test(web): run fixture browser cases through Host

apps/web/stress-tests/reasoning-chunks.stress.ts

@@ -1,22 +1,29 @@
 /**
  * Opt-in browser stress reproduction for reasoning-stream renderer stalls.
- * The fixture emits 100,000 individual chunks through the normal async
- * carrier; the test measures event-loop and scheduled-interaction delay while
- * the assembled React surface keeps a collapsed Think row live.
+ * A test-owned model adapter emits 100,000 individual chunks through the real
+ * Host, Gateway, and browser carriers; the test measures event-loop and
+ * scheduled-interaction delay while the assembled React surface keeps a
+ * collapsed Think row live.
  */
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { expect, it, onTestFailed } from 'vitest'
+import { LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm'
+import type {} from '@deepseek-ai/dsh-agent-default-model'
 import { launchWebScaffold, watchConsole, type WebScaffold } from '../tests/scaffold.ts'
-import { newEnglishPage, saveFailureShot } from '../tests/support.ts'
+import {
+  connectFreshWorkspace, newEnglishPage, saveFailureShot, writeComposerDraft,
+} from '../tests/support.ts'
 
 const CHUNK_COUNT = 100_000
 const CHUNKS_PER_INTERVAL = 128
 const CHUNK_INTERVAL_MS = 16
 const MAIN_THREAD_DELAY_BUDGET_MS = 250
+const PROVIDER = 'reasoning-stress-test'
+const MODEL = 'reasoning-storm'
+const MARKER = `REASONING_STRESS_COMPLETE:${String(CHUNK_COUNT)}`
 
 interface ReasoningChunkStormState {
-  sessionId: string
   chunkCount: number
   chunksPerInterval: number
   intervalMs: number
@@ -25,6 +32,86 @@ interface ReasoningChunkStormState {
   emitting: boolean
 }
 
+/** Externally paced model stream whose counters are observed outside the browser. */
+class ReasoningStressAdapter extends LlmAdapter {
+  private finishStream!: () => void
+  private resolveStarted!: () => void
+  private resolveCompleted!: () => void
+  private releaseBatch: (() => void) | undefined
+  private resolveBatch: (() => void) | undefined
+  private batchInFlight = false
+  private finishRequested = false
+  private readonly finishGate = new Promise<void>((resolve) => { this.finishStream = resolve })
+  readonly started = new Promise<void>((resolve) => { this.resolveStarted = resolve })
+  readonly completed = new Promise<void>((resolve) => { this.resolveCompleted = resolve })
+  private emitted = 0
+  private emitting = false
+
+  finish(): void {
+    this.finishRequested = true
+    this.releaseBatch?.()
+    this.finishStream()
+  }
+
+  async emitNextBatch(): Promise<void> {
+    if (!this.emitting || this.releaseBatch === undefined) {
+      throw new Error('reasoning stress adapter has no batch awaiting release')
+    }
+    if (this.batchInFlight) throw new Error('reasoning stress adapter accepts one batch release at a time')
+    this.batchInFlight = true
+    const delivered = new Promise<void>((resolve) => { this.resolveBatch = resolve })
+    const release = this.releaseBatch
+    this.releaseBatch = undefined
+    release()
+    await delivered
+  }
+
+  state(): ReasoningChunkStormState {
+    return {
+      chunkCount: CHUNK_COUNT,
+      chunksPerInterval: CHUNKS_PER_INTERVAL,
+      intervalMs: CHUNK_INTERVAL_MS,
+      emitted: this.emitted,
+      marker: MARKER,
+      emitting: this.emitting,
+    }
+  }
+
+  override async *stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
+    if (this.emitting || this.emitted !== 0) throw new Error('reasoning stress adapter accepts one model call')
+    this.emitting = true
+    const parts: string[] = []
+    yield { type: 'block-start', index: 0, blockType: 'reasoning' }
+    while (this.emitted < CHUNK_COUNT) {
+      await new Promise<void>((resolve) => {
+        this.releaseBatch = resolve
+        if (this.emitted === 0) this.resolveStarted()
+        if (this.finishRequested) resolve()
+      })
+      if (this.finishRequested) break
+      options.signal?.throwIfAborted()
+      const end = Math.min(this.emitted + CHUNKS_PER_INTERVAL, CHUNK_COUNT)
+      while (this.emitted < end) {
+        const text = this.emitted === CHUNK_COUNT - 1
+          ? `\n${MARKER}`
+          : this.emitted % 64 === 63 ? '推理\n' : '推理'
+        parts.push(text)
+        yield { type: 'reasoning-delta', index: 0, text }
+        this.emitted += 1
+      }
+      this.batchInFlight = false
+      this.resolveBatch?.()
+      this.resolveBatch = undefined
+    }
+    this.emitting = false
+    if (this.emitted === CHUNK_COUNT) this.resolveCompleted()
+    await this.finishGate
+    options.signal?.throwIfAborted()
+    yield { type: 'block-end', index: 0, block: { type: 'reasoning', text: parts.join('') } }
+    yield { type: 'finish', reason: { kind: 'stop' } }
+  }
+}
+
 interface StressProbe {
   intervalId: number
   intervalMs: number
@@ -36,10 +123,6 @@ interface StressProbe {
 }
 
