Merge remote-tracking branch 'origin/master' into worktree/context-source-cards

# Conflicts:
#	packages/client/runtime/README.i18n.yaml
#	packages/client/runtime/README.md
#	packages/client/runtime/README.zh.md
#	packages/client/ui-conversation/README.i18n.yaml

apps/web/tests/access-confirmation.e2e.ts

@@ -2,7 +2,6 @@
 // the same locale-aware, in-page risk confirmation. Zero model calls: the
 // scenario boots the shipped Web composition and exercises the real
 // permission projection, client command path, HTTP RPC, and pushed update.
-import { mkdirSync } from 'node:fs'
 import { fileURLToPath } from 'node:url'
 import { join } from 'node:path'
 import type { Browser, Page } from 'playwright'
@@ -12,27 +11,7 @@ import {
   assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
-
-/**
- * connectFreshWorkspace twin over the product default Chinese locale (the
- * shared helper's anchors assume the English page every other scenario
- * boots; this scenario deliberately keeps zh, so the localized picker
- * copy is the anchor set).
- */
-async function connectFreshWorkspaceZh(page: Page, root: string, name = 'workspace'): Promise<void> {
-  mkdirSync(join(root, name), { recursive: true })
-  await page.getByRole('button', { name: '选择工作区' }).click()
-  const dialog = page.getByRole('dialog', { name: '选择工作区目录' })
-  await dialog.waitFor({ timeout: 10_000 })
-  await dialog.getByRole('button', { name: '编辑路径' }).click()
-  const pathInput = dialog.getByRole('textbox', { name: '编辑路径' })
-  await pathInput.fill(join(root, name))
-  await pathInput.press('Enter')
-  await dialog.getByRole('button', { name: '打开', exact: true }).click()
-  await page.locator('textarea:enabled[placeholder="描述你想要构建的内容"]')
-    .waitFor({ timeout: 15_000 })
-}
+import { ZH_BROWSER_LOCALE, connectFreshWorkspaceZh, saveFailureShot } from './support.ts'
 
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/access-confirmation', import.meta.url))
 const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')

