Merge origin/master into codex/todo-goal-queue-layout

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

@@ -72,6 +72,7 @@ describe('core Web profile', () => {
         "tools": [
           "bash",
           "str_replace_editor",
+          "list_agents",
         ],
       }
     `)

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

@@ -0,0 +1,132 @@
+/** Published dsh web --dev + pnpm dev:web → browser HMR, with no page reload. */
+
+import { existsSync } from 'node:fs'
+import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { chromium } from 'playwright'
+import { expect, it } from 'vitest'
+import { Context } from 'cordis'
+import type { Fiber } from 'cordis'
+import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
+import type { SubprocessHandle, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess'
+import { REPO_ROOT } from './support.ts'
+
+function spawnSpec(argv: readonly string[], cwd: string, env?: Record<string, string>): SubprocessSpawnSpec {
+  return {
+    argv,
+    cwd,
+    stdio: { stdin: 'ignore', stdout: 'pipe', stderr: 'pipe' },
+    graceMs: 5_000,
+    ...env === undefined ? {} : { env },
+  }
+}
+
+function waitForOutput(child: SubprocessHandle, pattern: RegExp, label: string): Promise<string> {
+  return new Promise((resolveReady, reject) => {
+    let output = ''
+    let settled = false
+    const cleanup = (): void => {
+      clearTimeout(timer)
+      child.stdout?.off('data', onData)
+      child.stderr?.off('data', onData)
+    }
+    const resolveOnce = (value: string): void => {
+      if (settled) return
+      settled = true
+      cleanup()
+      resolveReady(value)
+    }
+    const rejectOnce = (error: Error): void => {
+      if (settled) return
+      settled = true
+      cleanup()
+      reject(error)
+    }
+    const onData = (chunk: Buffer): void => {
+      output += chunk.toString()
+      const match = pattern.exec(output)
+      if (match === null) return
+      resolveOnce(match[1] ?? match[0])
+    }
+    const timer = setTimeout(() => { rejectOnce(new Error(`${label} not ready:\n${output}`)) }, 60_000)
+    child.stdout?.on('data', onData)
+    child.stderr?.on('data', onData)
+    void child.done.then((outcome) => {
+      rejectOnce(new Error(`${label} exited before ready (${JSON.stringify(outcome)}):\n${output}`))
+    }, (error: unknown) => {
+      rejectOnce(new Error(`${label} failed before ready:\n${output}`, { cause: error }))
+    })
+  })
+}
+
+async function stopTree(child: SubprocessHandle): Promise<void> {
+  child.terminate()
+  const stopped = await child.waitForExit(AbortSignal.timeout(15_000))
+  if (!stopped) throw new Error(`process tree ${String(child.pid)} did not stop after termination escalation`)
+  await child.done
+}
+
+it('hot-reloads a real client-plugin source edit without refreshing the page', async () => {
+  const world = await mkdtemp(join(tmpdir(), 'dsh-web-hmr-world-'))
+  const sourcePath = join(REPO_ROOT, 'packages/client/ui-conversation/src/client/locales.ts')
+  const bundlePath = join(REPO_ROOT, 'packages/client/ui-conversation/lib/client.js')
+  const binPath = join(REPO_ROOT, 'apps/cli/lib/bin.js')
+  if (!existsSync(binPath)) throw new Error('HMR browser test needs the built dsh bin; run pnpm run build first')
+  const originalSource = await readFile(sourcePath)
+  const originalBundle = await readFile(bundlePath)
+  const oldText = "Let's start building"
+  const sourceNeedle = "'hero.headline': 'Let\\'s start building'"
+  const newText = `HMR UPDATED ${'x'.repeat(80)}`
+  const updatedSource = originalSource.toString().replace(sourceNeedle, `'hero.headline': '${newText}'`)
+  if (updatedSource === originalSource.toString()) throw new Error(`HMR source lacks ${JSON.stringify(sourceNeedle)}`)
+
+  const subprocessCtx = new Context()
+  let subprocessFiber: Fiber | undefined
+  let watcher: SubprocessHandle | undefined
+  let host: SubprocessHandle | undefined
+  let browser: Awaited<ReturnType<typeof chromium.launch>> | undefined
+  const failures: unknown[] = []
+  try {
+    subprocessFiber = await subprocessCtx.plugin(LocalSubprocessService)
+    watcher = subprocessCtx.subprocess.spawn(spawnSpec(['pnpm', 'run', 'dev:web'], REPO_ROOT))
+    await waitForOutput(watcher, /dev-web: watching/, 'pnpm run dev:web')
+    host = subprocessCtx.subprocess.spawn(spawnSpec(
+      [process.execPath, binPath, 'web', '--dev', '--port', '0'],
+      world,
+      {
+        DEEPSEEK_API_KEY: 'keyless-hmr-no-call',
+        DSH_HOME: join(world, '.dsh'),
+      },
+    ))
+    const baseUrl = await waitForOutput(host, /dsh web: (http:\/\/[^\s]+)/, 'built dsh web --dev')
+    browser = await chromium.launch()
+    const page = await browser.newPage()
+    const pageErrors: string[] = []
+    page.on('pageerror', error => pageErrors.push(String(error)))
+    await page.goto(baseUrl, { waitUntil: 'load' })
+    await page.getByText(oldText, { exact: true }).waitFor({ timeout: 15_000 })
+    const pageIdentity = await page.evaluate(() => {
+      const identity = crypto.randomUUID()
+      Object.defineProperty(window, '__dshHmrPageIdentity', { value: identity })
+      return identity
+    })
+
+    await writeFile(sourcePath, updatedSource)
+    await page.getByText(newText, { exact: true }).waitFor({ timeout: 30_000 })
+    expect(await page.evaluate(() => (window as Window & { __dshHmrPageIdentity?: string }).__dshHmrPageIdentity))
+      .toBe(pageIdentity)
+    expect(pageErrors).toEqual([])
+  } catch (error) {
+    failures.push(error)
+  } finally {
+    await writeFile(sourcePath, originalSource).catch((error: unknown) => failures.push(error))
+    if (watcher !== undefined) await stopTree(watcher).catch((error: unknown) => failures.push(error))
+    await writeFile(bundlePath, originalBundle).catch((error: unknown) => failures.push(error))
+    if (host !== undefined) await stopTree(host).catch((error: unknown) => failures.push(error))
+    await browser?.close().catch((error: unknown) => failures.push(error))
+    await subprocessFiber?.dispose().catch((error: unknown) => failures.push(error))
+    await rm(world, { recursive: true, force: true }).catch((error: unknown) => failures.push(error))
+  }
+  if (failures.length > 0) throw new AggregateError(failures, 'HMR browser test or cleanup failed')
+}, 120_000)

