Merge remote-tracking branch 'origin/master' into fix/stats

apps/web/tests/agent-preset-selection.e2e.ts

@@ -283,6 +283,7 @@ describe('web e2e: agent-preset selection', () => {
     expect(snapshot).toContain('Minimal mode')
     expect(snapshot).toContain('button "1 subagent"')
     expect(snapshot.indexOf('Minimal mode')).toBeLessThan(snapshot.indexOf('button "1 subagent"'))
+    expect(snapshot.indexOf('button "1 subagent"')).toBeLessThan(snapshot.indexOf('button "Session log"'))
     // Static chrome, not a control: the header can only report a composition
     // the host would refuse to change.
     expect(snapshot).not.toContain('button "Minimal mode"')

apps/web/tests/assembled-boot.ts

@@ -43,6 +43,7 @@ const PLUGINS: readonly (WebBootEntry & { bundlePath: string })[] = [
       '@deepseek-ai/dsh-client-ui-sidebar',
     ],
   },
+  { id: '@deepseek-ai/dsh-session-export', bundlePath: 'packages/session-query/session-export/lib/client.js', url: '/plugins/session-export.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-command', '@deepseek-ai/dsh-client-ui-conversation'] },
   { id: '@deepseek-ai/dsh-client-ui-trajectory', bundlePath: 'packages/client/ui-trajectory/lib/client.js', url: '/plugins/ui-trajectory.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
 ]
 

apps/web/tests/image-display.snapshot.ts

@@ -1,7 +1,7 @@
 // @vitest-environment jsdom
 // Multimodal image surfaces over the BUILT client graph (the code-mode-fixture
 // idiom: real bundles via AppWebEntry, keyless FixtureApiClient transport).
-// Opens the fixture history session whose turn 72 carries an image in BOTH a
+// Opens the fixture history session whose turn 73 carries an image in BOTH a
 // user message and an assistant message, and pins the product surfaces: the
 // history ImageGallery loading real fixture bytes through the authorized
 // sessions.attachment route, the single-click ImageLightbox, and the composer
@@ -143,8 +143,55 @@ it('accepts pasted images into the composer rail in order and removes them', asy
     },
   })
   const toast = await screen.findByRole('alert')
-  expect(toast.textContent).toContain('Unsupported image format: text/plain')
+  expect(toast.textContent).toContain('Only PNG, JPG, WebP, and GIF images are supported')
   await waitFor(() => {
     expect(screen.queryByRole('alert')).toBeNull()
   }, { timeout: 6_000 })
 })
+
+it('accepts a whole-page drop under the limits-labeled overlay and refuses an over-limit batch at intake', async () => {
+  mountAssembledApp()
+
+  const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
+  const start = tree.querySelector<HTMLButtonElement>('button[aria-label="New session in fixture"]')
+  if (start === null) throw new Error('fixture Workspace new-session action missing')
+  fireEvent.click(start)
+  const textarea = await screen.findByPlaceholderText('Describe what you want to build', {}, { timeout: 10_000 })
+
+  // A file drag anywhere over the page raises the full-viewport overlay whose
+  // desc line carries the projected limits — copy that can only render after
+  // the imageLimits projection crossed the real fixture transport.
+  const image = new File([new Uint8Array([137, 80, 78, 71])], 'dropped.png', { type: 'image/png' })
+  const dataTransfer = { types: ['Files'], files: [image], dropEffect: 'none' }
+  fireEvent.dragEnter(document.body, { dataTransfer })
+  const overlay = await screen.findByRole('status')
+  expect(overlay.textContent).toContain('Drag images here to add them')
+  await waitFor(() => {
+    expect(overlay.textContent).toContain('Up to 20 images, 5MB each')
+  })
+
+  // Dropping on the transcript area (not the composer card) lands in the rail.
+  fireEvent.drop(document.body, { dataTransfer })
+  await waitFor(() => {
+    const rail = document.querySelector('[role="group"][aria-label="Pending images"]')
+    if (rail === null) throw new Error('attachment rail missing after page drop')
+    expect([...rail.querySelectorAll('img')].map(img => img.getAttribute('alt'))).toEqual(['dropped.png'])
+  }, { timeout: 5_000 })
+  expect(screen.queryByRole('status')).toBeNull()
+
+  // An intake that would exceed the projected per-message count is refused as
+  // a whole batch at add time: the banner names the limit and the rail keeps
+  // only the previously accepted thumbnail — no submit-time rollback.
+  const batch = Array.from({ length: 20 }, (_, i) =>
+    new File([new Uint8Array([137, 80, 78, 71])], `bulk-${String(i)}.png`, { type: 'image/png' }))
+  fireEvent.paste(textarea, {
+    clipboardData: {
+      items: batch.map(file => ({ kind: 'file', type: 'image/png', getAsFile: () => file })),
+      getData: () => '',
+    },
+  })
+  const banner = await screen.findByRole('alert')
+  expect(banner.textContent).toContain('A message can include up to 20 images')
+  const rail = document.querySelector('[role="group"][aria-label="Pending images"]')
+  expect([...(rail?.querySelectorAll('img') ?? [])]).toHaveLength(1)
+})

