Merge master into fix/turn-actions

2026-07-31 01:27:56 +08:00
parent eef07b51a7 805ba9733e
commit 145a5eb9da
401 changed files with 15318 additions and 1437 deletions
--- a/apps/cli/README.i18n.yaml
+++ b/apps/cli/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write apps/cli/README.md
-README.md: 2bc36cce6205a4bfc3ba1d7ee15f0e0b2feab215
-README.zh.md: 0e0771658cecb4bee0f3eadd0639ad531e64ea3c
+README.md: d783d75cc9747d13887386fcf7609a6778e5dfb5
+README.zh.md: 3f5ce7e7a3a302fd9e255c1042ccb7b03deb59d9
--- a/apps/cli/README.md
+++ b/apps/cli/README.md
@@ -11,9 +11,9 @@ The TUI surface:
 - resumes a persisted session with `dsh --resume <session-id>` and, when the Node host exposes `process.execve`, supplies the TUI's in-place handoff host: after selector preflight and current-session flush, the host disposes the app and replaces the process with a normalized resume invocation; runtimes without process replacement leave the session running and say so. This CLI owns session identity and the exit line rather than the config: it mints or selects the `main` session id and provides it, plus the exact command that reproduces this invocation, on the boot context ([`MAIN_SESSION_ID_KEY`](../../packages/ui/tui/README.md) and `TUI_GOODBYE_MESSAGE_KEY`). No `cordis.yml` key can drop resume, and a missing or unreadable id fails loud instead of creating a fresh session;
 - treats the **invoking directory** as the workspace — sessions, relative paths, and workspace instructions resolve from the cwd (`dsh meta` is the sole exception, below);
 - tells the agent where its own source lives: after boot it adds a prompt section naming this harness checkout, resolved from the launcher's real path so it holds under a PATH symlink and an arbitrary cwd, so the self-referential `cordis` toolset can read and modify it;
- applies the personal overlay from `~/.dsh` (see [app-boot's Personal config](../../packages/ui/app-boot/README.md#personal-config)): `.env` fills environment gaps (ambient > project `.env` > personal `.env`), `config.yaml` patches the booted tree.
+- applies the personal overlay from `~/.dsh` (see [app-boot's Personal config](../../packages/ui/app-boot/README.md#personal-config)): `config.yaml` patches the booted tree, while `.env` there is the credential provider's own store (never hoisted into the environment, so keys stay rotatable). Environment precedence is ambient > project `.env`.

-`dsh meta` is that same TUI with this harness checkout as the workspace, so working on dsh itself needs no `cd`. It chdirs to the checkout root — resolved from the launcher's real path, the same root the source-path prompt section names — after both `.env` layers are loaded, so environment precedence is unchanged while the session cwd and HMR watch root move together. Meta always starts a fresh session and accepts no default-surface options; use ordinary `dsh --resume <id>` to resume a persisted session.
+`dsh meta` is that same TUI with this harness checkout as the workspace, so working on dsh itself needs no `cd`. It chdirs to the checkout root — resolved from the launcher's real path, the same root the source-path prompt section names — after the environment is settled, so precedence is unchanged while the session cwd and HMR watch root move together. Meta always starts a fresh session and accepts no default-surface options; use ordinary `dsh --resume <id>` to resume a persisted session.

 `dsh upgrade` is a guided fresh-session entry over the default TUI surface: it mints a fresh session in the invoking directory and seeds its first turn with the bundled `dsh-upgrade` skill, exactly as if the user typed `/skill:<name>`. The launcher passes the skill name on the boot context ([`INITIAL_SKILL_KEY`](../../packages/ui/tui/README.md)), which the TUI auto-invokes once the chat is live. Both take no options — `--config`, `-p`, and `--resume` fail loud — and seed only on this first launch, so a later `dsh --resume <id>` of the session is an ordinary TUI session with no re-injection.

--- a/apps/cli/README.zh.md
+++ b/apps/cli/README.zh.md
@@ -11,9 +11,9 @@ TUI 界面：
 - 使用 `dsh --resume <session-id>` 恢复已持久化会话。当 Node 宿主公开 `process.execve` 时，还会提供 TUI 的原地移交宿主：选择器预检并刷新当前会话后，宿主会释放应用，并以规范化的恢复调用替换进程；不支持进程替换的运行时会让会话继续运行并给出提示。会话身份与退出行由本 CLI 拥有，而非由配置指定：它创建或选定 `main` 会话 id，并把该 id 以及可复现本次调用的确切命令一起提供到启动上下文（[`MAIN_SESSION_ID_KEY`](../../packages/ui/tui/README.md) 与 `TUI_GOODBYE_MESSAGE_KEY`）。任何 `cordis.yml` 键都无法移除恢复能力；缺失或无法读取的 id 会明确报错，而不会创建新会话；
 - 将 **调用目录** 视为 workspace：会话、相对路径和 workspace 指令都从 cwd 解析（`dsh meta` 是唯一例外，见下文）；
 - 告知 agent 自身源码所在位置：启动后添加一个命名此 harness checkout 的提示词段。该路径从启动器的真实路径解析，因此在 PATH 符号链接和任意 cwd 下仍然有效，使自指的 `cordis` 工具集可以读取并修改它；
- 应用 `~/.dsh` 中的个人覆盖（参见 [app-boot 的个人配置](../../packages/ui/app-boot/README.md#personal-config)）：`.env` 填补环境缺口（环境中已有的值 > 项目 `.env` > 个人 `.env`），`config.yaml` 则修补已启动的树。
+- 应用 `~/.dsh` 中的个人覆盖（参见 [app-boot 的个人配置](../../packages/ui/app-boot/README.md#personal-config)）：`config.yaml` 修补已启动的树，而那里的 `.env` 是凭据 provider 自己的存储（绝不会被提升进环境，因此密钥始终可轮换）。环境优先级为环境中已有的值 > 项目 `.env`。

-`dsh meta` 是以本 harness checkout 为 workspace 的同一个 TUI，因此开发 dsh 自身无需 `cd`。它在两层 `.env` 都加载之后才 chdir 到 checkout 根目录（从启动器的真实路径解析，与源码路径提示词段所指的根目录相同），因此环境优先级不变，而会话 cwd 与 HMR 监视根目录会一并移动。Meta 始终创建新会话，不接受默认界面的任何选项；恢复已持久化会话应使用普通的 `dsh --resume <id>`。
+`dsh meta` 是以本 harness checkout 为 workspace 的同一个 TUI，因此开发 dsh 自身无需 `cd`。它在环境确定之后才 chdir 到 checkout 根目录（从启动器的真实路径解析，与源码路径提示词段所指的根目录相同），因此环境优先级不变，而会话 cwd 与 HMR 监视根目录会一并移动。Meta 始终创建新会话，不接受默认界面的任何选项；恢复已持久化会话应使用普通的 `dsh --resume <id>`。

 `dsh upgrade` 是默认 TUI 界面之上的引导式全新会话入口：它在调用目录中创建一个全新会话，并以内置 `dsh-upgrade` skill 播种其首轮，效果等同于用户手动键入 `/skill:<name>`。启动器将 skill 名称提供到启动上下文（[`INITIAL_SKILL_KEY`](../../packages/ui/tui/README.md)），TUI 在聊天就绪后自动调用它。两者都不接受任何选项——`--config`、`-p`、`--resume` 都会明确报错——且仅在首次启动时播种，因此之后 `dsh --resume <id>` 恢复该会话时是普通 TUI 会话，不会重复注入。

