Merge remote-tracking branch 'origin/master' into feat/web-message-feedback-ui

apps/cli/config/agent-presets/minimal/agent.cordis.yml

@@ -1,8 +1,9 @@
-# The `minimal` agent preset: a fixed-prompt, two-tool coding surface.
+# The `minimal` agent preset: a fixed-prompt, two-tool coding-agent composition.
 #
-# The persona is the complete system prompt, so global identity, Web surface,
+# The persona is the complete system prompt, so global identity, Web orientation,
 # tool guidance, and later assembly listeners cannot add prompt text. The model
-# composes only the persistent `bash` and `str_replace_editor` tools.
+# composes only the persistent `bash` and `str_replace_editor` tools. Context
+# compaction is deliberately absent.
 
 - id: persona
   name: '@deepseek-ai/dsh-persona'
@@ -41,33 +42,20 @@
           * Please avoid commands that may produce a very large amount of output.
           * Please run long lived commands in the background, e.g. 'sleep 10 &' or start a server in the background.
 
-# The editor requires absolute paths unconditionally.
-- id: str-replace-editor
-  name: '@deepseek-ai/dsh-tool-str-replace-editor'
-  config:
-    maxOutputChars: 16000
-
-# Model capacity comes from routed model metadata; this block states the
-# compaction policy explicitly.
-#
-# `tokenMeter` is deliberately NOT in this realm: the meter stays on the HOST
-# plane, and the row here resolves that one instance. It takes no configuration,
-# keys every fold by Session, and owns the context-meter projection units the
-# browser reads for every session — behind a realm those units would come and go
-# with whichever presets happen to be mounted. What a preset chooses is whether
-# its agent compacts at all, which is `compact-basic` below.
-- id: compaction
+# The bare local filesystem shadows the host's sandboxed provider only for this
+# preset. The editor shares that realm and requires absolute paths.
+- id: filesystem
   name: cordis:group
   group: true
   isolate:
-    compact: true
+    fs: true
   config:
-    - id: compact-basic
-      name: '@deepseek-ai/dsh-compact-basic'
+    - id: fs-local
+      name: '@deepseek-ai/dsh-fs-local'
       config:
-        thresholdRatio: 0.8
-        retainTokens: 20480
-        summarizationProvider: ''
-        summarizationModel: ''
-        maxTokens: 8192
-        compactionRetries: 1
+        cwd: !!js process.env.DSH_CWD ?? process.cwd()
+
+    - id: str-replace-editor
+      name: '@deepseek-ai/dsh-tool-str-replace-editor'
+      config:
+        maxOutputChars: 16000

apps/cli/package.json

@@ -35,6 +35,7 @@
     "@deepseek-ai/dsh-goal-session": "workspace:^",
     "@deepseek-ai/dsh-cmdline": "workspace:^",
     "@deepseek-ai/dsh-environment": "workspace:^",
+    "@deepseek-ai/dsh-fs-local": "workspace:^",
     "@deepseek-ai/dsh-headless": "workspace:^",
     "@deepseek-ai/dsh-mcp-client": "workspace:^",
     "@deepseek-ai/dsh-paths": "workspace:^",

apps/cli/tests/built-bin.e2e.ts

@@ -408,16 +408,15 @@ describe.skipIf(!existsSync(dshBin))('dsh BUILT bin (node lib/bin.js, no tsx)',
     }
   }, 30_000)
 