apps/web/tests/max-tokens-notice.snapshot.ts

@@ -0,0 +1,56 @@
+// @vitest-environment jsdom
+// Assembled max-tokens snapshot: boots the real built `packages/client/*/lib/
+// client.js` bundles through AppWebEntry's ModuleLoader path against the
+// keyless FixtureApiClient transport, opens the fixture session, and pins the
+// surface its max-tokens turn (72) reaches — the turn-end notice row that a
+// provider output-cap truncation must render instead of ending silently.
+//
+// The dot state is pinned beside the copy on purpose: `dot=warning` is what
+// distinguishes this notice from the error row, so a regression that routes
+// max-tokens through the turn-error presentation changes this file even when
+// its own copy still renders.
+import { mkdirSync, writeFileSync } from 'node:fs'
+import { dirname, join } from 'node:path'
+import { fireEvent, screen, waitFor, within } from '@testing-library/react'
+import { describe, expect, it } from 'vitest'
+import { hasClass, installAssembledBootEnv, mountAssembledApp, REFRESHING_GOLDEN } from './assembled-boot.ts'
+
+const EXPECTED = join(process.cwd(), 'apps/web/tests/snapshots/max-tokens-notice/history-turn.expected.txt')
+
+installAssembledBootEnv()
+
+/** Normalize the notice row to stable fields: its dot state, title, and hint. */
+function noticeShape(row: Element): string {
+  const first = (name: string): string =>
+    [...row.querySelectorAll('*')].filter(el => hasClass(el, name))[0]?.textContent?.trim() ?? '<absent>'
+  return [
+    `dot=${row.querySelector('[data-state]')?.getAttribute('data-state') ?? '<absent>'}`,
+    `title=${first('maxTokensTitle')}`,
+    `hint=${first('turnErrorMessage')}`,
+  ].join('\n')
+}
+
+describe('assembled max-tokens turn-end notice', () => {
+  it('renders the localized truncation notice after the cut-off answer instead of ending silently', async () => {
+    mountAssembledApp()
+
+    const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
+    fireEvent.click(await within(tree).findByText('Fixture 历史会话'))
+    // The truncated answer itself stays in the flow: the notice supplements the
+    // partial output, it never replaces it.
+    await screen.findByText(/条目 3：这一条写到一半被/, undefined, { timeout: 10_000 })
+    const row = await waitFor(() => {
+      const found = [...document.querySelectorAll('[role="status"]')]
+        .find(candidate => [...candidate.querySelectorAll('*')].some(el => hasClass(el, 'maxTokensTitle')))
+      expect(found).not.toBeUndefined()
+      return found!
+    }, { timeout: 10_000 })
+
+    const shape = noticeShape(row)
+    if (REFRESHING_GOLDEN) {
+      mkdirSync(dirname(EXPECTED), { recursive: true })
+      writeFileSync(EXPECTED, shape)
+    }
+    await expect(shape).toMatchFileSnapshot(EXPECTED)
+  })
+})