--- a/apps/cli/composition.md
+++ b/apps/cli/composition.md
@@ -28,6 +28,10 @@ flowchart LR
  cfg --> plugin_tui_tasks
  plugin_tui_llm_retry["llm-retry<br/>@deepseek-ai/dsh-llm-retry"]
  cfg --> plugin_tui_llm_retry
+  plugin_tui_settings["settings<br/>@deepseek-ai/dsh-settings-local"]
+  cfg --> plugin_tui_settings
+  plugin_tui_credentials["credentials<br/>@deepseek-ai/dsh-credentials-local"]
+  cfg --> plugin_tui_credentials
  plugin_tui_llm_pi_ai["llm-pi-ai<br/>@deepseek-ai/dsh-llm-pi-ai"]
  cfg --> plugin_tui_llm_pi_ai
  plugin_tui_session_persistence_jsonl["session-persistence-jsonl<br/>@deepseek-ai/dsh-session-persistence-jsonl"]
@@ -114,6 +118,8 @@ flowchart LR
 | `agent` | `@deepseek-ai/dsh-agent` |
 | `tasks` | `@deepseek-ai/dsh-tasks-local` |
 | `llm-retry` | `@deepseek-ai/dsh-llm-retry` |
+| `settings` | `@deepseek-ai/dsh-settings-local` |
+| `credentials` | `@deepseek-ai/dsh-credentials-local` |
 | `llm-pi-ai` | `@deepseek-ai/dsh-llm-pi-ai` |
 | `session-persistence-jsonl` | `@deepseek-ai/dsh-session-persistence-jsonl` |
 | `session-query-sqlite` | `@deepseek-ai/dsh-session-query-sqlite` |
--- a/apps/cli/config/base.cordis.yml
+++ b/apps/cli/config/base.cordis.yml
@@ -56,16 +56,28 @@
 - id: llm-retry
  name: '@deepseek-ai/dsh-llm-retry'

+# User-settings document (`$DSH_HOME/settings.yaml`, hot-reloaded): a
+# `llm-deepseek:` or `llm-pi-ai:` section there overrides the adapter entries
+# below without a restart, and is what the web Models page writes.
+- id: settings
+  name: '@deepseek-ai/dsh-settings-local'
+
+# Credential store: the live process environment over `$DSH_HOME/.env`
+# (owner-only file, hot-reloaded). Adapters resolve their key references
+# through it at each request, so no key is inlined in this file — and nothing
+# hoists that document into the process environment, which would make every
+# stored key read as an unrotatable ambient override.
+- id: credentials
+  name: '@deepseek-ai/dsh-credentials-local'
+
+# The pi-ai multi-provider twin, mounted dormant: zero routes (and no extra
+# models in the picker) until a `llm-pi-ai:` settings section supplies provider
+# profiles — then those routes register live, keys resolving per request
+# through their apiKeyEnv references, and drop again when the section empties.
+# Which adapters exist is composition; which providers run is the user's
+# settings document.
 - id: llm-pi-ai
  name: '@deepseek-ai/dsh-llm-pi-ai'
-  config:
-    providers:
-      - provider: openai
-        apiKey: !!js process.env.OPENAI_API_KEY
-        baseURL: !!js process.env.OPENAI_BASE_URL
-      - provider: anthropic
-        apiKey: !!js process.env.ANTHROPIC_API_KEY
-        baseURL: !!js process.env.ANTHROPIC_BASE_URL

 - id: session-persistence-jsonl
  name: '@deepseek-ai/dsh-session-persistence-jsonl'
@@ -102,6 +114,8 @@

 - id: tool-fs-search
  name: '@deepseek-ai/dsh-tool-fs-search'
+  config:
+    sampleOverCapGlobResults: false

 - id: workspace-context
  name: '@deepseek-ai/dsh-workspace-context'
@@ -221,10 +235,9 @@
 - id: fs-local
  name: '@deepseek-ai/dsh-fs-local'

-# The native DeepSeek adapter; reads the key/base-url the boot's layered .env
-# loading left in the environment. Thinking defaults are a surface choice.
+# The native DeepSeek adapter. No key or endpoint is inlined: both resolve per
+# request from the `llm-deepseek:` settings section over this entry, with the
+# key coming from the credential store below. Thinking defaults are a surface
+# choice.
 - id: llm-deepseek
  name: '@deepseek-ai/dsh-llm-deepseek'
-  config:
-    apiKey: !!js process.env.DEEPSEEK_API_KEY
-    baseURL: !!js process.env.DEEPSEEK_BASE_URL
--- a/apps/cli/config/web.cordis.yml
+++ b/apps/cli/config/web.cordis.yml
@@ -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:
--- a/apps/cli/package.json
+++ b/apps/cli/package.json
@@ -51,6 +51,7 @@
    "@deepseek-ai/dsh-commands": "workspace:^",
    "@deepseek-ai/dsh-compact-basic": "workspace:^",
    "@deepseek-ai/dsh-compact-tool-result-prune": "workspace:^",
+    "@deepseek-ai/dsh-credentials-local": "workspace:^",
    "@deepseek-ai/dsh-frontend": "workspace:^",
    "@deepseek-ai/dsh-fs-local": "workspace:^",
    "@deepseek-ai/dsh-fs-policy": "workspace:^",
@@ -58,7 +59,9 @@
    "@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:^",
@@ -71,7 +74,6 @@
    "@deepseek-ai/dsh-sandbox-local": "workspace:^",
    "@deepseek-ai/dsh-sandbox-policy": "workspace:^",
    "@deepseek-ai/dsh-scope": "workspace:^",
-    "@deepseek-ai/dsh-tool-cordis": "workspace:^",
    "@deepseek-ai/dsh-session": "workspace:^",
    "@deepseek-ai/dsh-session-checkpoint-policy": "workspace:^",
    "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
@@ -81,6 +83,7 @@
    "@deepseek-ai/dsh-session-reference": "workspace:^",
    "@deepseek-ai/dsh-session-title": "workspace:^",
    "@deepseek-ai/dsh-session-title-first-message-llm": "workspace:^",
+    "@deepseek-ai/dsh-settings-local": "workspace:^",
    "@deepseek-ai/dsh-skill": "workspace:^",
    "@deepseek-ai/dsh-skill-local": "workspace:^",
    "@deepseek-ai/dsh-spill-local": "workspace:^",
@@ -98,6 +101,7 @@
    "@deepseek-ai/dsh-token-meter": "workspace:^",
    "@deepseek-ai/dsh-tool-ask-user": "workspace:^",
    "@deepseek-ai/dsh-tool-bash": "workspace:^",
+    "@deepseek-ai/dsh-tool-cordis": "workspace:^",
    "@deepseek-ai/dsh-tool-fs": "workspace:^",
    "@deepseek-ai/dsh-tool-fs-search": "workspace:^",
    "@deepseek-ai/dsh-tool-goal": "workspace:^",
--- a/apps/cli/src/app-cli-entry.ts
+++ b/apps/cli/src/app-cli-entry.ts
@@ -1,10 +1,12 @@
 /**
 * AppCLIEntry — the pre-cordis boot glue the config-tree dsh surfaces share
 * for the Web/headless surface.
- * Everything here is what must exist before the Loader runs: layered env,
- * the patch composition over the shipped base and surface overlay (profile json + CLI
- * flags + the resolved frontend dist), and the fail-loud triple after the
- * tree settles.
+ * Everything here is what must exist before the Loader runs: the patch
+ * composition over the shipped base and surface overlay (profile json + CLI
+ * flags + the resolved frontend dist), and the fail-loud triple after the tree
+ * settles. The environment is what the bin already loaded (ambient plus the
+ * invoking directory's `.env`); `$DSH_HOME/.env` belongs to the credential
+ * provider and is never hoisted here.
 */

 import { readFileSync } from 'node:fs'
@@ -14,8 +16,7 @@ import { join, resolve } from 'node:path'
 import { Context } from 'cordis'
 import type { PatchOptions } from '@cordisjs/plugin-include'
 import yaml from 'js-yaml'
-import { boot, installFailLoud, loadEnv, loadOverlayPatches, loadPersonalPatches } from '@deepseek-ai/dsh-app-boot'
-import { resolveDshHome } from '@deepseek-ai/dsh-paths'
+import { boot, installFailLoud, loadOverlayPatches, loadPersonalPatches } from '@deepseek-ai/dsh-app-boot'
 // Empty type import carries the httpServer Context merge for the port read below.
 import type {} from '@deepseek-ai/dsh-host-webserver'

