Merge remote-tracking branch 'github/master' into xtr/trajectory-timeline-polish

# Conflicts:
#	packages/client/ui-trajectory/src/client/timeline.ts
#	packages/client/ui-trajectory/tests/views.spec.tsx

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

@@ -2,6 +2,7 @@
 // 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'
@@ -11,7 +12,7 @@ import {
   assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { saveFailureShot } from './support.ts'
+import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
 
 /**
  * connectFreshWorkspace twin over the product default Chinese locale (the
@@ -19,13 +20,16 @@ import { saveFailureShot } from './support.ts'
  * boots; this scenario deliberately keeps zh, so the localized picker
  * copy is the anchor set).
  */
-async function connectFreshWorkspaceZh(page: Page, name = 'workspace'): Promise<void> {
+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()
-  await page.getByRole('menuitem', { name: '新建工作区' }).click()
-  const dialog = page.getByRole('dialog', { name: '新建工作区' })
+  const dialog = page.getByRole('dialog', { name: '选择工作区目录' })
   await dialog.waitFor({ timeout: 10_000 })
-  await dialog.getByLabel('新工作区名称').fill(name)
-  await dialog.getByRole('button', { name: '创建工作区' }).click()
+  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 })
 }
@@ -49,11 +53,11 @@ describe('web e2e: Full access confirmation', () => {
     browser = await chromium.launch(executablePath === undefined ? {} : { executablePath })
     // Keep the product default Chinese locale: the golden pins the actual
     // registered dictionary rather than a test-local translation callback.
-    page = await browser.newPage({ viewport: { width: 1680, height: 1000 } })
+    page = await browser.newPage({ viewport: { width: 1680, height: 1000 }, locale: ZH_BROWSER_LOCALE })
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    await connectFreshWorkspaceZh(page)
+    await connectFreshWorkspaceZh(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

apps/web/tests/approval-composer.e2e.ts

@@ -61,7 +61,7 @@ describe('web e2e: approval takeover keeps its actions reachable', () => {
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

apps/web/tests/built-boot.snapshot.ts

@@ -112,11 +112,19 @@ it('boots the built plugin graph and renders a fixture session end to end', asyn
   }, { timeout: 10_000 })
 
   // The write/edit turns render a real diff card through the assembled graph
-  // (the keyed FileMutationRow + DiffBlock), not just the fixture's raw text.
-  // The write turn's `hello fixture\n` proves the terminator rule end to end: a
-  // trailing newline terminates its line, so the footer reads `+1` (not a
-  // phantom `+2`) and one distinct file. The `+ ` prefix is a CSS ::before, so
-  // it is absent from textContent — assert on the line body and the footer.
+  // (the keyed FileMutationRow composing ToolRow + DiffBlock), not just the
+  // fixture's raw text. The card is collapsed by default, so expand each edit/
+  // write row first. The write turn's `hello fixture\n` proves the terminator
+  // rule end to end: a trailing newline terminates its line, so the footer reads
+  // `+1` (not a phantom `+2`) and one distinct file. The `+ ` prefix is a CSS
+  // ::before, so it is absent from textContent — assert on the line body and the
+  // footer.
+  const mutationRows = [...document.querySelectorAll('[data-variant="write"],[data-variant="edit"]')]
+  expect(mutationRows.length).toBeGreaterThan(0)
+  for (const row of mutationRows) {
+    const toggle = row.querySelector('[data-expandable]')
+    if (toggle !== null) act(() => { fireEvent.click(toggle) })
+  }
   const diffCards = [...document.querySelectorAll('[data-diff]')]
   expect(diffCards.length).toBeGreaterThan(0)
   const footers = diffCards.map(card => card.textContent ?? '')
@@ -125,13 +133,20 @@ it('boots the built plugin graph and renders a fixture session end to end', asyn
   // The web render intent reaches the assembled boot graph: the fixture's
   // web_search / web_fetch turns render their keyed WebRow cards, proving the
   // registration, wire projection, and card rendering survive the real bundle
-  // path (not just the per-package src benches). The selector pins the KEYED
-  // WebRow (its own `data-variant="web"` wrapper), not the `[data-web]` attribute
-  // WebBlock draws — the generic fallback renders the same WebBlock, so a silent
-  // keyed-registration failure would still satisfy a bare `[data-web]` check.
+  // path (not just the per-package src benches). WebRow composes ToolRow, so the
+  // card is collapsed behind the row; the keyed row is pinned by its `data-tool`
+  // (ToolRow sets it from the wire tool name).
+  const webSearchRow = await waitFor(() => {
+    const row = document.querySelector('[data-tool="web_search"]')
+    expect(row).not.toBeNull()
+    expect(document.querySelector('[data-tool="web_fetch"]')).not.toBeNull()
+    return row!
+  }, { timeout: 10_000 })
+  // Expand the web_search row to prove its WebBlock card renders end to end.
+  const webToggle = webSearchRow.querySelector('[data-expandable]')
+  if (webToggle !== null) act(() => { fireEvent.click(webToggle) })
   await waitFor(() => {
-    expect(document.querySelector('[data-variant="web"][data-tool="web_search"]')).not.toBeNull()
-    expect(document.querySelector('[data-variant="web"][data-tool="web_fetch"]')).not.toBeNull()
+    expect(webSearchRow.querySelector('[data-web]')).not.toBeNull()
   }, { timeout: 10_000 })
 
   // Every bundle injected its plugin-owned style tag (the loader's CSS path).

apps/web/tests/code-mode-round.e2e.ts

@@ -49,7 +49,7 @@ describe('web e2e: Code Mode round renders nested sub-calls', () => {
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
     // Fresh world: connect a Workspace so the composer scenarios start live.
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

apps/web/tests/composer-draft-scroll.e2e.ts

@@ -0,0 +1,397 @@
+// Web e2e scenario: a composer draft longer than the 14-line cap scrolls its
+// GLYPHS, not just its caret.
+//
+// The composer paints its text in two stacked layers (see
+// packages/client/ui-conversation/src/client/skeleton/InputBar.module.css): the
+// `<textarea>` carries the value, the selection and the caret but renders its
+// own glyphs `color: transparent`, and every visible character is painted by the
+// `[data-input-backdrop]` div underneath it, which also carries the claim-token
+// highlight, the chips and the ghost hint. The backdrop is `position: absolute;
+// inset: 0; overflow: hidden` — it is CLIPPED, not scrolled, and nothing in the
+// browser links its scroll offset to the textarea's.
+//
+// So past the cap the textarea scrolled and the words did not: the caret walked
+// off the bottom of a block of text frozen at line 1, and no gesture — wheel,
+// drag, arrow key — moved it. `InputBar` now mirrors the offset onto the
+// backdrop on every textarea `scroll`, which is the one event every way of
+// moving the box ends in.
+//
+// Mirroring an offset is only correct while both layers can reach it, so the
+// geometry underneath is asserted here alongside the visible outcome: the
+// backdrop's trailing-line sentinel (a textarea reserves a line box for the
+// caret after a final newline; `pre-wrap` collapses one), and one wrap width
+// across all three layers (only the textarea scrolls, so only it can lose
+// width to a scrollbar that consumes layout space). Either breaks the extent
+// equality, and an unreachable offset clamps the glyphs below the caret.
+//
+// Only a real engine can show this. Scrolling is layout: jsdom reports
+// `scrollHeight === clientHeight` for every element and never scrolls one, so
+// the unit spec in packages/client/ui-conversation/tests/input-bar.spec.tsx has
+// to stub both offsets and can only prove the mirroring code path runs. What is
+// asserted here instead is the user-visible fact that path exists for — after
+// scrolling to the end of a long draft, the LAST line is the one on screen —
+// measured with a DOM Range over the backdrop's own text.
+//
+// Zero model calls: a fresh workspace's blank session already carries a live
+// composer, and the scenario only types into it. 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 {
+  assertFixtureInventory, compareOrRefreshGolden, launchWebScaffold, watchConsole,
+  webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/composer-draft-scroll', import.meta.url))
+/**
+ * Committed golden of the composer's two-layer scroll geometry. The change
+ * alters no DOM and no accessible name, so the aria goldens the other scenarios
+ * commit are byte-identical with and without it; this records the relations
+ * instead, which makes a shift in the cap or in the layer coupling a reviewable
+ * diff rather than an assertion someone has to reconstruct.
+ */
+const GEOMETRY_EXPECTED = join(SNAPSHOT_DIR, 'geometry.expected.md')
+const MODE = webSnapshotMode()
+
+/** Marks the first and last line so a Range can find them in the backdrop's text. */
+const FIRST_MARKER = 'FIRST-LINE-MARKER'
+const LAST_MARKER = 'LAST-LINE-MARKER'
+/** Comfortably past the 14-line cap, so the draft overflows however the lines wrap. */
+const DRAFT_LINES = 40
+const DRAFT = Array.from({ length: DRAFT_LINES }, (_unused, index) => {
+  if (index === 0) return FIRST_MARKER
+  if (index === DRAFT_LINES - 1) return LAST_MARKER
+  return `draft line ${String(index + 1).padStart(2, '0')}`
+}).join('\n')
+
+/**
+ * A draft ending in a newline: the shape whose layer extents diverge without
+ * the backdrop's trailing-line sentinel. A textarea reserves a line box for the
+ * caret after a final newline; `white-space: pre-wrap` collapses a text node's
+ * trailing newline and generates none, so the backdrop would come out exactly
+ * one line shorter and the mirrored offset would clamp a line above the caret.
+ */
+const DRAFT_TRAILING_NEWLINE = `${DRAFT}\n`
+
+/** The composer's two text layers as the browser lays them out. */
+interface ComposerMetrics {
+  /** True when the draft is taller than the capped box — the situation under test. */
+  overflows: boolean
+  /** Visible height of the textarea's content box: the cap in pixels. */
+  clientHeight: number
+  /** Whole lines that fit in the visible box, at the composer's own line-height. */
+  visibleLines: number
+  /** The textarea's scroll offset, which the caret and the selection follow. */
+  inputScrollTop: number
+  /** The backdrop's scroll offset, which every visible glyph follows. */
+  backdropScrollTop: number
+  /** True when the two layers agree — the coupling this scenario exists for. */
+  layersAgree: boolean
+  /**
+   * Top of the LAST draft line relative to the visible box's top, in pixels: at
+   * most `clientHeight` when that line is on screen. This is the reported
+   * symptom as a number — with the layers uncoupled the backdrop stays at offset
+   * 0, so the last line sits a full draft-height below the box.
+   */
+  lastLineOffset: number
+  /** Top of the FIRST draft line relative to the visible box's top: negative once it has scrolled out. */
+  firstLineOffset: number
+  /** Furthest the textarea can scroll. */
+  inputMax: number
+  /** Furthest the backdrop can scroll — equal to `inputMax`, or the mirror clamps below the caret. */
+  backdropMax: number
+  /** Content width the textarea wraps at. */
+  inputWrapWidth: number
+  /** Content width the backdrop wraps at — equal, or the layers break lines in different places. */
+  backdropWrapWidth: number
+  /** Content width the hidden auto-grow mirror wraps at — it decides the box's height. */
+  mirrorWrapWidth: number
+}
+
+/**
+ * Measure both composer layers in the page.
+ * @param page - the page under test.
+ * @returns the two layers' offsets and where the draft's first and last lines sit.
+ */
+function measureComposer(page: Page): Promise<ComposerMetrics> {
+  return page.evaluate(({ first, last }) => {
+    const input = document.querySelector<HTMLTextAreaElement>('textarea:enabled')
+    if (input === null) throw new Error('no live composer textarea in the DOM')
+    const backdrop = input.parentElement?.querySelector<HTMLElement>('[data-input-backdrop]')
+    if (backdrop === undefined || backdrop === null) throw new Error('no decoration backdrop beside the composer textarea')
+    // The hidden auto-grow mirror: the textarea's next sibling, and the layer
+    // that decides the box's height, so its wrap width matters as much as the
+    // two that carry glyphs.
+    const mirror = input.nextElementSibling
+    if (!(mirror instanceof HTMLElement)) throw new Error('no auto-grow mirror after the composer textarea')
+    const box = input.getBoundingClientRect()
+    // The draft carries no chips or claim token, so the decoration walk emits it
+    // as one text node — the backdrop's first, ahead of the trailing-line
+    // sentinel React renders as a second one. Both markers live in that first
+    // node, which is what the Range below needs.
+    const text = backdrop.firstChild
+    if (!(text instanceof Text)) throw new Error('backdrop does not open with a plain text node')
+    const offsetOf = (marker: string): number => {
+      const at = text.data.indexOf(marker)
+      if (at < 0) throw new Error(`marker ${marker} missing from the backdrop text`)
+      const range = document.createRange()
+      range.setStart(text, at)
+      range.setEnd(text, at + marker.length)
+      return range.getBoundingClientRect().top - box.top
+    }
+    const lineHeight = Number.parseFloat(getComputedStyle(input).lineHeight)
+    // Each layer's own maximum, probed by asking for an impossible offset and
+    // reading back what it clamped to, then restored. Reading scrollHeight -
+    // clientHeight instead would compute the maximum rather than observe it.
+    const restore = input.scrollTop
+    const restoreBackdrop = backdrop.scrollTop
+    input.scrollTop = 1e7
+    backdrop.scrollTop = 1e7
+    const inputMax = input.scrollTop
+    const backdropMax = backdrop.scrollTop
+    input.scrollTop = restore
+    backdrop.scrollTop = restoreBackdrop
+    return {
+      inputMax,
+      backdropMax,
+      inputWrapWidth: input.clientWidth,
+      backdropWrapWidth: backdrop.clientWidth,
+      mirrorWrapWidth: mirror.clientWidth,
+      overflows: input.scrollHeight > input.clientHeight,
+      clientHeight: input.clientHeight,
+      visibleLines: Math.floor(input.clientHeight / lineHeight),
+      inputScrollTop: input.scrollTop,
+      backdropScrollTop: backdrop.scrollTop,
+      layersAgree: input.scrollTop === backdrop.scrollTop,
+      lastLineOffset: offsetOf(last),
+      firstLineOffset: offsetOf(first),
+    }
+  }, { first: FIRST_MARKER, last: LAST_MARKER })
+}
+
+/**
+ * Render the golden body.
+ *
+ * Absolute glyph coordinates are deliberately absent: they depend on font
+ * metrics and would make the fixture fail on a machine that measures text
+ * differently — a golden that needs re-recording per platform documents the
+ * platform, not the change. What is recorded is the cap, the layer agreement,
+ * and which lines are on screen, each a comparison that survives any layout
+ * keeping the coupling.
+ * @param top - metrics with the draft scrolled to its start.
+ * @param bottom - metrics with the draft scrolled to its end.
+ * @param trailingNewline - metrics with the trailing-newline draft scrolled to its end.
+ * @returns the golden body, without a trailing newline.
+ */
+function renderGeometry(top: ComposerMetrics, bottom: ComposerMetrics, trailingNewline: ComposerMetrics): string {
+  return [
+    '# Composer draft scrolling (14-line cap, two text layers)',
+    '',
+    '## At the start of the draft',
+    '',
+    `- draft overflows the capped box: ${String(top.overflows)}`,
+    `- visible lines: ${String(top.visibleLines)}`,
+    `- both layers share one scroll extent: ${String(top.inputMax === top.backdropMax)}`,
+    `- all three layers wrap at one width: ${String(
+      top.inputWrapWidth === top.backdropWrapWidth && top.backdropWrapWidth === top.mirrorWrapWidth,
+    )}`,
+    `- textarea scroll offset: ${String(top.inputScrollTop)}px`,
+    `- glyph layer tracks it: ${String(top.layersAgree)}`,
+    `- first draft line is on screen: ${String(top.firstLineOffset >= 0 && top.firstLineOffset < top.clientHeight)}`,
+    `- last draft line is on screen: ${String(top.lastLineOffset >= 0 && top.lastLineOffset < top.clientHeight)}`,
+    '',
+    '## Scrolled to the end of the draft',
+    '',
+    `- textarea moved: ${String(bottom.inputScrollTop > 0)}`,
+    `- glyph layer tracks it: ${String(bottom.layersAgree)}`,
+    `- first draft line has scrolled out above: ${String(bottom.firstLineOffset < 0)}`,
+    `- last draft line is on screen: ${String(bottom.lastLineOffset >= 0 && bottom.lastLineOffset < bottom.clientHeight)}`,
+    '',
+    '## Draft ending in a newline, scrolled to the end',
+    '',
+    `- both layers share one scroll extent: ${String(trailingNewline.inputMax === trailingNewline.backdropMax)}`,
+    `- glyph layer tracks the caret: ${String(trailingNewline.layersAgree)}`,
+    `- last draft line is on screen: ${String(trailingNewline.lastLineOffset >= 0 && trailingNewline.lastLineOffset < trailingNewline.clientHeight)}`,
+  ].join('\n').trimEnd()
+}
+
+describe('web e2e: composer draft scrolling', () => {
+  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 })
+    await connectFreshWorkspace(page, scaffold.workspaceCwd, 'composer-draft-scroll')
+    await page.locator('textarea:enabled').first().fill(DRAFT)
+  }, 180_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('caps the draft box and keeps both text layers at the start', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-draft-scroll-top'))
+    // Vacuity guard: without an overflowing draft there is nothing to scroll and
+    // every assertion below holds trivially.
+    await expect.poll(async () => (await measureComposer(page)).overflows, { timeout: 10_000 }).toBe(true)
+    // Typing the draft left the caret — and the box — at its end, so reach the
+    // start by the same gesture a user would, and leave it there for the wheel
+    // case below.
+    await page.locator('textarea:enabled').first().hover()
+    await page.mouse.wheel(0, -2000)
+    await expect.poll(async () => (await measureComposer(page)).inputScrollTop, { timeout: 10_000 }).toBe(0)
+    const metrics = await measureComposer(page)
+    // The cap is the composer seat's `--dsh-composer-text-max-height` (336px =
+    // 14 x 24px lines). The count, not the pixels: it is the figma constant and
+    // survives a device-pixel-ratio change.
+    expect(metrics.visibleLines).toBe(14)
+    // Resting state: the draft's head is what a 40-line draft shows, and its
+    // tail is far below the box. Both layers sit at the origin, which is why the
+    // uncoupled build looks correct until something scrolls.
+    expect(metrics.inputScrollTop).toBe(0)
+    expect(metrics.layersAgree).toBe(true)
+    expect(metrics.firstLineOffset).toBeGreaterThanOrEqual(0)
+    expect(metrics.firstLineOffset).toBeLessThan(metrics.clientHeight)
+    expect(metrics.lastLineOffset).toBeGreaterThan(metrics.clientHeight)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('lays out all three text layers at one wrap width', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-draft-scroll-wrap-width'))
+    // The premise under the mirror, asserted rather than assumed. Only .input
+    // scrolls, so only .input can lose content width to a scrollbar that
+    // consumes layout space; a narrower .input wraps a long draft onto more
+    // lines, ends up taller, and its larger maximum makes the mirrored offset
+    // clamp below the caret. Measured on a standalone harness, an 8px width
+    // difference is worth 2 to 5 lines on a wrap-sensitive draft.
+    //
+    // This holds on the lane's engine and is what a regression would break —
+    // it is NOT vacuous: measured on the same app, WebKit reports 768 against
+    // 776 here, which is the divergence the Agent Note records as a
+    // pre-existing, engine-specific limitation. The mirror is unaffected there
+    // today because the extents still agree; this assertion is what would
+    // notice if the lane's engine ever moved into the same state.
+    const metrics = await measureComposer(page)
+    expect(metrics.backdropWrapWidth).toBe(metrics.inputWrapWidth)
+    // The mirror decides the box height, so it belongs in the same equality —
+    // were it alone to wrap wider, the box would be measured too short and
+    // clip content before the 14-line cap, with every other assertion green.
+    expect(metrics.mirrorWrapWidth).toBe(metrics.inputWrapWidth)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('a wheel gesture over a long draft moves the words, not only the caret', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-draft-scroll-wheel'))
+    const input = page.locator('textarea:enabled').first()
+    await input.hover()
+    // One delta past the whole draft: the textarea clamps at its own end, and
+    // the wheel-chaining handler leaves it native because the box is not yet at
+    // its edge when the gesture starts (the chaining itself is owned by the
+    // unit spec).
+    await page.mouse.wheel(0, 2000)
+    await expect.poll(async () => (await measureComposer(page)).inputScrollTop, { timeout: 10_000 })
+      .toBeGreaterThan(0)
+    const metrics = await measureComposer(page)
+    // The coupling, stated directly.
+    expect(metrics.layersAgree).toBe(true)
+    // The reported symptom, stated as what the user sees: the end of the draft
+    // is on screen and its beginning is not. On the uncoupled build the glyph
+    // layer stays at offset 0, so `lastLineOffset` is still a full draft below
+    // the box and `firstLineOffset` is still 0 — the text never moved.
+    expect(metrics.lastLineOffset).toBeGreaterThanOrEqual(0)
+    expect(metrics.lastLineOffset).toBeLessThan(metrics.clientHeight)
+    expect(metrics.firstLineOffset).toBeLessThan(0)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('typing at the end of a scrolled draft keeps the layers together', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-draft-scroll-edit'))
+    // The other way the box moves. Typing at the caret — parked at the draft's
+    // end by the wheel gesture — scrolls it into view, which is a `scroll` like
+    // any other; this pins that an edit is not a separate case needing its own
+    // mirror, which is why one listener is the whole implementation.
+    const input = page.locator('textarea:enabled').first()
+    await input.press('End')
+    await input.pressSequentially(' tail')
+    const metrics = await measureComposer(page)
+    expect(metrics.layersAgree).toBe(true)
+    expect(metrics.lastLineOffset).toBeGreaterThanOrEqual(0)
+    expect(metrics.lastLineOffset).toBeLessThan(metrics.clientHeight)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('a draft ending in a newline scrolls to its true end, not a line above it', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-draft-scroll-trailing-newline'))
+    // The layers reserve a final line box on different terms, so this shape is
+    // the one that separates equal extents from a mirror that clamps early.
+    const input = page.locator('textarea:enabled').first()
+    await input.fill(DRAFT_TRAILING_NEWLINE)
+    await expect.poll(async () => (await measureComposer(page)).overflows, { timeout: 10_000 }).toBe(true)
+    const extents = await measureComposer(page)
+    // The invariant the sentinel exists for. Without it the textarea measured
+    // 652 against the backdrop's 628 — one 24px line apart.
+    expect(extents.backdropMax).toBe(extents.inputMax)
+    await input.hover()
+    await page.mouse.wheel(0, 4000)
+    await expect.poll(async () => {
+      const m = await measureComposer(page)
+      return m.inputScrollTop === m.inputMax
+    }, { timeout: 10_000 }).toBe(true)
+    const bottom = await measureComposer(page)
+    // At the very bottom the glyphs are level with the caret, not a line behind.
+    expect(bottom.layersAgree).toBe(true)
+    expect(bottom.lastLineOffset).toBeGreaterThanOrEqual(0)
+    expect(bottom.lastLineOffset).toBeLessThan(bottom.clientHeight)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('matches the committed composer scroll geometry golden', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-draft-scroll-golden'))
+    const input = page.locator('textarea:enabled').first()
+    // Restore the pristine draft (the edit case appended to it) and return to
+    // its start, both through ordinary gestures.
+    await input.fill(DRAFT)
+    await input.hover()
+    await page.mouse.wheel(0, -2000)
+    await expect.poll(async () => (await measureComposer(page)).inputScrollTop, { timeout: 10_000 }).toBe(0)
+    const top = await measureComposer(page)
+    await input.hover()
+    await page.mouse.wheel(0, 2000)
+    await expect.poll(async () => (await measureComposer(page)).inputScrollTop, { timeout: 10_000 })
+      .toBeGreaterThan(0)
+    const bottom = await measureComposer(page)
+    await input.fill(DRAFT_TRAILING_NEWLINE)
+    await input.hover()
+    await page.mouse.wheel(0, 4000)
+    await expect.poll(async () => {
+      const m = await measureComposer(page)
+      return m.inputScrollTop === m.inputMax
+    }, { timeout: 10_000 }).toBe(true)
+    const trailingNewline = await measureComposer(page)
+    await compareOrRefreshGolden(GEOMETRY_EXPECTED, renderGeometry(top, bottom, trailingNewline), MODE)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('commits exactly the fixtures it reads', async () => {
+    // Zero model calls, so the scenario records no session fixture: 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/cordis-tool-round.e2e.ts