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

@@ -67,6 +67,10 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
     })
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    // The frame mounts before the asynchronous session-list baseline lands.
+    // Search must target the settled seeded row, not the startup input that
+    // the ready projection replaces.
+    await page.getByText('1 session', { exact: true }).waitFor({ timeout: 30_000 })
   }, 120_000)
 
   afterAll(async () => {

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

@@ -9,20 +9,23 @@
 // Record: DSH_SNAPSHOT=record rewrites session.jsonl, then a keyless
 // DSH_SNAPSHOT=refresh regenerates ui.expected.md.
 import { readFile } from 'node:fs/promises'
+import { join } from 'node:path'
 import { fileURLToPath } from 'node:url'
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
-import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
 import {
   assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
   launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+import { connectFreshWorkspace, newEnglishPage, REPO_ROOT, saveFailureShot } from './support.ts'
 
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/fresh-round-trip', import.meta.url))
 const FIXTURE = fileURLToPath(new URL('./snapshots/fresh-round-trip/session.jsonl', import.meta.url))
 const UI_EXPECTED = fileURLToPath(new URL('./snapshots/fresh-round-trip/ui.expected.md', import.meta.url))
+const SYSTEM_PROMPT_EXPECTED = fileURLToPath(new URL('./snapshots/fresh-round-trip/system-prompt.expected.md', import.meta.url))
 const MODE = webSnapshotMode()
 
 // The scenario's one drive prompt. Record sends it; replay asserts the
@@ -35,6 +38,7 @@ describe('web e2e: fresh round trip through the real assembly', () => {
   let browser: Browser
   let page: Page
   let tripwire: ReturnType<typeof watchConsole>
+  let settledSessionId: SessionId | undefined
   const sessionEvents: SessionEvent[] = []
 
   beforeAll(async () => {
@@ -69,11 +73,44 @@ describe('web e2e: fresh round trip through the real assembly', () => {
     await input.fill(PROMPT)
     await input.press('Enter')
     const sessionId = await settled
+    settledSessionId = sessionId
     if (MODE === 'record') {
       await recordFixture(scaffold, sessionId, FIXTURE)
     }
   }, 200_000)
 
+  it('records the Web surface, source checkout, and session cwd in the request header', async () => {
+    if (settledSessionId === undefined) throw new Error('the drive turn did not publish a session id')
+    const agent = scaffold.ctx.agents.get(settledSessionId)
+    if (agent === undefined) throw new Error(`the settled Web agent ${settledSessionId} is no longer live`)
+    const system = agent.session.requestHeader()?.system
+    if (system === undefined) throw new Error('the settled Web request has no system prompt')
+    const prefix = system.split('\n\n').slice(0, 4).join('\n\n')
+      .split(REPO_ROOT).join('{{sourceRoot}}')
+      .split(join(scaffold.workspaceCwd, 'workspace')).join('{{cwd}}')
+      .split(scaffold.baseUrl).join('{{webUrl}}')
+    await compareOrRefreshGolden(SYSTEM_PROMPT_EXPECTED, prefix, MODE)
+  })
+
+  it('exposes the assembled Web URL to the real bash tool', async () => {
+    if (settledSessionId === undefined) throw new Error('the drive turn did not publish a session id')
+    const agent = scaffold.ctx.agents.get(settledSessionId)
+    if (agent === undefined) throw new Error(`the settled Web agent ${settledSessionId} is no longer live`)
+    const result = await scaffold.ctx.tools.execute({
+      signal: AbortSignal.timeout(5_000),
+      callId: CallId('web-url-probe'),
+      name: 'bash',
+      arguments: {
+        command: 'printf \'%s\\n%s\\n\' "$DSH_WEB_URL" "$DSH_WEB_MODE"',
+        description: 'Print current Web runtime',
+      },
+      agent,
+    })
+    expect(result.isError).toBe(false)
+    expect(result.content.filter(block => block.type === 'text').map(block => block.text).join(''))
+      .toBe(`${scaffold.baseUrl}\nproduction\n`)
+  })
+
   it.skipIf(MODE === 'record')('rendered the settled turn: markdown, tool row, composer restore', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-round-trip-settled'))
     // Browser settled-poll after host completion (host strictly precedes render).
@@ -129,6 +166,6 @@ describe('web e2e: fresh round trip through the real assembly', () => {
   it.skipIf(MODE === 'record')('stayed clean: no pageerrors, no reconnect self-healing, no server errors', async () => {
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
-    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'ui.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'system-prompt.expected.md', 'ui.expected.md'])
   })
 })

apps/web/tests/scaffold.ts

@@ -53,6 +53,7 @@ import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis'
 // Empty type imports carry the httpServer/agents/sessionPersistence Context merges.
 import type {} from '@deepseek-ai/dsh-host-webserver'
 import type {} from '@deepseek-ai/dsh-agent'
+import { prepareWebRuntimeContext } from '../../cli/src/web.ts'
 import { DIST_INDEX, REPO_ROOT, requireDist } from './support.ts'
 