@@ -144,12 +145,11 @@ export class AppCLIEntry {
  constructor(private readonly options: AppCLIEntryOptions) {}

  /**
-   * Run the boot chain: layered env → patch composition → Loader include
-   * boot (dev row before await) → fail-loud triple.
+   * Run the boot chain: patch composition → Loader include boot (dev row
+   * before await) → fail-loud triple.
   * @returns the settled root context and the listening port.
   */
  async run(): Promise<{ ctx: Context; port: number }> {
-    this.loadEnvLayers()
    this.composePatches()
    await this.bootTree()
    this.assertBoot()
@@ -159,11 +159,6 @@ export class AppCLIEntry {
    return { ctx: this.ctx, port }
  }

-  /** Layered .env: ambient > cwd (bin already loaded) > $DSH_HOME (loadEnvFile never overrides). */
-  private loadEnvLayers(): void {
-    loadEnv('dsh', resolveDshHome())
-  }
-
  /**
   * Compose the patch set from profile json, CLI flags, and the resolved
   * frontend dist. Patches replace a row's config wholesale, so each patched row's yml
--- a/apps/cli/src/tui.ts
+++ b/apps/cli/src/tui.ts
@@ -26,12 +26,10 @@ import {
  addHarnessSourceSection,
  boot,
  installFailLoud,
-  loadEnv,
  loadOverlayPatches,
  loadPersonalPatches,
  resolveConfigPath,
 } from '@deepseek-ai/dsh-app-boot'
-import { resolveDshHome } from '@deepseek-ai/dsh-paths'
 import { SessionId } from '@deepseek-ai/dsh-session'
 import { SESSION_QUERY_SQLITE_PATH_KEY } from '@deepseek-ai/dsh-session-query-sqlite'
 import { CONFIGURED_AGENT_IDENTITIES_KEY } from '@deepseek-ai/dsh-agent-loop'
@@ -124,11 +122,12 @@ export async function runTui(
    process.exit(1)
  }
  installFailLoud(NAME)
-  // The bin already loaded the invoking directory's .env; the personal .env
-  // only fills what is still unset (process.loadEnvFile never overrides).
-  loadEnv(NAME, resolveDshHome())
-  // Both .env layers are loaded, so switching the workspace here cannot alter
-  // environment precedence. The cwd IS the workspace seam: the shipped config
+  // The bin already loaded the invoking directory's .env, and that is the
+  // whole environment: $DSH_HOME/.env is credentials-local's writable store,
+  // and hoisting it would make every stored key read as a read-only ambient
+  // override on the next run — unrotatable from the TUI or the web page.
+  // The environment is settled, so switching the workspace here cannot alter
+  // its precedence. The cwd IS the workspace seam: the shipped config
  // resolves the session cwd and the HMR watch root from it, so one chdir moves
  // both together. Sessions themselves live under the Harness home so `/resume`
  // spans every workspace, and are unaffected by this chdir.
--- a/apps/cli/tests/tui-keyless-smoke.e2e.ts
+++ b/apps/cli/tests/tui-keyless-smoke.e2e.ts
@@ -353,34 +353,40 @@ describe('dsh CLI keyless smoke (apps/cli through the same PTY)', () => {
    expect(output).toContain('\u001B[?2004l')
  }, LOADER_SMOKE_TEST_TIMEOUT_MS)

-  it('applies the personal overlay: config.yaml patches the tree and .env feeds its !!js', async () => {
-    // The whole personal-config chain in one boot: the personal .env supplies
-    // the variable, config.yaml patches the `tui` row — a row the SURFACE
-    // OVERLAY inserted, not one the base declares — with a `!!js` reference to
-    // it, and the banner renders the patched welcome verbatim. That proves a
-    // later patch list reaches a row an earlier one inserted.
+  it('applies the personal overlay: config.yaml patches an overlay-inserted row, the invoking directory\'s .env feeds its !!js, and the home .env stays out of the environment', async () => {
+    // The whole personal-config chain in one boot, plus the environment layer
+    // it deliberately excludes. config.yaml patches the `tui` row — a row the
+    // SURFACE OVERLAY inserted, not one the base declares — proving a later
+    // patch list reaches a row an earlier one inserted. The single `!!js`
+    // expression prefers the PERSONAL variable, so the welcome can only render
+    // the project value while the harness home's .env — the credential store
+    // of `dsh-credentials-local` — is NOT hoisted into `process.env`; hoisting
+    // it would make every stored key read as a read-only launch override on
+    // the next run and hand it to every subprocess the agent starts.
    const output = await smoke({
      label: 'dsh personal overlay',
      tempDirPrefix: 'dsh-personal-overlay-',
      binScript: dshBinScript,
      configArgs: [],
      prepare: seedWorkspace({
+        workspace: { '.env': 'DSH_PROJECT_WELCOME=PROJECT OVERLAY READY.\n' },
        personal: {
-          '.env': 'DSH_PERSONAL_WELCOME=PERSONAL OVERLAY READY.\n',
+          '.env': 'DSH_PERSONAL_WELCOME=HOME ENV LEAKED.\n',
          'config.yaml': [
            '- id: workspace-context',
            '  disabled: true',
            '- id: tui',
            '  config:',
            "    sessionId: !!js configuredAgentIdentities?.main?.id ?? 'main'",
-            '    welcome: !!js process.env.DSH_PERSONAL_WELCOME',
+            '    welcome: !!js process.env.DSH_PERSONAL_WELCOME ?? process.env.DSH_PROJECT_WELCOME',
            '',
          ].join('\n'),
        },
      }),
-      actions: [{ waitFor: 'PERSONAL OVERLAY READY.', send: '/exit\r' }],
+      actions: [{ waitFor: 'PROJECT OVERLAY READY.', send: '/exit\r' }],
    })
-    expect(output).toContain('PERSONAL OVERLAY READY.')
+    expect(output).toContain('PROJECT OVERLAY READY.')
+    expect(output).not.toContain('HOME ENV LEAKED.')
    expect(output).toContain('\u001B[?2004l')
  }, LOADER_SMOKE_TEST_TIMEOUT_MS)