apps/web/tests/composer-tab-geometry.e2e.ts

@@ -0,0 +1,420 @@
+// Web e2e scenario: the input card holds one horizontal position across the
+// Chat and Trajectory tabs.
+//
+// The composer seat is the same node in both tabs, but it measures itself
+// against a different edge in each (see
+// packages/client/ui-conversation/src/client/skeleton/ConversationRoot.module.css).
+// In Chat it is a sticky CHILD of the column's scroller, so it rides that
+// scroller's content box — the box a space-consuming scrollbar shortens. A view
+// that opts into a composer overlay (`data-conversation-composer-overlay`, which
+// Trajectory declares and which moves the column's own scrolling into the view)
+// gets an absolutely positioned seat instead, laid out against the padding box,
+// which the scrollbar never reduces.
+//
+// So the two tabs disagreed by exactly the bar's width for as long as the
+// transcript overflowed: the card jumped sideways on every tab switch, and
+// inside Chat alone at the moment a growing transcript started to scroll. The
+// column now reserves the gutter unconditionally (`scrollbar-gutter: stable`)
+// and states the overlay branch as a scroll container on the same axes, so both
+// edges are the same edge.
+//
+// Only a real engine can show this. The seat's geometry is layout: jsdom gives
+// every element a zero-sized box and reports no scrollbar at all, so a unit spec
+// can assert the declarations exist but not that the two states land in the same
+// place. What is asserted here is the user-visible fact — the card does not move
+// — measured as the distance between the two tabs' card rectangles.
+//
+// The browser is launched WITHOUT Playwright's default `--hide-scrollbars`,
+// which is load-bearing rather than incidental. Under that argument a scroll
+// container's bar consumes no layout width at all, so the two tabs agree before
+// this change as much as after it and every comparison below holds vacuously —
+// measured: the pre-fix cascade leaves both tabs' bands at 0 there, against 8
+// and 0 with the argument dropped. Dropping it is also the faithful
+// configuration: ui-theme's scrollbar.css gives `::-webkit-scrollbar` a width,
+// and a bar that occupies layout space is what the product actually draws.
+//
+// The scenario runs that pre-fix cascade in the page — `scrollbar-gutter: auto`
+// on the scroller, `overflow: hidden` on the overlay branch — and measures the
+// same two tabs through it, which is what keeps the equal rectangles above from
+// being explained by a tab switch that never reached the layout. It is the
+// reported symptom as a number: the card moves 4px, half the 8px band, on each
+// edge.
+//
+// Zero model calls: a seeded cold session renders from its log, and switching
+// tabs asks the host for nothing. A stray stream would fail loud with NO_ADAPTER.
+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 { createChatScrollFixture } from './chat-scroll-fixture.ts'
+import {
+  assertFixtureInventory, compareOrRefreshGolden, launchWebScaffold, seedSession, watchConsole,
+  webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/composer-tab-geometry', import.meta.url))
+/**
+ * Committed golden of where the input card sits in each tab, at a wide viewport
+ * (card at its width cap) and a narrow one (card shrinking with the column).
+ *
+ * Absolute coordinates are deliberately absent: they depend on the sidebar's
+ * laid-out width and on font metrics, so committing them would produce a fixture
+ * that has to be re-recorded per platform. What is recorded is the distance
+ * between the two tabs' rectangles, which is zero when the reservation holds and
+ * the bar's width when it does not — including under the control, so the golden
+ * carries the difference the fix removes rather than only its absence.
+ */
+const GEOMETRY_EXPECTED = join(SNAPSHOT_DIR, 'geometry.expected.md')
+const MODE = webSnapshotMode()
+
+/** Long enough that the transcript overflows the lane's 1000px viewport; the scenario asserts the overflow rather than trusting it. */
+const FIXTURE = createChatScrollFixture({
+  markerPrefix: 'TAB_GEOMETRY',
+  title: 'COMPOSER_TAB_GEOMETRY long session',
+  turns: 24,
+})
+const SEED_ID = 'composer-tab-geometry-web-e2e'
+
+/** Viewport widths the scenario measures at: the card capped, and the card shrinking with the column. */
+const WIDE_VIEWPORT = { width: 1680, height: 1000 }
+const NARROW_VIEWPORT = { width: 800, height: 1000 }
+
+/**
+ * Resize to one measurement viewport after the responsive sidebar and center
+ * column finish their track transition.
+ * @param page - the page under test.
+ * @param viewport - the viewport dimensions to apply.
+ * @param sidebarCollapsed - the sidebar state expected at this width.
+ */
+async function setMeasuredViewport(
+  page: Page,
+  viewport: { width: number; height: number },
+  sidebarCollapsed: boolean,
+): Promise<void> {
+  await page.setViewportSize(viewport)
+  await page.locator('[data-sidebar-collapsed="true"]').waitFor({
+    state: sidebarCollapsed ? 'attached' : 'detached',
+    timeout: 10_000,
+  })
+  await page.locator('[data-conversation-scroll]').evaluate(async (host) => {
+    const deadline = performance.now() + 5_000
+    let previous = host.getBoundingClientRect().width
+    let stableFrames = 0
+    while (performance.now() < deadline) {
+      await new Promise<void>((resolve) => { requestAnimationFrame(() => { resolve() }) })
+      const current = host.getBoundingClientRect().width
+      stableFrames = Math.abs(current - previous) < 0.01 ? stableFrames + 1 : 0
+      if (stableFrames >= 3) return
+      previous = current
+    }
+    throw new Error('conversation width did not settle after the viewport changed')
+  })
+}
+
+/**
+ * The pre-fix cascade, injected into the page: the reservation dropped and the
+ * overlay branch back to a hidden box. `!important` beats the module rules
+ * without a rebuild, and the id lets the control be lifted again in the same
+ * session.
+ */
+const CONTROL_STYLE_ID = 'composer-tab-geometry-control'
+const CONTROL_CSS = `
+[data-conversation-scroll] { scrollbar-gutter: auto !important; }
+[data-conversation-scroll]:has([data-conversation-composer-overlay]) { overflow: hidden !important; }
+`
+
+/** The column scroller and the input card as the browser lays them out, in one tab. */
+interface TabMetrics {
+  /** Resolved `scrollbar-gutter` on the column's scroller. */
+  gutter: string
+  /** Resolved `overflow-x`: `hidden` in both states, so neither grows a horizontal bar. */