@@ -66,7 +66,7 @@ describe('web e2e: Cordis tools use the generic row variants', () => {
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

apps/web/tests/core-web-profile.snapshot.ts

@@ -0,0 +1,84 @@
+import { writeFile } from 'node:fs/promises'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { afterAll, beforeAll, describe, expect, it } from 'vitest'
+import type { AgentHandle } from '@deepseek-ai/dsh-agent'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
+
+const CORE_WEB_OVERLAY = fileURLToPath(new URL('../../cli/config/core-web.cordis.yml', import.meta.url))
+
+describe('core Web profile', () => {
+  let scaffold: WebScaffold
+  let agentHandle: AgentHandle
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({
+      extraOverlayPath: CORE_WEB_OVERLAY,
+      toolsMode: 'native',
+    })
+    agentHandle = await scaffold.ctx.agents.create({
+      sessionId: SessionId('core-web-profile-smoke'),
+      meta: { cwd: scaffold.workspaceCwd },
+      agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
+    })
+  })
+
+  afterAll(async () => {
+    const failures: unknown[] = []
+    await agentHandle?.dispose().catch((error: unknown) => failures.push(error))
+    await scaffold?.close().catch((error: unknown) => failures.push(error))
+    if (failures.length === 1) throw failures[0]
+    if (failures.length > 1) throw new AggregateError(failures, 'core Web profile smoke teardown failed')
+  })
+
+  it('boots and executes both tools through the shipped Web composition', async () => {
+    const seedPath = join(scaffold.workspaceCwd, 'profile-smoke.txt')
+    await writeFile(seedPath, 'CORE_WEB_EDITOR_OK\n')
+    const signal = new AbortController().signal
+    const bash = await scaffold.ctx.tools.execute({
+      signal,
+      callId: CallId('core-web-bash-smoke'),
+      name: 'bash',
+      arguments: { command: "printf 'CORE_WEB_BASH_OK\\n'" },
+      agent: agentHandle.agent,
+    })
+    const editor = await scaffold.ctx.tools.execute({
+      signal,
+      callId: CallId('core-web-editor-smoke'),
+      name: 'str_replace_editor',
+      arguments: { command: 'view', path: seedPath },
+      agent: agentHandle.agent,
+    })
+
+    const text = (result: typeof bash): string => result.content
+      .filter(block => block.type === 'text')
+      .map(block => block.text)
+      .join('')
+      .replaceAll(scaffold.workspaceCwd, '{{cwd}}')
+      .trimEnd()
+
+    expect({
+      tools: scaffold.ctx.tools.schemas().map(tool => tool.name),
+      bash: text(bash),
+      editor: text(editor),
+    }).toMatchInlineSnapshot(`
+      {
+        "bash": "CORE_WEB_BASH_OK",
+        "editor": "Here's the content of {{cwd}}/profile-smoke.txt with line numbers (which has a total of 2 lines):
+           1  CORE_WEB_EDITOR_OK
+           2",
+        "tools": [
+          "bash",
+          "str_replace_editor",
+        ],
+      }
+    `)
+
+    const entries = [...scaffold.ctx.loader.entries()]
+    expect(entries.find(entry => entry.options.id === 'persistent-bash')?.fiber).toBeDefined()
+    expect(entries.find(entry => entry.options.id === 'pty-local')?.fiber).toBeDefined()
+    expect(entries.find(entry => entry.options.id === 'str-replace-editor')?.fiber).toBeDefined()
+  })
+})

apps/web/tests/details-session-lifecycle.e2e.ts

@@ -80,7 +80,7 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await appFrame(page).waitFor({ timeout: 30_000 })
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

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

@@ -50,7 +50,7 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
     // Fresh world: connect a Workspace so the composer scenarios start live.
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {
@@ -93,7 +93,7 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
     try {
       await activePage.goto(activeScaffold.baseUrl, { waitUntil: 'load' })
       await activePage.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-      await connectFreshWorkspace(activePage)
+      await connectFreshWorkspace(activePage, activeScaffold.workspaceCwd)
       const input = activePage.locator('textarea').first()
       await activePage.getByRole('button', { name: 'Commands' }).click()
       const menu = activePage.getByRole('listbox', { name: 'Trigger suggestions' })
@@ -172,10 +172,10 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
     await expect.poll(() => page.getByText('1 session', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
     await expect.poll(() => page.locator('[role="treeitem"][aria-selected="true"]').count(), { timeout: 10_000 }).toBe(1)
     await expect.poll(() => page.getByText('LIGHTHOUSE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
-    // Host: the session's durable header cwd is the workspace flow's
-    // create-by-name target (<workspaceRoot>/workspace, the composer's
-    // default draft name) — the proof the send went through workspace
-    // materialization rather than a bare default-cwd session.
+    // Host: the session's durable header cwd is the folder the workspace
+    // flow created and adopted (<workspaceCwd>/workspace) — the proof the
+    // send went through workspace materialization rather than a bare
+    // default-cwd session.
     const cwds = scaffold.ctx.sessions.list().map(session => session.header.cwd)
     expect(cwds).toEqual([join(scaffold.workspaceCwd, 'workspace')])
     const turnEnds = sessionEvents.filter(e => e.type === 'turn/end')

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

@@ -27,14 +27,15 @@ 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 per interactive end-state: 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 — three genuinely different terminal surfaces of one fixture.
+// 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,
+// 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
@@ -95,7 +96,7 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
     // Fresh world: connect a Workspace so the composer scenarios start live.
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }
 
   /**
@@ -133,6 +134,12 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
     // The marker IS the synchronization: the stream is provably parked in the
     // hang (prefix chunks delivered to the loop) before the stop click.
     await expect.poll(() => existsSync(marker), { timeout: 15_000 }).toBe(true)
+    await expect.poll(
+      () => page.getByRole('status').filter({ hasText: 'Deep diving...' }).isVisible(),
+      { timeout: 10_000 },
+    ).toBe(true)
+    const loadingSnapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold!.workspaceCwd)
+    await compareOrRefreshGolden(LOADING_EXPECTED, loadingSnapshot, MODE)
     await page.getByRole('button', { name: 'Stop generating' }).click()
     await settled
     expect(turnEndReasons(sessionEvents).at(-1)).toBe('aborted')
@@ -151,7 +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()
@@ -159,28 +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
@@ -231,7 +238,7 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
 
   it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
     await assertFixtureInventory(SNAPSHOT_DIR, [
-      'session.jsonl', 'cancel.expected.md', 'error-auth.expected.md', 'retry.expected.md',
+      'session.jsonl', 'cancel.expected.md', 'loading.expected.md', 'error-auth.expected.md', 'retry.expected.md',
     ])
   })
 })