--- a/apps/web/tests/approval-composer.e2e.ts
+++ b/apps/web/tests/approval-composer.e2e.ts
@@ -0,0 +1,181 @@
+// Web e2e scenario: the composer-takeover approval panel under a long
+// command. The shipped composition confines bash through the sandbox policy
+// and routes its escalation through the approval seam, so a read-only session
+// asked to write a file produces a REAL pending approval — the panel renders
+// in the browser, the test measures its geometry, answers through it, and the
+// escalated command then runs. Replay is deterministic: the denial, the
+// escalation retry and its command text arrive from replayed chunks, and the
+// answer click is the test's own gesture (the same sanctioned reaction to
+// model content as the question composer: the turn cannot complete without it).
+//
+// Geometry is the point of the scenario. The command is unbounded model text,
+// and before the cap a long one grew the card until the refuse/allow buttons
+// left the viewport — an approval the user could see and not answer.
+import { readFile } from 'node:fs/promises'
+import { fileURLToPath } from 'node:url'
+import { join } from 'node:path'
+import type { Browser, Page } from 'playwright'
+import { chromium } from 'playwright'
+import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+// Empty type import: carries the approval package's session-event merge, so
+// the decided-outcome assertion below type-checks against the real union.
+import type {} from '@deepseek-ai/dsh-user-approval'
+import {
+  assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
+  launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/approval-composer', import.meta.url))
+const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
+// The scenario's one golden: the waiting panel. Everything the answered state
+// proves is asserted directly — see the world-state block at the end.
+const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
+const MODE = webSnapshotMode()
+
+// Irreducible payload: the command has to be long enough to pass the card's
+// height cap, which is the only shape that reproduces an action row pushed off
+// screen. Unrelated tokens, not a repeated word — a repeated word is what the
+// model compressed into `printf 'alpha %.0s' {1..400}` while recording, and a
+// short command proves nothing here. The formula keeps the source small; the
+// model receives the expanded literal it has to put in the command.
+const TOKENS = Array.from({ length: 220 }, (_, index) => `tok${((index + 1) * 7919 % 99991).toString(36)}`).join(' ')
+const PROMPT = `Write a file named notes.txt in the workspace containing exactly this text on one line: ${TOKENS}. Use one bash command with the literal text inline. Then reply with the single word DONE and stop.`
+
+/** Draft used to measure the composer's own text cap: enough lines to pass it. */
+const CAP_PROBE = Array.from({ length: 40 }, (_, index) => `line ${index}`).join('\n')
+
+describe('web e2e: approval takeover keeps its actions reachable', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+  const sessionEvents: SessionEvent[] = []
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold(MODE === 'record' ? {} : { replayFixture: FIXTURE, paceMs: 15 })
+    scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { sessionEvents.push(event) })
+    browser = await chromium.launch()
+    page = await newEnglishPage(browser)
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await connectFreshWorkspace(page)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('caps the long command, answers through the panel, and runs the escalated command', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-approval'))
+    if (MODE !== 'record') {
+      expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([PROMPT])
+    }
+    const input = page.locator('textarea').first()
+    await input.waitFor({ timeout: 10_000 })
+
+    // The composer's own text cap, measured on the live textarea before the
+    // takeover replaces it. The panel's scroll region must stop at the same
+    // height (the designer's requirement: one cap for the composer seat), and
+    // measuring it here keeps the assertion free of the px value itself.
+    await input.fill(CAP_PROBE)
+    const composerCap = await input.evaluate(el => el.clientHeight)
+    expect(composerCap).toBeGreaterThan(0)
+    await input.fill('')
+
+    // Read-only: the mode whose denial the model escalates from. Switched
+    // through the shipped access-mode chip, not a test-only seam.
+    await page.locator('[aria-label^="Access mode"]').click()
+    await page.getByRole('menuitem', { name: 'Read Only' }).click()
+    await expect.poll(
+      () => page.locator('[aria-label="Access mode, current: Read Only"]').count(),
+      { timeout: 15_000 },
+    ).toBe(1)
+
+    const settled = scaffold.whenTurnSettled(MODE === 'record' ? 240_000 : 60_000)
+    await input.fill(PROMPT)
+    await input.press('Enter')
+
+    // The panel takes over the input area while the tool blocks. Its presence
+    // is a STABLE waiting state (it stays until answered), so waitFor is
+    // race-free.
+    const panel = page.locator('[data-approval-key]')
+    await panel.waitFor({ timeout: MODE === 'record' ? 180_000 : 60_000 })
+    const scroll = panel.locator('[data-approval-scroll]')
+    await expect.poll(() => scroll.getByText(/tok/).count(), { timeout: 15_000 }).toBeGreaterThan(0)
+
+    if (MODE !== 'record') {
+      // This golden owns the stable waiting surface; the answered golden below
+      // owns the resulting transcript.
+      const snapshot = await captureStableAria(page, '[data-approval-key]', scaffold.workspaceCwd)
+      await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
+
+      // The regression this scenario exists for: an uncapped card grew with
+      // the command until the action row left the viewport. Measured at the
+      // lane baseline and at a short viewport, on the live panel.
+      const original = page.viewportSize() ?? { width: 1680, height: 1000 }
+      for (const height of [1000, 700]) {
+        await page.setViewportSize({ width: 900, height })
+        const geometry = await panel.evaluate((root) => {
+          const region = root.querySelector<HTMLElement>('[data-approval-scroll]')
+          const card = region?.parentElement ?? null
+          // Role/text, not the CSS-module class names: the built client hashes those.
+          const buttons = [...root.querySelectorAll<HTMLElement>('button')]
+          const rows = buttons.map(button => button.getBoundingClientRect())
+          return {
+            buttons: buttons.length,
+            capped: region === null ? 0 : region.clientHeight,
+            // A scrolling region proves the cap is genuinely engaged; without
+            // it every assertion below would hold vacuously.
+            scrolls: region === null ? false : region.scrollHeight > region.clientHeight,
+            cardBottom: card === null ? Number.NaN : card.getBoundingClientRect().bottom,
+            actionsTop: Math.min(...rows.map(rect => rect.top)),
+            actionsBottom: Math.max(...rows.map(rect => rect.bottom)),
+            viewport: window.innerHeight,
+          }
+        })
+        expect(geometry.buttons).toBe(2)
+        expect(geometry.scrolls).toBe(true)
+        // One cap for the seat: the panel's text region stops where the
+        // composer draft does (sub-pixel tolerance for the shared padding).
+        expect(Math.abs(geometry.capped - composerCap)).toBeLessThan(1)
+        // Both buttons stay inside the card AND inside the viewport — the
+        // answerable state the cap exists to guarantee.
+        expect(geometry.actionsTop).toBeGreaterThan(0)
+        expect(geometry.actionsBottom).toBeLessThanOrEqual(geometry.viewport)
+        expect(geometry.actionsBottom).toBeLessThanOrEqual(geometry.cardBottom)
+      }
+      await page.setViewportSize(original)
+    }
+
+    await panel.getByRole('button', { name: '允许一次' }).click()
+
+    const sessionId = await settled
+    if (MODE === 'record') {
+      await recordFixture(scaffold, sessionId, FIXTURE)
+      return
+    }
+    // World state: the granted escalation is what let the command run, and the
+    // panel leaves with the regular composer restored. Asserted on the world
+    // and the DOM rather than through a transcript golden — the denied first
+    // attempt renders the OS's own refusal ("Operation not permitted" on
+    // macOS, "Read-only file system" on Linux), so the answered transcript is
+    // not a platform-neutral golden surface.
+    expect(JSON.stringify(sessionEvents.filter(e => e.type === 'approval/decided').at(-1)))
+      .toContain('allowed-once')
+    const written = await readFile(join(scaffold.workspaceCwd, 'workspace', 'notes.txt'), 'utf8')
+    expect(written).toContain(TOKENS.slice(0, 64))
+    await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 20_000 }).toBeGreaterThanOrEqual(1)
+    expect(await page.locator('[data-approval-key]').count()).toBe(0)
+    await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  }, 300_000)
+
+  it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
+    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'ui.expected.md'])
+  })
+})
--- a/apps/web/tests/details-session-lifecycle.e2e.ts
+++ b/apps/web/tests/details-session-lifecycle.e2e.ts
@@ -3,15 +3,19 @@
 // unselected states, and closes it only when a different Session takes ownership.
 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 {
-  acknowledgeReloadConnectionLoss, fixtureUserPrompts, launchWebScaffold, seedSession, watchConsole,
-  webSnapshotMode, type WebScaffold,
+  acknowledgeReloadConnectionLoss, assertFixtureInventory, compareOrRefreshGolden,
+  fixtureUserPrompts, launchWebScaffold, seedSession, watchConsole, webSnapshotMode,
+  type WebScaffold,
 } from './scaffold.ts'
 import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'

+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/details-session-lifecycle', import.meta.url))
+const HANDLES_EXPECTED = join(SNAPSHOT_DIR, 'handles.expected.md')
 const FIXTURE = fileURLToPath(new URL('./snapshots/lifecycle-chrome/session.jsonl', import.meta.url))
 const SEED_FIXTURE = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
 const PROMPT = 'Reply with the single word LIGHTHOUSE and stop.'
@@ -25,11 +29,41 @@ async function detailsTrack(page: Page): Promise<number> {
  })
 }