 /** Snapshot mode for the lane, from $DSH_SNAPSHOT (same vocabulary as the ACP/TUI suites). */
@@ -120,6 +121,11 @@ export interface LaunchOptions {
    * mounts).
    */
   replayFixture?: string
+  /**
+   * Recorded child logs assigned in child creation order. Each child owns its
+   * own positional replay cursor across initial and continuation turns.
+   */
+  replayChildFixtures?: string[]
   /**
    * Optional replay.override.json sidecar (whole-script replacement or
    * `{ patches }` augmentation) for throw/hang scenarios not expressible as
@@ -300,6 +306,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
     // The shipped CLI deliberately has no dependency on this opt-in package.
     // Keep the Loader row real without broadening the product installation.
     if (options.cordisTools === true) ctx.loader.builtins['tool-cordis'] = ToolCordis
+    prepareWebRuntimeContext(ctx, REPO_ROOT, 'production')
     await ctx.loader.create({
       name: 'cordis:include',
       config: { path: pathToFileURL(resolve(CONFIG_PATH)).href, patches },
@@ -326,6 +333,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
         file: options.replayFixture,
         providers: REPLAY_PROVIDERS,
         ...(options.replayOverride === undefined ? {} : { overrideFile: options.replayOverride }),
+        ...(options.replayChildFixtures === undefined ? {} : { childFiles: options.replayChildFixtures }),
         ...(options.paceMs === undefined ? {} : { paceMs: options.paceMs }),
       })
     }

apps/web/tests/shipped-composition.e2e.ts

@@ -28,13 +28,10 @@ const EXPECTED_TOOLS = [
   'edit',
   'exit_plan_mode',
   'get_goal',
+  'list_agents',
   'ralph',
   'read',
-  'session_event_read',
-  'session_event_search',
-  'session_event_trace',
-  'session_search',
-  'session_trace',
+  'send_message',
   'skill',
   'str_replace_editor',
   'subagent',

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

@@ -26,6 +26,8 @@ import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
 import { REPO_ROOT, connectFreshWorkspace, newEnglishPage, probeFreePort, requireDist, saveFailureShot } from './support.ts'
 
+const DEVELOPMENT_PROMPT = fileURLToPath(new URL('./snapshots/web-runtime-context/development-prompt.expected.md', import.meta.url))
+
 function waitForReadyLine(child: ChildProcess): Promise<string> {
   return new Promise((resolveReady, reject) => {
     let out = ''
@@ -184,7 +186,7 @@ describe('dsh web keyless CLI smoke', () => {
     }
   })
 
-  it('injects the invoking workspace AGENTS.md into the provider request', async () => {
+  it('routes --dev runtime context and workspace instructions through the real CLI request', async () => {
     requireDist()
     const workspace = mkdtempSync(join(tmpdir(), 'dsh-web-workspace-'))
     mkdirSync(join(workspace, '.git'))
@@ -220,7 +222,7 @@ describe('dsh web keyless CLI smoke', () => {
     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'],
+      ['--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', '0', '--dev'],
       {
         cwd: workspace,
         env: {
@@ -252,6 +254,10 @@ describe('dsh web keyless CLI smoke', () => {
         message.role === 'user' && message.content?.includes('<available_skills>'))).toBe(false)
       const workspaceMessage = captured.messages?.find(message =>
         message.role === 'user' && message.content?.includes('web-workspace-context-probe'))
+      const systemMessage = captured.messages?.find(message => message.role === 'system')
+      const expectedWebSection = readFileSync(DEVELOPMENT_PROMPT, 'utf8').trimEnd()
+        .replace('{{webUrl}}', baseUrl)
+      expect(systemMessage?.content).toContain(expectedWebSection)
       expect(workspaceMessage).toMatchInlineSnapshot(`
         {
           "content": "<system-reminder>

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

@@ -1,5 +1,6 @@
 - banner:
-  - 'heading "Using ONE run_code program: run" [level=1]'
+  - navigation "Session hierarchy":
+    - 'button "Using ONE run_code program: run" [disabled]'
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use only Cordis tools. First" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use only Cordis tools. First" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -0,0 +1,7 @@
+You are an AI agent powered by the DeepSeek Harness SDK.
+
+The DeepSeek Harness implementation checkout is at {{sourceRoot}}. The checkout location and current working directory are separate values and may differ; never infer the working directory from this path. Use pwd to determine the current working directory. Use this checkout only to inspect or extend DSH itself.
+
+You are interacting with the user through the DeepSeek Harness Web GUI at {{webUrl}}. When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. The browser provides no implicit DOM, route, or screenshot context. This Web process was launched without `--dev`, so HMR is inactive: rebuild the affected Web artifacts and verify this existing URL after a page refresh. If the user wants no-refresh client-plugin updates, explain that this GUI must be restarted with `dsh web --dev` and `pnpm run dev:web` must also run from this same checkout; do not present either command alone as sufficient. Starting another server does not update this GUI. The apps/web Vite entry builds the shell but is not a standalone application because only dsh web injects window.__DSH_BOOT__. Do not start a replacement server unless the user asks; if one is needed, use a managed background task and verify its exact URL.
+
+You are a coding agent powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use the bash tool to" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use the bash tool to" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with the single word" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with the single word" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with a one-sentence description" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with a one-sentence description" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with a one-sentence description" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with a one-sentence description" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use the read tool twice" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use the read tool twice" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - 'heading "Plan a small change: add" [level=1]'
+  - navigation "Session hierarchy":
+    - 'button "Plan a small change: add" [disabled]'
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use the ask_user_question tool to" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use the ask_user_question tool to" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with a one-sentence description" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with a one-sentence description" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "workspace" [level=1]
+  - navigation "Session hierarchy":
+    - button "workspace" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with a one-sentence description" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Reply with a one-sentence description" [level=1]
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use the read tool twice" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use the read tool twice" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use the read tool twice" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use the read tool twice" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use the ask_user_question tool to" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use the ask_user_question tool to" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use the ask_user_question tool to" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use the ask_user_question tool to" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

