Merge remote-tracking branch 'origin/master' into worktree/default-workspace-write-ui-20260731

# Conflicts:
#	apps/cli/README.i18n.yaml

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

@@ -1,16 +1,16 @@
 // Keyless browser coverage for pending queue actions through the shipped Web
-// composition and real HTTP/SSE wire. A replay override parks the active turn
-// so two ordinary follow-ups remain addressable while the page edits one and
-// removes one. The queue uses an existing recorded model
-// call; this scenario owns only the user-visible mid-turn golden.
+// composition and real HTTP/SSE wire. Replay overrides park consecutive turns
+// so the page can edit and remove exact occurrences, then stop the active turn
+// while proving the preserved Queue advances in FIFO order.
 import { existsSync } from 'node:fs'
-import { mkdtemp, rm, writeFile } from 'node:fs/promises'
+import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises'
 import { tmpdir } from 'node:os'
 import { fileURLToPath } from 'node:url'
 import { join } from 'node:path'
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterEach, describe, expect, it, onTestFailed } from 'vitest'
+import { deriveReplayScript, parseSessionLog, type ReplayEntry } from '@deepseek-ai/dsh-llm-replay'
 import type { SessionEvent } from '@deepseek-ai/dsh-session'
 import {
   assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
@@ -22,6 +22,7 @@ const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/queue-actions', import.m
 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 PRESERVED_EXPECTED = join(SNAPSHOT_DIR, 'preserved.expected.md')
 const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
 const MODE = webSnapshotMode()
 
@@ -29,6 +30,12 @@ const ACTIVE_PROMPT = 'Reply with a one-sentence description of event sourcing,
 const REMOVE = 'Queue item to remove'
 const EDIT = 'Queue item to edit'
 const EDITED = 'Edited queue item'
+const TAIL = 'Queue item preserved after stop'
+
+/** Durable turn-end classifications observed by the scenario. */
+function turnEndReasons(events: readonly SessionEvent[]): string[] {
+  return events.flatMap(event => event.type === 'turn/end' ? [event.data.reason.kind] : [])
+}
 
 describe('web e2e: queue row actions', () => {
   let scaffold: WebScaffold | undefined
@@ -52,13 +59,19 @@ describe('web e2e: queue row actions', () => {
     if (failures.length > 1) throw new AggregateError(failures, 'queue-actions teardown failed')
   })
 
-  it.skipIf(MODE === 'record')('edits and removes exact pending occurrences', async () => {
+  it.skipIf(MODE === 'record')('edits and removes exact occurrences and preserves Queue across stop', async () => {
     overrideDir = await mkdtemp(join(tmpdir(), 'dsh-web-queue-actions-'))
     const readyFile = join(overrideDir, '.hang-ready')
+    const nextReadyFile = join(overrideDir, '.next-hang-ready')
     const overridePath = join(overrideDir, 'replay.override.json')
-    await writeFile(overridePath, JSON.stringify({
-      patches: [{ at: 0, entry: { kind: 'hang', readyFile } }],
-    }))
+    const recorded = deriveReplayScript(parseSessionLog(await readFile(FIXTURE, 'utf8')))
+    expect(recorded).toHaveLength(1)
+    const replay: ReplayEntry[] = [
+      { kind: 'hang', readyFile },
+      { kind: 'hang', readyFile: nextReadyFile },
+      recorded[0]!,
+    ]
+    await writeFile(overridePath, JSON.stringify(replay))
 
     const sessionEvents: SessionEvent[] = []
     scaffold = await launchWebScaffold({ replayFixture: FIXTURE, replayOverride: overridePath })
@@ -135,17 +148,34 @@ describe('web e2e: queue row actions', () => {
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
 
-    const editedRow = page.getByText(EDITED, { exact: true }).locator('..')
-    await editedRow.getByRole('button', { name: 'Remove queued message' }).click()
-    await expect.poll(() => page.getByText(EDITED, { exact: true }).count()).toBe(0)
+    await input.fill(TAIL)
+    await input.press('Enter')
+    await expect.poll(
+      () => page.getByRole('button', { name: 'Remove queued message' }).count(),
+      { timeout: 10_000 },
+    ).toBe(2)
+
+    await page.getByRole('button', { name: 'Stop generating' }).click()
+    await expect.poll(() => existsSync(nextReadyFile), { timeout: 15_000 }).toBe(true)
+    await page.getByText(TAIL, { exact: true }).waitFor()
+    await expect.poll(() => page.getByRole('button', { name: 'Remove queued message' }).count())
+      .toBe(1)
+
+    const preservedSnapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(PRESERVED_EXPECTED, preservedSnapshot, MODE)
+
     await page.getByRole('button', { name: 'Stop generating' }).click()
     await settled
+    expect(turnEndReasons(sessionEvents)).toEqual(['aborted', 'aborted', 'completed'])
+    expect(sessionEvents.filter(event => event.type === 'user/message' && event.data.source.kind === 'user'))
+      .toHaveLength(3)
+    await expect.poll(() => page.locator('[data-queue-dock]').count()).toBe(0)
   }, 120_000)
 
   it.skipIf(MODE === 'record')('keeps its snapshot inventory closed', async () => {
     await assertFixtureInventory(
       SNAPSHOT_DIR,
-      ['collapsed.expected.md', 'editing.expected.md', 'ui.expected.md'],
+      ['collapsed.expected.md', 'editing.expected.md', 'preserved.expected.md', 'ui.expected.md'],
     )
   })
 })