+/** First AppFrame grid track in CSS pixels. */
+async function sidebarTrack(page: Page): Promise<number> {
+  return await appFrame(page).evaluate((element) => {
+    const tracks = getComputedStyle(element).gridTemplateColumns.split(' ')
+    return Number.parseFloat(tracks[0] ?? 'NaN')
+  })
+}
+
 /** AppFrame is the only product element with an inline grid track template. */
 function appFrame(page: Page) {
  return page.locator('[style*="grid-template-columns"]').first()
 }

+/** Render the two boundary affordances without platform-dependent coordinates. */
+async function handleSnapshot(page: Page): Promise<string> {
+  const handles = await page.locator('[class*="handle"]').evaluateAll(elements =>
+    elements.map(element => ({
+      side: element.getAttribute('data-side'),
+      cursor: getComputedStyle(element).cursor,
+      pillGenerated: getComputedStyle(element, '::after').content !== 'none',
+    })))
+  return [
+    '# AppFrame drag handles',
+    '',
+    ...handles.flatMap(handle => [
+      `## ${handle.side}`,
+      '',
+      '- hit strip present: true',
+      `- cursor: ${handle.cursor}`,
+      `- pill generated: ${String(handle.pillGenerated)}`,
+      '',
+    ]),
+  ].join('\n').trimEnd()
+}
+
 describe.skipIf(MODE === 'record')('web e2e: details panel follows the current Session lifecycle', () => {
  let scaffold: WebScaffold
  let browser: Browser
@@ -65,6 +99,18 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S

    await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
    expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
+    await compareOrRefreshGolden(HANDLES_EXPECTED, await handleSnapshot(page), MODE)
+
+    const sidebarBefore = await sidebarTrack(page)
+    const sidebarHandle = page.locator('[data-side="sidebar"]')
+    const sidebarBox = await sidebarHandle.boundingBox()
+    expect(sidebarBox).not.toBeNull()
+    const dragStartX = sidebarBox!.x + sidebarBox!.width / 2
+    await page.mouse.move(dragStartX, sidebarBox!.y + 200)
+    await page.mouse.down()
+    await page.mouse.move(dragStartX + 70, sidebarBox!.y + 200, { steps: 6 })
+    await page.mouse.up()
+    await expect.poll(() => sidebarTrack(page), { timeout: 5_000 }).toBe(sidebarBefore + 70)

    const warningStart = tripwire.warnings.length
    await page.reload({ waitUntil: 'load' })
@@ -101,5 +147,6 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S
    await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
    expect(tripwire.pageErrors).toEqual([])
    expect(tripwire.warnings).toEqual([])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['handles.expected.md'])
  }, 90_000)
 })
--- a/apps/web/tests/message-actions.e2e.ts
+++ b/apps/web/tests/message-actions.e2e.ts
@@ -8,6 +8,7 @@ import { fileURLToPath } from 'node:url'
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import { SessionId } from '@deepseek-ai/dsh-session'
 import {
  assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
  launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold,
@@ -19,6 +20,7 @@ const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/message-actions', import
 // a new recording (workspace-management / sidebar-scrollbar pattern).
 const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
 const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
+const FORK_EXPECTED = join(SNAPSHOT_DIR, 'fork.expected.md')
 const MODE = webSnapshotMode()
 const SEED_ID = 'message-actions-web-e2e'

@@ -85,9 +87,58 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
    await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
  })

