Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input

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)
 })

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

@@ -3,7 +3,9 @@
 // else covers: sidebar cold listing, the implicit resume/attach inside the
 // history RPC, history-page tool views, and the client fold of historical
 // events — with ZERO model calls in replay (no replay fixture; a stray stream
-// fails loud on the open llm seam). The seed is a recorded fixture under the
+// fails loud on the open llm seam). The cold session also carries the one
+// keyless command-row surface: an Access-chip pick runs `/permission` on the
+// host, so the settled row's copy has a golden here. The seed is a recorded fixture under the
 // same record discipline as every other: DSH_SNAPSHOT=record drives the turn
 // live through the composer (real read tool against seeded workspace files)
 // and harvests seed.jsonl; replay/refresh seed it cold and only render.
@@ -24,6 +26,9 @@ import { newEnglishPage, saveFailureShot } from './support.ts'
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/seeded-history', import.meta.url))
 const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
 const UI_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/ui.expected.md', import.meta.url))
+// The command-row golden: the same conversation after one /permission switch,
+// which is the only surface that shows a settled command row's copy.
+const COMMAND_ROW_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/command-row.expected.md', import.meta.url))
 const MODE = webSnapshotMode()
 const SEED_ID = 'seeded-history-web-e2e'
 
@@ -225,11 +230,33 @@ describe('web e2e: seeded history renders through cold resume', () => {
     await expect.poll(() => page.getByText('a.txt', { exact: false }).count(), { timeout: 5_000 }).toBeGreaterThan(0)
   })
 
+  it.skipIf(MODE === 'record')('an Access-chip switch lands one command row: bare name, non-repeating settlement text', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-command-row'))
+    // The Access chip submits `/permission <preset>` — a host command with no
+    // model call, so the settled row renders keylessly over this cold history.
+    // The row copy is the assertion: `permission · preset workspace-write`,
+    // where neither half repeats the other (the dispatched `/` and its
+    // argument stay out of the title, and the settlement text never restates
+    // the command's own name).
+    await page.getByRole('button', { name: 'Access mode, current: Danger Full Access' }).click()
+    await page.getByRole('menuitem', { name: 'Workspace Write' }).click()
+    await page.getByRole('button', { name: 'Access mode, current: Workspace Write' }).waitFor({ timeout: 10_000 })
+    // Scoped to the row itself, so unrelated page text that happens to read
+    // `permission` (a future resident slash menu) cannot satisfy or break it.
+    const row = page.locator('[data-variant="others"]').filter({ hasText: 'preset workspace-write' })
+    await expect.poll(() => row.count(), { timeout: 10_000 }).toBe(1)
+    expect(await row.getByText('permission', { exact: true }).count()).toBe(1)
+    expect(await row.getByText('/permission workspace-write', { exact: true }).count()).toBe(0)
+    const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
+      .split(SEED_ID).join('{{seededId}}')
+    await compareOrRefreshGolden(COMMAND_ROW_EXPECTED, snapshot, MODE)
+  }, 60_000)
+
   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.
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
-    await assertFixtureInventory(SNAPSHOT_DIR, ['seed.jsonl', 'ui.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['command-row.expected.md', 'seed.jsonl', 'ui.expected.md'])
   })
 })

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

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"':

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

@@ -5,7 +5,7 @@
     - 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}}"
+- text: "plan 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":

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

@@ -0,0 +1,49 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Use the read tool twice" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then 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 read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.":
+  - img
+  - img
+  - text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel.
+- img
+- text: Read
+- button "a.txt"
+- img
+- text: Read
+- button "b.txt"
+- button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.":
+  - img
+  - img
+  - text: Think Both files have been read. a.txt contains "alpha" and b.txt contains "beta". I'll now reply with DONE as instructed.
+- paragraph: DONE
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- text: {{clock}}
+- button "上下文注入":
+  - img
+  - img
+  - text: 上下文注入
+- img
+- text: permission preset workspace-write
+- textbox "Message the agent"
+- button "Add attachment":
+  - img
+- 'button "Access mode, current: Workspace Write"': Workspace Write
+- 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 98% Input 15.8K tok · Output 135 tok