户设置 seam 持有一份按 namespace 分节的用户文档，并把每个已注册 namespace 解析为：schema 默认值，然后注册方的组合 `base`，最后用户分节。[dsh-settings-local](../../packages/settings/settings-local) 这类 provider 存储原始文档并推送外部编辑；消费插件注册 schema 后读取或观察解析值。组合配置仍留在 `cordis.yml`——namespace 只承载用户可编辑子集。
+
+Source: [`packages/settings/settings/src/index.ts`](../../packages/settings/settings/src/index.ts)
+
+## 标识
+
+namespace 命名用户文档中一个插件所有的分节。brand 使其不与其他跨边界 id 混用；构造时校验小写 kebab-case 形态。
+
+```ts type-equiv
+/** Nominal id of one registered settings namespace. */
+type SettingsNamespace = Branded<'SettingsNamespace'>
+```
+
+## 注册
+
+注册把 schemastery schema 绑定到调用方插件 fiber 上的 namespace——dispose 该 fiber 即移除 namespace 及其观察者。options 携带组合层与 owner 的生效时机。
+
+```ts type-equiv
+/** Registration options beyond the namespace schema. */
+interface SettingsRegisterOptions<T> {
+  /** Composition-layer values resolved below the user layer (entry-config subset). */
+  base?: Partial<T>
+  /** Owner's effect timing, surfaced to configuration UIs; defaults to `live`. */
+  applies?: SettingsApplies
+}
+```
+
+`applies` 是 UI 提示而非机制：`restart` 的 owner 只是从不 watch，其值在构造期读取一次，配置界面可为待生效变更加标。
+
+```ts type-equiv
+/** When a namespace's changes take effect for its owner. */
+type SettingsApplies = 'live' | 'restart'
+```
+
+## Owner scope
+
+scope 是面向 owner 的句柄。`update` 把稀疏 patch 只合并进用户分节（绝不进 `base`）；`replace` 整体替换分节，是删除/重置路径——替换中缺席的键重新继承 `base` 与 schema 默认值。同一 namespace 的写入按调用顺序串行，解析值是深冻结快照。
+
+```ts type-equiv
+/** Owner-facing handle for one registered namespace. */
+interface SettingsScope<T> {
+  /** Current resolved value: schema defaults, then `base`, then the user layer. */
+  get(): T
+  /**
+   * Observe committed changes to this namespace's resolved value. Invocations
+   * of one callback run asynchronously, one at a time, in commit order; a
+   * rejection is contained and logged like a sync throw. After the disposer
+   * returns, no further invocation starts — one already queued is skipped;
+   * one already started still settles, and service disposal waits for it.
+   * @param callback - invoked after each commit with the next and previous values.
+   * @returns the disposer removing this observer.
+   */
+  watch(callback: (next: T, prev: T) => void | Promise<void>): () => void
+  /**
+   * Merge a partial patch into this namespace's user layer and persist it.
+   * @param patch - plain-object patch over the user section; JSON-shaped data
+   * only (non-JSON values reject with their path before anything persists).
+   */
+  update(patch: object): Promise<void>
+  /**
+   * Replace this namespace's user section wholesale; absent keys re-inherit
+   * the composition `base` and schema defaults (`replace({})` resets all).
+   * @param section - the complete next user section; JSON-shaped data only,
+   * as for {@link update}.
