Merge remote-tracking branch 'origin/master' into feat/web-diff-card

# Conflicts: # packages/client/ui-conversation/README.i18n.yaml # packages/client/ui-conversation/README.md # packages/client/ui-conversation/README.zh.md
2026-07-31 12:50:58 +08:00
parent 4bcec15edd e130f7afa7
commit 64c855737d
96 changed files with 2198 additions and 265 deletions
--- a/apps/web/tests/access-confirmation.e2e.ts
+++ b/apps/web/tests/access-confirmation.e2e.ts
@@ -0,0 +1,104 @@
+// Web e2e scenario: every visible permission picker gates Full access behind
+// 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 { 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, captureStableAria, compareOrRefreshGolden,
+  launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { saveFailureShot } from './support.ts'
+
+/**
+ * connectFreshWorkspace twin over the product default Chinese locale (the
+ * shared helper's anchors assume the English page every other scenario
+ * boots; this scenario deliberately keeps zh, so the localized picker
+ * copy is the anchor set).
+ */
+async function connectFreshWorkspaceZh(page: Page, name = 'workspace'): Promise<void> {
+  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' })
+  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 page.locator('textarea:enabled[placeholder="描述你想要构建的内容"]')
+    .waitFor({ timeout: 15_000 })
+}
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/access-confirmation', import.meta.url))
+const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
+const MODE = webSnapshotMode()
+
+describe('web e2e: Full access confirmation', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({})
+    // CI uses Playwright's pinned browser. A developer may point this one
+    // scenario at an installed Chromium when the matching browser download
+    // is temporarily unavailable.
+    const executablePath = process.env.DSH_PLAYWRIGHT_EXECUTABLE_PATH
+    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 } })
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await connectFreshWorkspaceZh(page)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('requires acknowledgement before the composer picker can enable Full access', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-full-access-confirmation'))
+    const access = page.locator('button[aria-label^="访问模式"]').first()
+    await access.waitFor({ timeout: 10_000 })
+
+    // Normalize the starting preset through the real command path. The
+    // shipped web config may already start at Full access.
+    if ((await access.getAttribute('aria-label'))?.endsWith('Full access') === true) {
+      await access.click()
+      await page.getByRole('menuitem', { name: 'Workspace Write' }).click()
+      await expect.poll(() => access.getAttribute('aria-label'), { timeout: 10_000 })
+        .toBe('访问模式，当前：Workspace Write')
+    }
+
+    await access.click()
+    await page.getByRole('menuitem', { name: 'Full access' }).click()
+    const dialog = page.getByRole('dialog', { name: '确认启用 Full access？' })
+    await dialog.waitFor({ timeout: 10_000 })
+    const enable = dialog.getByRole('button', { name: '启用 Full access' })
+    expect(await enable.isDisabled()).toBe(true)
+
+    // The modal is in this page's body (not a native/new window) and escapes
+    // the sticky composer's stacking context.
+    expect(await dialog.evaluate(node => node.parentElement?.parentElement === document.body)).toBe(true)
+    const snapshot = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
+
+    await dialog.getByRole('checkbox', { name: '我已了解风险，并愿意继续' }).check()
+    expect(await enable.isEnabled()).toBe(true)
+    await enable.click()
+    await expect.poll(() => access.getAttribute('aria-label'), { timeout: 10_000 })
+      .toBe('访问模式，当前：Full access')
+    expect(await dialog.count()).toBe(0)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
+  it('keeps its snapshot inventory closed', async () => {
+    expect(tripwire.warnings).toEqual([])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['ui.expected.md'])
+  })
+})
--- a/apps/web/tests/live-interactions.e2e.ts
+++ b/apps/web/tests/live-interactions.e2e.ts
@@ -221,8 +221,8 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
    // only on change, so attempt count is invisible there).
    expect(sessionEvents.filter(e => e.type === 'llm/retry').length).toBeGreaterThanOrEqual(1)
    await expect.poll(() => page.getByText('event sourcing', { exact: false }).count(), { timeout: 10_000 }).toBeGreaterThan(0)
-    // Golden of the recovered end-state: indistinguishable from a clean
-    // completion — retries are deliberately invisible in the transcript.
+    // Golden of the recovered end-state: the discarded partial stays absent,
+    // while the settled retry row remains as durable recovery context.
    const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold!.workspaceCwd)
    await compareOrRefreshGolden(RETRY_EXPECTED, snapshot, MODE)
    expect(tripwire.pageErrors).toEqual([])
--- a/apps/web/tests/seeded-history.e2e.ts
+++ b/apps/web/tests/seeded-history.e2e.ts
@@ -238,7 +238,7 @@ describe('web e2e: seeded history renders through cold resume', () => {
    // where neither half repeats the other (the dispatched `/` and its
    // argument stay out of the title, and the settlement text never restates
    // the command's own name).
