Merge remote-tracking branch 'origin/master' into worktree/unify-workspace-add

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

@@ -12,7 +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
@@ -53,7 +53,7 @@ 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 })

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/onboarding-deepseek-config.e2e.ts

@@ -12,7 +12,7 @@ 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'
 import { settingsNamespace } from '@deepseek-ai/dsh-settings'
 import {
   WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_COPY, WELCOME_NOTICE_SETTINGS_NAMESPACE,
@@ -34,7 +34,8 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
   beforeAll(async () => {
     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' })

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'

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
@@ -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/snapshots/onboarding-deepseek-config/welcome.expected.md

@@ -1,10 +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。
-  - paragraph: 目前的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。
+  - 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: 我们尤其希望听见那些失败、困惑与不顺手的时刻——
+    - 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/seeded-history/command-row.expected.md

@@ -29,6 +29,9 @@
 - 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

@@ -29,6 +29,9 @@
 - 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/support.ts

@@ -10,11 +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.