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

@@ -64,14 +64,14 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
     await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBe(1)
 
     // Focus-reveal the footers (hover:hover keeps them opacity-hidden until
-    // hover/focus-within). User has three actions; each turn's last content
-    // assistant has copy + branch.
+    // hover/focus-within). User and each turn's last content assistant both
+    // have copy + branch.
     const copyButtons = page.getByRole('button', { name: 'Copy' })
     await expect.poll(() => copyButtons.count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2)
     await copyButtons.first().focus()
     await expect.poll(() => page.getByRole('button', { name: 'Branch into a new conversation' }).count(), { timeout: 5_000 })
       .toBeGreaterThanOrEqual(2)
-    await expect.poll(() => page.getByRole('button', { name: 'Edit' }).count(), { timeout: 5_000 }).toBe(1)
+    await expect.poll(() => page.getByRole('button', { name: 'Edit' }).count(), { timeout: 5_000 }).toBe(0)
   }, 60_000)
 
   it.skipIf(MODE === 'record')('matches the conversation aria golden with IconActions and clocks', async () => {

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

@@ -20,7 +20,7 @@ import {
   assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { saveFailureShot } from './support.ts'
+import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
 
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/models-settings', import.meta.url))
 const EMPTY_EXPECTED = join(SNAPSHOT_DIR, 'empty.expected.md')
@@ -37,7 +37,8 @@ describe('web e2e: Models settings page configures a dormant provider', () => {
   beforeAll(async () => {
     scaffold = await launchWebScaffold({})
     browser = await chromium.launch()
-    page = await browser.newPage({ viewport: { width: 1680, height: 1000 } })
+    // The scenario asserts the shipped Chinese copy, so the browser asks for it.
+    page = await browser.newPage({ viewport: { width: 1680, height: 1000 }, locale: ZH_BROWSER_LOCALE })
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })

apps/web/tests/navigation-panes.e2e.ts

@@ -43,7 +43,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
 
   beforeAll(async () => {
     scaffold = await launchWebScaffold({})
-    // The workspace-aware flow runs sessions in <workspaceRoot>/workspace;
+    // The workspace-aware flow runs sessions in <workspaceCwd>/workspace;
     // the read targets must live in that session cwd (pre-creation is safe:
     // create-by-name adopts an existing directory).
     const sessionCwd = join(scaffold.workspaceCwd, 'workspace')

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

@@ -9,12 +9,18 @@ import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
 import {
-  assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
+  acknowledgeReloadConnectionLoss, assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { saveFailureShot } from './support.ts'
+import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
+import { settingsNamespace } from '@deepseek-ai/dsh-settings'
+import {
+  WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_COPY, WELCOME_NOTICE_SETTINGS_NAMESPACE,
+  WELCOME_NOTICE_VERSION,
+} from '@deepseek-ai/dsh-client-ui-settings-general'
 
 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 MODE = webSnapshotMode()
 
@@ -26,9 +32,10 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
   const browserConsole: string[] = []
 
   beforeAll(async () => {
-    scaffold = await launchWebScaffold({ deepSeekMissingCredential: true })
+    scaffold = await launchWebScaffold({ deepSeekMissingCredential: true, welcomeNoticePending: true })
     browser = await chromium.launch()
-    page = await browser.newPage({ viewport: { width: 1440, height: 960 } })
+    // The scenario asserts the shipped Chinese copy, so the browser asks for it.
+    page = await browser.newPage({ viewport: { width: 1440, height: 960 }, locale: ZH_BROWSER_LOCALE })
     tripwire = watchConsole(page)
     page.on('console', message => browserConsole.push(message.text()))
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
@@ -42,16 +49,61 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
 
   it('stores a key write-only and observes configured state without restarting', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-deepseek-config'))
-    const dialog = page.getByRole('dialog', { name: '添加一个 API Key 开始使用' })
-    await dialog.waitFor({ timeout: 15_000 })
-    expect(await dialog.getByRole('textbox').count()).toBe(0)
-    const initial = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
+    const welcome = page.getByRole('region', { name: WELCOME_NOTICE_COPY.zh.title })
+    await welcome.waitFor({ timeout: 15_000 })
+    expect(await page.locator('#root').evaluate(root => (root as HTMLElement).inert)).toBe(true)
+    const welcomeAria = await captureStableAria(page, '[role="region"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(WELCOME_EXPECTED, welcomeAria, MODE)
+    expect(await welcome.getByRole('button').allTextContents()).toEqual([WELCOME_NOTICE_COPY.zh.continueLabel])
+    expect(await welcome.locator('button').count()).toBe(1)
+
+    const mask = page.locator('[class*="onboardingMask"]')
+    expect(await mask.count()).toBe(1)
+    const maskStyles = await mask.evaluate((mask) => {
+      const style = getComputedStyle(mask)
+      const rect = mask.getBoundingClientRect()
+      return {
+        position: style.position,
+        left: style.left,
+        right: style.right,
+        top: style.top,
+        bottom: style.bottom,
+        background: style.backgroundColor,
+        backdropFilter: style.backdropFilter,
+        rect: { left: rect.left, top: rect.top, right: rect.right, bottom: rect.bottom },
+      }
+    })
+    expect(maskStyles).toEqual({
+      position: 'absolute',
+      left: '0px',
+      right: '0px',
+      top: '80px',
+      bottom: '0px',
+      background: 'rgba(0, 0, 0, 0.24)',
+      backdropFilter: 'blur(2px)',
+      rect: { left: 0, top: 80, right: 1440, bottom: 960 },
+    })
+
+    // Closing the process/page before acknowledgement writes nothing, so the
+    // same durable profile presents the notice again after reload.
+    const firstReloadWarnings = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    acknowledgeReloadConnectionLoss(tripwire, firstReloadWarnings)
+    await welcome.waitFor({ timeout: 15_000 })
+
+    await welcome.getByRole('button', { name: WELCOME_NOTICE_COPY.zh.continueLabel }).click()
+    await welcome.waitFor({ state: 'detached', timeout: 15_000 })
+    const credentialStep = page.getByRole('region', { name: '添加一个 API Key 开始使用' })
+    await credentialStep.waitFor({ timeout: 15_000 })
+    expect(await credentialStep.getByRole('textbox').count()).toBe(0)
+    const initial = await captureStableAria(page, '[role="region"]', scaffold.workspaceCwd)
     await compareOrRefreshGolden(MISSING_EXPECTED, initial, MODE)
 
-    await dialog.getByRole('button', { name: '前往配置' }).click()
-    await dialog.waitFor({ state: 'detached', timeout: 15_000 })
+    await credentialStep.getByRole('button', { name: '前往配置' }).click()
+    await credentialStep.waitFor({ state: 'detached', timeout: 15_000 })
     const settings = page.getByRole('dialog', { name: '设置' })
     await settings.waitFor({ timeout: 10_000 })
+    expect(await page.locator('#root').evaluate(root => (root as HTMLElement).inert)).toBe(false)
     const keyInput = settings.getByLabel('API 密钥', { exact: true })
     await keyInput.waitFor({ timeout: 10_000 })
 
@@ -78,6 +130,29 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
       { timeout: 10_000 },
     ).toBe('已配置——输入新值可替换')
 
+    const acknowledgedSettings = await readFile(join(scaffold.harnessHome, 'settings.yaml'), 'utf8')
+    expect(acknowledgedSettings).toContain(`${WELCOME_NOTICE_ACK_FIELD}: ${WELCOME_NOTICE_VERSION}`)
+
+    const secondReloadWarnings = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    acknowledgeReloadConnectionLoss(tripwire, secondReloadWarnings)
+    await page.waitForSelector('[class*="frame"]', { timeout: 15_000 })
+    expect(await page.getByRole('region', { name: WELCOME_NOTICE_COPY.zh.title }).count()).toBe(0)
+    expect(await page.getByRole('region', { name: '添加一个 API Key 开始使用' }).count()).toBe(0)
+
+    // A different stored copy version represents an intentional version bump:
+    // the welcome step returns even though the credential is already ready.
+    await scaffold.ctx.settings.mutate(settingsNamespace(WELCOME_NOTICE_SETTINGS_NAMESPACE), [{
+      op: 'set', path: [WELCOME_NOTICE_ACK_FIELD], value: 'previous-copy-version',
+    }])
+    const thirdReloadWarnings = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    acknowledgeReloadConnectionLoss(tripwire, thirdReloadWarnings)
+    await welcome.waitFor({ timeout: 15_000 })
+    await welcome.getByRole('button', { name: WELCOME_NOTICE_COPY.zh.continueLabel }).click()
+    await welcome.waitFor({ state: 'detached', timeout: 15_000 })
+    expect(await page.getByRole('region', { name: '添加一个 API Key 开始使用' }).count()).toBe(0)
+
     expect((await page.content()).includes(secret)).toBe(false)
     expect((await page.locator('body').ariaSnapshot()).includes(secret)).toBe(false)
     expect(browserConsole.some(line => line.includes(secret))).toBe(false)
@@ -86,6 +161,6 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
   }, 60_000)
 
   it('keeps the fixture inventory closed', async () => {
-    await assertFixtureInventory(SNAPSHOT_DIR, ['missing.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['missing.expected.md', 'welcome.expected.md'])
   })
 })

apps/web/tests/permission-policy-context.e2e.ts

@@ -0,0 +1,171 @@
+// Web acceptance for current sandbox-policy context. A real Chromium drives
+// the shipped /permission command through all three presets; record mode uses
+// the real provider, while replay keeps the same provider-authored behavior
+// keyless. Assertions read the exact durable header, runtime-context messages,
+// and tool calls, so assistant prose alone cannot satisfy the scenario.
+import { readFile } from 'node:fs/promises'
+import { join } from 'node:path'
+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 { canonicalPath } from '@deepseek-ai/dsh-sandbox'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import {
+  assertFixtureInventory, fixtureUserPrompts, launchWebScaffold, recordFixture,
+  watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/permission-policy-context', import.meta.url))
+const FIXTURE = fileURLToPath(new URL('./snapshots/permission-policy-context/session.jsonl', import.meta.url))
+const MODE = webSnapshotMode()
+
+const PROMPTS = [
+  'Can you create or edit a normal file right now under the current policy? Answer directly in one sentence. Do not call a tool just to discover the policy.',
+  'Does the DSH file sandbox currently restrict file operations? Answer directly in one sentence. Do not call tools.',
+  'Reply with exactly WORKSPACE_POLICY_SEEN. Do not call tools.',
+  'Create the relative path policy-neutral.txt in the current workspace containing exactly POLICY_NEUTRAL_OK, verify its contents, then report completion.',
+] as const
+
+const PRESET_LABELS = ['Read Only', 'Full access', 'Workspace Write'] as const
+
+function requestSystems(events: readonly SessionEvent[]): string[] {
+  return events.flatMap((event) => {
+    if (event.type !== 'request/header') return []
+    return typeof event.data.header.system === 'string' ? [event.data.header.system] : []
+  })
+}
+
+function runtimeContexts(events: readonly SessionEvent[]): string[] {
+  return events.flatMap((event) => {
+    if (event.type !== 'user/message'
+      || event.data.source.kind !== 'plugin'
+      || event.data.source.plugin !== '@deepseek-ai/dsh-system-prompt') return []
+    return event.data.content.flatMap(block => block.type === 'text' ? [block.text] : [])
+  })
+}
+
+function assistantTexts(events: readonly SessionEvent[]): string[] {
+  return events.flatMap((event) => {
+    if (event.type !== 'assistant/message') return []
+    const text = event.data.message.content.flatMap(block => block.type === 'text' ? [block.text] : []).join('').replaceAll('**', '')
+    return text.length === 0 ? [] : [text]
+  })
+}
+
+function callArgs(event: Extract<SessionEvent, { type: 'tool/call' }>): Record<string, unknown> {
+  return JSON.parse(event.data.arguments) as Record<string, unknown>
+}
+
+describe('web e2e: current sandbox policy reaches the model before tools', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+  let disposeApproval: (() => void) | undefined
+  let sessionWorkspace: string | undefined
+  const sessionEvents: SessionEvent[] = []
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold(MODE === 'record' ? {} : { replayFixture: FIXTURE })
+    disposeApproval = scaffold.ctx.on('approval/request', () => Promise.resolve('allowed-once'), { prepend: true })
+    scaffold.ctx.on('session/event', (session, event: SessionEvent) => {
+      sessionWorkspace = session.header.cwd
+      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, scaffold.workspaceCwd)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    disposeApproval?.()
+    await scaffold?.close()
+  })
+
+  it('switches read-only, danger-full-access, and workspace-write through the real GUI command path', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-permission-policy-context'))
+    if (MODE !== 'record') {
+      expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual(PROMPTS)
+    }
+
+    const input = page.locator('textarea').first()
+    let sessionId: Awaited<ReturnType<WebScaffold['whenTurnSettled']>> | undefined
+    for (const [index, preset] of ['read-only', 'danger-full-access', 'workspace-write'].entries()) {
+      await input.fill(`/permission ${preset}`)
+      await input.press('Enter')
+      await page.getByRole('button', { name: `Access mode, current: ${PRESET_LABELS[index]}` })
+        .waitFor({ timeout: 10_000 })
+
+      const settled = scaffold.whenTurnSettled()
+      await input.fill(PROMPTS[index] as string)
+      await input.press('Enter')
+      sessionId = await settled
+      await expect.poll(() => input.isEnabled(), { timeout: 10_000 }).toBe(true)
+    }
+
+    await input.fill('/permission read-only')
+    await input.press('Enter')
+    await page.getByRole('button', { name: 'Access mode, current: Read Only' }).waitFor({ timeout: 10_000 })
+    const settled = scaffold.whenTurnSettled()
+    await input.fill(PROMPTS[3])
+    await input.press('Enter')
+    sessionId = await settled
+
+    if (sessionId === undefined) throw new Error('permission-policy scenario completed no model turn')
+    if (MODE === 'record') await recordFixture(scaffold, sessionId, FIXTURE)
+  }, 240_000)
+
+  it.skipIf(MODE === 'record')('records cache-safe current policy before the corresponding model behavior', async () => {
+    const systems = requestSystems(sessionEvents)
+    expect(systems).toHaveLength(1)
+    expect(systems[0]).not.toContain('Current DSH file policy:')
+    expect(systems[0]).not.toContain('Approval policy:')
+    expect(systems[0]).not.toContain('Approval prompts are disabled in this session')
+
+    const contexts = runtimeContexts(sessionEvents)
+    expect(contexts).toHaveLength(4)
+    expect(contexts[0]).toContain('Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode.')
+    expect(contexts[0]).toContain('Do not refuse a required modification from this policy alone')
+    expect(contexts[0]).toContain('Approval policy: ask.')
+    expect(contexts[1]).toContain('Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.')
+    expect(contexts[1]).toContain('Approval prompts are disabled in this session')
+
+    if (sessionWorkspace === undefined) throw new Error('permission-policy scenario observed no session workspace')
+    expect(contexts[2]).toContain(`Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: ${JSON.stringify(canonicalPath(sessionWorkspace))}. Some platform temporary areas may also be writable.`)
+    expect(contexts[2]).toContain('Approval policy: ask.')
+    expect(contexts[2]).not.toContain('Approval prompts are disabled in this session')
+    expect(contexts[3]).toContain('Current DSH file policy: read-only.')
+
+    const answers = assistantTexts(sessionEvents)
+    expect(answers.length).toBeGreaterThanOrEqual(4)
+    expect(answers[0]).toMatch(/read-only.*(?:denied|cannot modify|cannot create or edit)/i)
+    expect(answers[1]).toMatch(/does not restrict.*(?:file operations|(?:write\/edit tools|write and edit tools).*one-shot bash commands)/i)
+    expect(answers[2]).toBe('WORKSPACE_POLICY_SEEN')
+    const calls = sessionEvents.filter(
+      (event): event is Extract<SessionEvent, { type: 'tool/call' }> => event.type === 'tool/call',
+    )
+    expect(calls.every(call => call.data.turn === 4)).toBe(true)
+    expect(calls.length).toBeGreaterThanOrEqual(2)
+    const firstCall = calls[0]
+    if (firstCall === undefined) throw new Error('neutral policy task produced no tool call')
+    expect(callArgs(firstCall)['sandbox_permissions']).toBeUndefined()
+    expect(calls.some(call => callArgs(call)['sandbox_permissions'] !== undefined)).toBe(true)
+    expect(sessionEvents.some(event => event.type === 'tool/result'
+      && JSON.stringify(event.data).includes('[sandbox: file access denied under read-only mode]'))).toBe(true)
+    expect(sessionEvents.some(event => event.type === 'approval/asked')).toBe(true)
+    if (sessionWorkspace === undefined) throw new Error('permission-policy scenario observed no session workspace')
+    expect(await readFile(join(sessionWorkspace, 'policy-neutral.txt'), 'utf8')).toBe('POLICY_NEUTRAL_OK')
+  })
+
+  it.skipIf(MODE === 'record')('stays clean and keeps the fixture inventory closed', async () => {
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl'])
+  })
+})