-    await page.getByRole('button', { name: 'Access mode, current: Danger Full Access' }).click()
+    await page.getByRole('button', { name: 'Access mode, current: Full access' }).click()
    await page.getByRole('menuitem', { name: 'Workspace Write' }).click()
    await page.getByRole('button', { name: 'Access mode, current: Workspace Write' }).waitFor({ timeout: 10_000 })
    // Scoped to the row itself, so unrelated page text that happens to read
--- a/apps/web/tests/smoke-real.e2e.ts
+++ b/apps/web/tests/smoke-real.e2e.ts
@@ -267,6 +267,98 @@ describe('dsh web keyless CLI smoke', () => {
    }
  })

+  it('retries a partial transport failure through the shipped Web composition', async () => {
+    requireDist()
+    const workspace = mkdtempSync(join(tmpdir(), 'dsh-web-retry-'))
+    const promptMarker = 'WEB_RETRY_REQUEST'
+    const recoveredMarker = 'WEB_RETRY_RECOVERED'
+    let mainAttempts = 0
+    const provider = createServer((request, response) => {
+      let body = ''
+      request.setEncoding('utf8')
+      request.on('data', (chunk: string) => { body += chunk })
+      request.on('end', () => {
+        const parsed = JSON.parse(body) as { max_tokens?: number; messages?: unknown[] }
+        const titleRequest = parsed.max_tokens === 64
+        const mainRequest = !titleRequest && body.includes(promptMarker)
+        response.writeHead(200, { 'content-type': 'text/event-stream' })
+        if (!mainRequest) {
+          response.end([
+            'data: {"choices":[{"delta":{"content":"Web retry title"}}]}',
+            'data: {"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":1,"completion_tokens":1}}',
+            'data: [DONE]',
+            '',
+          ].join('\n\n'))
+          return
+        }
+        mainAttempts++
+        if (mainAttempts === 1) {
+          response.write('data: {"choices":[{"delta":{"content":"WEB_RETRY_DISCARDED"}}]}\n\n')
+          setTimeout(() => { response.destroy() }, 20)
+          return
+        }
+        response.end([
+          `data: {"choices":[{"delta":{"content":"${recoveredMarker}"}}]}`,
+          'data: {"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}',
+          'data: [DONE]',
+          '',
+        ].join('\n\n'))
+      })
+    })
+    await new Promise<void>(resolve => provider.listen(0, '127.0.0.1', resolve))
+    const address = provider.address()
+    if (address === null || typeof address === 'string') throw new Error('mock provider did not bind a TCP port')
+    const tsxLoader = pathToFileURL(createRequire(join(REPO_ROOT, 'package.json')).resolve('tsx')).href
+    const child = spawn(
+      process.execPath,
+      ['--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', '0'],
+      {
+        cwd: workspace,
+        env: {
+          ...process.env,
+          DEEPSEEK_API_KEY: 'keyless-web-retry',
+          DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`,
+          DSH_HOME: join(workspace, '.dsh'),
+          TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
+        },
+        stdio: ['ignore', 'pipe', 'pipe'],
+      },
+    )
+    try {
+      const baseUrl = await waitForReadyLine(child)
+      const created = await rpc<{ sessionId: string }>(baseUrl, 'session.create', {})
+      await rpc<{ accepted: true }>(baseUrl, 'session.prompt', {
+        sessionId: created.sessionId,
+        mode: 'queue',
+        content: [{ type: 'text', text: promptMarker }],
+      })
+      let page: HistoryPage | undefined
+      await expect.poll(async () => {
+        page = await history(baseUrl, created.sessionId)
+        return hasAssistantMarker(page, recoveredMarker)
+      }, { timeout: 20_000 }).toBe(true)
+      if (page === undefined) throw new Error('retry history was not observed')
+      const retry = page.events.find(({ event }) => event.type === 'llm/retry')?.event
+      expect(mainAttempts).toBe(2)
+      expect(retry?.data).toMatchObject({
+        turn: 1,
+        step: 1,
+        retry: 1,
+        maxRetries: 2,
+        failure: { code: 'TRANSPORT' },
+      })
+      expect(JSON.stringify(page.events)).toContain('WEB_RETRY_DISCARDED')
+    } finally {
+      const closed = child.exitCode === null
+        ? new Promise<void>((resolveClose) => { child.once('close', () => { resolveClose() }) })
+        : Promise.resolve()
+      if (child.exitCode === null) child.kill('SIGTERM')
+      await closed
+      await new Promise<void>(resolveClose => provider.close(() => { resolveClose() }))