+  it.skipIf(MODE === 'record')('forks through the settled-message and session-row actions', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-message-fork'))
+    // Exercise the assistant action specifically; package coverage pins the
+    // user action separately at its own event seq.
+    await page.getByRole('button', { name: '在新对话中分支' }).last().click()
+    await expect.poll(
+      () => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SEED_ID)),
+      { timeout: 15_000 },
+    ).toBeDefined()
+    await expect.poll(
+      () => page.locator('[role="treeitem"]').count(),
+      { timeout: 10_000 },
+    ).toBe(3)
+    await expect.poll(
+      () => page.locator('[role="treeitem"][aria-selected="true"]').count(),
+      { timeout: 10_000 },
+    ).toBe(1)
+    // The row action owns a distinct ui-workspace injection from the message
+    // action above, so exercise both through the loaded app before capture.
+    const sourceRow = page.locator('[role="treeitem"][aria-selected="true"]')
+    const rowBox = await sourceRow.boundingBox()
+    if (rowBox === null) throw new Error('fork source row has no layout box')
+    const actionButton = sourceRow.locator('button[aria-label^="Session actions for "]')
+    await sourceRow.hover({ position: { x: rowBox.width - 16, y: rowBox.height / 2 } })
+    await expect.poll(() => actionButton.isVisible(), { timeout: 2_000 }).toBe(true)
+    const buttonBox = await actionButton.boundingBox()
+    if (buttonBox === null) throw new Error('fork source row action has no layout box')
+    await page.mouse.click(buttonBox.x + buttonBox.width / 2, buttonBox.y + buttonBox.height / 2)
+    await page.getByRole('menuitem', { name: 'Fork session' }).click()
+    await expect.poll(
+      () => scaffold.ctx.agents.list().filter(agent => agent.session.header.parentSession !== undefined).length,
+      { timeout: 15_000 },
+    ).toBe(2)
+    await expect.poll(
+      () => page.locator('[role="treeitem"]').count(),
+      { timeout: 10_000 },
+    ).toBe(4)
+    await expect.poll(
+      () => page.locator('[role="treeitem"][aria-selected="true"]').count(),
+      { timeout: 10_000 },
+    ).toBe(1)
+    const tree = await captureStableAria(
+      page,
+      '[role="tree"][aria-label="Sessions"]',
+      scaffold.workspaceCwd,
+    )
+    await compareOrRefreshGolden(FORK_EXPECTED, tree, MODE)
+  })
+
  it.skipIf(MODE === 'record')('issued zero model calls and kept a closed inventory', async () => {
    expect(tripwire.pageErrors).toEqual([])
    expect(tripwire.warnings).toEqual([])
-    await assertFixtureInventory(SNAPSHOT_DIR, ['ui.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['fork.expected.md', 'ui.expected.md'])
  })
 })
--- a/apps/web/tests/plan-review.e2e.ts
+++ b/apps/web/tests/plan-review.e2e.ts
@@ -0,0 +1,113 @@
+// Web e2e scenario: the plan-review takeover. The shipped composition mounts
+// plan mode and its client seat, so `/plan <task>` enters plan mode for real
+// and the recorded turn ends on exit_plan_mode blocking against the live
+// userInteraction seam. The composer is then occupied by the plan decision
+// card — not the generic question flow — and approving it through the card
+// completes the turn with the approval in the log.
+// Replay is deterministic: the plan content arrives from replayed chunks, the
+// review wait is real, and the approve click is the test's own gesture (the
+// turn cannot complete without it, in record and replay alike).
+import { readFile } from 'node:fs/promises'
+import { fileURLToPath } from 'node:url'
+import { join } from 'node:path'
+import type { Browser, Page } from 'playwright'
+import { chromium } from 'playwright'
+import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import {
+  assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
+  launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/plan-review', import.meta.url))
+const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
+// The waiting golden owns the decision card; the approved golden owns the
+// transcript the approval leaves behind — the state the card cannot see.
+const REVIEW_EXPECTED = join(SNAPSHOT_DIR, 'review.expected.md')
+const APPROVED_EXPECTED = join(SNAPSHOT_DIR, 'approved.expected.md')
+const MODE = webSnapshotMode()
+
+// One command line: /plan enters plan mode and submits the rest as the turn's
+// message. The task is deliberately self-contained (nothing to explore in a
+// fresh workspace) so the recorded turn is a plan and its review, and the
+// approved continuation is one word.
+const TASK = 'Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. '
+  + 'Call exit_plan_mode with a short plan of at most five bullet points. '
+  + 'Once the plan is approved, reply with the single word DONE and stop.'
+const LINE = `/plan ${TASK}`
+
+describe('web e2e: plan review takeover round trip', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+  const sessionEvents: SessionEvent[] = []
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold(MODE === 'record' ? {} : { replayFixture: FIXTURE, paceMs: 15 })
+    scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { sessionEvents.push(event) })
+    browser = await chromium.launch()
+    // English page: the decision copy is the surface under test, and the
+    // golden pins one language.
+    page = await newEnglishPage(browser)
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await connectFreshWorkspace(page)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('reviews the plan on a decision card and approves through it', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-plan-review'))
+    if (MODE !== 'record') {
+      expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([TASK])
+    }
+    const input = page.locator('textarea').first()
+    await input.waitFor({ timeout: 10_000 })
+    const settled = scaffold.whenTurnSettled(MODE === 'record' ? 180_000 : 30_000)
+    await input.fill(LINE)
+    await input.press('Enter')
+
+    // The card takes over the input area while exit_plan_mode blocks. Its
+    // presence is a STABLE waiting state (it stays until answered), so a plain
+    // waitFor is race-free.
+    const card = page.locator('[data-plan-review-key]')
+    await card.waitFor({ timeout: MODE === 'record' ? 120_000 : 30_000 })
+    // The plan-review request must NOT land on the generic question flow.
+    expect(await page.locator('[data-question-key]').count()).toBe(0)
+    await expect.poll(() => card.getByText('Plan review').count(), { timeout: 10_000 }).toBeGreaterThan(0)
+
+    if (MODE !== 'record') {
+      const snapshot = await captureStableAria(page, '[data-plan-review-key]', scaffold.workspaceCwd)
+      await compareOrRefreshGolden(REVIEW_EXPECTED, snapshot, MODE)
+    }
+
+    await card.getByRole('button', { name: 'Approve' }).click()
+
+    const sessionId = await settled
+    if (MODE === 'record') {
+      await recordFixture(scaffold, sessionId, FIXTURE)
+      return
+    }
+    // World state: the approval reached the tool, and plan mode is left behind.
+    const results = sessionEvents.filter(e => e.type === 'tool/result')
+    expect(JSON.stringify(results.at(-1))).toContain('Plan approved')
+    await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
+    // Card gone; regular input restored.
+    expect(await page.locator('[data-plan-review-key]').count()).toBe(0)
+    await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true)
+    const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(APPROVED_EXPECTED, snapshot, MODE)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  }, 200_000)
+
+  it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
+    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'review.expected.md', 'approved.expected.md'])
+  })
+})
--- a/apps/web/tests/queue-actions.e2e.ts
+++ b/apps/web/tests/queue-actions.e2e.ts
@@ -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'],
+    )
  })
 })
--- a/apps/web/tests/scaffold-hermetic.e2e.ts
+++ b/apps/web/tests/scaffold-hermetic.e2e.ts
@@ -0,0 +1,57 @@
+import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { expect, it } from 'vitest'
+import type {} from '@deepseek-ai/dsh-skill'
+import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
+
+async function writeSkill(root: string, name: string): Promise<void> {
+  const bundle = join(root, name)
+  await mkdir(bundle, { recursive: true })
+  await writeFile(join(bundle, 'SKILL.md'), `---
+name: ${name}
+description: Must not enter the Web replay scaffold
+---
+
+Ambient host state.
+`)
+}
+
+it('isolates replay skill discovery from every ambient host root', async () => {
+  const ambient = await mkdtemp(join(tmpdir(), 'dsh-web-ambient-skills-'))
+  const dshHome = join(ambient, 'dsh-home')
+  const agentsHome = join(ambient, 'agents-home')
+  const bundled = join(ambient, 'bundled')
+  await Promise.all([
+    writeSkill(join(dshHome, 'skills'), 'ambient-dsh'),