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

@@ -0,0 +1,121 @@
+// Keyless browser regression for durable per-message feedback. Cold-seeds a
+// settled two-turn transcript (zero model calls), rates one assistant message,
+// attaches a note, proves both survive a full page reload from the Host's
+// message-feedback sidecar, then retracts the rating.
+import { readFile } from 'node:fs/promises'
+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 {
+  acknowledgeReloadConnectionLoss, launchWebScaffold,
+  seedSession, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { newEnglishPage, saveFailureShot } from './support.ts'
+
+// Borrowed read-only: this scenario needs any settled assistant message to
+// address, not a new recording (message-actions / sidebar-scrollbar pattern).
+const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
+const MODE = webSnapshotMode()
+const SEED_ID = 'message-feedback-web-e2e'
+const NOTE = 'Read both files before answering.'
+
+describe('web e2e: durable per-message feedback', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({})
+    await seedSession(scaffold, await readFile(SEED, 'utf8'), SEED_ID)
+    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 })
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  /**
+   * Open the seeded transcript. The first treeitem is the collapsible group
+   * row; the session itself is the row beneath it. The group is already
+   * expanded on a fresh load, so clicking it unconditionally would collapse it
+   * and hide the session row.
+   */
+  async function openSeededSession(): Promise<void> {
+    const groupRow = page.locator('[role="treeitem"]').first()
+    await groupRow.waitFor({ timeout: 15_000 })
+    if (await groupRow.getAttribute('aria-expanded') !== 'true') await groupRow.click()
+    const sessionRow = page.locator('[role="treeitem"]').nth(1)
+    await sessionRow.waitFor({ timeout: 15_000 })
+    await sessionRow.click()
+  }
+
+  it.skipIf(MODE === 'record')('persists a rating and its note across a reload, then retracts', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-message-feedback'))
+    await openSeededSession()
+
+    // The controls live in the assistant message's IconActions row, which the
+    // transcript reveals on hover/focus like copy and branch. Wait for the
+    // settled closing text first: the strip mounts with that turn's tail.
+    await page.getByText('DONE', { exact: true }).waitFor({ timeout: 30_000 })
+    const like = page.getByRole('button', { name: 'Good response' }).first()
+    await like.waitFor({ timeout: 30_000 })
+    await like.scrollIntoViewIfNeeded()
+    await like.hover()
+    await like.click()
+    // A recorded rating relabels the button to what the next click would do,
+    // so the pressed control is addressed by the retract label from here on.
+    const rated = page.getByRole('button', { name: 'Remove rating' }).first()
+    await expect.poll(() => rated.getAttribute('aria-pressed'), { timeout: 10_000 }).toBe('true')
+
+    // A rated message offers the note editor; an unrated one does not.
+    await page.getByRole('button', { name: 'Add a note' }).first().click()
+    const editor = page.getByRole('textbox', { name: 'Feedback note' })
+    await editor.fill(NOTE)
+    await page.getByRole('button', { name: 'Save', exact: true }).click()
+    await expect.poll(() => editor.count(), { timeout: 10_000 }).toBe(0)
+    await page.getByText(NOTE, { exact: true }).waitFor({ timeout: 10_000 })
+
+    // The durable assertion: a cold browser re-reads the sidecar over the wire.
+    const warningStart = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    acknowledgeReloadConnectionLoss(tripwire, warningStart)
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await openSeededSession()
+    await page.getByText('DONE', { exact: true }).waitFor({ timeout: 30_000 })
+
+    // The controller defers its list read to the first hover or focus, so a
+    // cold reload shows the unrated label until the strip is touched. Hovering
+    // the unrated control is what triggers the authoritative re-read.
+    const cold = page.getByRole('button', { name: 'Good response' }).first()
+    await cold.waitFor({ timeout: 30_000 })
+    await cold.scrollIntoViewIfNeeded()
+    await cold.hover()
+
+    const restored = page.getByRole('button', { name: 'Remove rating' }).first()
+    await restored.waitFor({ timeout: 30_000 })
+    await restored.scrollIntoViewIfNeeded()
+    await restored.hover()
+    await expect.poll(() => restored.getAttribute('aria-pressed'), { timeout: 15_000 }).toBe('true')
+    await page.getByText(NOTE, { exact: true }).waitFor({ timeout: 10_000 })
+
+    // Re-clicking the active rating retracts it, and the note goes with it.
+    await restored.click()
+    await expect.poll(
+      () => page.getByRole('button', { name: 'Good response' }).first().getAttribute('aria-pressed'),
+      { timeout: 10_000 },
+    ).toBe('false')
+    await expect.poll(() => page.getByText(NOTE, { exact: true }).count(), { timeout: 10_000 }).toBe(0)
+  }, 90_000)
+
+  it.skipIf(MODE === 'record')('kept the console clean', () => {
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  })
+})

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

@@ -52,6 +52,11 @@ async function assertBaselineSucceeded(response: Response, method: string): Prom
 }
 
 async function ensureSeedOpen(page: Page): Promise<void> {
+  const welcome = page.locator('[class*="onboardingOverlay"]')
+  if (await welcome.count() > 0) {
+    await welcome.getByRole('button').click()
+    await welcome.waitFor({ state: 'detached', timeout: 15_000 })
+  }
   const chat = page.getByRole('tab', { name: 'Chat', exact: true })
   // Search is a collapsed header action; expand it so the input is actionable.
   const searchButton = page.getByRole('button', { name: 'Search sessions' })
@@ -283,14 +288,30 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
     await details.getByRole('button', { name: 'Close details' }).click()
   }, 60_000)
 