+      rmSync(workspace, { recursive: true, force: true })
+    }
+  }, 30_000)
+
  it('DSH_TOOLS_MODE=code collapses the provider wire tools to run_code with the SDK prompt section', async () => {
    requireDist()
    const workspace = mkdtempSync(join(tmpdir(), 'dsh-web-code-mode-'))
--- a/apps/web/tests/snapshots/access-confirmation/ui.expected.md
+++ b/apps/web/tests/snapshots/access-confirmation/ui.expected.md
@@ -0,0 +1,10 @@
+- dialog "确认启用 Full access？":
+  - heading "确认启用 Full access？" [level=2]
+  - button "Close":
+    - img
+  - img
+  - paragraph: 启用 Full access 后，agent 将减少确认步骤，并且可以直接执行更多操作，包括敏感操作、文件修改或外部命令。仅建议在你信任当前任务时使用。
+  - checkbox "我已了解风险，并愿意继续"
+  - text: 我已了解风险，并愿意继续
+  - button "取消"
+  - button "启用 Full access" [disabled]
--- a/apps/web/tests/snapshots/code-mode-round/ui.expected.md
+++ b/apps/web/tests/snapshots/code-mode-round/ui.expected.md
@@ -37,7 +37,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md
+++ b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md
@@ -52,7 +52,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md
+++ b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md
@@ -32,7 +32,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md
+++ b/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md
@@ -28,7 +28,7 @@
 - textbox "Describe what you want to build"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md
+++ b/apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md
@@ -28,7 +28,7 @@
 - textbox "Describe what you want to build"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Plan mode on, press to turn off": Plan
 - button "Select model, current deepseek-v4-flash":
  - text: deepseek-v4-flash
--- a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md
+++ b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md
@@ -24,7 +24,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/live-interactions/cancel.expected.md
+++ b/apps/web/tests/snapshots/live-interactions/cancel.expected.md
@@ -21,7 +21,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/live-interactions/error-auth.expected.md
+++ b/apps/web/tests/snapshots/live-interactions/error-auth.expected.md
@@ -14,7 +14,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/live-interactions/retry.expected.md
+++ b/apps/web/tests/snapshots/live-interactions/retry.expected.md
@@ -11,6 +11,8 @@
  - img
 - button "Edit":
  - img
+- 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.":
  - img
  - img
@@ -24,7 +26,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/message-actions/ui.expected.md
+++ b/apps/web/tests/snapshots/message-actions/ui.expected.md
@@ -39,7 +39,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current deepseek-v4-flash":
  - text: deepseek-v4-flash
  - img
--- a/apps/web/tests/snapshots/plan-review/approved.expected.md
+++ b/apps/web/tests/snapshots/plan-review/approved.expected.md
@@ -37,7 +37,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/question-composer/answered.expected.md
+++ b/apps/web/tests/snapshots/question-composer/answered.expected.md
@@ -32,7 +32,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/queue-actions/collapsed.expected.md
+++ b/apps/web/tests/snapshots/queue-actions/collapsed.expected.md
@@ -16,7 +16,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/queue-actions/editing.expected.md
+++ b/apps/web/tests/snapshots/queue-actions/editing.expected.md
@@ -29,7 +29,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/queue-actions/ui.expected.md
+++ b/apps/web/tests/snapshots/queue-actions/ui.expected.md
@@ -22,7 +22,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tests/snapshots/seeded-history/ui.expected.md
+++ b/apps/web/tests/snapshots/seeded-history/ui.expected.md
@@ -42,7 +42,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current deepseek-v4-flash":
  - text: deepseek-v4-flash
  - img
--- a/apps/web/tests/snapshots/steering/settled.expected.md
+++ b/apps/web/tests/snapshots/steering/settled.expected.md
@@ -33,7 +33,7 @@
 - textbox "Message the agent"
 - button "Commands":
  - img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- 'button "Access mode, current: Full access"': Full access
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
--- a/apps/web/tsconfig.json
+++ b/apps/web/tsconfig.json
@@ -43,7 +43,8 @@
    "tests/cordis-tool-round.e2e.ts",
    "tests/message-actions.e2e.ts",
    "tests/queue-actions.e2e.ts",
-    "tests/skill-invocation-policy.e2e.ts"
+    "tests/skill-invocation-policy.e2e.ts",
+    "tests/access-confirmation.e2e.ts"
  ],
  "references": [
    {