 interface StressWindow extends Window {
-  __fxTiming?: {
-    startReasoningChunkStorm(id: string, chunkCount: number, chunksPerInterval: number, intervalMs: number): string
-    reasoningChunkStormState(): ReasoningChunkStormState | null
-  }
   __reasoningStressProbe?: StressProbe
 }
 
@@ -47,23 +130,22 @@ it('keeps the browser responsive while rendering 100,000 reasoning chunks', asyn
   let scaffold: WebScaffold | undefined
   let browser: Browser | undefined
   let page: Page | undefined
+  const adapter = new ReasoningStressAdapter()
   try {
     scaffold = await launchWebScaffold()
+    scaffold.ctx.effect(
+      () => scaffold!.ctx.llm.registerAdapter([PROVIDER], adapter),
+      'reasoning stress adapter',
+    )
+    await scaffold.ctx.agentDefaultModel.saveSelection({ provider: PROVIDER, model: MODEL })
     browser = await chromium.launch({ headless: process.env.DSH_WEB_STRESS_HEADFUL !== '1' })
     page = await newEnglishPage(browser)
     const activePage = page
-    await activePage.addInitScript(() => {
-      localStorage.setItem('dsh.sessions.current', JSON.stringify({ sessionId: 'fx-alpha' }))
-    })
     const tripwire = watchConsole(activePage)
     onTestFailed(() => saveFailureShot(activePage, 'web-stress-reasoning-chunks'))
-    await activePage.goto(`${scaffold.baseUrl}?fixture`, { waitUntil: 'load' })
+    await activePage.goto(scaffold.authenticatedUrl, { waitUntil: 'load' })
     await activePage.waitForSelector('[class*="frame"]', { timeout: 30_000 })
-    // Fixture settings deliberately reject writes, so its welcome notice
-    // cannot acknowledge. Hide only that test overlay; the assembled chat
-    // tree beneath it remains mounted and exercises the production renderer.
-    await activePage.addStyleTag({ content: '[class*="onboardingOverlay"] { display: none !important; }' })
-    await activePage.locator('[data-sample="bash"]').first().waitFor({ timeout: 30_000 })
+    await connectFreshWorkspace(activePage, scaffold.workspaceCwd)
 
     await activePage.evaluate(() => {
       const intervalMs = 50
@@ -92,45 +174,42 @@ it('keeps the browser responsive while rendering 100,000 reasoning chunks', asyn
       ;(window as StressWindow).__reasoningStressProbe = probe
     })
 
-    const marker = await activePage.evaluate(({ chunkCount, chunksPerInterval, intervalMs }) => {
-      const hooks = (window as StressWindow).__fxTiming
-      if (hooks === undefined) throw new Error('reasoning stress fixture hooks unavailable')
-      return hooks.startReasoningChunkStorm('fx-alpha', chunkCount, chunksPerInterval, intervalMs)
-    }, {
-      chunkCount: CHUNK_COUNT,
-      chunksPerInterval: CHUNKS_PER_INTERVAL,
-      intervalMs: CHUNK_INTERVAL_MS,
-    })
+    const settled = scaffold.whenTurnSettled(540_000)
+    const input = activePage.locator('[data-composer-input]').first()
+    await writeComposerDraft(activePage, input, `Render ${String(CHUNK_COUNT)} reasoning chunks.`)
+    await input.press('Enter')
+    await adapter.started
 
