Merge latest master into PR 555

# Conflicts:
#	docs/architecture.i18n.yaml
#	docs/core-data-structures/core.i18n.yaml
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	packages/client/runtime/README.i18n.yaml
#	packages/client/ui-conversation/README.i18n.yaml
#	packages/client/ui-conversation/src/client/chat/MessageItem.tsx
#	packages/compact/compact-basic/README.i18n.yaml
#	packages/ui/tui/README.i18n.yaml

apps/web/tests/live-interactions.e2e.ts

@@ -28,14 +28,14 @@ import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './suppor
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/live-interactions', import.meta.url))
 const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
 // One golden pins the stable mid-turn loading state; the other three capture
-// what the user is left looking at after cancel, after a non-retryable failure
-// (pins the FIXME(web-error-surface) gap as a reviewable artifact: NO error
-// copy in the tree), and after retry recovery.
+// what the user is left looking at after cancel, after a non-retryable failure,
+// and after retry recovery.
 const CANCEL_EXPECTED = join(SNAPSHOT_DIR, 'cancel.expected.md')
 const LOADING_EXPECTED = join(SNAPSHOT_DIR, 'loading.expected.md')
 const ERROR_EXPECTED = join(SNAPSHOT_DIR, 'error-auth.expected.md')
 const RETRY_EXPECTED = join(SNAPSHOT_DIR, 'retry.expected.md')
 const MODE = webSnapshotMode()
+const AUTH_PROVIDER_MESSAGE = 'Authentication Fails, Your api key: sk-preview-secret is invalid'
 
 // The recorded base: one text-only turn whose derived script the sidecars
 // patch. Kept deliberately tool-free so the derived script is exactly one
@@ -158,7 +158,7 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
 
   it.skipIf(MODE === 'record')('surfaces a non-retryable AUTH failure without retrying', async () => {
     await launch(() => ({
-      patches: [{ at: 0, entry: { kind: 'throw', chunks: [], message: 'invalid api key', code: 'AUTH' } }],
+      patches: [{ at: 0, entry: { kind: 'throw', chunks: [], message: AUTH_PROVIDER_MESSAGE, code: 'AUTH' } }],
     }))
     onTestFailed(() => saveFailureShot(page, 'web-e2e-error-auth'))
     const { settled } = await sendPrompt()
@@ -166,28 +166,28 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
     expect(turnEndReasons(sessionEvents).at(-1)).toBe('error')
     // AUTH is outside llm-retry's retryable set: no retry record.
     expect(sessionEvents.filter(e => e.type === 'llm/retry').length).toBe(0)
-    // Product gap found by this lane, pinned as-is: the client consumes no
-    // agent/error frames and a pre-chunk failure freezes no partial, so THIS
-    // failure renders no error copy anywhere — the user sees the send simply
-    // stop. FIXME(web-error-surface): assert visible error text here once the
-    // web UI grows an error rendering; until then the pinned contract is
-    // "no crash, composer recovers, turn logged as error".
     await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true)
     expect(await page.locator('[data-streaming="true"]').count()).toBe(0)
-    // The blank workspace also has an enabled composer. Wait for the driven
-    // session's only visible message before capturing its no-error-copy state.
-    await expect.poll(() => page.getByText(PROMPT, { exact: true }).first().isVisible(), { timeout: 10_000 }).toBe(true)
-    // Golden of the same gap: the prompt bubble alone, no error copy in the
-    // tree — the diff that changes when web-error-surface lands.
+    const errorStatus = page.getByRole('status').filter({ hasText: 'This turn failed' })
+    await errorStatus.waitFor({ timeout: 10_000 })
+    expect(await errorStatus.textContent()).toContain('API key is invalid')
+    expect(await errorStatus.textContent()).toContain('AUTH')
+    expect(await page.locator('body').textContent()).not.toContain('sk-preview-secret')
     const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold!.workspaceCwd)
     await compareOrRefreshGolden(ERROR_EXPECTED, snapshot, MODE)
+    await page.getByRole('tab', { name: 'Trajectory' }).click()
+    const requestMarker = page.locator('tr[data-request-only="true"]').last()
+      .getByRole('button', { name: /Request #/ })
+    await requestMarker.click()
+    await page.getByText('API key is invalid', { exact: true }).waitFor({ timeout: 10_000 })
+    expect(await page.locator('body').textContent()).not.toContain('sk-preview-secret')
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
   }, 120_000)
 
   it.skipIf(MODE === 'record')('keeps a terminal request marker inside the trajectory table', async () => {
     await launch(() => ({
-      patches: [{ at: 0, entry: { kind: 'throw', chunks: [], message: 'invalid api key', code: 'AUTH' } }],
+      patches: [{ at: 0, entry: { kind: 'throw', chunks: [], message: AUTH_PROVIDER_MESSAGE, code: 'AUTH' } }],
     }))
     const { settled } = await sendPrompt()
     await settled