-  it('uses the Harness-home environment and managed credential through the published entry', async () => {
+  it('uses the launching endpoint and managed credential through the published entry', async () => {
     const apiKey = 'built-home-layer-key'
     const server = await startMockLlmServer({
       sequence: ['success'],
       apiKey,
-      successText: 'home environment reached the mock',
+      successText: 'launching endpoint reached the mock',
     })
     const home = mkdtempSync(join(tmpdir(), 'dsh-home-environment-'))
     const project = mkdtempSync(join(tmpdir(), 'dsh-home-project-'))
-    writeFileSync(join(home, '.env'), `DEEPSEEK_BASE_URL=${server.baseURL}\n`)
     writeFileSync(join(home, '.credentials.yaml'), `DEEPSEEK_API_KEY: ${apiKey}\n`, { mode: 0o600 })
     createEnvironmentProbeProfile(home, project)
     try {
@@ -427,7 +426,7 @@ describe.skipIf(!existsSync(dshBin))('dsh BUILT bin (node lib/bin.js, no tsx)',
           DSH_HOME: home,
           DSH_TELEMETRY_DISABLED: '1',
           DEEPSEEK_API_KEY: undefined,
-          DEEPSEEK_BASE_URL: undefined,
+          DEEPSEEK_BASE_URL: server.baseURL,
         },
         project,
       )
@@ -435,7 +434,7 @@ describe.skipIf(!existsSync(dshBin))('dsh BUILT bin (node lib/bin.js, no tsx)',
         result.code,
         `${result.stderr}\nstdout:\n${result.stdout}\nmock requests: ${String(server.requests.length)}`,
       ).toBe(0)
-      expect(result.stdout).toBe('home environment reached the mock')
+      expect(result.stdout).toBe('launching endpoint reached the mock')
       expect(result.stdout).not.toContain(apiKey)
       expect(result.stderr).not.toContain(apiKey)
       expect(server.requests).toHaveLength(1)

apps/cli/tests/web-agent-presets.e2e.ts

@@ -14,7 +14,7 @@ import { settingsNamespace } from '@deepseek-ai/dsh-settings'
 import { resolveSessionPreset, SETTINGS_NAMESPACE } from '@deepseek-ai/dsh-agent-presets'
 import { applyChildComposition, childSessionMeta } from '@deepseek-ai/dsh-subagent'
 import { CallId } from '@deepseek-ai/dsh-llm'
-import type { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
+import type {} from '@deepseek-ai/dsh-compact-basic'
 import type {} from '@deepseek-ai/dsh-skill'
 import type {} from '@deepseek-ai/dsh-tools'
 // Type-only: resolves `ctx.get('sessionProjections')` and `ctx.get('tokenMeter')`.
@@ -216,16 +216,8 @@ describe('the shipped Web composition', () => {
       expect(assembly.tools.find(tool => tool.name === 'bash')?.description).toBe(MINIMAL_BASH_DESCRIPTION)
       expect(JSON.stringify(assembly.tools.find(tool => tool.name === 'str_replace_editor')?.parameters))
         .toContain('Absolute path')
-      const compact = ctx.agentPresets.serviceFor(handle.agent, 'compact')
-      expect(compact).toBeDefined()
-      expect((compact as BasicCompactService).config).toMatchObject({
-        thresholdRatio: 0.8,
-        retainTokens: 20480,
-        summarizationProvider: '',
-        summarizationModel: '',
-        maxTokens: 8192,
-        compactionRetries: 1,
-      })
+      expect(ctx.agentPresets.serviceFor(handle.agent, 'compact')).toBeUndefined()
+      expect(handle.agent.ctx.get('compact')).toBeUndefined()
     } finally {
       await handle.dispose()
     }

apps/web/tests/minimal-preset.snapshot.ts

@@ -55,6 +55,10 @@ describe('minimal agent preset', () => {
 
     const requestHeader = agentHandle.agent.session.requestHeader()
     if (requestHeader === undefined) throw new Error('the minimal agent issued no model request')
+    const presetFileSystem = scaffold.ctx.agentPresets.serviceFor(agentHandle.agent, 'fs')
+    expect(presetFileSystem).toBeDefined()
+    expect(presetFileSystem?.sandboxMode).toBeUndefined()
+    expect(scaffold.ctx.agentPresets.serviceFor(agentHandle.agent, 'compact')).toBeUndefined()
 
     const stateDir = join(scaffold.workspaceCwd, 'persistent-state')
     await mkdir(stateDir)