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

@@ -0,0 +1,6 @@
+- tree "Sessions":
+  - treeitem "workspace 2 sessions" [expanded]:
+    - img
+    - text: workspace 2 sessions
+  - treeitem "Explain event sourcing in one (1) now" [selected]
+  - treeitem "Ask a research subagent to now"

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

@@ -0,0 +1,18 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Ask a research subagent to"
+    - text: /
+    - button "event-sourcing researcher"
+    - text: /
+    - button "example editor" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Give one concrete event sourcing example. {{clock}}
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- status:
+  - strong: 此子代理暂时只读
+  - text: 父会话当前不在线，重新打开父会话后即可继续发送消息。

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

@@ -0,0 +1,5 @@
+- tree "Sessions":
+  - treeitem "workspace 1 session" [expanded]:
+    - img
+    - text: workspace 1 session
+  - treeitem "Ask a research subagent to now"

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

@@ -0,0 +1,8 @@
+- tree "子代理会话":
+  - treeitem "event-sourcing researcher Explain event sourcing in one · 可继续 · 当前未运行 刚刚" [expanded] [level=1]:
+    - button "收起 event-sourcing researcher 的下级子代理":
+      - img
+    - text: event-sourcing researcher Explain event sourcing in one · 可继续 · 当前未运行 刚刚
+  - group:
+    - treeitem "example editor 可继续 · 当前未运行 刚刚" [level=2]
+  - treeitem "event-sourcing reviewer 一次性 · 当前未运行 刚刚" [level=1]

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

@@ -0,0 +1,50 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Ask a research subagent to"
+    - text: /
+    - button "event-sourcing researcher" [disabled]
+  - button "1 个子代理":
+    - text: 1 个子代理
+    - img
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Explain event sourcing in one sentence. {{clock}}
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- button "Context injection":
+  - img
+  - img
+  - text: Context injection
+- 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
+  - text: 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.
+- 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 "Branch into a new conversation":
+  - img
+- text: {{clock}} Now give the same explanation to a human reader. {{clock}}
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- 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
+  - text: 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.
+- 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 "Branch into a new conversation":
+  - img
+- text: {{clock}}
+- textbox "Message the agent"
+- button "Commands":
+  - img
+- 'button "Access mode, current: Workspace Write"': Workspace Write
+- button "Send message" [disabled]
+- text: 2 turns · 2 steps Context 6% of 128K Cache hit 99% Input 15.6K tok · Output 158 tok

apps/web/tests/snapshots/web-runtime-context/development-prompt.expected.md

@@ -0,0 +1 @@
+You are interacting with the user through the DeepSeek Harness Web GUI at {{webUrl}}. When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. The browser provides no implicit DOM, route, or screenshot context. This Web process was launched with `dsh web --dev`, so its client-plugin HMR receiver is active. No-refresh updates occur only when `pnpm run dev:web` is also running from this same checkout to rebuild client-plugin bundles; verify that watcher before promising automatic updates. Client-plugin changes then reload automatically, while apps/web shell and other plain-package changes still require a rebuild and page refresh. Starting another server does not update this GUI. The apps/web Vite entry builds the shell but is not a standalone application because only dsh web injects window.__DSH_BOOT__. Do not start a replacement server unless the user asks; if one is needed, use a managed background task and verify its exact URL.

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

@@ -1,5 +1,6 @@
 - banner:
-  - heading "Use web_search to search exactly" [level=1]
+  - navigation "Session hierarchy":
+    - button "Use web_search to search exactly" [disabled]
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/subagent-conversation.e2e.ts