+    writeSkill(join(agentsHome, 'skills'), 'ambient-agents'),
+    writeSkill(bundled, 'ambient-bundled'),
+  ])
+
+  const originalDshHome = process.env.DSH_HOME
+  const originalAgentsHome = process.env.DSH_AGENTS_HOME
+  const originalBundled = process.env.DSH_BUNDLED_SKILL_DIR
+  process.env.DSH_HOME = dshHome
+  process.env.DSH_AGENTS_HOME = agentsHome
+  process.env.DSH_BUNDLED_SKILL_DIR = bundled
+  let scaffold: WebScaffold | undefined
+  try {
+    scaffold = await launchWebScaffold()
+    const names = (await scaffold.ctx.skills.list({ cwd: scaffold.workspaceCwd })).map(skill => skill.name)
+    expect(names).not.toContain('ambient-dsh')
+    expect(names).not.toContain('ambient-agents')
+    expect(names).not.toContain('ambient-bundled')
+  } finally {
+    try {
+      await scaffold?.close()
+    } finally {
+      if (originalDshHome === undefined) delete process.env.DSH_HOME
+      else process.env.DSH_HOME = originalDshHome
+      if (originalAgentsHome === undefined) delete process.env.DSH_AGENTS_HOME
+      else process.env.DSH_AGENTS_HOME = originalAgentsHome
+      if (originalBundled === undefined) delete process.env.DSH_BUNDLED_SKILL_DIR
+      else process.env.DSH_BUNDLED_SKILL_DIR = originalBundled
+      await rm(ambient, { recursive: true, force: true })
+    }
+  }
+})
--- a/apps/web/tests/scaffold.ts
+++ b/apps/web/tests/scaffold.ts
@@ -9,12 +9,13 @@
 // from live session memory), refresh (keyless replay that rewrites goldens).
 //
 // Composition divergences from `dsh web`, all deliberate, all via include
-// patches after the shipped surface overlay: temp persistenceRoot;
-// workspace-context disabled (recorded fixtures must not embed this repo's
-// AGENTS.md); session-title-llm disabled (its fire-and-forget title call
-// would race the loop for the session's replay cursor); webserver pinned to
-// port 0 with the built dist; keyless modes disable llm-deepseek and fill
-// the open llm seam post-boot with installLlmReplay on the settled root ctx
+// patches after the shipped surface overlay: temp persistenceRoot; local skill
+// roots confined to the temp workspace; workspace-context disabled (recorded
+// fixtures must not embed this repo's AGENTS.md); session-title-llm disabled
+// (its fire-and-forget title call would race the loop for the session's replay
+// cursor); webserver pinned to port 0 with the built dist; keyless modes
+// disable llm-deepseek and fill the open llm seam post-boot with
+// installLlmReplay on the settled root ctx
 // (the plugin-row path discards the ReplayHandle; the direct install keeps
 // assertConsumed for the teardown fixture-consumption check).
 import { existsSync } from 'node:fs'
@@ -172,12 +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' }] }]
--- a/apps/web/tests/snapshots/approval-composer/session.jsonl
+++ b/apps/web/tests/snapshots/approval-composer/session.jsonl
--- a/apps/web/tests/snapshots/approval-composer/ui.expected.md
+++ b/apps/web/tests/snapshots/approval-composer/ui.expected.md
@@ -0,0 +1,4 @@
+- text: 等待审批
+- group "审批详情": "escalate sandbox to workspace-write: Need to write the notes.txt file as requested by the user. echo 'tok63z tokc7y tokibx tokofw tokujv tok10nu tok16rt tok1cvs tok1izr tok1p3q tok1v7p tok21bo tok2a4 tok8e3 tokei2 tokkm1 tokqq0 tokwtz tok12xy tok191x tok1f5w tok1l9v tok1rdu tok1xht tok23ls tok4k8 tokao7 tokgs6 tokmw5 tokt04 tokz43 tok1582 tok1bc1 tok1hg0 tok1njz tok1tny tok1zrx tokqd tok6uc tokcyb tokj2a tokp69 tokva8 tok11e7 tok17i6 tok1dm5 tok1jq4 tok1pu3 tok1vy2 tok2221 tok30h tok94g tokf8f toklce tokrgd tokxkc tok13ob tok19sa tok1fw9 tok1m08 tok1s47 tok1y86 tok24c5 tok5al tokbek tokhij toknmi toktqh tokzug tok15yf tok1c2e tok1i6d tok1oac tok1ueb tok20ia tok1gq tok7kp tokdoo tokjsn tokpwm tokw0l tok124k tok188j tok1eci tok1kgh tok1qkg tok1wof tok22se tok3qu tok9ut tokfys tokm2r toks6q tokyap tok14eo tok1ain tok1gmm tok1mql tok1suk tok1yyj tok252i tok60y tokc4x toki8w tokocv tokugu tok10kt tok16os tok1csr tok1iwq tok1p0p tok1v4o tok218n tok273 tok8b2 tokef1 tokkj0 tokqmz tokwqy tok12ux tok18yw tok1f2v tok1l6u tok1rat tok1xes tok23ir tok4h7 tokal6 tokgp5 tokmt4 toksx3 tokz12 tok1551 tok1b90 tok1hcz tok1ngy tok1tkx tok1zow toknc tok6rb tokcva tokiz9 tokp38 tokv77 tok11b6 tok17f5 tok1dj4 tok1jn3 tok1pr2 tok1vv1 tok21z0 tok2xg tok91f tokf5e tokl9d tokrdc tokxhb tok13la tok19p9 tok1ft8 tok1lx7 tok1s16 tok1y55 tok2494 tok57k tokbbj tokhfi toknjh tokktng tokzrf tok15ve tok1bzd tok1i3c tok1o7b tok1uba tok20f9 tok1dp tok7ho tokdln tokjpm tokptl tokvxk tok121j tok185i tok1e9h tok1kdg tok1qhf tok1wle tok22pd tok3nt tok9rs tokfvr toklzq toks3p toky7o tok14bn tok1afm tok1gjl tok1mnk tok1srj tok1yvi tok24zh tok5xx tokc1w toki5v toko9u tokudt tok10hs tok16lr tok1cpq tok1itp tok1oxo tok1v1n tok215m tok242 tok881 tokec0 tokfz tokqjy tokwnx' > notes.txt"
+- button "拒绝"
+- button "允许一次"
--- a/apps/web/tests/snapshots/details-session-lifecycle/handles.expected.md
+++ b/apps/web/tests/snapshots/details-session-lifecycle/handles.expected.md
@@ -0,0 +1,7 @@
+# AppFrame drag handles
+
+## sidebar
+
+- hit strip present: true
+- cursor: col-resize
+- pill generated: false
--- a/apps/web/tests/snapshots/message-actions/fork.expected.md
+++ b/apps/web/tests/snapshots/message-actions/fork.expected.md
@@ -0,0 +1,7 @@
+- tree "Sessions":
+  - treeitem "Ungrouped 3 sessions" [expanded]:
+    - img
+    - text: Ungrouped 3 sessions
+  - treeitem "Use the read tool twice (2) now" [selected]
+  - treeitem "Use the read tool twice (1) now"
+  - treeitem "Use the read tool twice 1min"
--- a/apps/web/tests/snapshots/navigation-panes/trajectory.expected.md
+++ b/apps/web/tests/snapshots/navigation-panes/trajectory.expected.md
@@ -11,7 +11,7 @@
      - cell "SYSTEM"
      - cell "Initial System Prompt"
    - 'row "USER, NavScenario: first run bash to print exactly NAVIGATION_OK, then read nav-a.md and nav-b.md using two read calls in ONE assistant message, then reply with the single word FIRST_DONE and stop."':
-      - cell "Turn 1 USER"
+      - cell "Turn 1 USER": USER
      - 'cell "NavScenario: first run bash to print exactly NAVIGATION_OK, then read nav-a.md and nav-b.md using two read calls in ONE assistant message, then reply with the single word FIRST_DONE and stop."'
    - 'row "Request 1, ASSISTANT, The user wants me to follow a specific navigation scenario. Let me: Run bash to print \"NAVIGATION_OK\" Read nav-a.md and nav-b.md in two read calls in ONE message Reply with \"FIRST_DONE\" Let me start with the bash command and the reads."':
      - 'cell "Request #1 ASSISTANT"':
@@ -33,7 +33,7 @@
        - text: ASSISTANT
      - cell "FIRST_DONE"
    - 'row "USER, Reply in markdown with: a level-2 heading \"Navigation Summary\", a bulleted list of exactly two items, and a fenced code block containing echo WATERFALL. Then stop."':
-      - cell "Turn 2 USER"
+      - cell "Turn 2 USER": USER
      - 'cell "Reply in markdown with: a level-2 heading \"Navigation Summary\", a bulleted list of exactly two items, and a fenced code block containing echo WATERFALL. Then stop."'
    - row "Request 3, ASSISTANT, Navigation Summary alpha nav beta nav echo WATERFALL":
      - 'cell "Request #3 ASSISTANT"':
--- a/apps/web/tests/snapshots/plan-review/approved.expected.md
+++ b/apps/web/tests/snapshots/plan-review/approved.expected.md
@@ -0,0 +1,46 @@
+- 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:
+  - 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
--- a/apps/web/tests/snapshots/plan-review/review.expected.md
+++ b/apps/web/tests/snapshots/plan-review/review.expected.md
@@ -0,0 +1,44 @@
+- region "Approve this plan and leave plan mode?":
+  - text: Plan review
+  - heading "Add --greeting flag to CLI" [level=1]:
+    - text: Add
+    - code: "--greeting"
+    - text: flag to CLI
+  - list:
+    - listitem:
+      - strong: Locate the CLI entry point
+      - text: (e.g.,
+      - code: cli.py
+      - text: ","
+      - code: main.go
+      - text: ","
+      - code: index.js
+      - text: etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).
+    - listitem:
+      - strong: Register a new optional string argument
+      - text: named
+      - code: "--greeting"
+      - text: with a short alias (
+      - code: "-g"
+      - text: if available) and a sensible default value (e.g.,
+      - code: "\"Hello\""
+      - text: ).
+    - listitem:
+      - strong: Thread the parsed value
+      - text: through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).
+    - listitem:
+      - strong: Update the help text
+      - text: so
+      - code: "--help"
+      - text: or
+      - code: "-h"
+      - text: shows the new flag with its description.
+    - listitem:
+      - strong: No tests or config changes
+      - text: unless they already exist and directly validate the flag's presence.
+  - status
+  - button "Chat about it":
+    - img
+    - text: Chat about it
+  - button "Refuse"
+  - button "Approve"