-  it.skipIf(MODE === 'record')('downloads the session-log ZIP from the trajectory toolbar', async () => {
+  it.skipIf(MODE === 'record')('downloads through the Session Header and /export with one dialog', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-export'))
     await ensureSeedOpen(page)
-    await page.getByRole('tab', { name: 'Trajectory' }).click()
+    const exportButton = page.getByRole('button', { name: 'Session log' })
+    expect(await exportButton.isDisabled()).toBe(false)
+    const header = exportButton.locator('xpath=ancestor::header[1]')
+    const [buttonBox, headerBox] = await Promise.all([
+      exportButton.boundingBox(), header.boundingBox(),
+    ])
+    if (buttonBox === null || headerBox === null) {
+      throw new Error('Session Header export geometry is unavailable')
+    }
+    expect(headerBox.x + headerBox.width - (buttonBox.x + buttonBox.width)).toBeLessThanOrEqual(32)
+    const responsePromise = page.waitForResponse(response =>
+      response.request().method() === 'HEAD'
+      && new URL(response.url()).pathname === '/api/session.export', { timeout: 30_000 })
     const downloadPromise = page.waitForEvent('download', { timeout: 30_000 })
-    await page.getByRole('button', { name: 'Export session log' }).click()
+    await exportButton.click()
+    const response = await responsePromise
+    expect(response.status()).toBe(200)
     const download = await downloadPromise
     expect(download.suggestedFilename()).toMatch(/^dsh-session-.+\.zip$/)
+    const dialog = page.getByRole('dialog', { name: 'Session download started' })
+    await dialog.waitFor({ timeout: 30_000 })
     // The real host streamed the ZIP; its root entry is the persisted log
     // text verbatim (the assembled seam: real route, real persistence read).
     const files = unzipSync(await readFile(await download.path()))
@@ -298,7 +319,63 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
     const content = strFromU8(files['session.jsonl'] as Uint8Array)
     expect(content.split('\n')[0]).toContain(SEED_ID)
     expect(content).toContain('FIRST_DONE')
-  }, 60_000)
+    await dialog.getByText('Close', { exact: true }).click()
+
+    const observer = await newEnglishPage(browser)
+    const observerTripwire = watchConsole(observer)
+    const observerSlotErrors: string[] = []
+    let observerDownloads = 0
+    observer.on('download', () => { observerDownloads += 1 })
+    observer.on('console', (message) => {
+      if (message.type() === 'error' && /slot entry crashed/i.test(message.text())) {
+        observerSlotErrors.push(message.text())
+      }
+    })
+    const observerSessionBaseline = baselineResponse(observer, 'session.list')
+    const observerWorkspaceBaseline = baselineResponse(observer, 'workspace.list')
+    const [, observerSessionResponse, observerWorkspaceResponse] = await Promise.all([
+      observer.goto(scaffold.baseUrl, { waitUntil: 'load' }),
+      observerSessionBaseline,
+      observerWorkspaceBaseline,
+    ])
+    await Promise.all([
+      assertBaselineSucceeded(observerSessionResponse, 'observer session.list'),
+      assertBaselineSucceeded(observerWorkspaceResponse, 'observer workspace.list'),
+    ])
+    await observer.getByText('Ungrouped', { exact: true }).waitFor({ timeout: 30_000 })
+    await ensureSeedOpen(observer)
+
+    try {
+      const input = page.locator('textarea').first()
+      const slashDownloadPromise = page.waitForEvent('download', { timeout: 30_000 })
+      await input.fill('/export')
+      await page.getByRole('option', { name: /export/u }).waitFor({ timeout: 10_000 })
+      await input.press('Enter')
+      const slashDownload = await slashDownloadPromise
+      expect(slashDownload.suggestedFilename()).toBe(download.suggestedFilename())
+      const slashFiles = unzipSync(await readFile(await slashDownload.path()))
+      const slashContent = strFromU8(slashFiles['session.jsonl'] as Uint8Array)
+      const slashEvents = parseSessionLog(slashContent)
+      const exportRun = slashEvents.findLast(event => event.type === 'command/run' && event.data.name === 'export')
+      if (exportRun?.type !== 'command/run') throw new Error('slash ZIP has no export command/run')
+      const exportDone = slashEvents.find(event =>
+        event.type === 'command/done' && event.data.commandId === exportRun.data.commandId)
+      expect(exportDone?.type).toBe('command/done')
+      await page.getByRole('dialog', { name: 'Session download started' }).waitFor({ timeout: 30_000 })
+      await page.getByRole('dialog', { name: 'Session download started' })
+        .getByText('Close', { exact: true }).click()
+      await observer.getByText('Session log download requested.', { exact: true }).waitFor({ timeout: 30_000 })
+      expect(observerDownloads).toBe(0)
+      expect(await observer.getByRole('dialog', { name: 'Session download started' }).count()).toBe(0)
+      expect({
+        pageErrors: observerTripwire.pageErrors,
+        slotErrors: observerSlotErrors,
+        warnings: observerTripwire.warnings,
+      }).toEqual({ pageErrors: [], slotErrors: [], warnings: [] })
+    } finally {
+      await observer.close()
+    }
+  }, 120_000)
 