@@ -0,0 +1,432 @@
+import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+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 {
+  SESSION_FORMAT_VERSION, SessionId as sessionId, type SessionEvent, type SessionId,
+} from '@deepseek-ai/dsh-session'
+import type {} from '@deepseek-ai/dsh-agent'
+import { snapshotSubagentDescriptor } from '@deepseek-ai/dsh-subagent'
+import {
+  acknowledgeReloadConnectionLoss, captureStableAria, compareOrRefreshGolden,
+  launchWebScaffold, watchConsole,
+  webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, saveFailureShot } from './support.ts'
+
+const BASE_FIXTURE = fileURLToPath(new URL('./snapshots/live-interactions/session.jsonl', import.meta.url))
+const AVAILABLE_CHILD_EXPECTED = fileURLToPath(new URL('./snapshots/subagent-conversation/ui.expected.md', import.meta.url))
+const TREE_EXPECTED = fileURLToPath(new URL('./snapshots/subagent-conversation/tree.expected.md', import.meta.url))
+const SIDEBAR_EXPECTED = fileURLToPath(new URL('./snapshots/subagent-conversation/sidebar.expected.md', import.meta.url))
+const UNAVAILABLE_GRANDCHILD_EXPECTED = fileURLToPath(new URL('./snapshots/subagent-conversation/nested.expected.md', import.meta.url))
+const FORK_EXPECTED = fileURLToPath(new URL('./snapshots/subagent-conversation/fork.expected.md', import.meta.url))
+const MODE = webSnapshotMode()
+const LABEL = 'event-sourcing researcher'
+const ONE_SHOT_LABEL = 'event-sourcing reviewer'
+const NESTED_LABEL = 'example editor'
+const PARENT_PROMPT = 'Ask a research subagent to explain event sourcing.'
+const INITIAL_PROMPT = 'Explain event sourcing in one sentence.'
+const FOLLOWUP = 'Now give the same explanation to a human reader.'
+const POST_FORK_FOLLOWUP = 'Continue the original conversation after the fork.'
+
+function childFixture(source: string, fixtureId: string, withContinuation: boolean): string {
+  const [header, ...eventLines] = source.trimEnd().split('\n')
+  if (header === undefined) throw new Error('base replay fixture has no header')
+  const childHeader = header
+    .replace('"id":"{{sessionId}}"', `"id":"${fixtureId}"`)
+    .replace(/"createdAt":\d+/, '"createdAt":1784998084442')
+  if (!withContinuation) return [childHeader, ...eventLines, ''].join('\n')
+  const continued = eventLines.map(line => line
+    .replace(/"seq":(\d+)/g, (_match, seq: string) => `"seq":${String(Number(seq) + 100)}`)
+    .replace(/"seq0":(\d+)/g, (_match, seq: string) => `"seq0":${String(Number(seq) + 100)}`)
+    .replaceAll('"turn":1', '"turn":2'))
+  return [childHeader, ...eventLines, ...continued, ''].join('\n')
+}
+
+async function waitForAgentToSettle(scaffold: WebScaffold, id: SessionId): Promise<void> {
+  const deadline = Date.now() + 30_000
+  while (scaffold.ctx.agents.get(id) !== undefined) {
+    if (Date.now() >= deadline) throw new Error(`subagent ${id} did not settle`)
+    await new Promise<void>(resolve => setTimeout(resolve, 10))
+  }
+}
+
+describe('web e2e: persisted subagent conversation and human continuation', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let sidecarRoot: string
+  let childId: SessionId
+  let oneShotId: SessionId
+  let grandchildId: SessionId
+  let tripwire: ReturnType<typeof watchConsole>
+  const apiCalls: string[] = []
+
+  beforeAll(async () => {
+    if (MODE === 'record') throw new Error('subagent conversation is a keyless assembled snapshot')
+    const baseFixture = await readFile(BASE_FIXTURE, 'utf8')
+    sidecarRoot = await mkdtemp(join(tmpdir(), 'dsh-web-subagent-'))
+    const childFixturePath = join(sidecarRoot, 'child.jsonl')
+    await writeFile(childFixturePath, childFixture(baseFixture, 'recorded-subagent', true))
+    scaffold = await launchWebScaffold({
+      replayFixture: BASE_FIXTURE,
+      replayChildFixtures: [childFixturePath],
+      paceMs: 25,
+    })
+    browser = await chromium.launch()
+    page = await browser.newPage({ viewport: { width: 1680, height: 1000 } })
+    page.on('request', (request) => {
+      const path = new URL(request.url()).pathname
+      if (path.startsWith('/api/')) apiCalls.push(path)
+    })
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
+
+    const parent = scaffold.ctx.agents.roots()[0]
+    if (parent === undefined) throw new Error('fresh workspace did not publish its parent Agent')
+    const parentSettled = scaffold.whenTurnSettled()
+    const parentInput = page.locator('textarea:enabled').first()
+    await parentInput.fill(PARENT_PROMPT)
+    await parentInput.press('Enter')
+    expect(await parentSettled).toBe(parent.id)
+
+    const started = await scaffold.ctx.subagents.startContinuable({
+      provider: 'spawn',
+      label: LABEL,
+      signal: new AbortController().signal,
+      request: {
+        prompt: [{ type: 'text', text: INITIAL_PROMPT }],
+        parent,
+      },
+    })
+    childId = started.childId
+    await waitForAgentToSettle(scaffold, childId)
+    oneShotId = sessionId('recorded-one-shot')
+    const oneShotAt = Date.now()
+    await scaffold.ctx.sessionPersistence.create({
+      version: SESSION_FORMAT_VERSION,
+      id: oneShotId,
+      createdAt: oneShotAt,
+      cwd: scaffold.workspaceCwd,
+      parentSession: parent.id,
+      origin: 'subagent',
+      delegationDepth: 1,
+    })
+    await scaffold.ctx.sessionPersistence.append(oneShotId, [
+      {
+        type: 'turn/start',
+        seq: 0,
+        time: oneShotAt,
+        data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } },
+      },
+      {
+        type: 'user/message',
+        seq: 1,
+        time: oneShotAt + 1,
+        data: {
+          content: [{ type: 'text', text: 'Review the event sourcing explanation.' }],
+          source: { kind: 'user' },
+        },
+        surfaceOp: 'append',
+      },
+      {
+        type: 'subagent/descriptor',
+        seq: 2,
+        time: oneShotAt + 2,
+        data: snapshotSubagentDescriptor({
+          mode: 'one-shot', provider: 'spawn', label: ONE_SHOT_LABEL,
+        }),
+      },
+      {
+        type: 'turn/end',
+        seq: 3,
+        time: oneShotAt + 3,
+        data: { turn: 1, reason: { kind: 'completed' } },
+      },
+    ] as SessionEvent[])
+    grandchildId = sessionId('recorded-grandchild')
+    const authoredAt = Date.now()
+    await scaffold.ctx.sessionPersistence.create({
+      version: SESSION_FORMAT_VERSION,
+      id: grandchildId,
+      createdAt: authoredAt,
+      cwd: scaffold.workspaceCwd,
+      parentSession: childId,