apps/web/tests/pin-browse-picker.overlay.yml

@@ -0,0 +1,11 @@
+# Loader overlay for the W5 real-host smoke (`dsh web --config`): pin the
+# in-browser directory picker. The shipped row is `-auto`, which resolves to
+# the native OS chooser on a loopback bind with a local display — an
+# interaction a Playwright page cannot drive, so the resolved backend would
+# otherwise decide whether the smoke passes. The disable+insert pair mirrors
+# apps/web/tests/scaffold.ts.
+- id: directory-picker
+  disabled: true
+- insert:
+    - id: directory-picker-browse
+      name: '@deepseek-ai/dsh-host-directory-picker-browse'

apps/web/tests/plan-review.e2e.ts

@@ -54,7 +54,7 @@ describe('web e2e: plan review takeover round trip', () => {
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

apps/web/tests/question-composer.e2e.ts

@@ -49,7 +49,7 @@ describe('web e2e: resident question composer round trip', () => {
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
     // Fresh world: connect a Workspace so the composer scenarios start live.
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

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

@@ -68,7 +68,7 @@ describe('web e2e: queue row actions', () => {
     const tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
     onTestFailed(() => saveFailureShot(page, 'web-e2e-queue-actions'))
 
     const input = page.locator('textarea').first()
@@ -131,7 +131,7 @@ describe('web e2e: queue row actions', () => {
 
     const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
     await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
-    expect(sessionEvents.filter(event => event.type === 'user/message')).toHaveLength(1)
+    expect(sessionEvents.filter(event => event.type === 'user/message' && event.data.source.kind === 'user')).toHaveLength(1)
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
 

apps/web/tests/replay-round-trip.e2e.ts

@@ -48,7 +48,7 @@ describe('web e2e: fresh round trip through the real assembly', () => {
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
     // Fresh world: connect a Workspace so the composer scenarios start live.
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

apps/web/tests/scaffold.ts

@@ -11,13 +11,14 @@
 // masking its credential, without making a model call.
 //
 // Composition divergences from `dsh web`, all deliberate, all via include
-// 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; ordinary 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, over the SAME tree (never a
+// second yml): temp persistenceRoot; host-level skill roots confined to the
+// temp workspace while project skill discovery remains real; 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; ordinary 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'
@@ -32,6 +33,11 @@ import Loader from '@cordisjs/plugin-loader'
 import Include, { type PatchOptions } from '@cordisjs/plugin-include'
 import { scrubRequestHeaders } from '@deepseek-ai/dsh-acp-snapshot'
 import { assertEntriesLoaded, loadOverlayPatches } from '@deepseek-ai/dsh-app-boot'
+import { dshHomePath } from '@deepseek-ai/dsh-paths'
+import {
+  WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_SETTINGS_NAMESPACE, WELCOME_NOTICE_VERSION,
+} from '@deepseek-ai/dsh-client-ui-settings-general'
+import { settingsNamespace } from '@deepseek-ai/dsh-settings'
 import type { ReplayHandle } from '@deepseek-ai/dsh-llm-replay'
 import { installLlmReplay, parseSessionLog } from '@deepseek-ai/dsh-llm-replay'
 import SessionStore, {
@@ -100,6 +106,12 @@ export interface WebScaffold {
 
 /** Options for {@link launchWebScaffold}. */
 export interface LaunchOptions {
+  /**
+   * Optional product overlay applied after the shipped Web surface and before
+   * the scaffold's hermetic test patches, matching AppCLIEntry's `--config`
+   * ordering.
+   */
+  extraOverlayPath?: string
   /**
    * Replay fixture (session.jsonl) served by the inserted dsh-llm-replay row
    * in replay/refresh modes; ignored in record mode (the real adapter
@@ -135,6 +147,19 @@ export interface LaunchOptions {
    * keyless first-run configuration lane; the default disables the adapter.
    */
   deepSeekMissingCredential?: boolean
+  /**
+   * Patch the shipped DeepSeek search row to a deterministic endpoint and
+   * credential reference. Browser search scenarios keep the real provider and
+   * credentials seam while avoiding external search traffic and ambient keys.
+   */
+  deepSeekSearch?: {
+    /** Anthropic-compatible base URL; the provider appends `/messages`. */
+    baseURL: string
+    /** Credential reference resolved by the shipped search provider. */
+    apiKeyEnv: string
+  }
+  /** Leave the current welcome notice unacknowledged; ordinary scenarios publish it as complete before browser boot. */
+  welcomeNoticePending?: boolean
 }
 
 /** Dispose the booted tree and remove both owned temp roots, reporting every independent cleanup failure. */
@@ -196,13 +221,17 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
   // snapshot overlay use, applied over the SAME shipped tree (a patch id that
   // stops matching a row fails the boot sweep loudly instead of drifting).
   const surfacePatches = loadOverlayPatches('web e2e scaffold', WEB_OVERLAY_PATH)
+  const extraOverlayPatches = options.extraOverlayPath === undefined
+    ? []
+    : loadOverlayPatches('web e2e scaffold', options.extraOverlayPath)
   const patches: PatchOptions[] = [
     ...surfacePatches,
+    ...extraOverlayPatches,
     { id: 'session-persistence-jsonl', config: { root: persistenceRoot } },
     { id: 'session-query-sqlite', config: { path: ':memory:', openAt: 'first-search' } },
-    // storage-json's './.storages' yml default is cwd-relative and resolves
-    // per write; the scaffold restores the original cwd after boot, so the
-    // row gets an absolute temp root (removed with the workspace at close).
+    // storage-json's yml root is anchored to the real $DSH_HOME; pin the row
+    // to an absolute temp root (removed with the workspace at close) so tests
+    // never write the user's harness home.
     { 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
@@ -241,6 +270,15 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
     ...options.cordisTools === true
       ? [{ insert: [{ id: 'tool-cordis', name: 'cordis:tool-cordis' }] }]
       : [],
+    ...options.deepSeekSearch === undefined
+      ? []
+      : [{
+        id: 'web-search-deepseek',
+        config: {
+          apiKeyEnv: options.deepSeekSearch.apiKeyEnv,
+          baseURL: options.deepSeekSearch.baseURL,
+        },
+      }],
     ...mode === 'record' || options.deepSeekMissingCredential === true
       ? []
       : [{ id: 'llm-deepseek', disabled: true }],
@@ -255,6 +293,8 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
   try {
     process.chdir(workspaceCwd)
     ctx.baseUrl = pathToFileURL(join(resolve(CONFIG_PATH), '..')).href + '/'
+    // This direct Loader harness supplies the same root-path capability as app-boot.
+    ctx.provide('dshHomePath', dshHomePath)
     await ctx.plugin(Loader)
     ctx.loader.builtins.include = Include
     // The shipped CLI deliberately has no dependency on this opt-in package.
@@ -266,6 +306,11 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
     })
     await ctx.loader.await()
     assertEntriesLoaded(ctx, 'web e2e scaffold')
+    if (options.welcomeNoticePending !== true) {
+      await ctx.settings.mutate(settingsNamespace(WELCOME_NOTICE_SETTINGS_NAMESPACE), [{
+        op: 'set', path: [WELCOME_NOTICE_ACK_FIELD], value: WELCOME_NOTICE_VERSION,
+      }])
+    }
     const boundPort = ctx.get('httpServer')?.port
     if (boundPort === undefined) {
       throw new Error('web e2e scaffold: httpServer service missing after settled boot')

apps/web/tests/search-card.snapshot.ts

@@ -0,0 +1,170 @@
+// @vitest-environment jsdom
+// Assembled search-card snapshot: boots the real built `packages/client/*/lib/
+// client.js` bundles through AppWebEntry's ModuleLoader path against the keyless
+// FixtureApiClient transport (no API key, no model round), opens the fixture
+// session, and pins the search card the `grep` turn (fixture turn 66) renders in
+// the assembled application. The built-boot smoke proves the graph boots but
+// carries no behavior assertions by contract; this is the assembled-output check
+// that a broken SearchRow registration or a dropped card would fail — the
+// per-package suites bench over src and cannot see the bundled wiring.
+//
+// Keyless and deterministic: the fixture is the fake server, so the grep turn's
+// matches, its truncation summary, and its head/tail cap are fixed in the
+// fixture, not harvested from a live model. The recovery-footer arm is a pure
+// derivation over the result view, pinned at every render site by the
+// ui-conversation suite; here the fixture turn exercises the assembled card
+// shape and its cap.
+import { mkdirSync, readFileSync, writeFileSync } from 'node:fs'
+import { dirname, join } from 'node:path'
+import { act, cleanup, fireEvent, screen, waitFor, within } from '@testing-library/react'
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
+import type { WebBootEntry } from '@deepseek-ai/dsh-client-modules/client'
+import { AppWebEntry } from '@deepseek-ai/dsh-client-web'
+
+const EXPECTED = join(process.cwd(), 'apps/web/tests/snapshots/search-card/grep-card.expected.txt')
+const refreshing = process.env.DSH_SNAPSHOT === 'record' || process.env.DSH_SNAPSHOT === 'refresh'
+
+const PLUGINS: readonly (WebBootEntry & { dir: string })[] = [
+  { id: '@deepseek-ai/dsh-client-connection', dir: 'connection', url: '/plugins/connection.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', url: '/plugins/runtime.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
+  { id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', url: '/plugins/ui-theme.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-locale', dir: 'locale', url: '/plugins/locale.js', rev: 'fx', inject: [], immediately: true },
+  { id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', url: '/plugins/ui-layout.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-runtime'] },
+  { id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', url: '/plugins/ui-sidebar.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  { id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', url: '/plugins/ui-conversation.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
+  {
+    id: '@deepseek-ai/dsh-client-ui-workspace',
+    dir: 'ui-workspace',
+    url: '/plugins/ui-workspace.js',
+    rev: 'fx',
+    inject: [
+      '@deepseek-ai/dsh-client-runtime',
+      '@deepseek-ai/dsh-client-ui-conversation',
+      '@deepseek-ai/dsh-client-ui-sidebar',
+    ],
+  },
+  { id: '@deepseek-ai/dsh-client-ui-trajectory', dir: 'ui-trajectory', url: '/plugins/ui-trajectory.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
+]
+
+const bundles = new Map(PLUGINS.map(plugin => [
+  plugin.url,
+  readFileSync(join(process.cwd(), 'packages/client', plugin.dir, 'lib/client.js'), 'utf8'),
+]))
+
+interface FixtureWindow extends Window {
+  __DSH_BOOT__?: { rev: string; entries: WebBootEntry[] }
+  __ModuleLoader__?: unknown
+}
+
+class ResizeObserverStub {
+  observe(): void {}
+  disconnect(): void {}
+  unobserve(): void {}
+}
+
+const win = window as FixtureWindow
+let unmount: (() => void) | undefined
+
+/** Normalize a rendered search card to a stable text shape: the kind, the banner
+ *  summary, each file header (path + count), each visible match line, the expand
+ *  control label, and the recovery footer. CSS-module class names carry a
+ *  per-build hash in one of two schemes — ui-primitives emits `_<name>_<hash>`
+ *  (name bounded by underscores), ui-conversation emits `<hash>_<name>` (name at
+ *  the end). `hasClass` matches a module class by its logical name under either,
+ *  without matching a longer name that contains it (`line` must not hit
+ *  `lineNumber`). */
+function hasClass(el: Element, name: string): boolean {
+  return [...el.classList].some(cls => cls === name || cls.endsWith(`_${name}`) || cls.startsWith(`_${name}_`) || cls.includes(`_${name}_`))
+}
+
+function cardShape(root: Element): string {
+  const card = root.querySelector('[data-search]')
+  if (card === null) return '<no search card>'
+  const pick = (from: Element, name: string): Element[] =>
+    [...from.querySelectorAll('*')].filter(el => hasClass(el, name))
+  const lines: string[] = [`kind=${card.getAttribute('data-search')}`]
+  const summary = pick(card, 'summary')[0]?.textContent?.trim()
+  if (summary !== undefined && summary !== '') lines.push(`summary=${summary}`)
+  for (const header of pick(card, 'fileHeader')) lines.push(`file=${header.textContent?.trim() ?? ''}`)
+  for (const row of pick(card, 'line')) lines.push(`line=${row.textContent?.trim() ?? ''}`)
+  const expand = pick(card, 'expand')[0]?.textContent?.trim()
+  if (expand !== undefined && expand !== '') lines.push(`expand=${expand}`)
+  const recovery = pick(root, 'searchRecovery')[0]?.textContent?.trim()
+  if (recovery !== undefined && recovery !== '') lines.push(`recovery=${recovery}`)
+  return lines.join('\n')
+}
+
+beforeEach(() => {
+  localStorage.clear()
+  // English pinned before boot so the sidebar's role/text locators stay
+  // deterministic (the built-boot smoke's convention).
+  localStorage.setItem('dsh.locale', 'en')
+  document.title = 'DeepSeek Harness'
+  vi.stubGlobal('ResizeObserver', ResizeObserverStub)
+  vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) =>
+    setTimeout(() => { callback(0) }, 0) as unknown as number)
+  vi.stubGlobal('cancelAnimationFrame', (id: number) => { clearTimeout(id) })
+})
+
+afterEach(() => {
+  act(() => { unmount?.() })
+  unmount = undefined
+  cleanup()
+  delete win.__DSH_BOOT__
+  delete win.__ModuleLoader__
+  document.body.innerHTML = ''
+  document.head.querySelectorAll('style[data-plugin]').forEach((style) => { style.remove() })
+  document.title = ''
+  history.replaceState(null, '', '/')
+  vi.unstubAllGlobals()
+})
+
+describe('assembled search card', () => {
+  it('renders the grep card, its truncation summary, and its capped head/tail slice from the built bundles', async () => {
+    history.replaceState(null, '', '/?fixture')
+    const root = document.createElement('div')
+    root.id = 'root'
+    document.body.appendChild(root)
+    win.__DSH_BOOT__ = { rev: 'fx', entries: PLUGINS.map(({ dir: _dir, ...plugin }) => plugin) }
+    act(() => {
+      const entry = new AppWebEntry(root, {
+        fetchBundle: (url) => {
+          const code = bundles.get(url)
+          return code === undefined ? Promise.reject(new Error(`missing built bundle ${url}`)) : Promise.resolve(code)
+        },
+        executeBundle: (code) => { (0, eval)(code) },
+      })
+      void entry.run()
+      unmount = () => { entry.dispose() }
+    })
+
+    const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
+    fireEvent.click(await within(tree).findByText('Fixture 历史会话'))
+    // Wait for chat content to reach the fixture's later turns (the bash sample
+    // is turn 65, the grep card turn 66).
+    await waitFor(() => {
+      expect(document.querySelector('[data-sample="bash-global"]')).not.toBeNull()
+    }, { timeout: 10_000 })
+    // The grep turn's keyed SearchRow composes ToolRow: the card is collapsed
+    // by default, so wait for the summary row, then expand it to reach the card.
+    await waitFor(() => {
+      const tools = [...document.querySelectorAll('[data-tool]')].map(el => el.getAttribute('data-tool'))
+      expect(tools, `tools present: ${tools.join(', ')}`).toContain('grep')
+    }, { timeout: 10_000 })
+
+    // `data-tool` sits on the ToolRow root; the collapsed row is the expand
+    // toggle. Click it so the card and its recovery footer mount, then shape the
+    // whole row (the card lives inside ToolRow's body wrapper).
+    const grepRow = document.querySelector('[data-tool="grep"]')!
+    act(() => { fireEvent.click(grepRow.querySelector('[data-expandable]') ?? grepRow) })
+    await waitFor(() => {
+      expect(grepRow.querySelector('[data-search]')).not.toBeNull()
+    }, { timeout: 10_000 })
+    const shape = cardShape(grepRow)
+    if (refreshing) {
+      mkdirSync(dirname(EXPECTED), { recursive: true })
+      writeFileSync(EXPECTED, shape)
+    }
+    await expect(shape).toMatchFileSnapshot(EXPECTED)
+  })
+})