+  overflowX: string
+  /** Resolved `overflow-y`: `auto` in both states, which is the form WebKit honours the gutter on. */
+  overflowY: string
+  /** Border-box width minus client width: the space the scrollbar takes out of the content area. */
+  band: number
+  /** True when the column's scroller actually scrolls — only Chat does. */
+  scrolls: boolean
+  /** Left edge of the input card in viewport coordinates. */
+  cardLeft: number
+  /** Right edge of the input card. */
+  cardRight: number
+  /** Width of the input card, capped at the composer card max width. */
+  cardWidth: number
+}
+
+/** One tab's metrics beside the other's, plus the distances between them. */
+interface TabComparison {
+  chat: TabMetrics
+  trajectory: TabMetrics
+  /** Distance between the two tabs' card left edges: 0 when the card holds its position. */
+  leftShift: number
+  /** Distance between the two tabs' card right edges. */
+  rightShift: number
+  /** Difference between the two tabs' card widths. */
+  widthShift: number
+}
+
+/**
+ * Measure the column scroller and the input card in the tab currently shown.
+ * @param page - the page under test.
+ * @returns the scroller's resolved overflow style and the card's rectangle.
+ */
+function measureTab(page: Page): Promise<TabMetrics> {
+  return page.evaluate(() => {
+    const host = document.querySelector<HTMLElement>('[data-conversation-scroll]')
+    if (host === null) throw new Error('conversation column scroller not in the DOM')
+    const card = host.querySelector<HTMLElement>('[data-composer-seat] [data-composer-card]')
+    if (card === null) throw new Error('no input card inside the composer seat')
+    const style = getComputedStyle(host)
+    const hostRect = host.getBoundingClientRect()
+    const cardRect = card.getBoundingClientRect()
+    return {
+      gutter: style.scrollbarGutter,
+      overflowX: style.overflowX,
+      overflowY: style.overflowY,
+      band: hostRect.width - host.clientWidth,
+      scrolls: host.scrollHeight > host.clientHeight,
+      cardLeft: cardRect.left,
+      cardRight: cardRect.right,
+      cardWidth: cardRect.width,
+    }
+  })
+}
+
+/**
+ * Show one tab and wait for the view that owns it to be laid out.
+ * @param page - the page under test.
+ * @param tab - the tab to show.
+ */
+async function showTab(page: Page, tab: 'Chat' | 'Trajectory'): Promise<void> {
+  await page.getByRole('tab', { name: tab, exact: true }).click()
+  if (tab === 'Trajectory') await page.getByLabel('Trajectory timeline').waitFor({ timeout: 30_000 })
+  else await page.locator('[data-conversation-scroll] [data-chat-anchor-key]').first().waitFor({ timeout: 30_000 })
+  // Both measurements are taken after a paint, so a rectangle read mid-transition
+  // cannot be reported as a shift the cascade did not cause.
+  await page.evaluate(() => new Promise<void>((settle) => {
+    requestAnimationFrame(() => { requestAnimationFrame(() => { settle() }) })
+  }))
+}
+
+/**
+ * Measure both tabs and the distances between them, leaving Chat shown.
+ * @param page - the page under test.
+ * @returns each tab's metrics and the card's displacement between them.
+ */
+async function compareTabs(page: Page): Promise<TabComparison> {
+  await showTab(page, 'Chat')
+  const chat = await measureTab(page)
+  await showTab(page, 'Trajectory')
+  const trajectory = await measureTab(page)
+  await showTab(page, 'Chat')
+  return {
+    chat,
+    trajectory,
+    leftShift: Math.abs(trajectory.cardLeft - chat.cardLeft),
+    rightShift: Math.abs(trajectory.cardRight - chat.cardRight),
+    widthShift: Math.abs(trajectory.cardWidth - chat.cardWidth),
+  }
+}
+
+/**
+ * Run the pre-fix cascade in the page for one measurement, then lift it.
+ * @param page - the page under test.
+ * @returns the comparison as the column laid out before this change.
+ */
+async function compareTabsWithoutReservation(page: Page): Promise<TabComparison> {
+  await page.evaluate(({ id, css }) => {
+    const style = document.createElement('style')
+    style.id = id
+    style.textContent = css
+    document.head.append(style)
+  }, { id: CONTROL_STYLE_ID, css: CONTROL_CSS })
+  try {
+    return await compareTabs(page)
+  } finally {
+    await page.evaluate((id) => { document.getElementById(id)?.remove() }, CONTROL_STYLE_ID)
+  }
+}
+
+/**
+ * Open the seeded session from the sidebar search.
+ *
+ * Cold summaries carry the temp workspace's basename, so the persisted first
+ * message is the stable identity to search for, and the query itself drives the
+ * lazy content-index reconciliation. Hand-rolled polling because `expect.poll`
+ * is test-scoped and this runs in `beforeAll`.
+ * @param page - the page under test.
+ */
+async function openSeededSession(page: Page): Promise<void> {
+  const search = page.getByRole('textbox', { name: 'Search name, keywords...', exact: true })
+  await search.fill(FIXTURE.markers.user(1))
+  const results = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
+  const deadline = Date.now() + 60_000
+  for (;;) {
+    if (await results.count() === 1) break
+    if (Date.now() > deadline) throw new Error('seeded session never appeared in the sidebar search results')
+    await page.waitForTimeout(200)
+  }
+  await results.click()
+}
+
+/**
+ * Render the golden body.
+ * @param wide - comparison at the viewport where the card sits at its width cap.
+ * @param narrow - comparison at the viewport where the card shrinks with the column.
+ * @param control - comparison at the wide viewport with the reservation removed.
+ * @returns the golden body, without a trailing newline.
+ */
+function renderGeometry(wide: TabComparison, narrow: TabComparison, control: TabComparison): string {
+  const section = (name: string, comparison: TabComparison): string[] => [
+    `## ${name}`,
+    '',
+    `- Chat: scrollbar-gutter ${comparison.chat.gutter}, overflow ${comparison.chat.overflowX}/${comparison.chat.overflowY}`,
+    `- Chat scroller scrolls: ${String(comparison.chat.scrolls)}`,
+    `- Chat reserved band: ${String(comparison.chat.band)}px`,
+    `- Trajectory: scrollbar-gutter ${comparison.trajectory.gutter}, overflow ${comparison.trajectory.overflowX}/${comparison.trajectory.overflowY}`,
+    `- Trajectory scroller scrolls: ${String(comparison.trajectory.scrolls)}`,
+    `- Trajectory reserved band: ${String(comparison.trajectory.band)}px`,
+    `- input card left edge moves between tabs: ${String(comparison.leftShift)}px`,
+    `- input card right edge moves between tabs: ${String(comparison.rightShift)}px`,