   it.skipIf(MODE === 'record')('focuses the ledger by dragging an overview interval', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-timeline'))

apps/web/tests/plugin-config.e2e.ts

@@ -56,9 +56,9 @@ describe('web e2e: plugin configuration section', () => {
     await page.getByRole('button', { name: '设置', exact: true }).click()
     const dialog = page.getByRole('dialog', { name: '设置' })
     await dialog.waitFor({ timeout: 10_000 })
-    await dialog.getByRole('button', { name: '插件' }).click()
+    await dialog.getByRole('button', { name: '插件配置', exact: true }).click()
     await expect
-      .poll(() => dialog.getByRole('button', { name: '插件' }).getAttribute('aria-current'), { timeout: 5_000 })
+      .poll(() => dialog.getByRole('button', { name: '插件配置', exact: true }).getAttribute('aria-current'), { timeout: 5_000 })
       .toBe('true')
     return dialog
   }

apps/web/tests/scaffold.ts

@@ -51,7 +51,7 @@ import { dshHomePath } from '@deepseek-ai/dsh-paths'
 // } from '@deepseek-ai/dsh-client-ui-settings-general'
 export const WELCOME_NOTICE_SETTINGS_NAMESPACE = 'ui-onboarding'
 export const WELCOME_NOTICE_ACK_FIELD = 'welcomeNoticeVersion'
-export const WELCOME_NOTICE_VERSION = '2026-07-30.7'
+export const WELCOME_NOTICE_VERSION = '2026-08-11.1'
 export const WELCOME_NOTICE_COPY = { zh: { title: '内测声明', continueLabel: '继续' } } as const
 
 import { settingsNamespace } from '@deepseek-ai/dsh-settings'
@@ -421,7 +421,14 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
     // disclosure passes a local dead endpoint instead of disabling the row.
     options.telemetryUrl === undefined
       ? { id: 'telemetry-otel', disabled: true }
-      : { id: 'telemetry-otel', config: { exporter: { url: options.telemetryUrl }, shutdownTimeoutMillis: 1_000 } },
+      : {
+        id: 'telemetry-otel',
+        config: {
+          mode: 'FULL',
+          exporter: { url: options.telemetryUrl },
+          shutdownTimeoutMillis: 1_000,
+        },
+      },
     {
       id: 'webserver',
       config: { host: '127.0.0.1', port: 0 },

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

@@ -23,6 +23,8 @@ 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')
+const PLUGINS_EXPECTED = join(SNAPSHOT_DIR, 'plugins.expected.md')
+const PLUGIN_ROW_SELECTOR = '[data-plugin-entry$="ui-settings"]'
 const MODE = webSnapshotMode()
 
 describe('web e2e: settings modal and General preferences', () => {
@@ -92,6 +94,28 @@ describe('web e2e: settings modal and General preferences', () => {
     await dialog.getByRole('button', { name: '模型' }).click()
     await expect.poll(() => dialog.getByRole('button', { name: '模型' }).getAttribute('aria-current'), { timeout: 5_000 }).toBe('true')
     expect(await dialog.getByRole('button', { name: '通用设置' }).getAttribute('aria-current')).toBeNull()
+    // Plugins is a read-only projection of the same assembled Loader tree.
+    // Capture one stable shipped row rather than the whole inventory so adding
+    // an unrelated plugin does not rewrite this surface's golden.
+    await dialog.getByRole('button', { name: '插件', exact: true }).click()
+    await dialog.getByRole('heading', { name: '插件', exact: true }).waitFor({ timeout: 10_000 })
+    const pluginRow = dialog.locator(PLUGIN_ROW_SELECTOR)
+    await pluginRow.waitFor({ timeout: 10_000 })
+    const expectedPluginCount = [...scaffold.ctx.loader.entries()]
+      .filter(entry => !entry.options.group)
+      .length
+    expect(await dialog.getByRole('searchbox', { name: '搜索插件' }).count()).toBe(1)
+    expect(await dialog.locator('[data-plugin-entry]').count()).toBe(expectedPluginCount)
+    expect(await dialog.locator('[data-plugin-count]').getAttribute('data-plugin-count'))
+      .toBe(String(expectedPluginCount))
+    expect(await dialog.getByRole('button', { name: '插件', exact: true }).getAttribute('aria-current')).toBe('true')
+    expect(await dialog.getByRole('button', { name: '模型' }).getAttribute('aria-current')).toBeNull()
+    const pluginsSnapshot = await captureStableAria(
+      page,
+      PLUGIN_ROW_SELECTOR,
+      scaffold.workspaceCwd,
+    )
+    await compareOrRefreshGolden(PLUGINS_EXPECTED, pluginsSnapshot, MODE)
     // Close path 1: Escape.
     await page.keyboard.press('Escape')
     await expect.poll(() => page.getByRole('dialog', { name: '设置' }).count(), { timeout: 5_000 }).toBe(0)
@@ -454,6 +478,6 @@ describe('web e2e: settings modal and General preferences', () => {
 
   it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
     expect(tripwire.warnings).toEqual([])
-    await assertFixtureInventory(SNAPSHOT_DIR, ['dialog.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['dialog.expected.md', 'plugins.expected.md'])
   })
 })