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

@@ -1,11 +1,12 @@
 // Web e2e scenario: seeded history. A recorded session seeded cold through
 // the REAL persistence API renders purely from the log — the surface nothing
 // else covers: sidebar cold listing, the implicit resume/attach inside the
-// history RPC, history-page tool views, and the client fold of historical
+// history RPC, history-page tool views, and the client's log-ordered transcript
 // events — with ZERO model calls in replay (no replay fixture; a stray stream
 // 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
+// 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.
@@ -34,6 +35,90 @@ const SEED_ID = 'seeded-history-web-e2e'
 
 const PROMPT = 'Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop.'
 
+/**
+ * Append a complete, valid compaction transaction over the recorded turn's own
+ * surface. The recording stays model-authentic and reusable; replay adds this
+ * deterministic condition before seeding it cold, so the scenario pins the bug
+ * this change fixes — a landed compaction must not erase history the reader
+ * already saw — through the real host and the real browser.
+ * @param raw - the committed seed fixture text.
+ * @returns the fixture with a compacted turn appended.
+ */
+function withCompaction(raw: string): string {
+  const lines = raw.trimEnd().split('\n')
+  const events = lines.slice(1).map(line => JSON.parse(line) as {
+    type: string
+    seq: number
+    time: number
+    surfaceOp?: unknown
+    data?: { turn?: unknown }
+  })
+  const surfaceSeqs = events
+    .filter(event => event.surfaceOp === 'append'
+      && (event.type === 'user/message'
+        || event.type === 'assistant/message'
+        || event.type === 'tool/result'
+        || event.type === 'steering/message'))
+    .map(event => event.seq)
+  const first = surfaceSeqs[0]
+  const last = surfaceSeqs.at(-1)
+  const tail = events.at(-1)
+  if (first === undefined || last === undefined || tail === undefined) {
+    throw new Error('seeded-history compaction requires a non-empty closed surface')
+  }
+  // The transaction opens the turn after the recording's last closed one; read
+  // it from the fixture so a re-recording with a different turn count stays
+  // valid instead of appending a duplicate turn number.
+  const lastTurn = events.filter(event => event.type === 'turn/end').at(-1)?.data?.turn
+  if (typeof lastTurn !== 'number') {
+    throw new Error('seeded-history compaction requires a recording ending on a closed turn')
+  }
+  const turn = lastTurn + 1
+  let seq = tail.seq + 1
+  let time = tail.time + 1
+  /**
+   * Append one event at the next seq/time.
+   * @param event - the event body, without seq/time.
+   * @returns the seq it took, so provenance cites the push instead of arithmetic over the push order below.
+   */
+  const at = (event: Record<string, unknown>): number => {
+    const taken = seq++
+    lines.push(JSON.stringify({ ...event, seq: taken, time: time++ }))
+    return taken
+  }
+  at({ type: 'turn/start', data: { turn, trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'compact' } } } })
+  const startSeq = at({ type: 'compact/start', data: { turn } })
+  const summarySeq = at({
+    type: 'compact/summary',
+    data: {
+      summary: [{
+        type: 'text',
+        text: '## Cold resume compact summary\n\n- The exact summary remains available.',
+      }],
+      shadowedRange: { start: first, end: last },
+      shadowedSeqs: surfaceSeqs,
+      shadowedTokenCount: 10_000,
+      provider: 'snapshot',
+      model: 'snapshot-compactor',
+    },
+  })
+  at({
+    type: 'user/message',
+    data: {
+      content: [{
+        type: 'text',
+        text: '<context_checkpoint>Model-only compact checkpoint.</context_checkpoint>',
+      }],
+      source: { kind: 'plugin', plugin: 'compact' },
+    },
+    surfaceOp: { op: 'replace', start: first, end: last },
+    sourceEventSeqs: [startSeq, summarySeq, ...surfaceSeqs],
+  })
+  at({ type: 'compact/end', data: { turn } })
+  at({ type: 'turn/end', data: { turn, reason: { kind: 'completed' } } })
+  return `${lines.join('\n')}\n`
+}
+
 describe('web e2e: seeded history renders through cold resume', () => {
   let scaffold: WebScaffold
   let browser: Browser
@@ -42,7 +127,7 @@ describe('web e2e: seeded history renders through cold resume', () => {
 
   beforeAll(async () => {
     scaffold = await launchWebScaffold({})
-    // The workspace-aware flow runs sessions in <workspaceRoot>/workspace
+    // The workspace-aware flow runs sessions in <workspaceCwd>/workspace
     // (the composer's default draft name); the read-tool targets must live in
     // that session cwd. Pre-creating the directory is safe: create-by-name
     // adopts an existing directory.
@@ -53,7 +138,7 @@ describe('web e2e: seeded history renders through cold resume', () => {
     if (MODE !== 'record') {
       const raw = await readFile(SEED, 'utf8')
       expect(fixtureUserPrompts(raw), 'seed fixture must carry exactly the drive prompt').toEqual([PROMPT])
-      await seedSession(scaffold, raw, SEED_ID)
+      await seedSession(scaffold, withCompaction(raw), SEED_ID)
     }
     browser = await chromium.launch()
     page = await newEnglishPage(browser)
@@ -119,11 +204,15 @@ describe('web e2e: seeded history renders through cold resume', () => {
     await sessionRow.click()
     // Settled barrier for history: the recorded final assistant text renders.
     await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBe(1)
+    await expect.poll(() => page.getByText('Context compacted', { exact: true }).count(), { timeout: 10_000 }).toBe(1)
     // Tool cards render from logged tool/call + tool/result alone (views are
     // host-recomputed per page; the generic card is the documented default).
     const toolRows = page.locator('[data-variant], [data-sample]')
     await expect.poll(() => toolRows.count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2)
     expect(await page.getByText('a.txt', { exact: false }).count()).toBeGreaterThan(0)
+    // The bug this fixes: the compaction shadowed the whole recorded surface on
+    // the model side, and the prompt and full tool output are still on screen.
+    expect(await page.getByText(PROMPT, { exact: true }).count()).toBe(1)
 
     const agent = scaffold.ctx.agents.get(SessionId(SEED_ID))
     if (agent === undefined) throw new Error('seeded session did not attach an agent')
@@ -230,6 +319,22 @@ 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')('expands the cold-resumed compact summary', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-compaction'))
+    const marker = page.getByRole('button', { name: /Context compacted/ })
+    await marker.waitFor({ timeout: 10_000 })
+    expect(await marker.getAttribute('aria-expanded')).toBe('false')
+    await marker.click()
+    await expect.poll(() => marker.getAttribute('aria-expanded'), { timeout: 5_000 }).toBe('true')
+    await expect.poll(() => page.getByRole('heading', { name: 'Cold resume compact summary' }).count(), {
+      timeout: 5_000,
+    }).toBe(1)
+    expect(await page.getByText('The exact summary remains available.', { exact: false }).count()).toBeGreaterThan(0)
+    // Restore the shared page state for any later case.
+    await marker.click()
+    await expect.poll(() => marker.getAttribute('aria-expanded'), { timeout: 5_000 }).toBe('false')
+  })
+
   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

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

@@ -18,7 +18,7 @@ import {
   acknowledgeReloadConnectionLoss, assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { saveFailureShot } from './support.ts'
+import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
 
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/settings-chrome', import.meta.url))
 const DIALOG_EXPECTED = join(SNAPSHOT_DIR, 'dialog.expected.md')
@@ -33,7 +33,9 @@ describe('web e2e: settings modal and General preferences', () => {
   beforeAll(async () => {
     scaffold = await launchWebScaffold({})
     browser = await chromium.launch()
-    page = await browser.newPage({ viewport: { width: 1680, height: 1000 } })
+    // Chinese browser: the shared page asserts the localized settings surface
+    // the client derives from it (the English default has its own spec below).
+    page = await browser.newPage({ viewport: { width: 1680, height: 1000 }, locale: ZH_BROWSER_LOCALE })
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
@@ -215,6 +217,30 @@ describe('web e2e: settings modal and General preferences', () => {
     expect(tripwire.pageErrors).toEqual([])
   }, 90_000)
 
+  it('opens an English browser in English without any stored preference', async () => {
+    // A second page under a different browser language: nothing is persisted
+    // for it, so the settings surface must follow the browser rather than the
+    // product fallback the shared zh page shows.
+    const enPage = await browser.newPage({ viewport: { width: 1680, height: 1000 }, locale: 'en-US' })
+    const enTripwire = watchConsole(enPage)
+    onTestFailed(() => saveFailureShot(enPage, 'web-e2e-settings-browser-language'))
+    try {
+      await enPage.goto(scaffold.baseUrl, { waitUntil: 'load' })
+      await enPage.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+      expect(await enPage.evaluate(() => localStorage.getItem('dsh.locale'))).toBeNull()
+      await enPage.getByRole('button', { name: 'Settings', exact: true }).click()
+      const dialog = enPage.getByRole('dialog', { name: 'Settings' })
+      await dialog.waitFor({ timeout: 10_000 })
+      await dialog.getByRole('button', { name: 'English' }).waitFor({ timeout: 10_000 })
+      // This page has no closing inventory spec to sweep its console, so the
+      // scenario clears both tripwire channels itself.
+      expect(enTripwire.pageErrors).toEqual([])
+      expect(enTripwire.warnings).toEqual([])
+    } finally {
+      await enPage.close()
+    }
+  }, 90_000)
+
   it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
     expect(tripwire.warnings).toEqual([])
     await assertFixtureInventory(SNAPSHOT_DIR, ['dialog.expected.md'])

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/skill-invocation-policy.e2e.ts

@@ -84,7 +84,7 @@ describe('web e2e: skill invocation policy through the real host', () => {
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

apps/web/tests/smoke-real.e2e.ts

@@ -20,7 +20,7 @@ import { createServer } from 'node:http'
 import { createRequire } from 'node:module'
 import { tmpdir } from 'node:os'
 import { join } from 'node:path'
-import { pathToFileURL } from 'node:url'
+import { fileURLToPath, pathToFileURL } from 'node:url'
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
@@ -163,6 +163,8 @@ describe('dsh web keyless CLI smoke', () => {
         env: {
           ...process.env,
           DEEPSEEK_API_KEY: 'keyless-web-no-call',
+          DSH_HOME: join(sessionsDir, '.dsh'),
+          DSH_AGENTS_HOME: join(sessionsDir, '.agents'),
           TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
         },
         stdio: ['ignore', 'pipe', 'pipe'],
@@ -188,8 +190,12 @@ describe('dsh web keyless CLI smoke', () => {
     mkdirSync(join(workspace, '.git'))
     writeFileSync(join(workspace, 'AGENTS.md'), 'web-workspace-context-probe\n')
 