+    `- input card width changes between tabs: ${String(comparison.widthShift)}px`,
+    '',
+  ]
+  return [
+    '# Input card position across the Chat and Trajectory tabs',
+    '',
+    ...section(`Wide viewport (${String(WIDE_VIEWPORT.width)}px, card at its cap)`, wide),
+    ...section(`Narrow viewport (${String(NARROW_VIEWPORT.width)}px, card shrinking with the column)`, narrow),
+    ...section('Wide viewport, reservation removed in the page (control)', control),
+  ].join('\n').trimEnd()
+}
+
+describe('web e2e: input card position across view tabs', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({})
+    await seedSession(scaffold, FIXTURE.log, SEED_ID)
+    // Scrollbars must take layout space here or the scenario proves nothing;
+    // see the file header for the measurement behind dropping this argument.
+    browser = await chromium.launch({ ignoreDefaultArgs: ['--hide-scrollbars'] })
+    page = await newEnglishPage(browser, WIDE_VIEWPORT.height)
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await openSeededSession(page)
+    await page.getByRole('tab', { name: 'Chat', exact: true }).waitFor({ timeout: 30_000 })
+    await page.getByText(FIXTURE.markers.assistant(FIXTURE.turns), { exact: false }).last()
+      .waitFor({ timeout: 30_000 })
+  }, 180_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('reserves the same gutter in both tabs while the transcript scrolls', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-band'))
+    await setMeasuredViewport(page, WIDE_VIEWPORT, false)
+    // Vacuity guard, in two parts. A transcript that does not overflow gives
+    // Chat no scrollbar, and a hidden or overlaid bar gives it no width; either
+    // would make the tabs agree without the reservation doing anything.
+    await expect.poll(async () => (await measureTab(page)).scrolls, { timeout: 10_000 }).toBe(true)
+    const comparison = await compareTabs(page)
+    expect(comparison.chat.band).toBeGreaterThan(0)
+    // The reservation reaches both states, which is the whole change: the same
+    // band, on a box that scrolls and on one that only holds a view.
+    expect(comparison.chat.gutter).toBe('stable')
+    expect(comparison.trajectory.gutter).toBe('stable')
+    expect(comparison.trajectory.band).toBe(comparison.chat.band)
+    // Declared as a scroll container on both axes rather than left to compute:
+    // `overflow: hidden` would drop the reservation in WebKit, and a `visible`
+    // horizontal axis computes to `auto` beside a scrolling one.
+    expect(comparison.trajectory.overflowY).toBe('auto')
+    expect(comparison.trajectory.overflowX).toBe('hidden')
+    // Only Chat scrolls this box; the Trajectory view owns its own scrollers.
+    expect(comparison.trajectory.scrolls).toBe(false)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('holds the input card in place when the tab changes', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-wide'))
+    await setMeasuredViewport(page, WIDE_VIEWPORT, false)
+    const comparison = await compareTabs(page)
+    // The reported symptom as a number. At this viewport the card sits at its
+    // width cap, so the pre-fix shift showed up as a centring difference — half
+    // the band on each edge — rather than as a width change.
+    expect(comparison.leftShift).toBe(0)
+    expect(comparison.rightShift).toBe(0)
+    expect(comparison.widthShift).toBe(0)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('holds the input card in place at a viewport where it shrinks with the column', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-narrow'))
+    await setMeasuredViewport(page, WIDE_VIEWPORT, false)
+    const capped = await measureTab(page)
+    await setMeasuredViewport(page, NARROW_VIEWPORT, true)
+    const comparison = await compareTabs(page)
+    // The other geometry, and a different failure: below the cap the card takes
+    // the column's width, so an unreserved gutter changed its WIDTH by the whole
+    // band instead of shifting it by half. Asserted against the capped
+    // measurement rather than against the cap's pixel value, which belongs to
+    // the stylesheet.
+    expect(comparison.chat.cardWidth).toBeLessThan(capped.cardWidth)
+    expect(comparison.leftShift).toBe(0)
+    expect(comparison.rightShift).toBe(0)
+    expect(comparison.widthShift).toBe(0)
+    await setMeasuredViewport(page, WIDE_VIEWPORT, false)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('moves the card again once the reservation is removed in the page', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-control'))
+    await setMeasuredViewport(page, WIDE_VIEWPORT, false)
+    // The control: without it, equal rectangles could also mean the tab switch
+    // never reached the layout. Under the pre-fix cascade the Chat scroller keeps
+    // its bar and the Trajectory branch goes back to a hidden box with none, and
+    // the card moves by half the band on each edge.
+    const comparison = await compareTabsWithoutReservation(page)
+    expect(comparison.chat.gutter).toBe('auto')
+    expect(comparison.chat.band).toBeGreaterThan(0)
+    expect(comparison.trajectory.band).toBe(0)
+    expect(comparison.leftShift).toBe(comparison.chat.band / 2)
+    expect(comparison.rightShift).toBe(comparison.chat.band / 2)
+    // Restoring the sheet restores the fix, so the control cannot leak into the
+    // remaining measurements.
+    const restored = await compareTabs(page)
+    expect(restored.leftShift).toBe(0)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('matches the committed tab geometry golden', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-golden'))
+    await setMeasuredViewport(page, WIDE_VIEWPORT, false)
+    const wide = await compareTabs(page)
+    await setMeasuredViewport(page, NARROW_VIEWPORT, true)
+    const narrow = await compareTabs(page)
+    await setMeasuredViewport(page, WIDE_VIEWPORT, false)
+    const control = await compareTabsWithoutReservation(page)
+    await compareOrRefreshGolden(GEOMETRY_EXPECTED, renderGeometry(wide, narrow, control), MODE)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('commits exactly the fixtures it reads', async () => {
+    // The seeded session is generated in-process, so the geometry golden is the
+    // whole inventory.
+    await assertFixtureInventory(SNAPSHOT_DIR, ['geometry.expected.md'])
+  })
+
+  it.skipIf(MODE === 'record')('issued zero model calls and stayed clean', () => {
+    expect(tripwire.warnings).toEqual([])
+    expect(tripwire.pageErrors).toEqual([])
+  })
+})