+    await adapter.emitNextBatch()
     const liveThink = activePage.locator('[data-variant="think"][data-state="running"]').last()
     await liveThink.waitFor({ timeout: 60_000 })
-    await expect.poll(async () => await activePage.evaluate(() => {
-      const hooks = (window as StressWindow).__fxTiming
-      return hooks?.reasoningChunkStormState()?.emitted ?? 0
-    }), { timeout: 540_000, interval: 100 }).toBe(CHUNK_COUNT)
-    await expect.poll(() => liveThink.textContent(), { timeout: 60_000, interval: 100 }).toContain(marker)
+    await activePage.evaluate(intervalMs => new Promise<void>((resolve) => {
+      window.setTimeout(resolve, intervalMs)
+    }), CHUNK_INTERVAL_MS)
+    while (adapter.state().emitted < CHUNK_COUNT) {
+      await adapter.emitNextBatch()
+      await activePage.evaluate(intervalMs => new Promise<void>((resolve) => {
+        window.setTimeout(resolve, intervalMs)
+      }), CHUNK_INTERVAL_MS)
+    }
+    await adapter.completed
+    await expect.poll(() => liveThink.textContent(), { timeout: 60_000, interval: 100 }).toContain(MARKER)
 
-    const report = await activePage.evaluate(() => {
+    const browserReport = await activePage.evaluate(() => {
       const win = window as StressWindow
       const probe = win.__reasoningStressProbe
-      const state = win.__fxTiming?.reasoningChunkStormState()
-      if (probe === undefined || state === undefined || state === null) {
-        throw new Error('reasoning stress metrics unavailable')
-      }
+      if (probe === undefined) throw new Error('reasoning stress metrics unavailable')
       window.clearInterval(probe.intervalId)
       const interactionDelayMs = probe.interactionHandledAt === null
         ? null
         : probe.interactionHandledAt - probe.interactionDueAt
       return {
-        chunkCount: state.chunkCount,
-        chunksPerInterval: state.chunksPerInterval,
-        intervalMs: state.intervalMs,
-        emitted: state.emitted,
         maxMainThreadDelayMs: Math.max(0, probe.maxDelayMs),
         interactionDelayMs,
         heartbeatSamples: probe.samples,
       }
     })
+    const report = { ...adapter.state(), ...browserReport }
     process.stdout.write(`reasoning-chunk stress report: ${JSON.stringify(report)}\n`)
 
     expect(report).toMatchObject({
@@ -146,7 +225,10 @@ it('keeps the browser responsive while rendering 100,000 reasoning chunks', asyn
     expect(interactionDelayMs, JSON.stringify(report)).toBeLessThan(MAIN_THREAD_DELAY_BUDGET_MS)
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
+    adapter.finish()
+    await settled
   } finally {
+    adapter.finish()
     await browser?.close()
     await scaffold?.close()
   }

apps/web/tests/goal-bar.e2e.ts

@@ -1,18 +1,19 @@
-// Keyless assembled-browser coverage for the goal bar over the shipped Web
-// bundles and the fixture Connection RPC. The command creates a real projected
-// goal in the fixture session; the golden pins the active strip, while the
-// clear gesture proves the acknowledged tombstone leaves neither stale chrome
-// nor a duplicate-mutation error.
+// Keyless browser coverage for the goal bar over the shipped Web composition.
+// The command creates a real projected goal in a real Host session. The
+// goldens pin the active and disarmed strips, while the clear gesture proves
+// the acknowledged tombstone leaves neither stale chrome nor a
+// duplicate-mutation error.
 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 {} from '@deepseek-ai/dsh-goal'
 import {
   assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { newEnglishPage, saveFailureShot } from './support.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
 