apps/web/tests/shipped-composition.e2e.ts

@@ -0,0 +1,83 @@
+// Boots the shipped Web composition over the built dist this lane already uses
+// and asserts what that composition produces: the model-visible tool catalog
+// and the sandbox/approval knobs it ships with. No browser and no model call —
+// these are composition facts, and the browser scenarios in this lane cover the
+// surface itself.
+import { tmpdir } from 'node:os'
+import { afterEach, expect, it } from 'vitest'
+import { canonicalPath, writableRoots } from '@deepseek-ai/dsh-sandbox'
+// Empty type imports carry the tools/sandboxPolicy/approval Context merges.
+import type {} from '@deepseek-ai/dsh-tools'
+import type {} from '@deepseek-ai/dsh-sandbox-policy'
+import type {} from '@deepseek-ai/dsh-user-approval'
+import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
+
+/**
+ * The catalog the shipped Web composition puts in front of the model, minus the
+ * ripgrep-dependent pair below. The absences are deliberate, not incidental
+ * gaps: the `cordis_*` toolset executes model-written JavaScript that no
+ * sandbox row confines, `web_fetch` chooses its own request target, and
+ * `mcp_*` servers spawn outside `ctx.bash`. The composition Agent Note owns the
+ * rationale and its sources.
+ */
+const EXPECTED_TOOLS = [
+  'ask_user_question',
+  'bash',
+  'create_goal',
+  'edit',
+  'exit_plan_mode',
+  'get_goal',
+  'ralph',
+  'read',
+  'session_event_read',
+  'session_event_search',
+  'session_event_trace',
+  'session_search',
+  'session_trace',
+  'skill',
+  'str_replace_editor',
+  'subagent',
+  'subagent_fork',
+  'task_kill',
+  'task_list',
+  'task_output',
+  'todo_write',
+  'update_goal',
+  'web_search',
+  'workflow',
+  'write',
+]
+
+/**
+ * `glob` and `grep` come from `dsh-tool-fs-search`, which probes `command -v rg`
+ * through the mounted bash executor at load and registers neither tool when
+ * ripgrep is absent. That is a host dependency, not a composition decision, so the
+ * pair is asserted separately — present together or absent together.
+ */
+const RIPGREP_TOOLS = ['glob', 'grep']
+
+let scaffold: WebScaffold | undefined
+
+afterEach(async () => {
+  await scaffold?.close()
+  scaffold = undefined
+})
+
+it('assembles the shipped Web catalog and keeps its access default', async () => {
+  scaffold = await launchWebScaffold()
+  const names = scaffold.ctx.tools.schemas().map(schema => schema.name).sort()
+  expect(names.filter(name => !RIPGREP_TOOLS.includes(name))).toEqual(EXPECTED_TOOLS)
+  expect([[], RIPGREP_TOOLS]).toContainEqual(names.filter(name => RIPGREP_TOOLS.includes(name)))
+  // `workspace-write` is not "the workspace and nothing else": the shared roots
+  // helper always admits the temp directories too. Pinning it against an
+  // explicit mode keeps the claim independent of this surface's default, and
+  // keeps a future boundary test from being run inside /tmp — where an
+  // "escape" write succeeds by design and reads as a sandbox failure.
+  expect(writableRoots(scaffold.ctx.sandboxPolicy.resolve({ mode: 'workspace-write' }))).toEqual(
+    expect.arrayContaining([canonicalPath('/tmp'), canonicalPath(tmpdir())]),
+  )
+  // The Web surface keeps its shipped access default; the base's confined one
+  // reaches the TUI. Pinning both keeps a base change from moving Web silently.
+  expect(scaffold.ctx.sandboxPolicy.defaultMode).toBe('danger-full-access')
+  expect(scaffold.ctx.approval.config.policy).toBe('never')
+}, 120_000)

apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md

@@ -1,6 +1,7 @@
 - listbox "Trigger suggestions":
   - text: Commands
-  - option "goal set or view the goal for a long-running task" [selected]
+  - option "compact Compact older conversation history" [selected]
+  - option "goal set or view the goal for a long-running task"
   - option "permission Switch the permission preset (sandbox mode + approval policy)"
   - option "plan Enter or leave plan mode"
   - option "model Select the model for this conversation"

apps/web/tests/snapshots/live-interactions/error-auth.expected.md

@@ -13,6 +13,9 @@
   - img
   - img
   - text: Context injection
+- status:
+  - text: This turn failedAPI key is invalid
+  - code: AUTH
 - textbox "Message the agent"
 - button "Commands":
   - img