apps/web/tests/lifecycle-chrome.e2e.ts

@@ -104,6 +104,10 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
       await input.press('Enter')
       const planButton = activePage.getByRole('button', { name: 'Plan mode on, press to turn off' })
       await planButton.waitFor({ timeout: 10_000 })
+      // The golden encodes an empty composer, and the button arriving does not
+      // mean the submitted text is gone yet: under load the capture caught a
+      // textbox still holding `/plan`.
+      await expect.poll(() => input.inputValue(), { timeout: 10_000 }).toBe('')
       const planSnapshot = await captureStableAria(activePage, '[class*="frame"]', activeScaffold.workspaceCwd)
       await compareOrRefreshGolden(PLAN_ACTIVE_EXPECTED, planSnapshot, MODE)
       const planStyle = await planButton.evaluate((element) => {

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

@@ -126,9 +126,8 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
 
   it.skipIf(MODE === 'record')('matches the conversation aria golden with IconActions and clocks', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-message-actions-aria'))
-    await page.getByRole('button', {
-      name: 'Select model, current deepseek-v4-flash',
-    }).waitFor({ timeout: 10_000 })
+    await page.getByRole('button', { name: 'Select model', exact: true })
+      .waitFor({ timeout: 10_000 })
     // Keep a footer focused so opacity-hidden actions stay in the a11y tree
     // as an active/focused control during the capture.
     await page.getByRole('button', { name: 'Copy' }).first().focus()

apps/web/tests/onboarding-deepseek-config.e2e.ts

@@ -12,7 +12,7 @@ import {
   acknowledgeReloadConnectionLoss, assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
+import { ZH_BROWSER_LOCALE, connectFreshWorkspaceZh, saveFailureShot } from './support.ts'
 import { settingsNamespace } from '@deepseek-ai/dsh-settings'
 import {
   WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_COPY, WELCOME_NOTICE_SETTINGS_NAMESPACE,
@@ -22,6 +22,7 @@ import {
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/onboarding-deepseek-config', import.meta.url))
 const WELCOME_EXPECTED = join(SNAPSHOT_DIR, 'welcome.expected.md')
 const MISSING_EXPECTED = join(SNAPSHOT_DIR, 'missing.expected.md')
+const MODELS_EXPECTED = join(SNAPSHOT_DIR, 'models.expected.md')
 const MODE = webSnapshotMode()
 
 describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup', () => {
@@ -160,7 +161,60 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
     expect(tripwire.pageErrors).toEqual([])
   }, 60_000)
 