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

@@ -138,13 +138,13 @@ async function detailsTrack(page: Page): Promise<number> {
   return Number(cols.split(' ').pop()!.replace('px', ''))
 }
 
-// Readiness gate: `dsh web` serves all ten production manifest plugins; until every UI
+// Readiness gate: `dsh web` serves every production manifest plugin; until every UI
 // plugin's client bundle exists and exports apply, the loader fail-louds and
 // the frame never appears.
 const UI_PLUGIN_DIRS = [
   'connection', 'runtime', 'ui-theme', 'locale', 'ui-layout', 'ui-sidebar',
   'ui-settings', 'ui-settings-general', 'ui-models', 'ui-conversation',
-  'ui-model', 'ui-question', 'ui-trajectory',
+  'ui-model', 'ui-question', 'ui-trajectory', '../session-query/session-export',
 ]
 const ROUND_DONE_MARKER = 'WEB_ROUND_DONE'
 const notReady = UI_PLUGIN_DIRS.filter((dir) => {

apps/web/tests/snapshots/agent-preset-authoring/created.expected.md

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

apps/web/tests/snapshots/agent-preset-authoring/damaged.expected.md

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

apps/web/tests/snapshots/agent-preset-authoring/section.expected.md

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

apps/web/tests/snapshots/agent-preset-selection/header.expected.md

@@ -5,3 +5,6 @@
 - button "1 subagent":
   - text: 1 subagent
   - img
+- button "Session log":
+  - text: Session log
+  - img

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

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - 'button "Run two shell commands: wait" [disabled]'
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - 'button "Using ONE run_code program: run" [disabled]'
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -33,6 +36,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

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

@@ -3,6 +3,9 @@
     - button "Use only Cordis tools. First" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -48,6 +51,10 @@
 - paragraph: CORDIS_UI_DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/feedback-command/ack.expected.md

@@ -3,6 +3,9 @@
     - button "Reply with the single word" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -20,6 +23,10 @@
 - paragraph: LIGHTHOUSE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

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

@@ -3,6 +3,9 @@
     - button "Use the bash tool to" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -28,6 +31,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/goal-command-presentation/ui.expected.md

@@ -3,6 +3,9 @@
     - button "workspace" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/goal-multi-turn-actions/ui.expected.md

@@ -3,6 +3,9 @@
     - button "workspace" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -78,6 +81,10 @@
 - paragraph: 这是一个很典型的轻量 TypeScript 包结构：入口 + 实现 + 测试。这一轮到此结束，等系统开启下一个 turn。
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s
@@ -187,6 +194,10 @@
   - text: ）的结构，或者其他格式的输出（比如带文件大小的树形图），随时告诉我。
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - tooltip "Branch into a new conversation"

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

@@ -1,6 +1,7 @@
 - listbox "Trigger suggestions":
   - text: Commands
   - option "compact Compact older conversation history" [selected]
+  - option "export Download this Session log as a ZIP archive"
   - option "feedback record feedback about this session"
   - option "goal set or view the goal for a long-running task"
   - option "permission Switch the permission preset (sandbox mode + approval policy)"

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

@@ -3,6 +3,9 @@
     - button "Reply with the single word" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -20,6 +23,10 @@
 - paragraph: LIGHTHOUSE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

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

@@ -3,6 +3,9 @@
     - button "Reply with a one-sentence description" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "Reply with a one-sentence description" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "Reply with a one-sentence description" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "Reply with a one-sentence description" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -22,6 +25,10 @@
 - paragraph: Event sourcing is a pattern where all changes to an application's state are stored as an immutable, append-only sequence of events, rather than persisting only the current state, enabling full auditability, temporal queries, and event-driven architectures.
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "CJK strong emphasis" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -35,6 +38,10 @@
 - paragraph: CJK_STRONG_DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}}

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

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Markdown image policy" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -14,6 +17,10 @@
 - paragraph: REMOTE_IMAGE_DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}}

apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Inline code links" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -26,6 +29,10 @@
 - paragraph: INLINE_CODE_LINK_DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}}

apps/web/tests/snapshots/math-rendering/ui.expected.md

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Math rendering" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -30,6 +33,10 @@
 - paragraph: MATH_RENDERING_DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}}

apps/web/tests/snapshots/max-tokens-notice/history-turn.expected.txt

@@ -0,0 +1,3 @@
+dot=warning
+title=Output token limit reached
+hint=The reply was cut off; earlier output is preserved in the conversation. Send "continue" to let the model resume.