-    let resolveProviderRequest!: (request: { messages?: { role?: string; content?: string }[] }) => void
-    const providerRequest = new Promise<{ messages?: { role?: string; content?: string }[] }>((resolve) => {
+    interface NativeProviderRequest {
+      messages?: { role?: string; content?: string }[]
+      tools?: { function?: { name?: string } }[]
+    }
+    let resolveProviderRequest!: (request: NativeProviderRequest) => void
+    const providerRequest = new Promise<NativeProviderRequest>((resolve) => {
       resolveProviderRequest = resolve
     })
     const provider = createServer((request, response) => {
@@ -197,7 +203,7 @@ describe('dsh web keyless CLI smoke', () => {
       request.setEncoding('utf8')
       request.on('data', (chunk: string) => { body += chunk })
       request.on('end', () => {
-        resolveProviderRequest(JSON.parse(body) as { messages?: { role?: string; content?: string }[] })
+        resolveProviderRequest(JSON.parse(body) as NativeProviderRequest)
         response.writeHead(200, { 'content-type': 'text/event-stream' })
         response.end([
           'data: {"choices":[{"delta":{"role":"assistant","content":null,"reasoning_content":""}}]}',
@@ -222,6 +228,7 @@ describe('dsh web keyless CLI smoke', () => {
           DEEPSEEK_API_KEY: 'keyless-web-workspace',
           DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`,
           DSH_HOME: join(workspace, '.dsh'),
+          DSH_AGENTS_HOME: join(workspace, '.agents'),
           TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
         },
         stdio: ['ignore', 'pipe', 'pipe'],
@@ -241,6 +248,8 @@ describe('dsh web keyless CLI smoke', () => {
           setTimeout(() => { reject(new Error('provider request not received in 10s')) }, 10_000).unref()
         }),
       ])
+      expect(captured.messages?.some(message =>
+        message.role === 'user' && message.content?.includes('<available_skills>'))).toBe(false)
       const workspaceMessage = captured.messages?.find(message =>
         message.role === 'user' && message.content?.includes('web-workspace-context-probe'))
       expect(workspaceMessage).toMatchInlineSnapshot(`
@@ -256,6 +265,13 @@ describe('dsh web keyless CLI smoke', () => {
           "role": "user",
         }
       `)
+      expect(captured.tools?.map(tool => tool.function?.name)
+        .filter(name => name === 'web_search' || name === 'web_fetch'))
+        .toMatchInlineSnapshot(`
+          [
+            "web_search",
+          ]
+        `)
     } finally {
       const closed = child.exitCode === null
         ? new Promise<void>((resolveClose) => { child.once('close', () => { resolveClose() }) })
@@ -402,6 +418,7 @@ describe('dsh web keyless CLI smoke', () => {
           DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`,
           DSH_TOOLS_MODE: 'code',
           DSH_HOME: join(workspace, '.dsh'),
+          DSH_AGENTS_HOME: join(workspace, '.agents'),
           TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
         },
         stdio: ['ignore', 'pipe', 'pipe'],
@@ -450,17 +467,23 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
     sessionsDir = mkdtempSync(join(tmpdir(), 'dsh-web-w5-'))
     const port = await probeFreePort()
     // tsx boot mirrors demo:web — lib/ may be unbuilt in this worktree. Isolate
-    // the global Harness home inside the temp world; tsx also needs the repo's
-    // loader and tsconfig paths pointed at explicitly.
+    // the host-level Harness and shared-agent homes inside the temp world; tsx
+    // also needs the repo's loader and tsconfig paths pointed at explicitly.
     const tsxLoader = pathToFileURL(createRequire(join(REPO_ROOT, 'package.json')).resolve('tsx')).href
     child = spawn(
       process.execPath,
-      ['--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', String(port)],
+      [
+        '--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', String(port),
+        // Pin the in-browser picker: the shipped `-auto` row would resolve to
+        // the native OS chooser on this bind, and no page can drive that.
+        '--config', fileURLToPath(new URL('./pin-browse-picker.overlay.yml', import.meta.url)),
+      ],
       {
         cwd: sessionsDir,
         env: {
           ...process.env,
           DSH_HOME: join(sessionsDir, '.dsh'),
+          DSH_AGENTS_HOME: join(sessionsDir, '.agents'),
           TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
         },
         stdio: ['ignore', 'pipe', 'pipe'],
@@ -495,8 +518,18 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
 
   it('2+3 empty-state first send completes a real model round', async () => {
     onTestFailed(() => saveFailureShot(page, 'w5-first-round'))
+    // This scenario spawns its own server against a fresh $DSH_HOME, so the
+    // first-run welcome notice is unacknowledged and its overlay owns pointer
+    // events (the shared scaffold acknowledges it before boot instead). The
+    // notice is anchored structurally, not by its copy: this spec sits in the
+    // client TypeScript program, which does not reference the package that
+    // owns the strings.
+    const welcome = page.locator('[class*="onboardingOverlay"]')
+    await welcome.waitFor({ timeout: 15_000 })
+    await welcome.getByRole('button').click()
+    await welcome.waitFor({ state: 'detached', timeout: 15_000 })
     // Fresh world: connect a Workspace so the composer starts live.
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, sessionsDir)
     const input = page.locator('textarea').first()
     await input.waitFor({ timeout: 10_000 })
     await screen(page, '02-empty-state')

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

@@ -9,8 +9,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - 'button "Think The user wants me to write a single `run_code` program that:"':
   - img
   - img
@@ -20,7 +22,7 @@
   - img
   - text: Code Run bash echo and catch missing file read
 - img
-- text: Bash Echo CODE_ROUND_OK
+- text: Bash Echo CODE_ROUND_OK Failed
 - 'button "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"':
   - img
   - text: "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"
@@ -42,4 +44,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 52% Input 17.2K tok · Output 252 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 7% of 128K Cache hit 52% Input 17.2K tok · Output 252 tok

apps/web/tests/snapshots/composer-draft-scroll/geometry.expected.md

@@ -0,0 +1,25 @@
+# Composer draft scrolling (14-line cap, two text layers)
+
+## At the start of the draft
+
+- draft overflows the capped box: true
+- visible lines: 14
+- both layers share one scroll extent: true
+- all three layers wrap at one width: true
+- textarea scroll offset: 0px
+- glyph layer tracks it: true
+- first draft line is on screen: true
+- last draft line is on screen: false
+
+## Scrolled to the end of the draft
+
+- textarea moved: true
+- glyph layer tracks it: true
+- first draft line has scrolled out above: true
+- last draft line is on screen: true
+
+## Draft ending in a newline, scrolled to the end
+
+- both layers share one scroll extent: true
+- glyph layer tracks the caret: true
+- last draft line is on screen: true

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

@@ -9,8 +9,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - button "Think The user wants me to:":
   - img
   - img
@@ -57,4 +59,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 4 steps Tool call {{duration}} Cache hit 77% Input 66.5K tok · Output 312 tok
+- text: 1 turns · 4 steps Tool call {{duration}} Context 13% of 128K Cache hit 77% Input 66.5K tok · Output 312 tok

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

@@ -9,8 +9,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - button "Think The user wants me to run a simple bash command and reply with \"DONE\".":
   - img
   - img
@@ -37,4 +39,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 99% Input 15.7K tok · Output 111 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 6% of 128K Cache hit 99% Input 15.7K tok · Output 111 tok

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/lifecycle-chrome/hero.expected.md

@@ -7,7 +7,7 @@
 - text: Workspaces
 - button "Group by":
   - img
-- button "Create workspace":
+- button "Add workspace":
   - img
 - button "Search sessions":
   - img
@@ -16,7 +16,7 @@
   - treeitem "workspace 1 session" [expanded]:
     - img
     - text: workspace 1 session
-  - treeitem "New Session now" [selected]
+  - treeitem "New Session" [selected]
 - button "Settings":
   - img
   - text: Settings

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

@@ -7,7 +7,7 @@
 - text: Workspaces
 - button "Group by":
   - img
-- button "Create workspace":
+- button "Add workspace":
   - img
 - button "Search sessions":
   - img
@@ -16,7 +16,7 @@
   - treeitem "workspace 1 session" [expanded]:
     - img
     - text: workspace 1 session
-  - treeitem "New Session now" [selected]
+  - treeitem "New Session" [selected]
 - button "Settings":
   - img
   - text: Settings

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

@@ -9,8 +9,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - button "Think The user wants me to reply with a single word. Let me comply.":
   - img
   - img
@@ -29,4 +31,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 1 steps Cache hit 99% Input 7.8K tok · Output 21 tok
+- text: 1 turns · 1 steps Context 6% of 128K Cache hit 99% Input 7.8K tok · Output 21 tok

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

@@ -9,8 +9,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - paragraph: partial
 - text: Stopped
 - button "Copy":

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

@@ -9,8 +9,13 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - 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/snapshots/live-interactions/loading.expected.md

@@ -0,0 +1,25 @@
+- 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 "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- button "Context injection":
+  - img
+  - img
+  - text: Context injection
+- paragraph: partial
+- status: Deep diving...
+- 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"

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

@@ -9,8 +9,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - group:
   - status: Retried model request (1/2) · {{duration}}
 - button "Think The user is asking for a one-sentence description of event sourcing. This is a straightforward knowledge question that doesn't require any skill loading or tool calls.":
@@ -31,4 +33,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 1 steps Cache hit 99% Input 7.8K tok · Output 79 tok
+- text: 1 turns · 1 steps Context 6% of 128K Cache hit 99% Input 7.8K tok · Output 79 tok

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

@@ -10,8 +10,6 @@
 - tooltip "Copy"
 - button "Branch into a new conversation":
   - img
-- button "Edit":
-  - 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

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

@@ -1,6 +1,5 @@
-- dialog "添加一个 API Key 开始使用":
+- region "添加一个 API Key 开始使用":
   - heading "添加一个 API Key 开始使用" [level=2]
-  - button "稍后配置":
-    - img
   - paragraph: 配置 DeepSeek 官方模型，即可开始使用。
+  - button "稍后配置"
   - button "前往配置"

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

@@ -0,0 +1,9 @@
+- region "内测声明":
+  - heading "内测声明" [level=2]
+  - paragraph: 感谢您愿意拨冗试用 DeepSeek Harness。当前版本仍处于内部测试阶段，功能仍待完善，体验难免有些粗糙。
+  - blockquote: “如切如磋，如琢如磨。” 产品的成长，离不开一次次真实的碰撞与坦诚的反馈。您在真实使用中发现的问题，也可能促使我们重新审视，甚至推翻已有的设计。
+  - paragraph:
+    - text: 为了帮助我们更准确地还原您真实使用中的问题，内测版本默认会上传所有 Session Log；如需关闭，可以设置环境变量 DSH_TELEMETRY_DISABLED=1。另外，
+    - strong: 如果您有任何反馈与建议，请在企业微信群中留言告诉我们
+    - text: 。每一条反馈，都会帮助我们把它打磨得更好。
+  - button "继续"

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

@@ -10,8 +10,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - '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
@@ -42,4 +44,4 @@
   - 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
+- text: 1 turns · 2 steps Tool call {{duration}} Context 4% of 128K Cache hit 51% Input 10.2K tok · Output 346 tok

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

@@ -9,8 +9,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - button "Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.":
   - img
   - img
@@ -37,4 +39,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 95% Input 8.6K tok · Output 180 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 3% of 128K Cache hit 95% Input 8.6K tok · Output 180 tok

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

@@ -9,9 +9,12 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - paragraph: partial
+- status: Deep diving...
 - button "2 queued messages"
 - textbox "Message the agent"
 - button "Commands":

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

@@ -9,9 +9,12 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - paragraph: partial
+- status: Deep diving...
 - button "2 queued messages" [disabled] [expanded]
 - list:
   - listitem:

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

@@ -9,9 +9,12 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - paragraph: partial
+- status: Deep diving...
 - list:
   - listitem:
     - text: Edited queue item

apps/web/tests/snapshots/search-card/grep-card.expected.txt

@@ -0,0 +1,27 @@
+kind=matches
+summary=显示 9 / 共 42 处匹配 · 3 个文件
+file=packages/client/ui-primitives/src/SearchBlock.tsx3
+file=packages/client/ui-conversation/src/client/toolviews/search-row.tsx4
+line=16: export const DEFAULT_SEARCH_MAX_LINES = 16
+line=138: export function SearchBlock(props: SearchBlockProps) {
+line=141:   const [collapsed, setCollapsed] = useState<ReadonlySet<number>>(() => new Set())
+line=35:   const search = searchCardModel(block)
+line=52:       search={search}
+line=73:     ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep', locale: NS }, SearchRow)
+expand=… 其余 4 行
+recovery=Found 9 of 42 matches
+
+packages/client/ui-primitives/src/SearchBlock.tsx
+Line 16: export const DEFAULT_SEARCH_MAX_LINES = 16
+Line 138: export function SearchBlock(props: SearchBlockProps) {
+Line 141:   const [collapsed, setCollapsed] = useState<ReadonlySet<number>>(() => new Set())
+packages/client/ui-conversation/src/client/contract/search-card-model.ts
+Line 24: export const CHAT_SEARCH_MAX_LINES = 8
+Line 60: export function searchCardModel(block: ToolCallBlock): SearchCardModel | null {
+packages/client/ui-conversation/src/client/toolviews/search-row.tsx
+Line 33: export function SearchRow({ toolName, block, inspect, t }: SearchRowProps) {
+Line 35:   const search = searchCardModel(block)
+Line 52:       search={search}
+Line 73:     ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep', locale: NS }, SearchRow)
+
+(Full grep result stored at: fixture://spill/grep-66. Read it to see every match.)

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

@@ -9,8 +9,6 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
-  - 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
@@ -35,6 +33,9 @@
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}}
+- button "Context compacted View compaction summary":
+  - img
+  - text: Context compacted View compaction summary
 - button "Context injection":
   - img
   - img

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

@@ -9,8 +9,6 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
-  - 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
@@ -35,6 +33,9 @@
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}}
+- button "Context compacted View compaction summary":
+  - img
+  - text: Context compacted View compaction summary
 - button "Context injection":
   - img
   - img

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

@@ -9,16 +9,20 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - button "Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.":
   - img
   - img
   - text: Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.
+- text: Running
 - button "Ask question waiting":
   - img
   - img
   - text: Ask question waiting
+- status: Deep diving...
 - region "Ready to continue?":
   - text: Checkpoint
   - heading "Ready to continue?" [level=2]

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

@@ -9,8 +9,10 @@
   - img
 - button "Branch into a new conversation":
   - img
-- button "Edit":
+- button "Context injection":
   - img
+  - img
+  - text: Context injection
 - button "Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.":
   - img
   - img
@@ -38,4 +40,4 @@
   - 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 156 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 6% of 128K Cache hit 98% Input 15.8K tok · Output 156 tok

apps/web/tests/snapshots/web-search-round/session.jsonl

@@ -0,0 +1,12 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785456000000,"cwd":"{{cwd}}"}
+{"type":"user/message","seq":0,"time":1785456000001,"data":{"content":[{"type":"text","text":"Use web_search to search exactly \"DeepSeek Harness snapshot search\". Then reply exactly SEARCH_DONE and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
+{"type":"assistant/chunk","seq":1,"time":1785456000002,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":2,"time":1785456000003,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_web_search","name":"web_search","argumentsDelta":"{\"query\":\"DeepSeek Harness snapshot search\"}"}}}
+{"type":"assistant/chunk","seq":3,"time":1785456000004,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_web_search","name":"web_search","arguments":"{\"query\":\"DeepSeek Harness snapshot search\"}"}}}}
+{"type":"assistant/chunk","seq":4,"time":1785456000005,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
+{"type":"assistant/chunk","seq":5,"time":1785456000006,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/chunk","seq":6,"time":1785456000007,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":7,"time":1785456000008,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"SEARCH_DONE"}}}
+{"type":"assistant/chunk","seq":8,"time":1785456000009,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"SEARCH_DONE"}}}}
+{"type":"assistant/chunk","seq":9,"time":1785456000010,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2}}}}
+{"type":"assistant/chunk","seq":10,"time":1785456000011,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}

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

@@ -0,0 +1,34 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Use web_search to search exactly" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Use web_search to search exactly "DeepSeek Harness snapshot search". Then reply exactly SEARCH_DONE and stop. {{clock}}
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- button "Context injection":
+  - img
+  - img
+  - text: Context injection
+- button "Search DeepSeek Harness snapshot search":
+  - img
+  - img
+  - text: Search DeepSeek Harness snapshot search
+- paragraph: SEARCH_DONE
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- text: {{clock}}
+- 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 "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Context 0% of 128K Cache hit 0% Input 22 tok · Output 7 tok

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/tests/steering.e2e.ts

@@ -72,7 +72,7 @@ describe('web e2e: mid-turn steering lands durably and visibly', () => {
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
     // Fresh world: connect a Workspace so the composer scenarios start live.
-    await connectFreshWorkspace(page)
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {

apps/web/tests/support.ts

@@ -1,6 +1,7 @@
 // Shared plumbing for the web smoke tests (dist location, free port, failure shots).
 import { existsSync, mkdirSync } from 'node:fs'
 import { createServer } from 'node:net'
+import { join } from 'node:path'
 import { fileURLToPath } from 'node:url'
 import type { Browser, Page } from 'playwright'
 
@@ -9,11 +10,18 @@ export const DIST_INDEX = fileURLToPath(new URL('../dist/index.html', import.met
 
 export const REPO_ROOT = fileURLToPath(new URL('../../..', import.meta.url))
 