+      origin: 'subagent',
+      delegationDepth: 2,
+    })
+    await scaffold.ctx.sessionPersistence.append(grandchildId, [
+      {
+        type: 'turn/start',
+        seq: 0,
+        time: authoredAt,
+        data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } },
+      },
+      {
+        type: 'user/message',
+        seq: 1,
+        time: authoredAt + 1,
+        data: {
+          content: [{ type: 'text', text: 'Give one concrete event sourcing example.' }],
+          source: { kind: 'user' },
+        },
+        surfaceOp: 'append',
+      },
+      {
+        type: 'subagent/descriptor',
+        seq: 2,
+        time: authoredAt + 2,
+        data: snapshotSubagentDescriptor({
+          mode: 'continuable', provider: 'spawn', label: NESTED_LABEL,
+        }),
+      },
+      {
+        type: 'turn/end',
+        seq: 3,
+        time: authoredAt + 3,
+        data: { turn: 1, reason: { kind: 'completed' } },
+      },
+    ] as SessionEvent[])
+    expect(scaffold.ctx.agents.get(childId)).toBeUndefined()
+    expect(scaffold.ctx.agents.get(oneShotId)).toBeUndefined()
+    expect(scaffold.ctx.agents.get(grandchildId)).toBeUndefined()
+    await expect(scaffold.ctx.subagents.listChildren(parent.id)).resolves.toMatchObject([
+      {
+        kind: 'child', id: childId, mode: 'continuable', label: LABEL,
+        activity: 'inactive', hasChildren: true,
+      },
+      {
+        kind: 'child', id: oneShotId, mode: 'one-shot',
+        label: ONE_SHOT_LABEL, activity: 'inactive', hasChildren: false,
+      },
+    ])
+    await expect(scaffold.ctx.subagents.listChildren(childId)).resolves.toMatchObject([
+      {
+        kind: 'child', id: grandchildId, mode: 'continuable',
+        label: NESTED_LABEL, activity: 'inactive', hasChildren: false,
+      },
+    ])
+    // These two cold fixtures were authored after the page's initial
+    // session.list and intentionally emitted no session-added frame. Reload
+    // to exercise the restart baseline that discovers their full lineage.
+    const warningStart = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    const catalogButton = page.getByRole('button', { name: /个子代理/ })
+    await catalogButton.waitFor({ timeout: 15_000 })
+    await catalogButton.click()
+    const catalogTree = page.getByRole('tree', { name: '子代理会话' })
+    await catalogTree.getByRole('treeitem').nth(1).waitFor({ timeout: 15_000 })
+    await catalogTree.press('Escape')
+    await page.getByRole('button', { name: '3 个子代理' }).waitFor({ timeout: 15_000 })
+    acknowledgeReloadConnectionLoss(tripwire, warningStart)
+  }, 120_000)
+
+  afterAll(async () => {
+    const failures: unknown[] = []
+    await browser?.close().catch((error: unknown) => failures.push(error))
+    await scaffold?.close().catch((error: unknown) => failures.push(error))
+    if (sidecarRoot !== undefined) {
+      await rm(sidecarRoot, { recursive: true, force: true })
+        .catch((error: unknown) => failures.push(error))
+    }
+    if (failures.length === 1) throw failures[0]
+    if (failures.length > 1) throw new AggregateError(failures, 'subagent Web teardown failed')
+  })
+
+  it('expands a persisted grandchild progressively without activating either level', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-subagent-tree'))
+    await page.getByRole('button', { name: '3 个子代理' }).click()
+    expect(await page.getByRole('button', {
+      name: `展开 ${ONE_SHOT_LABEL} 的下级子代理`,
+    }).count()).toBe(0)
+    await page.getByRole('button', { name: `展开 ${LABEL} 的下级子代理` }).click()
+    await page.getByRole('treeitem', { name: new RegExp(NESTED_LABEL) }).waitFor({ timeout: 15_000 })
+    expect(scaffold.ctx.agents.get(childId)).toBeUndefined()
+    expect(scaffold.ctx.agents.get(grandchildId)).toBeUndefined()
+    const snapshot = await captureStableAria(
+      page,
+      '[role="tree"][aria-label="子代理会话"]',
+      scaffold.workspaceCwd,
+    )
+    await compareOrRefreshGolden(TREE_EXPECTED, snapshot, MODE)
+    await page.getByRole('tree', { name: '子代理会话' }).press('Escape')
+  })
+
+  it('opens the completed child from persistence without activating it', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-subagent-open'))
+    await page.getByRole('button', { name: '3 个子代理' }).click()
+    await page.getByRole('treeitem', { name: new RegExp(LABEL) }).click()
+    await expect.poll(
+      () => page.getByText(INITIAL_PROMPT, { exact: true }).count(),
+      { timeout: 15_000 },
+    ).toBe(1)
+    if (scaffold.ctx.agents.get(childId) !== undefined) {
+      throw new Error(`viewing the child activated it; API calls: ${apiCalls.join(', ')}`)
+    }
+    const hierarchy = page.getByRole('navigation', { name: 'Session hierarchy' })
+    await hierarchy.getByRole('button', { name: LABEL, disabled: true }).waitFor()
+    const sidebar = await captureStableAria(
+      page,
+      '[role="tree"][aria-label="Sessions"]',
+      scaffold.workspaceCwd,
+    )
+    await compareOrRefreshGolden(SIDEBAR_EXPECTED, sidebar, MODE)
+  })
+
+  it('continues through FIFO follow-up admission and receives the child mux events', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-subagent-followup'))
+    const ended = new Promise<void>((resolveEnded, reject) => {
+      const timer = setTimeout(() => {
+        off()
+        reject(new Error('subagent follow-up did not reach turn/end'))
+      }, 30_000)
+      const off = scaffold.ctx.on('session/event', (session: { id: SessionId }, event: SessionEvent) => {
+        if (session.id !== childId || event.type !== 'turn/end') return
+        clearTimeout(timer)
+        off()
+        resolveEnded()
+      })
+    })
+    const input = page.getByRole('textbox', { name: 'Message the agent' })
+    await input.fill(FOLLOWUP)
+    await input.press('Enter')
+    await expect.poll(
+      () => scaffold.ctx.agents.get(childId)?.status,
+      { timeout: 10_000 },
+    ).toBe('running')
+    const hierarchy = page.getByRole('navigation', { name: 'Session hierarchy' })
+    await hierarchy.getByRole('button').first().click()
+    const runningTrigger = page.getByRole('button', { name: '3 个子代理，正在运行' })
+    await runningTrigger.waitFor({ timeout: 10_000 })
+    expect(await runningTrigger.locator('[data-state="ongoing"]').count()).toBe(1)
+    await runningTrigger.click()
+    await page.getByRole('treeitem', {
+      name: new RegExp(`${LABEL}.*正在运行`),
+    }).waitFor({ timeout: 10_000 })
+    await ended
