Merge remote-tracking branch 'origin/master' into worktree/turn-tail-actions

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

@@ -3,21 +3,27 @@ import { join } from 'node:path'
 import { fileURLToPath } from 'node:url'
 import { afterAll, beforeAll, describe, expect, it } from 'vitest'
 import type { AgentHandle } from '@deepseek-ai/dsh-agent'
-import { CallId } from '@deepseek-ai/dsh-llm'
+import { CallId, createUserMessage } from '@deepseek-ai/dsh-llm'
 import { SessionId } from '@deepseek-ai/dsh-session'
-import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
+import { assertFixtureInventory, launchWebScaffold, type WebScaffold } from './scaffold.ts'
 
 const CORE_WEB_OVERLAY = fileURLToPath(new URL('../../cli/config/core-web.cordis.yml', import.meta.url))
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/core-web-profile', import.meta.url))
+const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
+const PROMPT = 'Reply exactly CORE_WEB_REQUEST_OK and stop.'
 
 describe('core Web profile', () => {
   let scaffold: WebScaffold
   let agentHandle: AgentHandle
 
   beforeAll(async () => {
-    scaffold = await launchWebScaffold({
-      extraOverlayPath: CORE_WEB_OVERLAY,
-      toolsMode: 'native',
-    })
+    const systemPrompt = process.env.DSH_SYSTEM_PROMPT
+    Reflect.deleteProperty(process.env, 'DSH_SYSTEM_PROMPT')
+    try {
+      scaffold = await launchWebScaffold({ extraOverlayPath: CORE_WEB_OVERLAY, replayFixture: FIXTURE })
+    } finally {
+      if (systemPrompt !== undefined) process.env.DSH_SYSTEM_PROMPT = systemPrompt
+    }
     agentHandle = await scaffold.ctx.agents.create({
       sessionId: SessionId('core-web-profile-smoke'),
       meta: { cwd: scaffold.workspaceCwd },
@@ -33,7 +39,16 @@ describe('core Web profile', () => {
     if (failures.length > 1) throw new AggregateError(failures, 'core Web profile smoke teardown failed')
   })
 
-  it('boots and executes both tools through the shipped Web composition', async () => {
+  it('sends the RL prompt and tool schemas through a real request, then executes both tools', async () => {
+    agentHandle.agent.followup(createUserMessage({
+      content: [{ type: 'text', text: PROMPT }],
+      source: { kind: 'user' },
+    }))
+    await agentHandle.agent.whenIdle()
+
+    const requestHeader = agentHandle.agent.session.requestHeader()
+    if (requestHeader === undefined) throw new Error('the core Web agent issued no model request')
+
     const seedPath = join(scaffold.workspaceCwd, 'profile-smoke.txt')
     await writeFile(seedPath, 'CORE_WEB_EDITOR_OK\n')
     const signal = new AbortController().signal
@@ -60,7 +75,8 @@ describe('core Web profile', () => {
       .trimEnd()
 
     expect({
-      tools: scaffold.ctx.tools.schemas().map(tool => tool.name),
+      prompt: requestHeader.system,
+      tools: requestHeader.tools?.map(tool => tool.name),
       bash: text(bash),
       editor: text(editor),
     }).toMatchInlineSnapshot(`
@@ -69,16 +85,53 @@ describe('core Web profile', () => {
         "editor": "Here's the content of {{cwd}}/profile-smoke.txt with line numbers (which has a total of 2 lines):
            1  CORE_WEB_EDITOR_OK
            2",
+        "prompt": "You are a helpful software engineer assistant.",
         "tools": [
           "bash",
           "str_replace_editor",
         ],
       }
     `)
+    expect(requestHeader.tools).toEqual(scaffold.ctx.tools.schemas(agentHandle.agent))
 