+   */
+  replace(section: object): Promise<void>
+}
+```
+
+## 描述符
+
+`describe()` 为配置界面序列化每个已注册 namespace：schemastery 的 `toJSON()` 信封驱动 schema 渲染的表单，解析值填充表单。
+
+```ts type-equiv
+/** One registered namespace as surfaced to configuration UIs. */
+interface SettingsDescriptor {
+  /** The registered namespace. */
+  ns: SettingsNamespace
+  /** Serialized schemastery schema (`schema.toJSON()`). */
+  schema: unknown
+  /** Current resolved value. */
+  value: unknown
+  /** Owner's declared effect timing. */
+  applies: SettingsApplies
+}
+```
+
+## 变更提交
+
+每次提交的变更——进程内写入或 provider 观察到的外部编辑——在新值成为权威值之后发出 `settings/updated (ns, next, prev, source)`，解析值深相等时绝不发出。source 标记区分两条入口路径。
+
+```ts type-equiv
+/** Origin of one committed settings change. */
+type SettingsUpdateSource = 'update' | 'provider'
+```
@@ -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
@@ -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
 }
 ```

@@ -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
 }
 ```

@@ -36,6 +36,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:81`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), `apiproxy`, [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection-cache`](../packages/session-projection/session-projection-cache), [`session-telemetry`](../packages/telemetry/session-telemetry), [`session-title`](../packages/session-title/session-title) |
 | `session/event` | `emit` | [`packages/core/session/src/index.ts:93`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/acp/acp), `apiproxy`, [`cli-demo`](../packages/examples/cli-demo), [`compact`](../packages/compact/compact), [`compact-basic`](../packages/compact/compact-basic), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection`](../packages/session-projection/session-projection), [`session-projection-cache`](../packages/session-projection/session-projection-cache), [`session-telemetry`](../packages/telemetry/session-telemetry), [`session-title`](../packages/session-title/session-title), [`token-meter`](../packages/llm/token-meter), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-approval`](../packages/ui/user-approval), [`workspace-context`](../packages/context/workspace-context) |
 | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:103`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence), [`session-telemetry`](../packages/telemetry/session-telemetry) |
+| `settings/updated` | `emit` | [`packages/settings/settings/src/index.ts:108`](../packages/settings/settings/src/index.ts) | [`settings`](../packages/settings/settings) (`events.dispatch`) | [`settings`](../packages/settings/settings) |
 | `skills/change` | `emit` | [`packages/skill/skill/src/index.ts:188`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`events.dispatch`) | [`tui`](../packages/ui/tui) |
 | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:140`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc), [`subagent`](../packages/subagent/subagent) |
 | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:114`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
@@ -189,6 +189,7 @@ flowchart TD
  subgraph group_host["packages/host"]
    pkg_host_apiproxy["host-apiproxy"]
    pkg_host_directory_picker["host-directory-picker"]
+    pkg_host_directory_picker_auto["host-directory-picker-auto"]
    pkg_host_directory_picker_browse["host-directory-picker-browse"]
    pkg_host_directory_picker_native["host-directory-picker-native"]
    pkg_host_webserver["host-webserver"]
@@ -223,6 +224,10 @@ flowchart TD
    pkg_session_projection["session-projection"]
    pkg_session_projection_cache["session-projection-cache"]
  end
+  subgraph group_settings["packages/settings"]
+    pkg_settings["settings"]
+    pkg_settings_local["settings-local"]
+  end
  subgraph group_storage["packages/storage"]
    pkg_storage["storage"]
    pkg_storage_domain["storage-domain"]
@@ -316,6 +321,8 @@ flowchart TD
  pkg_telemetry --> pkg_brand
  pkg_telemetry --> pkg_invariants
  pkg_telemetry --> pkg_paths
+  pkg_settings --> pkg_brand
+  pkg_settings --> pkg_invariants
  pkg_storage_domain --> pkg_invariants
  pkg_storage_domain --> pkg_storage
  pkg_storage_json --> pkg_invariants
@@ -379,6 +386,9 @@ flowchart TD
  pkg_lsp --> pkg_llm
  pkg_sandbox --> pkg_invariants
  pkg_sandbox --> pkg_llm
+  pkg_settings_local --> pkg_invariants
+  pkg_settings_local --> pkg_paths
+  pkg_settings_local --> pkg_settings
  pkg_token_meter --> pkg_invariants
  pkg_token_meter --> pkg_llm
  pkg_token_meter --> pkg_session
@@ -446,6 +456,10 @@ flowchart TD
  pkg_code_runtime_worker --> pkg_invariants
  pkg_code_runtime_worker --> pkg_session
  pkg_code_runtime_worker --> pkg_timeout
+  pkg_host_directory_picker_auto --> pkg_host_directory_picker_browse
+  pkg_host_directory_picker_auto --> pkg_host_directory_picker_native
+  pkg_host_directory_picker_auto --> pkg_host_webserver
+  pkg_host_directory_picker_auto --> pkg_invariants
  pkg_lsp_local --> pkg_brand
  pkg_lsp_local --> pkg_invariants
  pkg_lsp_local --> pkg_llm
@@ -871,6 +885,7 @@ flowchart TD
  pkg_tui --> pkg_agent
  pkg_tui --> pkg_agent_loop
  pkg_tui --> pkg_commands
+  pkg_tui --> pkg_compact
  pkg_tui --> pkg_goal
  pkg_tui --> pkg_invariants
  pkg_tui --> pkg_llm
@@ -1020,6 +1035,7 @@ flowchart TD
 | [`client-ui-workspace`](../packages/client/ui-workspace) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) |