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

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Use the read tool twice" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -15,6 +18,10 @@
 - paragraph: I will read both files before answering.
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation" [disabled]:
   - img
 - text: Available only on the last message of a completed turn 7/25 {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s
@@ -38,6 +45,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}}

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

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

apps/web/tests/snapshots/models-settings/declared-edit.expected.md

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

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

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

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

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

apps/web/tests/snapshots/navigation-panes/trajectory.expected.md

@@ -2,7 +2,6 @@
   - button "Use actual duration": Duration
   - button "Collapse turns": Turns
   - button "Collapse calls": Calls
-  - button "Export session log": Export
   - img
   - searchbox "Search trajectory"
 - region "Trajectory timeline":

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

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

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

@@ -3,7 +3,7 @@
   - 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，
+    - text: 内测版本默认不会上传 Session Log。如需在提交反馈时共享会话日志，可以设置环境变量 DSH_TELEMETRY_MODE=FEEDBACK_ONLY；如需持续上传，可以设置 DSH_TELEMETRY_MODE=FULL，但该模式同时会启用 dsh-sdk 命令遥测，上报匿名 ID、命令结果以及脱敏后的项目配置。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/onboarding-usable-provider/dismissed.expected.md

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

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

@@ -3,6 +3,9 @@
     - 'button "Plan a small change: add" [disabled]'
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -33,6 +36,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/plugin-config/section.expected.md

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

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

@@ -3,6 +3,9 @@
     - button "Use the ask_user_question tool to" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -28,6 +31,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

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

@@ -3,6 +3,9 @@
     - button "Reply with a one-sentence description" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "Reply with a one-sentence description" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "workspace" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "Reply with a one-sentence description" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "Reply with a one-sentence description" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Use the read tool twice" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -28,6 +31,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

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

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Use the read tool twice" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -28,6 +31,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

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

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Use the read tool twice" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -28,6 +31,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

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

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "插件":
+      - img
+      - text: 插件
     - button "Agent 预设":
       - img
       - text: Agent 预设

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

@@ -0,0 +1,6 @@
+- listitem:
+  - button "ui-settings, 已挂载, 已启用":
+    - strong: ui-settings
+    - img "已挂载"
+    - text: 已启用
+    - img

apps/web/tests/snapshots/skill-tool-row/ui.expected.md

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Load the snapshot-skill skill with" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -31,6 +34,10 @@
 - paragraph: DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{date}} {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/skill-user-invoke/ui.expected.md

@@ -3,6 +3,9 @@
     - button "/user-invoke-demo and confirm the fixtur" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -20,6 +23,10 @@
 - paragraph: USER_INVOKE_REPLY acknowledged; following the injected skill.
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/stats-paged-history/ui.expected.md

@@ -1,6 +1,9 @@
 - banner:
   - navigation "Session hierarchy":
     - button "{{workspace}}" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -10,6 +13,10 @@
 - paragraph: r1
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m2 7/25 {{clock}}
@@ -18,6 +25,10 @@
 - paragraph: r2
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m3 7/25 {{clock}}
@@ -26,6 +37,10 @@
 - paragraph: r3
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m4 7/25 {{clock}}
@@ -34,6 +49,10 @@
 - paragraph: r4
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m5 7/25 {{clock}}
@@ -42,6 +61,10 @@
 - paragraph: r5
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m6 7/25 {{clock}}
@@ -50,6 +73,10 @@
 - paragraph: r6
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m7 7/25 {{clock}}
@@ -58,6 +85,10 @@
 - paragraph: r7
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m8 7/25 {{clock}}
@@ -66,6 +97,10 @@
 - paragraph: r8
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m9 7/25 {{clock}}
@@ -74,6 +109,10 @@
 - paragraph: r9
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m10 7/25 {{clock}}
@@ -82,6 +121,10 @@
 - paragraph: r10
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m11 7/25 {{clock}}
@@ -90,6 +133,10 @@
 - paragraph: r11
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m12 7/25 {{clock}}
@@ -98,6 +145,10 @@
 - paragraph: r12
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m13 7/25 {{clock}}
@@ -106,6 +157,10 @@
 - paragraph: r13
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m14 7/25 {{clock}}
@@ -114,6 +169,10 @@
 - paragraph: r14
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m15 7/25 {{clock}}
@@ -122,6 +181,10 @@
 - paragraph: r15
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m16 7/25 {{clock}}
@@ -130,6 +193,10 @@
 - paragraph: r16
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m17 7/25 {{clock}}
@@ -138,6 +205,10 @@
 - paragraph: r17
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m18 7/25 {{clock}}
@@ -146,6 +217,10 @@
 - paragraph: r18
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m19 7/25 {{clock}}
@@ -154,6 +229,10 @@
 - paragraph: r19
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m20 7/25 {{clock}}
@@ -162,6 +241,10 @@
 - paragraph: r20
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m21 7/25 {{clock}}
@@ -170,6 +253,10 @@
 - paragraph: r21
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m22 7/25 {{clock}}
@@ -178,6 +265,10 @@
 - paragraph: r22
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m23 7/25 {{clock}}
@@ -186,6 +277,10 @@
 - paragraph: r23
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m24 7/25 {{clock}}
@@ -194,6 +289,10 @@
 - paragraph: r24
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m25 7/25 {{clock}}
@@ -202,6 +301,10 @@
 - paragraph: r25
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m26 7/25 {{clock}}
@@ -210,6 +313,10 @@
 - paragraph: r26
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m27 7/25 {{clock}}
@@ -218,6 +325,10 @@
 - paragraph: r27
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}} m28 7/25 {{clock}}
@@ -226,6 +337,10 @@
 - paragraph: r28
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}} Ran for {{duration}}