apps/web/tests/startup-auto-selection.e2e.ts

@@ -0,0 +1,119 @@
+// Web e2e scenario: startup auto-selection keeps the hero on screen.
+//
+// A page load with a workspace already registered runs
+// `WorkspacesService.startInitialSelection`: it connects the most recent
+// workspace and opens its blank session. `openState` flips to `loading` the
+// moment `open()` lands, which used to drive `data-phase=settling` on the
+// conversation root — `visibility:hidden` over the composer seat and the
+// header for the whole `session.history` round-trip, so the center column went
+// blank and repainted, reading as a full-page refresh on every launch.
+//
+// The unit spec pins the phase condition over hand-built stores. What only the
+// assembled application can show is that the path a user actually takes
+// reaches it: the real selection service, the real client session opening over
+// the real /api transport, and a real browser deciding what is painted.
+//
+// The round-trip against a loopback host is far too fast to observe, so this
+// scenario HOLDS the `session.history` response open at the browser's network
+// boundary and asserts the visible frame while it is in flight. That gate is
+// what makes the assertions non-vacuous: with the exemption reverted the held
+// window is exactly when `settling` is painted and the composer is hidden.
+//
+// Zero model calls: registering a workspace and opening its blank session are
+// host RPCs with no model involvement. A stray stream would fail loud with
+// NO_ADAPTER.
+import type { Browser, Page } from 'playwright'
+import { chromium } from 'playwright'
+import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import { acknowledgeReloadConnectionLoss, launchWebScaffold, watchConsole, type WebScaffold } from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+/** Wire path of the history round-trip the conversation root waits out (POST /api/session.history). */
+const HISTORY_ROUTE = '**/api/session.history'
+
+/**
+ * The conversation root's own phase attribute. `div` disambiguates it from the
+ * composer textarea, which carries an unrelated `data-phase` of its own.
+ */
+const ROOT_PHASE = 'div[data-phase]'
+
+/** Every distinct `data-phase` the conversation root shows, in order, across one page load. */
+function recordedPhases(page: Page): Promise<string[]> {
+  return page.evaluate(() => (window as unknown as { __conversationPhases: string[] }).__conversationPhases)
+}
+
+describe('web e2e: startup auto-selection', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({})
+    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 })
+    // A registered workspace is the precondition for auto-selection: the first
+    // load has nothing to select, so the reload below is the path under test.
+    await connectFreshWorkspace(page, scaffold.workspaceCwd, 'startup-auto-selection')
+  }, 180_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('keeps the hero and the composer on screen while the auto-selected blank session opens', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-startup-auto-selection'))
+    // Runs before any page script on the reload below, so the first phase the
+    // root ever renders is recorded, not just the ones after a listener attaches.
+    await page.addInitScript(() => {
+      const phases: string[] = []
+      ;(window as unknown as { __conversationPhases: string[] }).__conversationPhases = phases
+      setInterval(() => {
+        const phase = document.querySelector('div[data-phase]')?.getAttribute('data-phase')
+        if (phase === null || phase === undefined) return
+        if (phases[phases.length - 1] !== phase) phases.push(phase)
+      }, 8)
+    })
+
+    let releaseHistory = (): void => {}
+    const historyHeld = new Promise<void>((resolve) => { releaseHistory = resolve })
+    let historyRequested = (): void => {}
+    const historyInFlight = new Promise<void>((resolve) => { historyRequested = resolve })
+    let gated = false
+    await page.route(HISTORY_ROUTE, async (route) => {
+      // Only the auto-selection's own round-trip is held; later pages must not
+      // deadlock behind a gate this test has already released.
+      if (gated) { await route.continue(); return }
+      gated = true
+      historyRequested()
+      await historyHeld
+      await route.continue()
+    })
+
+    const warningsBefore = tripwire.warnings.length
+    await page.reload({ waitUntil: 'commit' })
+    await historyInFlight
+
+    // The frame a user sees while the session is still opening: hero phase, the
+    // hero title, and a composer that is actually painted (`settling` hides the
+    // seat with `visibility:hidden`, which Playwright reports as not visible).
+    await page.waitForSelector(ROOT_PHASE, { timeout: 15_000 })
+    expect(await page.locator(ROOT_PHASE).first().getAttribute('data-phase')).toBe('hero')
+    expect(await page.getByText("Let's start building").isVisible()).toBe(true)
+    expect(await page.locator('textarea').first().isVisible()).toBe(true)
+
+    releaseHistory()
+    await page.locator('textarea:enabled[placeholder="Describe what you want to build"]')
+      .waitFor({ timeout: 15_000 })
+    acknowledgeReloadConnectionLoss(tripwire, warningsBefore)
+
+    // Settling is not merely absent from the frame sampled above: the root
+    // never entered it at any point of the load.
+    expect(await recordedPhases(page)).toEqual(['hero'])
+    expect(tripwire.pageErrors).toEqual([])
+  }, 120_000)
+})

apps/web/tsconfig.json

@@ -48,7 +48,9 @@
     "tests/queue-actions.e2e.ts",
     "tests/skill-invocation-policy.e2e.ts",
     "tests/permission-policy-context.e2e.ts",
-    "tests/access-confirmation.e2e.ts"
+    "tests/access-confirmation.e2e.ts",
+    "tests/shipped-composition.e2e.ts",
+    "tests/startup-auto-selection.e2e.ts"
   ],
   "references": [
     {