     const entries = [...scaffold.ctx.loader.entries()]
     expect(entries.find(entry => entry.options.id === 'persistent-bash')?.fiber).toBeDefined()
     expect(entries.find(entry => entry.options.id === 'pty-local')?.fiber).toBeDefined()
     expect(entries.find(entry => entry.options.id === 'str-replace-editor')?.fiber).toBeDefined()
+    expect(entries.find(entry => entry.options.id === 'web-runtime')?.fiber).toBeDefined()
+    expect(entries.find(entry => entry.options.id === 'workspace-context')?.fiber).toBeUndefined()
+    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl'])
+  })
+
+  it('uses DSH_SYSTEM_PROMPT as the complete prompt when configured', async () => {
+    const previous = process.env.DSH_SYSTEM_PROMPT
+    process.env.DSH_SYSTEM_PROMPT = 'RL prompt override'
+    let overrideScaffold: WebScaffold | undefined
+    let overrideAgent: AgentHandle | undefined
+    try {
+      overrideScaffold = await launchWebScaffold({ extraOverlayPath: CORE_WEB_OVERLAY, replayFixture: FIXTURE })
+      overrideAgent = await overrideScaffold.ctx.agents.create({
+        sessionId: SessionId('core-web-profile-override'),
+        meta: { cwd: overrideScaffold.workspaceCwd },
+        agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
+      })
+      overrideAgent.agent.followup(createUserMessage({
+        content: [{ type: 'text', text: PROMPT }],
+        source: { kind: 'user' },
+      }))
+      await overrideAgent.agent.whenIdle()
+      expect(overrideAgent.agent.session.requestHeader()?.system).toBe('RL prompt override')
+    } finally {
+      try {
+        await overrideAgent?.dispose()
+      } finally {
+        try {
+          await overrideScaffold?.close()
+        } finally {
+          if (previous === undefined) Reflect.deleteProperty(process.env, 'DSH_SYSTEM_PROMPT')
+          else process.env.DSH_SYSTEM_PROMPT = previous
+        }
+      }
+    }
   })
 })

apps/web/tests/onboarding-deepseek-config.e2e.ts

@@ -161,6 +161,58 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
     expect(tripwire.pageErrors).toEqual([])
   }, 60_000)
 
+  it('never paints the takeover chrome on a configured reload, even with the settings join held open', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-configured-reload'))
+    // Regression pin for the reload white flash: both steps are satisfied
+    // (welcome acknowledged, credential configured), yet each must LOAD its
+    // private join before it can decide not to show. The chrome lives inside
+    // the step (OnboardingSurface), so the deciding window paints and blocks
+    // nothing. Holding settings.describe widens that window from loopback
+    // RTT scale to a deterministic hundreds of milliseconds, removing all
+    // timing dependence from the sampler assertions below.
+    //
+    // The sampler init script persists across this shared page's later
+    // navigations (init scripts re-run per navigation); that stays harmless
+    // because no later scenario in this file legitimately shows the
+    // takeover, and only this test reads __takeoverSightings.
+    await page.addInitScript(() => {
+      const sightings: string[] = []
+      ;(window as unknown as { __takeoverSightings: string[] }).__takeoverSightings = sightings
+      setInterval(() => {
+        if (document.querySelector('[class*="onboardingStage"], [class*="onboardingMask"]') !== null) {
+          sightings.push('chrome')
+        }
+        if (document.getElementById('root')?.inert === true) sightings.push('inert')
+      }, 8)
+    })
+    // EVERY settings.describe issued before the release is held — not just
+    // the first — so the pin cannot silently collapse back to loopback
+    // timing if a second boot-time consumer of the join ever appears.
+    let released = false
+    const heldRoutes: Array<() => void> = []
+    const releaseDescribe = (): void => {
+      released = true
+      for (const resolve of heldRoutes.splice(0)) resolve()
+    }
+    await page.route('**/api/settings.describe', async (route) => {
+      if (!released) await new Promise<void>((resolve) => { heldRoutes.push(resolve) })
+      await route.continue()
+    })
+    const warningsBefore = tripwire.warnings.length
+    await page.reload({ waitUntil: 'commit' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 15_000 })
+    // The app is painted and interactive while the steps are still deciding.
+    await page.waitForTimeout(600)
+    releaseDescribe()
+    await page.waitForTimeout(400)
+    await page.unroute('**/api/settings.describe')
+    acknowledgeReloadConnectionLoss(tripwire, warningsBefore)
+    expect(await page.evaluate(() =>
+      (window as unknown as { __takeoverSightings: string[] }).__takeoverSightings)).toEqual([])
+    expect(await page.locator('[class*="onboardingStage"]').count()).toBe(0)
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
   it('configures arbitrary DeepSeek models and prompts after the selected model is removed', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-deepseek-models'))
     // Opened here rather than inherited: the credential test reloads the page

apps/web/tests/pin-browse-picker.overlay.yml

@@ -1,4 +1,4 @@
-# Loader overlay for the W5 real-host smoke (`dsh web --config`): pin the
+# Loader overlay for the W5 real-host smoke (`dsh web --patch`): pin the
 # in-browser directory picker. The shipped row is `-auto`, which resolves to
 # the native OS chooser on a loopback bind with a local display — an
 # interaction a Playwright page cannot drive, so the resolved backend would