+  it('configures arbitrary DeepSeek models and prompts after the selected model is removed', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-deepseek-models'))
+    // Opened here rather than inherited: the credential test reloads the page
+    // to exercise the welcome step, so nothing carries an open dialog across.
+    await page.getByRole('button', { name: '设置', exact: true }).click()
+    const settings = page.getByRole('dialog', { name: '设置' })
+    await settings.waitFor({ timeout: 10_000 })
+    await settings.getByRole('button', { name: '模型' }).click()
+    const deepSeek = settings.getByText('DeepSeek', { exact: true }).first()
+    await deepSeek.waitFor({ timeout: 10_000 })
+    await deepSeek.locator('xpath=ancestor::li').getByRole('button', { name: '编辑' }).click()
+    await settings.getByText('自定义设置').click()
+    await settings.getByRole('button', { name: /删除模型/ }).first().click()
+    await settings.getByRole('button', { name: '添加模型' }).click()
+    const customModelId = settings.getByLabel('模型 ID 2')
+    await customModelId.fill('private-preview')
+    await settings.getByLabel('显示名称 2').fill('Private Preview')
+    // Capacities live behind the row's own disclosure, as in the pi-ai form.
+    await settings.getByRole('button', { name: '容量 2' }).click()
+    await settings.getByLabel('上下文窗口 2').fill('131072')
+    await settings.getByLabel('最大输出 token 数 2').fill('64K')
+
+    const modelEditor = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(MODELS_EXPECTED, modelEditor, MODE)
+    await settings.getByRole('button', { name: '保存', exact: true }).click()
+    await customModelId.waitFor({ state: 'detached', timeout: 15_000 })
+
+    const document = await readFile(join(scaffold.harnessHome, 'settings.yaml'), 'utf8')
+    expect(document).toContain('id: deepseek-v4-pro')
+    expect(document).toContain('id: private-preview')
+    expect(document).toContain('name: Private Preview')
+    expect(document).toContain('contextWindow: 131072')
+    expect(document).toContain('maxTokens: 64000')
+    expect(document).not.toContain('id: deepseek-v4-flash')
+
+    await page.keyboard.press('Escape')
+    // A connected Workspace is what puts a live composer — and its model
+    // trigger — on the page; the scaffold boots without one.
+    await connectFreshWorkspaceZh(page, scaffold.workspaceCwd, 'model-fallback-e2e')
+
+    const modelTrigger = page.getByRole('button', { name: '选择模型', exact: true })
+    await modelTrigger.waitFor({ timeout: 10_000 })
+    await modelTrigger.click()
+    await page.getByRole('menuitem', { name: /模型/ }).click()
+    expect(await page.getByText('deepseek-v4-flash', { exact: true }).count()).toBe(0)
+    await page.getByRole('menuitemradio', { name: 'Private Preview' }).waitFor({ timeout: 10_000 })
+    expect(tripwire.warnings).toEqual([])
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
   it('keeps the fixture inventory closed', async () => {
-    await assertFixtureInventory(SNAPSHOT_DIR, ['missing.expected.md', 'welcome.expected.md'])
+    await assertFixtureInventory(
+      SNAPSHOT_DIR,
+      ['missing.expected.md', 'models.expected.md', 'welcome.expected.md'],
+    )
   })
 })

apps/web/tests/scaffold.ts

@@ -56,7 +56,7 @@ import type {} from '@deepseek-ai/dsh-agent'
 import { prepareWebRuntimeContext } from '../../cli/src/web.ts'
 import { DIST_INDEX, REPO_ROOT, requireDist } from './support.ts'
 
-/** Snapshot mode for the lane, from $DSH_SNAPSHOT (same vocabulary as the ACP/TUI suites). */
+/** Snapshot mode for the lane, from $DSH_SNAPSHOT (same vocabulary as the other snapshot suites). */
 export type WebSnapshotMode = 'replay' | 'record' | 'refresh'
 
 /**
@@ -592,9 +592,9 @@ export async function compareOrRefreshGolden(goldenPath: string, actual: string,
 }
 
 /**
- * Fixture-inventory guard (the TUI afterAll shape): the scenario directory
- * holds exactly the expected files and every committed JSONL is a scrub
- * fixed-point without a run-local browser RPC id.
+ * Fixture-inventory guard: the scenario directory holds exactly the expected
+ * files and every committed JSONL is a scrub fixed-point without a run-local
+ * browser RPC id.
  * @param dir - the scenario snapshot directory.
  * @param expected - the exact expected file inventory.
  */

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

@@ -245,12 +245,11 @@ describe('web e2e: seeded history renders through cold resume', () => {
 
   it.skipIf(MODE === 'record')('matches the historical conversation aria golden', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-aria'))
-    await page.getByRole('button', {
-      // This scenario deliberately leaves the LLM seam open to prove zero
-      // model calls. History still restores the selected id, but no catalog
-      // adapter exists to provide its presentation name.
-      name: 'Select model, current deepseek-v4-flash',
-    }).waitFor({ timeout: 10_000 })
+    // This scenario deliberately leaves the LLM seam open to prove zero
+    // model calls. History still restores the routed id, but without an
+    // advertised catalog row the selector prompts for a listed replacement.
+    await page.getByRole('button', { name: 'Select model', exact: true })
+      .waitFor({ timeout: 10_000 })
     const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
       .split(SEED_ID).join('{{seededId}}')
     await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)

apps/web/tests/settings-chrome.e2e.ts

@@ -61,6 +61,30 @@ describe('web e2e: settings modal and General preferences', () => {
     await dialog.getByRole('button', { name: 'Workspace Write' }).waitFor({ timeout: 10_000 })
     await expect.poll(() => dialog.getByText('语言', { exact: true }).count(), { timeout: 5_000 }).toBe(1)
     await expect.poll(() => dialog.getByText('外观', { exact: true }).count(), { timeout: 5_000 }).toBe(1)
+    const openDocument = dialog.getByRole('button', { name: '打开配置文件' })
+    await openDocument.waitFor({ timeout: 10_000 })
+    let openRequests = 0
+    await page.route('**/api/settings.openDocument', async (route) => {
+      const envelope = route.request().postDataJSON() as {
+        rpcId: string
+        payload: Record<string, never>
+      }
+      expect(envelope.payload).toEqual({})
+      openRequests += 1
+      await route.fulfill({
+        status: 200,
+        contentType: 'application/json',
+        body: JSON.stringify({
+          type: 'server-response',
+          rpcId: envelope.rpcId,
+          result: { ok: true, value: { opened: true } },
+        }),
+      })
+    })
+    await openDocument.click()
+    await expect.poll(() => openRequests, { timeout: 5_000 }).toBe(1)
+    await expect.poll(() => openDocument.isEnabled(), { timeout: 5_000 }).toBe(true)
+    await page.unroute('**/api/settings.openDocument')
     // Golden of the freshly opened dialog (default zh, General active).
     const snapshot = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
     await compareOrRefreshGolden(DIALOG_EXPECTED, snapshot, MODE)