apps/web/tests/scaffold.ts

@@ -496,7 +496,7 @@ export async function seedSession(scaffold: WebScaffold, fixtureText: string, id
  * volatility collapse to stable tokens.
  */
 function normalizeAria(snapshot: string, workspaceCwd: string): string {
-  // The header breadcrumb renders the workspace's basename, not the full
+  // The session heading renders the workspace's basename, not the full
   // path, so both spellings must collapse to the token.
   const base = workspaceCwd.split('/').pop()!
   return snapshot

apps/web/tests/seeded-history.e2e.ts

@@ -357,6 +357,27 @@ describe('web e2e: seeded history renders through cold resume', () => {
     await compareOrRefreshGolden(COMMAND_ROW_EXPECTED, snapshot, MODE)
   }, 60_000)
 
+  it.skipIf(MODE === 'record')('fits short injected context without a scrollport', async () => {
+    const agent = scaffold.ctx.agents.get(SessionId(SEED_ID))
+    if (agent === undefined) throw new Error('seeded session did not attach an agent')
+    agent.inject(createUserMessage({
+      content: [{ type: 'text', text: 'Short injected context.' }],
+      source: { kind: 'plugin', plugin: 'fixture' },
+    }))
+
+    const disclosures = page.getByRole('button', { name: 'Context injection' })
+    await expect.poll(() => disclosures.count(), { timeout: 10_000 }).toBe(2)
+    const disclosure = disclosures.nth(1)
+    await disclosure.click()
+    await expect.poll(() => disclosure.getAttribute('aria-expanded')).toBe('true')
+
+    const body = page.locator('[data-context-injection-body]')
+    const bodyBox = await body.boundingBox()
+    if (bodyBox === null) throw new Error('short context disclosure geometry is not measurable')
+    expect(bodyBox.height).toBeLessThan(141)
+    expect(await body.evaluate(element => element.scrollHeight > element.clientHeight)).toBe(false)
+  })
+
   it.skipIf(MODE === 'record')('issued zero model calls and stayed clean', async () => {
     // No replay fixture was installed and the llm seam is open — any stray
     // stream would have failed the turn loudly. Cleanliness pins the wire.

apps/web/tests/snapshots/code-mode-round/ui.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - 'button "Using ONE run_code program: run" [disabled]'
+  - 'heading "Using ONE run_code program: run" [level=1]'
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/cordis-tool-round/ui.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use only Cordis tools. First" [disabled]
+  - heading "Use only Cordis tools. First" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/fresh-round-trip/ui.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use the bash tool to" [disabled]
+  - heading "Use the bash tool to" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Reply with the single word" [disabled]
+  - heading "Reply with the single word" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/live-interactions/cancel.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Reply with a one-sentence description" [disabled]
+  - heading "Reply with a one-sentence description" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Reply with a one-sentence description" [disabled]
+  - heading "Reply with a one-sentence description" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/live-interactions/loading.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Reply with a one-sentence description" [disabled]
+  - heading "Reply with a one-sentence description" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/live-interactions/retry.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Reply with a one-sentence description" [disabled]
+  - heading "Reply with a one-sentence description" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use the read tool twice" [disabled]
+  - heading "Use the read tool twice" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - 'button "Plan a small change: add" [disabled]'
+  - 'heading "Plan a small change: add" [level=1]'
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/question-composer/answered.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use the ask_user_question tool to" [disabled]
+  - heading "Use the ask_user_question tool to" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/queue-actions/collapsed.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Reply with a one-sentence description" [disabled]
+  - heading "Reply with a one-sentence description" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/queue-actions/editing.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Reply with a one-sentence description" [disabled]
+  - heading "Reply with a one-sentence description" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/queue-actions/preserved.expected.md

@@ -0,0 +1,43 @@
+- banner:
+  - heading "Reply with a one-sentence description" [level=1]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- button "Context injection":
+  - img
+  - img
+  - text: Context injection
+- paragraph: partial
+- text: Stopped
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- text: {{clock}} Edited queue item {{clock}}
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- paragraph: partial
+- status: Deep diving...
+- list:
+  - listitem:
+    - text: Queue item preserved after stop
+    - button "Edit queued message":
+      - img
+    - button "Remove queued message":
+      - img
+- textbox "Message the agent"
+- button "Commands":
+  - img
+- 'button "Access mode, current: Full access"': Full access
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Stop generating"
+- text: 1 turns · 1 steps Input 0 tok · Output 0 tok

apps/web/tests/snapshots/queue-actions/ui.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Reply with a one-sentence description" [disabled]
+  - heading "Reply with a one-sentence description" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/seeded-history/command-row.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use the read tool twice" [disabled]
+  - heading "Use the read tool twice" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/seeded-history/ui.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use the read tool twice" [disabled]
+  - heading "Use the read tool twice" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/steering/mid-steer.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use the ask_user_question tool to" [disabled]
+  - heading "Use the ask_user_question tool to" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/steering/settled.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use the ask_user_question tool to" [disabled]
+  - heading "Use the ask_user_question tool to" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/web-search-round/ui.expected.md

@@ -1,6 +1,5 @@
 - banner:
-  - navigation "Session hierarchy":
-    - button "Use web_search to search exactly" [disabled]
+  - heading "Use web_search to search exactly" [level=1]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"