apps/web/tests/produced-files.e2e.ts

@@ -1,28 +1,107 @@
-// Web e2e scenario: the produced-files row a finished turn ends with. Cold-seeds
-// a recorded write turn (zero model calls). Package tests cover the derivation
-// in isolation, but only the assembled application shows that a turn's writes
-// reach the transcript as an openable row (docs/testing.md snapshot rule). The
-// click itself is not driven here: it hands the path to the Host's opener,
-// which would launch a real application on the machine running the suite.
-import { readFile, writeFile, mkdir } from 'node:fs/promises'
-import { join } from 'node:path'
+// Web e2e scenario: the single-line produced-files summary a finished turn
+// ends with. Cold-seeds ten writes (zero model calls), then verifies the real
+// assembled lane keeps a precise +N and a capability-gated folder handoff.
+// The folder request is intercepted so one real browser click can exercise
+// the full client carrier without launching a native application in CI.
 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 { afterAll, beforeAll, describe, expect, it, onTestFailed, vi } from 'vitest'
+import { CallId, createAssistantMessage, createToolResultMessage, createUserMessage } from '@deepseek-ai/dsh-llm'
+import { SESSION_FORMAT_VERSION, Session, SessionId } from '@deepseek-ai/dsh-session'
+import type {} from '@deepseek-ai/dsh-session-title'
 import {
   launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
 import { newEnglishPage, saveFailureShot } from './support.ts'
 
-// Borrowed read-only: this scenario needs any settled turn whose tools WROTE a
-// file, not a new recording (the message-actions borrowing pattern).
-const SEED = fileURLToPath(new URL('./snapshots/permission-policy-context/session.jsonl', import.meta.url))
 const MODE = webSnapshotMode()
+const OVERLAY = fileURLToPath(new URL('./produced-files.overlay.yml', import.meta.url))
 const SEED_ID = 'produced-files-web-e2e'
+const DONE = 'PRODUCED_FILES_DONE'
 
-/** The file the borrowed recording's write tool produces. */
-const PRODUCED = 'policy-neutral.txt'
+/** Short leading names plus a long third name make the narrow lane deterministically show two. */
+const PRODUCED = [
+  '关于我.md',
+  'index.html',
+  'long-generated-experience-specification-for-produced-files-overflow.md',
+  'styles.css',
+  'app.ts',
+  'schema.json',
+  'README.md',
+  'preview.svg',
+  'notes.txt',
+  'manifest.yaml',
+] as const
+
+/** Build one settled turn whose successful write calls carry ten locations. */
+function producedFixture(): string {
+  const session = Session.create(SessionId('produced-files-source'))
+  const eventTimeOrigin = new Date().setHours(12, 0, 0, 0)
+  session.append('turn/start', { turn: 1 })
+  const user = session.append('user/message', createUserMessage({
+    content: [{ type: 'text', text: 'Create the site files.' }],
+    source: { kind: 'user' },
+  }), { surfaceOp: 'append' })
+  session.append('session/title', {
+    title: 'Produced files overflow', messageSeqs: [user.seq], source: { kind: 'fallback' },
+  })
+  session.append('step/start', { turn: 1, step: 1 })
+  const calls = PRODUCED.map((path, index) => ({
+    path,
+    callId: CallId(`produced-files-${String(index)}`),
+    args: JSON.stringify({ file_path: path, content: `content of ${path}\n` }),
+  }))
+  session.append('assistant/message', {
+    turn: 1,
+    step: 1,
+    message: createAssistantMessage({
+      content: calls.map(call => ({
+        type: 'tool-call' as const,
+        id: call.callId,
+        name: 'write',
+        arguments: call.args,
+      })),
+      source: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
+    }),
+  }, { surfaceOp: 'append' })
+  for (const call of calls) {
+    const source = session.append('tool/call', {
+      turn: 1, step: 1, callId: call.callId, name: 'write', arguments: call.args,
+    })
+    session.append('tool/result', {
+      turn: 1,
+      step: 1,
+      message: createToolResultMessage({
+        callId: call.callId,
+        content: [{ type: 'text', text: `Created ${call.path}` }],
+        isError: false,
+      }),
+    }, { surfaceOp: 'append', sourceEventSeqs: [source.seq] })
+  }
+  session.append('step/start', { turn: 1, step: 2 })
+  session.append('assistant/message', {
+    turn: 1,
+    step: 2,
+    message: createAssistantMessage({
+      content: [{ type: 'text', text: `Created the site.\n\n${DONE}` }],
+      source: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
+    }),
+  }, { surfaceOp: 'append' })
+  session.append('step/end', { turn: 1, step: 2 })
+  session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
+
+  return [
+    JSON.stringify({
+      type: 'session', version: SESSION_FORMAT_VERSION, id: '{{sessionId}}',
+      createdAt: 0, cwd: '{{cwd}}',
+    }),
+    ...session.events.map(event => JSON.stringify({
+      ...event, time: eventTimeOrigin + event.seq * 1_000,
+    })),
+    '',
+  ].join('\n')
+}
 