apps/web/tests/scaffold.ts

@@ -1,7 +1,8 @@
 // Shared scaffold for the keyless browser e2e lane (Agent Note:
 // .agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md).
-// Boots the REAL web composition — the shipped base plus web overlay through
-// the vendored Loader (the same include boot AppCLIEntry drives), patched the
+// Boots the REAL web composition — the dsh-base and dsh-web-app bundle
+// patches over the empty profile root through the vendored Loader (the same
+// layer stack the profile boot composes), patched the
 // snapshot way — so a real chromium exercises the real HTTP uplink/WebSocket
 // downlink, api-gateway, agent loop, tools, and persistence. Modes ride $DSH_SNAPSHOT:
 // replay (default, keyless: normally disables the llm-deepseek row and
@@ -11,7 +12,7 @@
 // masking its credential, without making a model call.
 //
 // Composition divergences from `dsh web`, all deliberate, all via include
-// patches after the shipped surface overlay, over the SAME tree (never a
+// patches after the shipped bundle layers, over the SAME tree (never a
 // second yml): temp persistenceRoot; host-level skill roots confined to the
 // temp workspace while project skill discovery remains real; workspace-context
 // disabled (recorded fixtures must not embed this repo's AGENTS.md);
@@ -22,9 +23,9 @@
 // (the plugin-row path discards the ReplayHandle; the direct install keeps
 // assertConsumed for the teardown fixture-consumption check).
 import { existsSync } from 'node:fs'
-import { mkdtemp, readFile, readdir, realpath, rm, utimes, writeFile } from 'node:fs/promises'
+import { mkdir, mkdtemp, readFile, readdir, realpath, rm, utimes, writeFile } from 'node:fs/promises'
 import { tmpdir } from 'node:os'
-import { join, resolve } from 'node:path'
+import { join } from 'node:path'
 import { pathToFileURL } from 'node:url'
 import type { Page } from 'playwright'
 import { expect } from 'vitest'
@@ -32,7 +33,13 @@ import { Context } from 'cordis'
 import Loader from '@cordisjs/plugin-loader'
 import Include, { type PatchOptions } from '@cordisjs/plugin-include'
 import { scrubRequestHeaders } from '@deepseek-ai/dsh-acp-snapshot'
-import { assertEntriesLoaded, loadOverlayPatches } from '@deepseek-ai/dsh-app-boot'
+import {
+  addHarnessSourceSection,
+  assertEntriesLoaded,
+  composeEntries,
+  healProfilesModuleFallback,
+  loadOverlayPatches,
+} from '@deepseek-ai/dsh-app-boot'
 import { dshHomePath } from '@deepseek-ai/dsh-paths'
 import {
   WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_SETTINGS_NAMESPACE, WELCOME_NOTICE_VERSION,
@@ -53,8 +60,7 @@ 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'
+import { REPO_ROOT, requireDist } from './support.ts'
 
 /** Snapshot mode for the lane, from $DSH_SNAPSHOT (same vocabulary as the other snapshot suites). */
 export type WebSnapshotMode = 'replay' | 'record' | 'refresh'
@@ -70,9 +76,11 @@ export function webSnapshotMode(): WebSnapshotMode {
   throw new Error(`DSH_SNAPSHOT must be replay, record, or refresh; got ${JSON.stringify(value)}`)
 }
 
-/** The shipped composition under test: apps/cli's shared base and web overlay. */
-const CONFIG_PATH = join(REPO_ROOT, 'apps/cli/config/base.cordis.yml')
-const WEB_OVERLAY_PATH = join(REPO_ROOT, 'apps/cli/config/web.cordis.yml')
+/** The shipped composition under test: the dsh-base and dsh-web-app bundle patches over the empty profile root. */
+const BASE_PATCH_PATH = join(REPO_ROOT, 'packages/bundle/base/cordis.patch.yml')
+const WEB_PATCH_PATH = join(REPO_ROOT, 'packages/bundle/web-app/cordis.patch.yml')
+/** The installation anchor whose dependency surface the profile module fallback mirrors. */
+const INSTALL_ANCHOR = join(REPO_ROOT, 'apps/cli/package.json')
 
 // Replay publishes the provider catalog the gateway routes to (providers
 // mode, never catch-all: with llm-deepseek disabled no adapter exists, so a
@@ -117,7 +125,7 @@ export interface WebScaffold {
 export interface LaunchOptions {
   /**
    * Optional product overlay applied after the shipped Web surface and before
-   * the scaffold's hermetic test patches, matching AppCLIEntry's `--config`
+   * the scaffold's hermetic test patches, matching the launcher's `--patch`
    * ordering.
    */
   extraOverlayPath?: string
@@ -240,14 +248,22 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
   }
   if (maskDeepSeekCredential) Reflect.deleteProperty(process.env, 'DEEPSEEK_API_KEY')
 