 const SNAPSHOT_DIR = fileURLToPath(new URL('./expected/goal-bar', import.meta.url))
 const ACTIVE_EXPECTED = join(SNAPSHOT_DIR, 'active.expected.md')
@@ -27,14 +28,13 @@ describe('web e2e: goal bar clear convergence', () => {
   let tripwire: ReturnType<typeof watchConsole>
 
   beforeAll(async () => {
-    scaffold = await launchWebScaffold({ extraOverlayPath: OVERLAY, welcomeNoticePending: true })
+    scaffold = await launchWebScaffold({ extraOverlayPath: OVERLAY })
     browser = await chromium.launch()
     page = await newEnglishPage(browser)
     tripwire = watchConsole(page)
-    const login = await page.context().request.get(scaffold.authenticatedUrl, { maxRedirects: 0 })
-    expect(login.status()).toBe(303)
-    await page.goto(`${scaffold.baseUrl}?fixture`, { waitUntil: 'load' })
+    await page.goto(scaffold.authenticatedUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
   }, 120_000)
 
   afterAll(async () => {
@@ -44,8 +44,6 @@ describe('web e2e: goal bar clear convergence', () => {
 
   it('renders one active goal and clears it without exposing a stale error', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-goal-bar-clear'))
-    // Startup reuses the fixture workspace's blank session, keeping this
-    // command independent of alpha's running replay and pending question.
     const input = page.locator('[data-composer-input][data-placeholder="Describe what you want to build, / commands, @ files or sessions"]')
     await input.waitFor({ timeout: 10_000 })
     await input.fill('/goal guard rapid clear clicks')
@@ -53,15 +51,16 @@ describe('web e2e: goal bar clear convergence', () => {
 
     const bar = page.locator('[data-goal-bar]')
     await bar.waitFor({ timeout: 10_000 })
-    await expect.poll(() => bar.getByRole('button', { name: 'Pause goal' }).count(), {
+    const pause = bar.getByRole('button', { name: 'Pause goal' })
+    await expect.poll(() => pause.count(), {
       timeout: 10_000,
     }).toBe(1)
     const snapshot = await captureStableAria(page, '[data-goal-bar]', scaffold.workspaceCwd)
     await compareOrRefreshGolden(ACTIVE_EXPECTED, snapshot, MODE)
 
-    await page.evaluate(() => {
-      (globalThis as unknown as { __fxTiming?: { disarmOnlyGoal(): void } }).__fxTiming?.disarmOnlyGoal()
-    })
+    const agents = scaffold.ctx.agents.list()
+    expect(agents).toHaveLength(1)
+    scaffold.ctx.goals.disarm(agents[0]!)
     await expect.poll(() => bar.getByRole('button', { name: 'Resume goal' }).count(), {
       timeout: 10_000,
     }).toBe(1)

apps/web/tests/goal-bar.overlay.yml

@@ -1,5 +1,4 @@
-# The client-side FixtureApiClient intentionally rejects settings traffic, so
-# this goal-only scenario omits the settings shell and the onboarding steps it
-# would mount. Onboarding owns separate assembled-browser coverage.
-- id: ui-settings-general
+# This scenario owns Goal bar actions, not autonomous Goal rounds. Keeping the
+# driver out prevents an active Goal from issuing an unrelated model request.
+- id: goal-round-driver
   disabled: true

vitest.web-stress.config.ts

@@ -1,10 +1,10 @@
 import tsconfigPaths from 'vite-tsconfig-paths'
 import { defineConfig } from 'vitest/config'
-import { vitestExecArgv } from './vitest.shared.ts'
+import { standardDecoratorPlugin, vitestExecArgv } from './vitest.shared.ts'
 
 /** Opt-in browser performance lane; no default Vitest config includes *.stress.ts. */
 export default defineConfig({
-  plugins: [tsconfigPaths({ projects: ['./tsconfig.base.json'] })],
+  plugins: [tsconfigPaths({ projects: ['./tsconfig.base.json'] }), standardDecoratorPlugin()],
   test: {
     execArgv: vitestExecArgv,
     include: ['apps/web/stress-tests/**/*.stress.ts'],