+    await page.getByRole('treeitem', {
+      name: new RegExp(`${LABEL}.*当前未运行`),
+    }).waitFor({ timeout: 10_000 })
+    expect(await page.getByRole('button', { name: '3 个子代理' })
+      .locator('[data-state="ongoing"]').count()).toBe(0)
+    await page.getByRole('treeitem', { name: new RegExp(LABEL) }).click()
+    await expect.poll(() => page.getByText(FOLLOWUP, { exact: true }).count(), { timeout: 10_000 }).toBe(1)
+    await expect.poll(() => scaffold.ctx.agents.get(childId), { timeout: 10_000 }).toBeUndefined()
+    expect(await page.getByRole('button', { name: 'Stop generating' }).count()).toBe(0)
+  })
+
+  it('matches the settled addressed-conversation aria golden and stays clean', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-subagent-aria'))
+    const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(AVAILABLE_CHILD_EXPECTED, snapshot, MODE)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  })
+
+  it('opens an unavailable persisted grandchild after recording the available child', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-subagent-grandchild'))
+    await page.getByRole('button', { name: '1 个子代理' }).click()
+    await page.getByRole('treeitem', { name: new RegExp(NESTED_LABEL) }).click()
+    await page.getByText('父会话当前不在线，重新打开父会话后即可继续发送消息。').waitFor()
+    const hierarchy = page.getByRole('navigation', { name: 'Session hierarchy' })
+    const crumbs = await hierarchy.getByRole('button').allTextContents()
+    expect(crumbs.slice(-2)).toEqual([LABEL, NESTED_LABEL])
+    expect(scaffold.ctx.agents.get(childId)).toBeUndefined()
+    expect(scaffold.ctx.agents.get(grandchildId)).toBeUndefined()
+    await compareOrRefreshGolden(
+      UNAVAILABLE_GRANDCHILD_EXPECTED,
+      await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd),
+      MODE,
+    )
+  })
+
+  it('opens a one-shot child as permanently read-only history', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-subagent-one-shot'))
+    const parentSession = page.getByRole('tree', { name: 'Sessions' })
+      .getByRole('treeitem')
+      .last()
+    await parentSession.click()
+    await page.getByRole('button', { name: '3 个子代理' }).click()
+    await page.getByRole('treeitem', { name: new RegExp(ONE_SHOT_LABEL) }).click()
+    await page.getByText('一次性任务不支持后续消息，可在这里查看完整执行记录。').waitFor()
+    expect(scaffold.ctx.agents.get(oneShotId)).toBeUndefined()
+  })
+
+  it('places an ordinary fork from a subagent beside its workspace-owning ancestor', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-subagent-fork'))
+    await page.getByRole('tree', { name: 'Sessions' })
+      .getByRole('treeitem', { name: /Ask a research subagent to/ })
+      .click()
+    await page.getByRole('button', { name: '3 个子代理' }).click()
+    await page.getByRole('treeitem', { name: new RegExp(LABEL) }).click()
+    await page.getByRole('textbox', { name: 'Message the agent' }).waitFor()
+    const forkResponse = page.waitForResponse(response =>
+      new URL(response.url()).pathname === '/api/session.fork')
+    await page.getByRole('button', { name: 'Branch into a new conversation' }).last().click()
+    const forkReceipt = await (await forkResponse).json() as { result: { ok: boolean } }
+    expect(forkReceipt.result).toMatchObject({ ok: true })
+    await expect.poll(
+      () => page.getByRole('tree', { name: 'Sessions' }).getByRole('treeitem').count(),
+      { timeout: 15_000 },
+    ).toBe(3)
+    expect(await page.getByText('Ungrouped', { exact: true }).count()).toBe(0)
+    const hierarchy = page.getByRole('navigation', { name: 'Session hierarchy' })
+    expect(await hierarchy.getByRole('button').count()).toBe(1)
+    await compareOrRefreshGolden(
+      FORK_EXPECTED,
+      await captureStableAria(page, '[role="tree"][aria-label="Sessions"]', scaffold.workspaceCwd),
+      MODE,
+    )
+  })
+
+  it('cold-resumes the original subagent while its ordinary fork stays active', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-subagent-post-fork-followup'))
+    const sessions = page.getByRole('tree', { name: 'Sessions' })
+    await sessions.getByRole('treeitem', { name: /Ask a research subagent to/ }).click()
+    await page.getByRole('button', { name: '3 个子代理' }).click()
+    await page.getByRole('treeitem', { name: new RegExp(LABEL) }).click()
+    await page.locator('textarea:enabled').first().waitFor()
+    expect(scaffold.ctx.agents.get(childId)).toBeUndefined()
+
+    const forkResponse = page.waitForResponse(response =>
+      new URL(response.url()).pathname === '/api/session.fork')
+    await page.getByRole('button', { name: 'Branch into a new conversation' }).last().click()
+    const forkReceipt = await (await forkResponse).json() as {
+      result: { ok: true; value: { sessionId: string } } | { ok: false }
+    }
+    expect(forkReceipt.result).toMatchObject({ ok: true })
+    if (!forkReceipt.result.ok) return
+    const forkId = sessionId(forkReceipt.result.value.sessionId)
+    await expect.poll(() => scaffold.ctx.agents.get(forkId)).not.toBeUndefined()
+
+    await sessions.getByRole('treeitem', { name: /Ask a research subagent to/ }).click()
+    await page.getByRole('button', { name: '3 个子代理' }).click()
+    await page.getByRole('treeitem', { name: new RegExp(LABEL) }).click()
+    const input = page.locator('textarea:enabled').first()
+    await input.waitFor()
+    const promptResponse = page.waitForResponse(response =>
+      new URL(response.url()).pathname === '/api/subagent.prompt')
+    await input.fill(POST_FORK_FOLLOWUP)
+    await input.press('Enter')
+    const promptReceipt = await (await promptResponse).json() as {
+      result: { ok: true } | { ok: false; error: { code: string; message: string } }
+    }
+    if (!promptReceipt.result.ok) {
+      throw new Error(`post-fork follow-up rejected: ${JSON.stringify(promptReceipt.result.error)}`)
+    }
+    await expect.poll(async () => {
+      const loaded = await scaffold.ctx.sessionPersistence.load(childId)
+      const messageIndex = loaded.events.findIndex(event => event.type === 'user/message'
+        && event.data.content.some(block => block.type === 'text' && block.text === POST_FORK_FOLLOWUP))
+      return messageIndex >= 0 && loaded.events.slice(messageIndex + 1).some(event => event.type === 'turn/end')
+    }, { timeout: 30_000 }).toBe(true)
+    expect(scaffold.ctx.agents.get(forkId)).not.toBeUndefined()
+    await expect.poll(() => scaffold.ctx.agents.get(childId), { timeout: 10_000 }).toBeUndefined()
+  })
+})