apps/web/tests/snapshots/bash-abort-row/ui.expected.md

@@ -26,8 +26,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 1 turns · 1 steps Tool call {{duration}} Cache hit 0% Input 10 tok · Output 10 tok

apps/web/tests/snapshots/composer-tab-geometry/geometry.expected.md

@@ -0,0 +1,37 @@
+# Input card position across the Chat and Trajectory tabs
+
+## Wide viewport (1680px, card at its cap)
+
+- Chat: scrollbar-gutter stable, overflow auto/auto
+- Chat scroller scrolls: true
+- Chat reserved band: 8px
+- Trajectory: scrollbar-gutter stable, overflow hidden/auto
+- Trajectory scroller scrolls: false
+- Trajectory reserved band: 8px
+- input card left edge moves between tabs: 0px
+- input card right edge moves between tabs: 0px
+- input card width changes between tabs: 0px
+
+## Narrow viewport (800px, card shrinking with the column)
+
+- Chat: scrollbar-gutter stable, overflow auto/auto
+- Chat scroller scrolls: true
+- Chat reserved band: 8px
+- Trajectory: scrollbar-gutter stable, overflow hidden/auto
+- Trajectory scroller scrolls: false
+- Trajectory reserved band: 8px
+- input card left edge moves between tabs: 0px
+- input card right edge moves between tabs: 0px
+- input card width changes between tabs: 0px
+
+## Wide viewport, reservation removed in the page (control)
+
+- Chat: scrollbar-gutter auto, overflow auto/auto
+- Chat scroller scrolls: true
+- Chat reserved band: 8px
+- Trajectory: scrollbar-gutter auto, overflow hidden/hidden
+- Trajectory scroller scrolls: false
+- Trajectory reserved band: 0px
+- input card left edge moves between tabs: 4px
+- input card right edge moves between tabs: 4px
+- input card width changes between tabs: 0px

apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md

@@ -30,8 +30,8 @@
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
 - button "Plan mode on, press to turn off": Plan
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: Details

apps/web/tests/snapshots/markdown-images/ui.expected.md

@@ -24,8 +24,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 1 turns · 1 steps Input 0 tok · Output 0 tok

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

@@ -51,8 +51,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 2 turns · 3 steps Tool call {{duration}} Cache hit 98% Input 7.8K tok · Output 103 tok

apps/web/tests/snapshots/models-settings/configured.expected.md

@@ -7,6 +7,7 @@
     - button "模型":
       - img
       - text: 模型
+  - button "打开配置文件"
   - button "关闭":
     - img
     - text: 关闭

apps/web/tests/snapshots/models-settings/empty.expected.md

@@ -7,6 +7,7 @@
     - button "模型":
       - img
       - text: 模型
+  - button "打开配置文件"
   - button "关闭":
     - img
     - text: 关闭

apps/web/tests/snapshots/onboarding-deepseek-config/models.expected.md

@@ -0,0 +1,71 @@
+- dialog "设置":
+  - navigation:
+    - text: 设置
+    - button "通用设置":
+      - img
+      - text: 通用设置
+    - button "模型":
+      - img
+      - text: 模型
+  - button "打开配置文件"
+  - button "关闭":
+    - img
+    - text: 关闭
+  - heading "模型" [level=2]
+  - paragraph: 填入各提供方的 API 密钥即可使用其模型。
+  - list:
+    - listitem:
+      - text: DeepSeek
+      - button "编辑"
+      - text: DeepSeek deepseek-official API 密钥
+      - textbox "API 密钥":
+        - /placeholder: 已配置——输入新值可替换
+      - group:
+        - text: 自定义设置 API 地址
+        - textbox "API 地址":
+          - /placeholder: https://api.deepseek.com
+        - text: 推理强度
+        - combobox "推理强度":
+          - option "默认" [selected]
+          - option "off"
+          - option "high"
+          - option "max"
+        - region "模型目录":
+          - text: 模型目录 已自定义模型目录
+          - button "恢复默认模型"
+          - textbox "模型 ID 1":
+            - /placeholder: 模型 ID
+            - text: deepseek-v4-pro
+          - textbox "显示名称 1":
+            - /placeholder: 显示名称
+            - text: DeepSeek-V4-Pro
+          - button "容量 1":
+            - img
+          - button "删除模型 1":
+            - img
+          - textbox "模型 ID 2":
+            - /placeholder: 模型 ID
+            - text: private-preview
+          - textbox "显示名称 2":
+            - /placeholder: 显示名称
+            - text: Private Preview
+          - button "容量 2" [expanded]:
+            - img
+          - button "删除模型 2":
+            - img
+          - text: 上下文窗口
+          - textbox "上下文窗口 2":
+            - /placeholder: 1M
+            - text: "131072"
+          - text: 最大输出 token 数
+          - textbox "最大输出 token 数 2":
+            - /placeholder: 256K
+            - text: 64K
+          - button "添加模型":
+            - img
+            - text: 添加模型
+      - button "取消"
+      - button "保存"
+  - button "添加提供方":
+    - img
+    - text: 添加提供方