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

@@ -3,6 +3,9 @@
     - button "Use the ask_user_question tool to" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/steer-all/settled.expected.md

@@ -3,6 +3,9 @@
     - button "Use the ask_user_question tool to" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -30,6 +33,10 @@
 - paragraph: "Got it: BANANA and ORANGE."
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

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

@@ -3,6 +3,9 @@
     - button "Use the ask_user_question tool to" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "Use the ask_user_question tool to" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -31,6 +34,10 @@
 - paragraph: Great, let's move forward. BANANA!
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/subagent-conversation/nested.expected.md

@@ -5,6 +5,9 @@
     - button "event-sourcing researcher"
     - text: /
     - button "example editor" [disabled]
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/subagent-conversation/ui.expected.md

@@ -8,6 +8,9 @@
   - button "1 subagent":
     - text: 1 subagent
     - img
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -25,6 +28,10 @@
 - paragraph: Event sourcing is a pattern where all changes to an application's state are stored as an immutable, append-only sequence of events, rather than persisting only the current state, enabling full auditability, temporal queries, and event-driven architectures.
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s Now give the same explanation to a human reader. {{clock}}
@@ -37,6 +44,10 @@
 - paragraph: Event sourcing is a pattern where all changes to an application's state are stored as an immutable, append-only sequence of events, rather than persisting only the current state, enabling full auditability, temporal queries, and event-driven architectures.
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/subagent-interrupt/offline-composer.expected.md

@@ -5,6 +5,9 @@
     - button "event-sourcing researcher" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/turn-tail-actions/running.expected.md

@@ -3,6 +3,9 @@
     - button "Begin your reply with the" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/turn-tail-actions/settled.expected.md

@@ -3,6 +3,9 @@
     - button "Begin your reply with the" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -3,6 +3,9 @@
     - button "Use web_search to search exactly" [disabled]
   - img
   - text: Standard mode
+  - button "Session log":
+    - text: Session log
+    - img
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
@@ -20,6 +23,10 @@
 - paragraph: SEARCH_DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/snapshots/workflow-run/ui.expected.md

@@ -27,6 +27,10 @@
 - paragraph: WORKFLOW_DONE
 - button "Copy":
   - img
+- button "Good response":
+  - img
+- button "Bad response":
+  - img
 - button "Branch into a new conversation":
   - img
 - text: {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s

apps/web/tests/todo-row.snapshot.ts

@@ -2,7 +2,7 @@
 // Assembled todo snapshot: boots the real built `packages/client/*/lib/
 // client.js` bundles through AppWebEntry's ModuleLoader path against the
 // keyless FixtureApiClient transport, opens the fixture session, and pins the
-// two surfaces the fixture's parallel plan (turn 73, two items `in_progress`)
+// two surfaces the fixture's parallel plan (turn 74, two items `in_progress`)
 // reaches — the `todo_write` tool row and the dock's plan strip.
 //
 // The row is pinned as three separate fields on purpose. `summary=` is the

apps/web/tsconfig.json

@@ -56,6 +56,7 @@
     "tests/cordis-tool-round.e2e.ts",
     "tests/web-search-round.e2e.ts",
     "tests/message-actions.e2e.ts",
+    "tests/message-feedback.e2e.ts",
     "tests/markdown-images.e2e.ts",
     "tests/math-rendering.e2e.ts",
     "tests/markdown-cjk-strong.e2e.ts",