-  // The include patch set — the same mechanism AppCLIEntry and the ACP
-  // snapshot overlay use, applied over the SAME shipped tree (a patch id that
-  // stops matching a row fails the boot sweep loudly instead of drifting).
-  const surfacePatches = loadOverlayPatches('web e2e scaffold', WEB_OVERLAY_PATH)
+  // The include patch set — the same layer stack the profile boot composes
+  // (bundle patches in dsh.profile.bundles order), applied over the SAME empty root (a
+  // patch id that stops matching a row fails the boot sweep loudly instead of
+  // drifting).
+  const basePatches = loadOverlayPatches('web e2e scaffold', BASE_PATCH_PATH)
+  const surfacePatches = loadOverlayPatches('web e2e scaffold', WEB_PATCH_PATH)
   const extraOverlayPatches = options.extraOverlayPath === undefined
     ? []
     : loadOverlayPatches('web e2e scaffold', options.extraOverlayPath)
+  const composedRows = composeEntries([basePatches, surfacePatches, extraOverlayPatches])
+  const webRuntimeConfig = composedRows.find(row => row.id === 'web-runtime')?.config as {
+    surfaceContext?: boolean
+  } | undefined
+  const surfaceContext = webRuntimeConfig?.surfaceContext !== false
   const patches: PatchOptions[] = [
+    ...basePatches,
     ...surfacePatches,
     ...extraOverlayPatches,
     { id: 'session-persistence-jsonl', config: { root: persistenceRoot } },
@@ -280,8 +296,13 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
     { id: 'telemetry-otel', disabled: true },
     {
       id: 'webserver',
-      config: { host: '127.0.0.1', port: 0, distIndex: DIST_INDEX },
+      config: { host: '127.0.0.1', port: 0 },
     },
+    // The bundle's web-runtime row resolves the same built dist under test
+    // (apps/web IS @deepseek-ai/dsh-frontend); only the URL line is silenced.
+    // Preserve the composed surface-context choice because a patch replaces
+    // the row's complete config.
+    { id: 'web-runtime', config: { mode: 'production', printUrl: false, surfaceContext } },
     ...options.remoteAuthority === undefined
       ? []
       : [{ id: 'connection', config: { trustedHosts: [options.remoteAuthority] } }],
@@ -321,7 +342,15 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
   let replayHandle: ReplayHandle | undefined
   try {
     process.chdir(workspaceCwd)
-    ctx.baseUrl = pathToFileURL(join(resolve(CONFIG_PATH), '..')).href + '/'
+    // The production resolution shape: an empty profile root inside the temp
+    // harness home, with bare plugin names resolving through the flat module
+    // fallback the launcher heals under <home>/profiles.
+    healProfilesModuleFallback(INSTALL_ANCHOR, harnessHome)
+    const profileDir = join(harnessHome, 'profiles', 'scaffold')
+    await mkdir(profileDir, { recursive: true })
+    const rootConfig = join(profileDir, 'cordis.yml')
+    await writeFile(rootConfig, '[]\n')
+    ctx.baseUrl = pathToFileURL(profileDir).href + '/'
     // This direct Loader harness supplies the same root-path capability as app-boot.
     ctx.provide('dshHomePath', dshHomePath)
     await ctx.plugin(Loader)
@@ -329,10 +358,12 @@ 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')
+    if (surfaceContext) {
+      ctx.inject(['systemPrompt'], (promptCtx) => { addHarnessSourceSection(promptCtx, REPO_ROOT) })
+    }
     await ctx.loader.create({
       name: 'cordis:include',
-      config: { path: pathToFileURL(resolve(CONFIG_PATH)).href, patches },
+      config: { path: pathToFileURL(rootConfig).href, patches },
     })
     await ctx.loader.await()
     assertEntriesLoaded(ctx, 'web e2e scaffold')

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

@@ -487,7 +487,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
         '--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', String(port),
         // Pin the in-browser picker: the shipped `-auto` row would resolve to
         // the native OS chooser on this bind, and no page can drive that.
-        '--config', fileURLToPath(new URL('./pin-browse-picker.overlay.yml', import.meta.url)),
+        '--patch', fileURLToPath(new URL('./pin-browse-picker.overlay.yml', import.meta.url)),
       ],
       {
         cwd: sessionsDir,

apps/web/tests/snapshots/core-web-profile/session.jsonl

@@ -0,0 +1,7 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785974400000,"cwd":"{{cwd}}"}
+{"type":"user/message","seq":0,"time":1785974400001,"data":{"content":[{"type":"text","text":"Reply exactly CORE_WEB_REQUEST_OK and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
+{"type":"assistant/chunk","seq":1,"time":1785974400002,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":2,"time":1785974400003,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"CORE_WEB_REQUEST_OK"}}}
+{"type":"assistant/chunk","seq":3,"time":1785974400004,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"CORE_WEB_REQUEST_OK"}}}}
+{"type":"assistant/chunk","seq":4,"time":1785974400005,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":4}}}}
+{"type":"assistant/chunk","seq":5,"time":1785974400006,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}