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

@@ -47,8 +47,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Read Only"': Read Only
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok

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

@@ -45,8 +45,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok

apps/web/tests/snapshots/settings-chrome/dialog.expected.md

@@ -7,6 +7,7 @@
     - button "模型":
       - img
       - text: 模型
+  - button "打开配置文件"
   - button "关闭":
     - img
     - text: 关闭

apps/web/tests/support.ts

@@ -88,6 +88,28 @@ export async function connectFreshWorkspace(page: Page, root: string, name = 'wo
     .waitFor({ timeout: 15_000 })
 }
 
+/**
+ * {@link connectFreshWorkspace} over the product default Chinese locale: the
+ * English helper's anchors assume the locale every other scenario boots, so a
+ * scenario that deliberately keeps zh needs the localized picker copy.
+ * @param page - the browser page under test.
+ * @param root - workspace parent directory.
+ * @param name - directory created under `root` and connected.
+ */
+export async function connectFreshWorkspaceZh(page: Page, root: string, name = 'workspace'): Promise<void> {
+  mkdirSync(join(root, name), { recursive: true })
+  await page.getByRole('button', { name: '选择工作区' }).click()
+  const dialog = page.getByRole('dialog', { name: '选择工作区目录' })
+  await dialog.waitFor({ timeout: 10_000 })
+  await dialog.getByRole('button', { name: '编辑路径' }).click()
+  const pathInput = dialog.getByRole('textbox', { name: '编辑路径' })
+  await pathInput.fill(join(root, name))
+  await pathInput.press('Enter')
+  await dialog.getByRole('button', { name: '打开', exact: true }).click()
+  await page.locator('textarea:enabled[placeholder="描述你想要构建的内容"]')
+    .waitFor({ timeout: 15_000 })
+}
+
 /** Failure evidence goes to the gitignored .artifacts/ (repo convention). */
 export async function saveFailureShot(page: Page, name: string): Promise<void> {
   const dir = fileURLToPath(new URL('../../../.artifacts', import.meta.url))

apps/web/tests/workspace-management.e2e.ts

@@ -90,9 +90,9 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff
       { timeout: 10_000 },
     ).not.toBeUndefined()
     // First adoption births a blank Session+Agent whose workspace attach must
-    // settle before a test may delete the registration; the reuse path (same
-    // canonical cwd already has a blank session) creates no agent, so callers
-    // opt in only where a fresh attach is possible.
+    // settle before a test may delete the registration; re-registration after
+    // a delete mints a fresh blank Session+Agent too (the old cwd-only reuse
+    // path is gone), so callers opt in only where a fresh attach is possible.
     if (options.waitForAgent === true) {
       await expect.poll(() => scaffold.ctx.agents.list().length, { timeout: 10_000 })
         .toBeGreaterThan(agentsBefore)
@@ -251,8 +251,10 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff
     expect((await scaffold.ctx.sessionPersistence.inspect(SessionId(SEED_ID))).events.length).toBeGreaterThan(0)
 
     // Re-registering the exact deleted path immediately, without a reload, is
-    // a supported reversible flow. It creates a fresh Workspace id without
-    // re-adopting the retained Session.
+    // a supported reversible flow. It creates a fresh Workspace id and does
+    // NOT re-adopt the retained (non-blank) Session; the New Session flow
+    // mints a fresh blank session and attaches it to the new registration
+    // (the old cwd-only blank reuse is gone, so the account is never empty).
     await adoptDirectory(scaffold.workspaceCwd)
     await expect.poll(
       () => scaffold.ctx.workspace.resolveByPath(scaffold.workspaceCwd),
@@ -261,7 +263,11 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff
     const reregistered = await scaffold.ctx.workspace.resolveByPath(scaffold.workspaceCwd)
     expect(reregistered?.id).toBeDefined()
     expect(reregistered?.id).not.toBe(workspace.id)
-    expect(reregistered?.sessionIds).toEqual([])
+    await expect.poll(
+      () => reregistered?.sessionIds ?? [],
+      { timeout: 10_000 },
+    ).not.toEqual([])
+    expect(reregistered?.sessionIds).not.toContain(SEED_ID)
     await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 10_000 })
       .toBeGreaterThanOrEqual(1)
     expect(await readFile(join(scaffold.workspaceCwd, 'workspace', 'a.txt'), 'utf8')).toBe('alpha\n')