 | [`helper`](../packages/sdk/helper) | `sdk` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`subprocess`](../packages/subprocess/subprocess) |
 | [`telemetry`](../packages/sdk/telemetry) | `sdk` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`paths`](../packages/util/paths) |
+| [`settings`](../packages/settings/settings) | `settings` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants) |
 | [`storage-domain`](../packages/storage/storage-domain) | `storage` | [`invariants`](../packages/support/invariants), [`storage`](../packages/storage/storage) |
 | [`storage-json`](../packages/storage/storage-json) | `storage` | [`invariants`](../packages/support/invariants), [`storage`](../packages/storage/storage) |
 | [`storage-sqlite`](../packages/storage/storage-sqlite) | `storage` | [`invariants`](../packages/support/invariants), [`storage`](../packages/storage/storage) |
@@ -1039,6 +1055,7 @@ flowchart TD
 | [`host-directory-picker-native`](../packages/host/directory-picker-native) | `host` | [`client-runtime`](../packages/client/runtime), [`client-ui-slots`](../packages/client/ui-slots), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/support/invariants) |
 | [`lsp`](../packages/lsp/lsp) | `lsp` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm) |
 | [`sandbox`](../packages/sandbox/sandbox) | `sandbox` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm) |
+| [`settings-local`](../packages/settings/settings-local) | `settings` | [`invariants`](../packages/support/invariants), [`paths`](../packages/util/paths), [`settings`](../packages/settings/settings) |
 | [`token-meter`](../packages/llm/token-meter) | `llm` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`agent`](../packages/core/agent) | `core` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
 | [`bash`](../packages/bash/bash) | `bash` | [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`subprocess`](../packages/subprocess/subprocess) |
@@ -1058,6 +1075,7 @@ flowchart TD
 | [`client-ui-skill`](../packages/client/ui-skill) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) |
 | [`client-ui-subagent`](../packages/client/ui-subagent) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) |
 | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) |
+| [`host-directory-picker-auto`](../packages/host/directory-picker-auto) | `host` | [`host-directory-picker-browse`](../packages/host/directory-picker-browse), [`host-directory-picker-native`](../packages/host/directory-picker-native), [`host-webserver`](../packages/host/webserver), [`invariants`](../packages/support/invariants) |
 | [`lsp-local`](../packages/lsp/lsp-local) | `lsp` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout) |
 | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) |
 | [`sandbox-policy`](../packages/sandbox/sandbox-policy) | `sandbox` | [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) |
@@ -1137,7 +1155,7 @@ flowchart TD
 | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
 | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
 | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
-| [`tui`](../packages/ui/tui) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`commands`](../packages/ui/commands), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`session-reference`](../packages/context/session-reference), [`session-title`](../packages/session-title/session-title), [`skill`](../packages/skill/skill), [`subprocess`](../packages/subprocess/subprocess), [`system-prompt`](../packages/core/system-prompt), [`token-meter`](../packages/llm/token-meter), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
+| [`tui`](../packages/ui/tui) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`commands`](../packages/ui/commands), [`compact`](../packages/compact/compact), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`session-reference`](../packages/context/session-reference), [`session-title`](../packages/session-title/session-title), [`skill`](../packages/skill/skill), [`subprocess`](../packages/subprocess/subprocess), [`system-prompt`](../packages/core/system-prompt), [`token-meter`](../packages/llm/token-meter), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
 | [`client-ui-plan`](../packages/client/ui-plan) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants), [`plan-mode`](../packages/plan/plan-mode) |
 | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`paths`](../packages/util/paths), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-title`](../packages/session-title/session-title), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks-local`](../packages/tasks/tasks-local), [`tool-bash`](../packages/bash/tool-bash), [`tool-goal`](../packages/goal/tool-goal), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) |
 | [`sdk-protocol`](../packages/sdk/sdk-protocol) | `sdk` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) |
@@ -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`

@@ -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 },
@@ -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'
@@ -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
@@ -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
@@ -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." }
+  ]
+}
@@ -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"}}}
@@ -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"}}
--- a/Show More
+++ b/Show More