+/**
+ * Browser language a page must advertise to boot into the product's Chinese
+ * surface: with no stored preference the client derives its initial locale
+ * from the browser, and Playwright's default browser asks for English.
+ */
+export const ZH_BROWSER_LOCALE = 'zh-CN'
+
 /**
  * Open the standard browser-test page with English selected before client
  * boot. This keeps role locators and goldens deterministic across localized
- * component migrations; the settings locale scenario deliberately bypasses
- * this helper to cover the product's default Chinese state.
+ * component migrations; the scenarios asserting the Chinese surface bypass
+ * this helper and advertise {@link ZH_BROWSER_LOCALE} instead.
  * @param browser - Playwright browser owning the page.
  * @param height - Viewport height; width is fixed to the lane baseline.
  * @returns the initialized page.
@@ -48,23 +56,32 @@ export function probeFreePort(): Promise<number> {
 }
 
 /**
- * Drive the hero's workspace picker through its create-by-name dialog until
- * the live composer unlocks. A fresh world has no Workspace, so the boot
+ * Drive the hero's workspace picker through the composed directory dialog
+ * until the live composer unlocks. A fresh world has no Workspace, so the boot
  * lands in the locked view state (startup auto-selection has nothing to
  * select); every scenario that types into the composer must connect one
- * first. The default name 'workspace' keeps the session header cwd at
- * <workspaceRoot>/workspace — the materialization proof several scenarios
+ * first. With nothing to list, the chip gesture raises the dialog directly —
+ * adding a workspace is the picker's only entry. The directory is staged here
+ * and adopted through the path editor, which is idempotent across the repeated
+ * connects a scenario may make; creating a folder from inside the dialog (the
+ * product's other half of the same route) is covered by
+ * workspace-management.e2e.ts. The default name 'workspace' keeps the session
+ * header cwd at <root>/workspace, the materialization proof several scenarios
  * assert.
  * @param page - the page under test.
- * @param name - workspace name typed into the create dialog.
+ * @param root - host directory the workspace folder is staged in (the scaffold's `workspaceCwd`).
+ * @param name - folder name staged and adopted as the workspace.
  */
-export async function connectFreshWorkspace(page: Page, name = 'workspace'): Promise<void> {
+export async function connectFreshWorkspace(page: Page, root: string, name = 'workspace'): Promise<void> {
+  mkdirSync(join(root, name), { recursive: true })
   await page.getByRole('button', { name: 'Choose workspace' }).click()
-  await page.getByRole('menuitem', { name: 'Create a new workspace' }).click()
-  const dialog = page.getByRole('dialog', { name: 'Create a new workspace' })
+  const dialog = page.getByRole('dialog', { name: 'Select Workspace Directory' })
   await dialog.waitFor({ timeout: 10_000 })
-  await dialog.getByLabel('New workspace name').fill(name)
-  await dialog.getByRole('button', { name: 'Create workspace' }).click()
+  await dialog.getByRole('button', { name: 'Edit path' }).click()
+  const pathInput = dialog.getByRole('textbox', { name: 'Edit path' })
+  await pathInput.fill(join(root, name))
+  await pathInput.press('Enter')
+  await dialog.getByRole('button', { name: 'Open', exact: true }).click()
   // The pick connected the workspace: the blank session's live composer
   // replaces the locked placeholder and enables.
   await page.locator('textarea:enabled[placeholder="Describe what you want to build"]')

apps/web/tests/web-search-round.e2e.ts

@@ -0,0 +1,207 @@
+// Web e2e scenario for the shipped default search composition. A real browser
+// drives `web_search`; the model stream is replayed while the real DeepSeek
+// provider calls a deterministic local Anthropic-compatible endpoint through
+// the real credentials service.
+import { readFile } from 'node:fs/promises'
+import { createServer, type Server } from 'node:http'
+import type { AddressInfo } from 'node:net'
+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 { credentialRef } from '@deepseek-ai/dsh-credentials'
+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/web-search-round', import.meta.url))
+const FIXTURE = fileURLToPath(new URL('./snapshots/web-search-round/session.jsonl', import.meta.url))
+const UI_EXPECTED = fileURLToPath(new URL('./snapshots/web-search-round/ui.expected.md', import.meta.url))
+const MODE = webSnapshotMode()
+const QUERY = 'DeepSeek Harness snapshot search'
+const PROMPT = `Use web_search to search exactly "${QUERY}". Then reply exactly SEARCH_DONE and stop.`
+const SEARCH_CREDENTIAL_REF = credentialRef('DSH_WEB_SEARCH_E2E_KEY')
+const SEARCH_CREDENTIAL = 'snapshot-search-key'
+const RESULT_URL = 'https://docs.example.test/search'
+
+interface CapturedSearchRequest {
+  path: string
+  apiKey: string | undefined
+  body: unknown
+}
+
+/** Start the deterministic DeepSeek Messages double used by the real provider. */
+async function startSearchServer(captured: CapturedSearchRequest[]): Promise<{ server: Server; baseURL: string }> {
+  const server = createServer((request, response) => {
+    let body = ''
+    request.setEncoding('utf8')
+    request.on('data', (chunk: string) => { body += chunk })
+    request.on('end', () => {
+      captured.push({
+        path: request.url ?? '',
+        apiKey: typeof request.headers['x-api-key'] === 'string' ? request.headers['x-api-key'] : undefined,
+        body: JSON.parse(body) as unknown,
+      })
+      response.writeHead(200, { 'content-type': 'application/json' })
+      response.end(JSON.stringify({
+        content: [
+          {
+            type: 'text',
+            text: 'Found one source.',
+            citations: [{
+              type: 'web_search_result_location',
+              url: RESULT_URL,
+              cited_text: 'Snapshot search excerpt.',
+            }],
+          },
+          {
+            type: 'web_search_tool_result',
+            content: [{
+              type: 'web_search_result',
+              url: RESULT_URL,
+              title: 'Snapshot Search Result',
+              page_age: '2026-07-31',
+            }],
+          },
+        ],
+      }))
+    })
+  })
+  await new Promise<void>((resolve, reject) => {
+    server.once('error', reject)
+    server.listen(0, '127.0.0.1', () => {
+      server.off('error', reject)
+      resolve()
+    })
+  })
+  const address = server.address() as AddressInfo
+  return { server, baseURL: `http://127.0.0.1:${address.port}` }
+}
+
+describe('web e2e: shipped default web search', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let searchServer: Server | undefined
+  let searchBaseURL: string
+  let tripwire: ReturnType<typeof watchConsole>
+  const searchRequests: CapturedSearchRequest[] = []
+  const sessionEvents: SessionEvent[] = []
+
+  beforeAll(async () => {
+    const search = await startSearchServer(searchRequests)
+    searchServer = search.server
+    searchBaseURL = search.baseURL
+    scaffold = await launchWebScaffold({
+      deepSeekSearch: {
+        baseURL: search.baseURL,
+        apiKeyEnv: SEARCH_CREDENTIAL_REF,
+      },
+      ...(MODE === 'record' ? {} : { replayFixture: FIXTURE, paceMs: 15 }),
+    })
+    await scaffold.ctx.credentials.set(SEARCH_CREDENTIAL_REF, SEARCH_CREDENTIAL)
+    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, scaffold.workspaceCwd)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+    await new Promise<void>((resolve, reject) => {
+      if (searchServer === undefined) {
+        resolve()
+        return
+      }
+      searchServer.close((error) => {
+        if (error === undefined) resolve()
+        else reject(error)
+      })
+    })
+  })
+
+  it('drives the recorded search to a settled turn (all modes)', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-search-drive'))
+    if (MODE !== 'record') {
+      expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([PROMPT])
+    }
+    const input = page.locator('textarea').first()
+    await input.waitFor({ timeout: 10_000 })
+    const settled = scaffold.whenTurnSettled()
+    await input.fill(PROMPT)
+    await input.press('Enter')
+    const sessionId = await settled
+    if (MODE === 'record') await recordFixture(scaffold, sessionId, FIXTURE)
+  }, 200_000)
+
+  it.skipIf(MODE === 'record')('uses the real provider and persists the structured result', () => {
+    expect(searchRequests).toHaveLength(1)
+    expect(searchRequests[0]).toMatchObject({
+      path: '/messages',
+      apiKey: SEARCH_CREDENTIAL,
+      body: {
+        messages: [{
+          role: 'user',
+          content: [{ type: 'text', text: `Perform a web search for the query: ${QUERY}` }],
+        }],
+        tools: [{ type: 'web_search_20250305', name: 'web_search' }],
+      },
+    })
+
+    const auxiliaryRequest = sessionEvents.find(
+      (event): event is Extract<SessionEvent, { type: 'web/deepseek-search-llm-request' }> =>
+        event.type === 'web/deepseek-search-llm-request',
+    )
+    expect(auxiliaryRequest?.data).toEqual({
+      endpoint: `${searchBaseURL}/messages`,
+      apiVersion: '2023-06-01',
+      body: searchRequests[0]?.body,
+    })
+
+    const searchCall = sessionEvents.find(
+      (event): event is Extract<SessionEvent, { type: 'tool/call' }> =>
+        event.type === 'tool/call' && event.data.name === 'web_search',
+    )
+    if (searchCall === undefined) throw new Error('the replayed turn did not call web_search')
+    const searchResult = sessionEvents.find(
+      (event): event is Extract<SessionEvent, { type: 'tool/result' }> =>
+        event.type === 'tool/result' && event.data.message.source.callId === searchCall.data.callId,
+    )
+    if (searchResult === undefined) throw new Error('web_search produced no durable result')
+    const content = searchResult.data.message.content[0]
+    expect(content.isError).toBe(false)
+    expect(content.content.filter(block => block.type === 'text').map(block => block.text).join(''))
+      .toContain(`[Snapshot Search Result](${RESULT_URL})`)
+    expect(searchResult.data.meta).toMatchObject({
+      sources: [{
+        url: RESULT_URL,
+        title: 'Snapshot Search Result',
+        snippet: 'Snapshot search excerpt.',
+        publishedAt: '2026-07-31',
+      }],
+      truncated: false,
+    })
+  })
+
+  it.skipIf(MODE === 'record')('matches the settled search card aria golden', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-search-aria'))
+    await expect.poll(() => page.getByText('SEARCH_DONE', { exact: true }).count(), { timeout: 15_000 })
+      .toBeGreaterThanOrEqual(1)
+    await page.locator('[data-tool="web_search"]').waitFor({ timeout: 10_000 })
+    const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
+  })
+
+  it.skipIf(MODE === 'record')('stayed clean and kept the exact fixture inventory', async () => {
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'ui.expected.md'])
+  })
+})

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

@@ -1,14 +1,19 @@
-// Web e2e scenarios: workspace management — the create-by-name dialog, the
-// rename round trip over the real wire (workspace.rename RPC + durable
-// registry), duplicate-name pre-check, the flat "In one list" view with its
-// persisted group-by preference, and the session hover card. Zero model
-// calls: workspace.create/rename are host RPCs with no model involvement,
-// and the one session row the flat/hover scenarios need comes from a seeded
-// fixture (the seeded-history seed reused verbatim — no new recording).
+// Web e2e scenarios: workspace management — adding a workspace through the
+// composed directory dialog (its own New folder affordance is the product's
+// one creation route), same-basename directory adoption, the rename round
+// trip over the real wire (workspace.rename RPC + durable registry), the
+// duplicate-name pre-check, the
+// flat "In one list" view with its persisted group-by preference, the session
+// hover card and row action menu, and the session archive round trip (row
+// menu → workspace.archiveSession RPC → durable global set → row hidden
+// across reload). Zero model calls: workspace.create/rename/archiveSession
+// are host RPCs with no model involvement, and the one session row the
+// flat/hover/menu/archive scenarios need comes from a seeded fixture (the
+// seeded-history seed reused verbatim — no new recording).
 import { mkdir, readFile, stat, writeFile } from 'node:fs/promises'
 import { fileURLToPath } from 'node:url'
 import { join } from 'node:path'
-import type { Browser, Page } from 'playwright'
+import type { Browser, Locator, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
 import { SessionId } from '@deepseek-ai/dsh-session'
@@ -25,29 +30,59 @@ const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', impo
 const MODE = webSnapshotMode()
 const BROWSER_EXPECTED = join(SNAPSHOT_DIR, 'directory-browser.expected.md')
 const SEED_ID = 'workspace-management-web-e2e'
+// Both waits exceed ui-primitives' 200ms POINTER_GRACE_MS. Keep them coupled
+// to that contract if the shared grace tuning changes.
+const POINTER_TRANSIT_MS = 300
+const POINTER_HOLD_MS = 600
 
-describe('web e2e: workspace management (create / rename / flat view / hover card)', () => {
+describe('web e2e: workspace management (create / rename / flat view / hover affordances)', () => {
   let scaffold: WebScaffold
   let browser: Browser
   let page: Page
   let tripwire: ReturnType<typeof watchConsole>
 
   /**
-   * Drive the in-app browser to a directory via its path-edit affordance,
-   * confirm it, and wait for the adoption to settle host-side (workspace
-   * registered + the flow's New-Session agent up), so later test steps can't
-   * race the in-flight blank-session attach.
+   * Raise the region header's directory dialog and drive it to a directory via
+   * the path-edit affordance. Adding is the header button's only action, so
+   * the click lands in the dialog with no menu in between.
    */
-  async function openLocalFolder(path: string, options: { waitForAgent?: boolean } = {}): Promise<void> {
-    const agentsBefore = scaffold.ctx.agents.list().length
-    await page.getByRole('button', { name: 'Create workspace' }).click()
-    await page.getByRole('menuitem', { name: 'Open local folder…' }).click()
+  async function browseTo(path: string): Promise<Locator> {
+    await page.getByRole('button', { name: 'Add workspace' }).click()
     const dialog = page.getByRole('dialog', { name: 'Select Workspace Directory' })
     await dialog.waitFor({ timeout: 10_000 })
     await dialog.getByRole('button', { name: 'Edit path' }).click()
     await dialog.getByLabel('Edit path').fill(path)
     await dialog.getByLabel('Edit path').press('Enter')
-    await dialog.getByRole('button', { name: 'Open' }).click()
+    return dialog
+  }
+
+  /**
+   * Create a folder inside `parent` through the dialog and adopt it — the
+   * product's only route to a brand-new workspace directory.
+   */
+  async function addNewFolderWorkspace(parent: string, name: string): Promise<void> {
+    const dialog = await browseTo(parent)
+    await dialog.getByRole('button', { name: 'New folder' }).click()
+    await page.getByLabel('Folder name').fill(name)
+    await page.getByRole('button', { name: 'Create', exact: true }).click()
+    // Creating selects the new folder in the listing; Open adopts it.
+    await dialog.getByRole('button', { name: 'Open', exact: true }).click()
+    await dialog.waitFor({ state: 'hidden', timeout: 10_000 })
+    await expect.poll(
+      () => scaffold.ctx.workspace.resolveByPath(join(parent, name)),
+      { timeout: 10_000 },
+    ).not.toBeUndefined()
+  }
+
+  /**
+   * Adopt an existing directory, waiting for the adoption to settle host-side
+   * (workspace registered + the flow's New-Session agent up), so later test
+   * steps can't race the in-flight blank-session attach.
+   */
+  async function adoptDirectory(path: string, options: { waitForAgent?: boolean } = {}): Promise<void> {
+    const agentsBefore = scaffold.ctx.agents.list().length
+    const dialog = await browseTo(path)
+    await dialog.getByRole('button', { name: 'Open', exact: true }).click()
     await dialog.waitFor({ state: 'hidden', timeout: 10_000 })
     await expect.poll(
       () => scaffold.ctx.workspace.resolveByPath(path),
@@ -83,22 +118,17 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
     await scaffold?.close()
   })
 
