Merge branch 'master' into agent/message-feedback-backend

apps/web/tests/background-task-list.e2e.ts

@@ -0,0 +1,133 @@
+// Web e2e scenario: the session-header background-task list over the real
+// host. No model call is involved — a genuine `run_in_background` bash call
+// registers with `ctx.tasks`, and the assertion chain is the whole delivery
+// path: registry change feed → api-proxy `session/tasks` frame → the client's
+// `tasksBySession` mirror → the header action.
+import { readFile } from 'node:fs/promises'
+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 type { Agent } from '@deepseek-ai/dsh-agent'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import { TaskId } from '@deepseek-ai/dsh-tasks'
+import {
+  assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
+  launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { newEnglishPage, saveFailureShot } from './support.ts'
+
+const FIXTURE = fileURLToPath(new URL('./snapshots/fresh-round-trip/session.jsonl', import.meta.url))
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/background-task-list', import.meta.url))
+const RUNNING_EXPECTED = join(SNAPSHOT_DIR, 'running.expected.md')
+const SETTLED_EXPECTED = join(SNAPSHOT_DIR, 'settled.expected.md')
+const MODE = webSnapshotMode()
+const SEED_ID = 'background-task-list-web-e2e'
+// Long enough that the running assertions never race the process exiting on
+// their own; the test kills it explicitly to reach the settled state.
+const COMMAND = 'sleep 45'
+
+/**
+ * Wait for the Host to publish the live Agent that opening a session resumes.
+ * @param scaffold - the booted web scaffold.
+ * @param sessionId - the opened session's identity.
+ * @returns the registered Agent instance.
+ */
+async function liveAgent(scaffold: WebScaffold, sessionId: SessionId): Promise<Agent> {
+  const deadline = Date.now() + 30_000
+  for (;;) {
+    const found = scaffold.ctx.agents.get(sessionId)
+    if (found !== undefined) return found
+    if (Date.now() > deadline) throw new Error(`opening session "${sessionId}" published no live Agent`)
+    await new Promise(resolve => setTimeout(resolve, 100))
+  }
+}
+
+describe.skipIf(MODE === 'record')('web e2e: background task list', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+  let agent: Agent
+  let taskId: TaskId
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({})
+    await seedSession(scaffold, await readFile(FIXTURE, '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 })
+
+    const groupRow = page.locator('[role="treeitem"]').first()
+    await groupRow.waitFor({ timeout: 15_000 })
+    await groupRow.click()
+    const sessionRow = page.locator('[role="treeitem"]').nth(1)
+    await sessionRow.waitFor({ timeout: 10_000 })
+    await sessionRow.click()
+
+    // Opening the session drives the Host's ordinary Agent resolution; the
+    // task owner must be that exact live instance, never a second one.
+    // `expect.poll` is test-scoped, so this hook polls by hand.
+    agent = await liveAgent(scaffold, SessionId(SEED_ID))
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('shows a running background task in the session header without a refresh', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-background-task-running'))
+    // Point assertion, not a poll: `expect.poll` retries until a predicate
+    // holds, so polling for zero passes at t=0 and proves nothing. The
+    // "renders nothing without a task" branch is owned by the component suite.
+    const trigger = page.getByRole('button', { name: '1 background task running' })
+    expect(await trigger.count()).toBe(0)
+
+    const started = await scaffold.ctx.tools.execute({
+      signal: new AbortController().signal,
+      callId: CallId('background-task-list-e2e'),
+      name: 'bash',
+      arguments: { command: COMMAND, description: 'Hold a background slot open', run_in_background: true },
+      agent,
+    })
+    const reported = started.content.map(block => block.type === 'text' ? block.text : '').join('')
+    const matched = /\bbash-\d+\b/.exec(reported)
+    if (matched === null) throw new Error(`background bash reported no task id: ${reported}`)
+    taskId = TaskId(matched[0])
+
+    await trigger.waitFor({ timeout: 15_000 })
+    await trigger.click()
+    const row = page.getByRole('list', { name: 'Background tasks' }).getByRole('listitem').first()
+    await row.waitFor({ timeout: 10_000 })
+    await expect.poll(() => row.textContent()).toContain(COMMAND)
+
+    const snapshot = await captureStableAria(page, '[class*="menu"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(RUNNING_EXPECTED, snapshot, MODE)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  }, 60_000)
+
+  it('flips the open list to the cancelled outcome when the registry settles it', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-background-task-settled'))
+    expect(scaffold.ctx.tasks.kill(taskId, agent, 'web e2e cancellation')).toBe('requested')
+
+    // The trigger drops its live count once the task leaves running/stopping,
+    // which is also the proof that settlement reached the browser unprompted.
+    const idle = page.getByRole('button', { name: '1 background task' })
+    await idle.waitFor({ timeout: 20_000 })
+
+    const snapshot = await captureStableAria(page, '[class*="menu"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(SETTLED_EXPECTED, snapshot, MODE)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  }, 60_000)
+
+  it('keeps its snapshot inventory closed', async () => {
+    await assertFixtureInventory(SNAPSHOT_DIR, ['running.expected.md', 'settled.expected.md'])
+  })
+})

apps/web/tests/snapshots/background-task-list/running.expected.md

@@ -0,0 +1,2 @@
+- list "Background tasks":
+  - listitem: bash sleep 45 running {{duration}}

apps/web/tests/snapshots/background-task-list/settled.expected.md

@@ -0,0 +1,2 @@
+- list "Background tasks":
+  - listitem: "bash sleep 45 signal: SIGTERM {{duration}}"

apps/web/tests/support.ts

@@ -57,9 +57,9 @@ export function probeFreePort(): Promise<number> {
 /**
  * Drive the hero's workspace picker through the composed directory dialog
  * until the live composer unlocks. A fresh world has no Workspace, so the boot
- * lands in the locked view state (startup auto-selection has nothing to
+ * lands in the Workspace-trigger view state (startup auto-selection has nothing to
  * select); every scenario that types into the composer must connect one
- * first. With nothing to list, the chip gesture raises the dialog directly —
+ * first. With nothing to list, activating the textarea raises the dialog directly —
  * adding a workspace is the picker's only entry. The directory is staged here
  * and adopted through the path editor, which is idempotent across the repeated
  * connects a scenario may make; creating a folder from inside the dialog (the
@@ -73,7 +73,7 @@ export function probeFreePort(): Promise<number> {
  */
 export async function connectFreshWorkspace(page: Page, root: string, name = 'workspace'): Promise<void> {
   mkdirSync(join(root, name), { recursive: true })
-  await page.getByRole('button', { name: 'Choose workspace' }).click()
+  await page.getByRole('textbox', { name: 'Choose workspace' }).click()
   const dialog = page.getByRole('dialog', { name: 'Select Workspace Directory' })
   await dialog.waitFor({ timeout: 10_000 })
   await dialog.getByRole('button', { name: 'Edit path' }).click()
@@ -97,7 +97,7 @@ export async function connectFreshWorkspace(page: Page, root: string, name = 'wo
  */
 export async function connectFreshWorkspaceZh(page: Page, root: string, name = 'workspace'): Promise<void> {
   mkdirSync(join(root, name), { recursive: true })
-  await page.getByRole('button', { name: '选择工作区' }).click()
+  await page.getByRole('textbox', { name: '选择工作区' }).click()
   const dialog = page.getByRole('dialog', { name: '选择工作区目录' })
   await dialog.waitFor({ timeout: 10_000 })
   await dialog.getByRole('button', { name: '编辑路径' }).click()