--- a/apps/web/tests/snapshots/plan-review/session.jsonl
+++ b/apps/web/tests/snapshots/plan-review/session.jsonl
@@ -0,0 +1,39 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785406804293,"cwd":"{{cwd}}/workspace"}
+{"type":"command/run","seq":0,"time":1785406804350,"data":{"commandId":"cmd-228a60ef-1","name":"plan","args":" Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop.","source":{"kind":"user"}}}
+{"type":"plan/mode","seq":1,"time":1785406804350,"data":{"active":true}}
+{"type":"command/done","seq":2,"time":1785406804352,"data":{"commandId":"cmd-228a60ef-1","kind":"success","text":"Plan mode on. Use /plan off to leave."}}
+{"type":"turn/start","seq":3,"time":1785406804353,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":4,"time":1785406804353,"data":{"content":[{"type":"text","text":"Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"a22bd0d2-15dc-4bfb-b978-0d5961459e57"},"surfaceOp":"append"}
+{"type":"session/title","seq":5,"time":1785406804354,"data":{"title":"Plan a small change: add","messageSeqs":[4],"source":{"kind":"fallback"}}}
+{"type":"step/start","seq":6,"time":1785406804355,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":7,"time":1785406804356,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"assistant/chunk","seq":8,"time":1785406805697,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"reasoning-chunks","seq0":9,"time0":1785406805698,"data":{"turn":1,"step":1,"index":0,"dt":[151,31,0,0,0,0,18,1,0,0,0,31,1,0,0,0,1,23,0,0,0,19,0,0,37,1,0,0,0,0,12,1,0,0,28,0,1,0,24,1,0,0,0,0,26,1,0,0,26,1,22],"texts":["The"," user"," wants"," me"," to"," plan"," a"," small"," change"," to"," add"," a"," `","--","gre","eting","`"," flag"," to"," a"," CLI","."," They"," explicitly"," told"," me"," not"," to"," read"," or"," write"," any"," files",","," and"," to"," call"," exit","_","plan","_mode"," with"," a"," short"," plan","."," Let"," me"," do"," that"," directly","."]}}
+{"type":"assistant/chunk","seq":61,"time":1785406806155,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
+{"type":"text-chunks","seq0":62,"time0":1785406806156,"data":{"turn":1,"step":1,"index":1,"dt":[0,20,0,34,23,26,0,1,0,0,28,0,0,0,32,0,15,1,0,30,1,0,0,23,1,0,24,0,0,0],"texts":["Since"," the"," user"," has"," explicitly"," asked"," me"," not"," to"," read"," or"," write"," any"," files"," and"," to"," go"," straight"," to"," planning",","," I","'ll"," proceed"," with"," `","exit","_","plan","_mode","`."]}}
+{"type":"assistant/chunk","seq":93,"time":1785406806493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":2,"blockType":"tool-call"}}}
+{"type":"tool-call-chunks","seq0":94,"time0":1785406806493,"data":{"turn":1,"step":1,"index":2,"dt":[27,1,0,0,0,24,0,0,29,1,0,0,0,1,20,0,27,1,0,21,28,0,0,31,1,23,0,0,1,23,0,0,0,23,1,0,28,20,26,28,1,0,29,1,0,0,21,28,0,0,25,1,26,1,0,0,24,1,0,26,0,0,0,1,23,1,0,0,22,29,0,31,1,1,0,21,1,0,0,0,0,20,0,32,25,0,0,22,0,0,27,0,1,0,31,0,1,0,0,20,1,0,0,0,0,24,0,1,0,26,1,29,1,26,1,0,25,30,1,18,0,30,0,0,30,21,1,28,0,21,1,0,0,23,1,23,36,0,0,1,0,13,1,28,27,0,0,25,1,45,1,11,0,21,0,0,0,0,23,0,0,32,1,0,0,0,16,28,0,27,1,0,22,31,1,24,1,21,32,1,0,24,1,0,24],"id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","args":["","{","\"","plan","\"",": ","\"","#"," Add"," `","--","gre","eting","`"," flag"," to"," CLI","\\n\\n","-"," **","Loc","ate"," the"," CLI"," entry"," point","**"," (","e",".g",".,"," `","cli",".py","`,"," `","main",".go","`,"," `","index",".js","`"," etc",".)"," and"," find"," the"," argument"," parser"," definition"," (","arg","parse",","," click",","," cob","ra",","," y","args",","," or"," similar",").\\n","-"," **","Register"," a"," new"," optional"," string"," argument","**"," named"," `","--","gre","eting","`"," with"," a"," short"," alias"," (`","-","g","`"," if"," available",")"," and"," a"," sensible"," default"," value"," (","e",".g",".,"," `","\\\"","Hello","\\\"","`",").\\n","-"," **","Thread"," the"," parsed"," value","**"," through"," the"," main"," handler"," function"," so"," it"," is"," passed"," where"," the"," greeting"," string"," is"," used"," (","e",".g",".,"," the"," welcome","/","response"," message",").\\n","-"," **","Update"," the"," help"," text","**"," so"," `","--","help","`"," or"," `","-","h","`"," shows"," the"," new"," flag"," with"," its"," description",".\\n","-"," **","No"," tests"," or"," config"," changes","**"," unless"," they"," already"," exist"," and"," directly"," validate"," the"," flag","'s"," presence",".","\"","}"]}}
+{"type":"assistant/chunk","seq":280,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."}}}}
+{"type":"assistant/chunk","seq":281,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."}}}}
+{"type":"assistant/chunk","seq":282,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":2,"block":{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}}}}
+{"type":"assistant/chunk","seq":283,"time":1785406808319,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52}}}}
+{"type":"assistant/chunk","seq":284,"time":1785406808319,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":285,"time":1785406808324,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."},{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."},{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"b9e18116-68f6-4442-b5a5-a33277ef526c"},"usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52}},"sourceEventSeqs":[8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284],"surfaceOp":"append"}
+{"type":"tool/call","seq":286,"time":1785406808325,"data":{"turn":1,"step":1,"callId":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}}
+{"type":"tool/result","seq":287,"time":1785406808720,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_TPh5fH8x5kRezK115kgx8155"},"content":[{"type":"tool-result","toolCallId":"call_00_TPh5fH8x5kRezK115kgx8155","content":[{"type":"text","text":"Plan approved — plan mode exited; carry out the plan starting with your next step."}],"isError":false}],"role":"user","id":"e7cf1f9f-e143-48df-b975-440a9d61a538"}},"sourceEventSeqs":[286],"surfaceOp":"append"}
+{"type":"step/end","seq":288,"time":1785406808721,"data":{"turn":1,"step":1}}
+{"type":"plan/mode","seq":289,"time":1785406808721,"data":{"active":false}}
+{"type":"step/start","seq":290,"time":1785406808723,"data":{"turn":1,"step":2}}
+{"type":"request/header","seq":291,"time":1785406808723,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
+{"type":"assistant/chunk","seq":292,"time":1785406809855,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"reasoning-chunks","seq0":293,"time0":1785406809855,"data":{"turn":1,"step":2,"index":0,"dt":[133,28,1,0,0,17,0,28,1,0,0,29,0,0,0,0,0,21,0,0,0,35,0,0,0,0,0,14,1,37,1,0,1,17,0,0,0,0,1],"texts":["The"," plan"," was"," approved","."," The"," user","'s"," last"," instruction"," says",":"," \"","Once"," the"," plan"," is"," approved",","," reply"," with"," the"," single"," word"," D","ONE"," and"," stop",".\""," So"," I"," should"," just"," reply"," with"," D","ONE"," and"," stop","."]}}
+{"type":"assistant/chunk","seq":333,"time":1785406810252,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":334,"time":1785406810253,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
+{"type":"assistant/chunk","seq":335,"time":1785406810253,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
+{"type":"assistant/chunk","seq":336,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."}}}}
+{"type":"assistant/chunk","seq":337,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
+{"type":"assistant/chunk","seq":338,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}}}}
+{"type":"assistant/chunk","seq":339,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":340,"time":1785406810257,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"2d9da552-d236-4166-9d06-dffa9bace4cd"},"usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}},"sourceEventSeqs":[292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339],"surfaceOp":"append"}
+{"type":"step/end","seq":341,"time":1785406810258,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":342,"time":1785406810258,"data":{"turn":1,"reason":{"kind":"completed"}}}
--- a/apps/web/tests/snapshots/queue-actions/collapsed.expected.md
+++ b/apps/web/tests/snapshots/queue-actions/collapsed.expected.md
@@ -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"
--- a/apps/web/tests/snapshots/queue-actions/editing.expected.md
+++ b/apps/web/tests/snapshots/queue-actions/editing.expected.md
@@ -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
--- a/apps/web/tsconfig.json
+++ b/apps/web/tsconfig.json
@@ -23,8 +23,11 @@
  // cannot see both sides of the cordis Context merges).
  "exclude": [
    "tests/scaffold.ts",
+    "tests/scaffold-hermetic.e2e.ts",
    "tests/live-interactions.e2e.ts",
    "tests/question-composer.e2e.ts",
+    "tests/approval-composer.e2e.ts",
+    "tests/plan-review.e2e.ts",
    "tests/steering.e2e.ts",
    "tests/navigation-panes.e2e.ts",
    "tests/lifecycle-chrome.e2e.ts",