-  it('creates two workspaces by name through the region-header dialog', async () => {
+  it('adds two workspaces through the dialog, each on a folder it created', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-create'))
-    const createByName = async (name: string): Promise<void> => {
-      await page.getByRole('button', { name: 'Create workspace' }).click()
-      await page.getByRole('menuitem', { name: 'Create a new workspace' }).click()
-      const dialog = page.getByRole('dialog', { name: 'Create a new workspace' })
-      await dialog.waitFor({ timeout: 10_000 })
-      await dialog.getByLabel('New workspace name').fill(name)
-      await dialog.getByRole('button', { name: 'Create workspace' }).click()
-      await expect.poll(() => page.getByRole('dialog', { name: 'Create a new workspace' }).count(), { timeout: 10_000 }).toBe(0)
+    const add = async (name: string): Promise<void> => {
+      await addNewFolderWorkspace(scaffold.workspaceCwd, name)
       // The real workspace materializes in the tree as a group row.
       await expect.poll(() => page.getByText(name, { exact: true }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
     }
-    await createByName('alpha-ws')
-    await createByName('beta-ws')
-    // Durable on the host: both registered, newest first (create prepends).
+    await add('alpha-ws')
+    await add('beta-ws')
+    // Durable on the host: both registered, newest first (create prepends),
+    // each titled after the folder the dialog made.
     const titles = scaffold.ctx.workspace.list().map(workspace => workspace.title)
     expect(titles.slice(0, 2)).toEqual(['beta-ws', 'alpha-ws'])
     expect(tripwire.pageErrors).toEqual([])
@@ -164,7 +194,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
       collect()
     })
     // Register the scaffold's existing project directory through the real UI.
-    await openLocalFolder(scaffold.workspaceCwd, { waitForAgent: true })
+    await adoptDirectory(scaffold.workspaceCwd, { waitForAgent: true })
     const workspace = await scaffold.ctx.workspace.resolveByPath(scaffold.workspaceCwd)
     if (workspace === undefined) throw new Error('GUI did not register the existing project directory')
     await workspace.attachSession(SessionId(SEED_ID))
@@ -222,7 +252,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
     // 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.
-    await openLocalFolder(scaffold.workspaceCwd)
+    await adoptDirectory(scaffold.workspaceCwd)
     await expect.poll(
       () => scaffold.ctx.workspace.resolveByPath(scaffold.workspaceCwd),
       { timeout: 10_000 },
@@ -292,7 +322,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
       collect()
     })
 
-    await openLocalFolder(oldPath)
+    await adoptDirectory(oldPath)
     await expect.poll(
       () => scaffold.ctx.workspace.resolveByPath(oldPath),
       { timeout: 10_000 },
@@ -308,12 +338,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
       .getByRole('button', { name: 'Delete workspace' }).click()
     await expect.poll(() => scaffold.ctx.workspace.get(oldWorkspace.id), { timeout: 10_000 }).toBeUndefined()
 
-    await page.getByRole('button', { name: 'Create workspace' }).click()
-    await page.getByRole('menuitem', { name: 'Create a new workspace' }).click()
-    const create = page.getByRole('dialog', { name: 'Create a new workspace' })
-    await create.getByLabel('New workspace name').fill(title)
-    await create.getByRole('button', { name: 'Create workspace' }).click()
-    await expect.poll(() => create.count(), { timeout: 10_000 }).toBe(0)
+    await addNewFolderWorkspace(scaffold.workspaceCwd, title)
     const fresh = scaffold.ctx.workspace.list().find(workspace => workspace.title === title)
     expect(fresh?.id).toBeDefined()
     expect(fresh?.id).not.toBe(oldWorkspace.id)
@@ -363,13 +388,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
     process.env.HOME = scaffold.workspaceCwd
     process.env.USERPROFILE = scaffold.workspaceCwd
     try {
-      await page.getByRole('button', { name: 'Create workspace' }).click()
-      await page.getByRole('menuitem', { name: 'Open local folder…' }).click()
-      const dialog = page.getByRole('dialog', { name: 'Select Workspace Directory' })
-      await dialog.waitFor({ timeout: 10_000 })
-      await dialog.getByRole('button', { name: 'Edit path' }).click()
-      await dialog.getByLabel('Edit path').fill(staged)
-      await dialog.getByLabel('Edit path').press('Enter')
+      const dialog = await browseTo(staged)
       await expect.poll(() => dialog.getByText('alpha', { exact: true }).count(), { timeout: 10_000 }).toBe(1)
       const snapshot = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
       await compareOrRefreshGolden(BROWSER_EXPECTED, snapshot, MODE)
@@ -384,14 +403,17 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
     expect(tripwire.pageErrors).toEqual([])
   }, 60_000)
 
-  it('shows the session hover card after a dwell on the row', async () => {
-    onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-hover'))
-    // Expand Ungrouped to reveal the seeded session row, then dwell on it
-    // (the card opens after a 500ms hover delay, portaled to body).
+  /**
+   * Expand Ungrouped and return its seeded session row. The only visible child
+   * is the non-blank persisted Session; the blank Session created while
+   * adopting the Workspace stays hidden.
+   * @returns the session row locator, already present.
+   */
+  async function seededSessionRow() {
     const ungroupedRow = page.getByText('Ungrouped', { exact: true }).locator('..').locator('..')
     const ungroupedSection = ungroupedRow.locator('..')
-    // Initial-current auto-expansion can race this following test's gesture;
-    // converge on expanded rather than assuming which update wins first.
+    // Initial-current auto-expansion can race this gesture; converge on
+    // expanded rather than assuming which update wins first.
     await expect.poll(async () => {
       if (await ungroupedRow.getAttribute('aria-expanded') !== 'true') {
         await page.getByText('Ungrouped', { exact: true }).click()
@@ -399,20 +421,145 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
       }
       return await ungroupedRow.getAttribute('aria-expanded')
     }, { timeout: 5_000 }).toBe('true')
-    // The only visible child is the non-blank persisted Session; the blank
-    // Session created while adopting the Workspace remains hidden.
-    const sessionRow = ungroupedSection.locator('[role="treeitem"]').nth(1)
-    await sessionRow.waitFor({ timeout: 10_000 })
+    const row = ungroupedSection.locator('[role="treeitem"]').nth(1)
+    await row.waitFor({ timeout: 10_000 })
+    return row
+  }
+
+  it('shows the session hover card after a dwell on the row', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-hover'))
+    // Dwell on the seeded row; the card opens after a 500ms hover delay,
+    // portaled to body.
+    const sessionRow = await seededSessionRow()
+    const rowTitle = await sessionRow.locator('[class*="title"]').innerText()
     await sessionRow.hover()
-    // Card content: the full title plus the Idle status line (display-only
-    // card; no aria role — text anchors are the stable selector).
+    // Card content: the full title plus the Idle status line (no aria role —
+    // text anchors are the stable selector).
     await expect.poll(() => page.getByText('Idle', { exact: true }).count(), { timeout: 5_000 }).toBeGreaterThanOrEqual(1)
-    // Leaving the anchor closes it with no delay.
+    // The card is REACHABLE: it sits 8px off the row, so getting to it means
+    // crossing ground that belongs to neither. Hovering it must not dismiss
+    // it — the regression this scenario guards.
+    const card = page.getByRole('button', { name: `Copy: ${rowTitle}` })
+    await card.hover()
+    await page.waitForTimeout(POINTER_HOLD_MS)
+    expect(await page.getByText('Idle', { exact: true }).count()).toBeGreaterThanOrEqual(1)
+    // The full title is the card's primary value: activating anywhere on the
+    // card writes it through the browser clipboard and localizes the success
+    // feedback through the English locale seat.
+    await page.context().grantPermissions(['clipboard-read', 'clipboard-write'])
+    const cardHeight = (await card.boundingBox())?.height
+    await card.click()
+    const copied = page.getByRole('status').getByText('Copied', { exact: true })
+    await copied.waitFor({ timeout: 5_000 })
+    await page.waitForTimeout(POINTER_HOLD_MS)
+    expect((await card.boundingBox())?.height).toBe(cardHeight)
+    expect(await copied.isVisible()).toBe(true)
+    expect(await page.evaluate(() => navigator.clipboard.readText())).toBe(rowTitle)
+    // Leaving anchor and card together closes it after the grace.
     await page.getByRole('button', { name: 'Settings' }).hover()
-    await expect.poll(() => page.getByText('Idle', { exact: true }).count(), { timeout: 5_000 }).toBe(0)
+    await expect.poll(() => card.count(), { timeout: 5_000 }).toBe(0)
     expect(tripwire.pageErrors).toEqual([])
   }, 60_000)
 
+  it('keeps an open row menu up while the pointer moves between trigger and list', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-row-menu'))
+    const sessionRow = await seededSessionRow()
+    // The trigger is display:none until its row hovers.
+    await sessionRow.hover()
+    const trigger = sessionRow.locator('button[aria-label^="Session actions for "]')
+    await trigger.click()
+    const item = page.getByRole('menuitem', { name: 'Rename' })
+    await item.waitFor({ timeout: 5_000 })
+    // Into the list, then back up to the trigger across the 4px gap below it:
+    // that return trip used to fire the list's pointerleave and close the
+    // menu, so a hesitating pointer lost it. Order matters — clicking leaves
+    // the pointer ON the trigger, so entering the list has to come first for
+    // the return to be a real departure.
+    await item.hover()
+    await page.waitForTimeout(POINTER_TRANSIT_MS)
+    await trigger.hover()
+    await page.waitForTimeout(POINTER_HOLD_MS)
+    expect(await page.getByRole('menuitem', { name: 'Rename' }).count()).toBe(1)
+    // ...and back down into the list, which must still be there to enter.
+    await item.hover()
+    await page.waitForTimeout(POINTER_HOLD_MS)
+    expect(await page.getByRole('menuitem', { name: 'Rename' }).count()).toBe(1)
+    // Pointer-leave dismissal still applies once the pointer genuinely leaves.
+    await page.getByRole('button', { name: 'Settings' }).hover()
+    await expect.poll(() => page.getByRole('menuitem', { name: 'Rename' }).count(), { timeout: 5_000 }).toBe(0)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('archives the seeded session from its row menu, hiding it durably across reload', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-archive'))
+    // The seeded session lives under Ungrouped (expanded by the hover-card
+    // test's gesture; converge again for order independence).
+    const ungroupedRow = page.getByText('Ungrouped', { exact: true }).locator('..').locator('..')
+    const ungroupedSection = ungroupedRow.locator('..')
+    await expect.poll(async () => {
+      if (await ungroupedRow.getAttribute('aria-expanded') !== 'true') {
+        await page.getByText('Ungrouped', { exact: true }).click()
+        await page.waitForTimeout(50)
+      }
+      return await ungroupedRow.getAttribute('aria-expanded')
+    }, { timeout: 5_000 }).toBe('true')
+    // Anchor on session rows (the rows carrying a session actions button),
+    // not a positional index, and assert the single-stray assumption loudly
+    // so a fixture gaining a second stray fails here instead of archiving
+    // the wrong row. CSS attribute match, not getByRole: the button is
+    // display:none until its row hovers, and role queries skip hidden nodes.
+    const sessionRows = ungroupedSection.locator('[role="treeitem"]')
+      .filter({ has: page.locator('button[aria-label^="Session actions for "]') })
+    await expect.poll(() => sessionRows.count(), { timeout: 10_000 }).toBe(1)
+    const sessionRow = sessionRows.first()
+    const rowTitle = await sessionRow.locator('[class*="title"]').innerText()
+    // Row menu: hover reveals the actions button; Archive session commits
+    // without a confirmation dialog (non-destructive: log + accounting stay).
+    await sessionRow.hover()
+    await sessionRow.getByRole('button', { name: `Session actions for ${rowTitle}` }).click()
+    await page.getByRole('menuitem', { name: 'Archive session' }).click()
+    // The row disappears on the archive-set echo; with no other visible
+    // stray, the whole Ungrouped bucket withdraws.
+    await expect.poll(() => page.getByText(rowTitle, { exact: true }).count(), { timeout: 10_000 }).toBe(0)
+    await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 10_000 }).toBe(0)
+    // Durable on the host: the registry-global set carries the id while the
+    // session log itself stays in persistence untouched.
+    expect([...scaffold.ctx.workspace.archivedSessionIds]).toEqual([SessionId(SEED_ID)])
+    expect((await scaffold.ctx.sessionPersistence.list()).map(header => header.id)).toContain(SessionId(SEED_ID))
+    // Reload: the hidden state is rebuilt from the workspace.list baseline.
+    const warningStart = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    acknowledgeReloadConnectionLoss(tripwire, warningStart)
+    await expect.poll(() => page.getByText('Workspaces', { exact: true }).count(), { timeout: 15_000 }).toBe(1)
+    // The archived row must not resurface (the Ungrouped bucket itself may
+    // reappear if selection restore lands on another stray — not this test's
+    // concern).
+    expect(await page.getByText(rowTitle, { exact: true }).count()).toBe(0)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 90_000)
+
+  it('opens folders with identical basenames as distinct workspaces', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-duplicate-basename'))
+    const firstPath = join(scaffold.workspaceCwd, 'same-basename-a', 'xx')
+    const secondPath = join(scaffold.workspaceCwd, 'same-basename-b', 'xx')
+    await mkdir(firstPath, { recursive: true })
+    await mkdir(secondPath, { recursive: true })
+
+    await adoptDirectory(firstPath, { waitForAgent: true })
+    await adoptDirectory(secondPath, { waitForAgent: true })
+
+    const matchingWorkspaces = scaffold.ctx.workspace.list()
+      .filter(workspace => workspace.title === 'xx')
+    expect(matchingWorkspaces.map(workspace => workspace.path).sort())
+      .toEqual([firstPath, secondPath].sort())
+    await expect.poll(
+      () => page.locator('button[aria-label="Workspace actions for xx"]').count(),
+      { timeout: 10_000 },
+    ).toBe(2)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 90_000)
+
   it.skipIf(MODE === 'record')('issued zero model calls and stayed clean', async () => {
     expect(tripwire.warnings).toEqual([])
     // The directory-browser aria golden is this spec's one owned artifact;

apps/web/tsconfig.json

@@ -24,6 +24,7 @@
   "exclude": [
     "tests/scaffold.ts",
     "tests/scaffold-hermetic.e2e.ts",
+    "tests/core-web-profile.snapshot.ts",
     "tests/live-interactions.e2e.ts",
     "tests/question-composer.e2e.ts",
     "tests/approval-composer.e2e.ts",
@@ -40,11 +41,16 @@
     "tests/seeded-history.e2e.ts",
     "tests/sidebar-scrollbar.e2e.ts",
     "tests/code-mode-round.e2e.ts",
+    "tests/composer-draft-scroll.e2e.ts",
     "tests/cordis-tool-round.e2e.ts",
+    "tests/web-search-round.e2e.ts",
     "tests/message-actions.e2e.ts",
     "tests/queue-actions.e2e.ts",
     "tests/skill-invocation-policy.e2e.ts",
-    "tests/access-confirmation.e2e.ts"
+    "tests/permission-policy-context.e2e.ts",
+    "tests/access-confirmation.e2e.ts",
+    "tests/shipped-composition.e2e.ts",
+    "tests/startup-auto-selection.e2e.ts"
   ],
   "references": [
     {