apps/web/tests/support/listen-probe.mjs

@@ -0,0 +1,9 @@
+import { appendFileSync } from 'node:fs'
+import { Server } from 'node:net'
+
+const marker = process.env.DSH_LISTEN_PROBE_MARKER
+const listen = Server.prototype.listen
+Server.prototype.listen = function (...args) {
+  if (marker !== undefined) appendFileSync(marker, 'listen\n')
+  return listen.apply(this, args)
+}

apps/web/tests/vite-entry.e2e.ts

@@ -0,0 +1,63 @@
+/** Bare Vite must fail before it can present a bootless shell as a working GUI. */
+
+import { fileURLToPath, pathToFileURL } from 'node:url'
+import { join } from 'node:path'
+import { existsSync, mkdtempSync, rmSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { createServer } from 'node:net'
+import { execa } from 'execa'
+import { describe, expect, it } from 'vitest'
+
+const WEB_ROOT = fileURLToPath(new URL('..', import.meta.url))
+
+/** Reserve an available loopback port, then release it for the child invocation. */
+async function freePort(): Promise<number> {
+  const server = createServer()
+  await new Promise<void>((resolve, reject) => {
+    server.once('error', reject)
+    server.listen(0, '127.0.0.1', resolve)
+  })
+  const address = server.address()
+  if (address === null || typeof address === 'string') throw new Error('port probe returned no address')
+  await new Promise<void>((resolve, reject) => server.close((error) => {
+    if (error === undefined) resolve()
+    else reject(error)
+  }))
+  return address.port
+}
+
+describe('Web development entry', () => {
+  it('rejects the package dev alias with the full-host correction', async () => {
+    const result = await execa('pnpm', ['run', 'dev'], { cwd: WEB_ROOT, reject: false })
+    expect(result.exitCode).not.toBe(0)
+    expect(result.stderr).toContain('apps/web is not a standalone application')
+    expect(result.stderr).toContain('dsh web')
+  })
+
+  it('rejects the standalone Vite server with the full-host correction', async () => {
+    const probeRoot = mkdtempSync(join(tmpdir(), 'dsh-vite-listen-probe-'))
+    const marker = join(probeRoot, 'listen-called')
+    const port = await freePort()
+    try {
+      const probeModule = fileURLToPath(new URL('./support/listen-probe.mjs', import.meta.url))
+      const result = await execa(join(WEB_ROOT, 'node_modules/.bin/vite'), ['--host', '127.0.0.1', '--port', String(port)], {
+        cwd: WEB_ROOT,
+        reject: false,
+        timeout: 10_000,
+        env: {
+          ...process.env,
+          DSH_LISTEN_PROBE_MARKER: marker,
+          NODE_OPTIONS: `${process.env.NODE_OPTIONS ?? ''} --import ${pathToFileURL(probeModule).href}`.trim(),
+        },
+      })
+      expect(result.timedOut).toBe(false)
+      expect(result.exitCode).not.toBe(0)
+      expect(result.stderr).toContain('apps/web is not a standalone application')
+      expect(result.stderr).toContain('dsh web')
+      expect(result.stderr).toContain('window.__DSH_BOOT__')
+      expect(existsSync(marker), 'Vite called Server.listen before rejecting standalone serve mode').toBe(false)
+    } finally {
+      rmSync(probeRoot, { recursive: true, force: true })
+    }
+  })
+})