 describe('web e2e: a finished turn ends with the files it produced', () => {
   let scaffold: WebScaffold
@@ -31,16 +110,13 @@ describe('web e2e: a finished turn ends with the files it produced', () => {
   let tripwire: ReturnType<typeof watchConsole>
 
   beforeAll(async () => {
-    scaffold = await launchWebScaffold({})
-    // The seeded Session's cwd is the scaffold workspace; the recording's own
-    // nested directory is created too, so its paths stay resolvable.
-    await mkdir(join(scaffold.workspaceCwd, 'workspace'), { recursive: true })
-    await writeFile(join(scaffold.workspaceCwd, PRODUCED), 'neutral\n')
-    const raw = await readFile(SEED, 'utf8')
-    expect(raw, 'borrowed recording must carry the write this scenario reads').toContain(PRODUCED)
-    await seedSession(scaffold, raw, SEED_ID)
+    scaffold = await launchWebScaffold({ extraOverlayPath: OVERLAY })
+    await seedSession(scaffold, producedFixture(), SEED_ID)
     browser = await chromium.launch()
     page = await newEnglishPage(browser)
+    // Keep the responsive sidebar available while selecting the cold seed;
+    // the assertion itself narrows the conversation after navigation.
+    await page.setViewportSize({ width: 1280, height: 900 })
     tripwire = watchConsole(page)
     await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
     await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
@@ -51,24 +127,52 @@ describe('web e2e: a finished turn ends with the files it produced', () => {
     await scaffold?.close()
   })
 
-  it.skipIf(MODE === 'record')('lists the written file under the closing message, as an opener', async () => {
+  it.skipIf(MODE === 'record')('keeps a narrow ten-file summary on one line with +8 and a folder action', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-produced-files'))
     const groupRow = page.locator('[role="treeitem"]').first()
     await groupRow.waitFor({ timeout: 15_000 })
-    await groupRow.click()
+    if (await groupRow.getAttribute('aria-expanded') !== 'true') await groupRow.click()
     const sessionRow = page.locator('[role="treeitem"]').nth(1)
     await sessionRow.waitFor({ timeout: 10_000 })
     await sessionRow.click()
 
-    // The row the turn ends with — derived from the write call's locations,
-    // not from whatever the closing message happened to say.
-    const chip = page.getByRole('button', { name: `Open ${PRODUCED}`, exact: true }).first()
-    await chip.waitFor({ timeout: 15_000 })
-    expect(await chip.innerText()).toBe(PRODUCED)
-    // The full path stays reachable for a reader who wants to copy it.
-    expect(await chip.getAttribute('title')).toContain(PRODUCED)
-    // A turn's produced files are labelled, not left as bare chips.
-    expect(await page.getByText('Produced', { exact: true }).count()).toBeGreaterThan(0)
+    await expect.poll(() => page.getByText(DONE, { exact: true }).count(), { timeout: 15_000 }).toBe(1)
+    await page.setViewportSize({ width: 780, height: 900 })
+    const row = page.locator('[data-produced-files-row]')
+    await row.waitFor({ timeout: 15_000 })
+    const chips = row.getByRole('button')
+    await expect.poll(() => chips.count()).toBe(2)
+    expect(await chips.nth(0).innerText()).toBe('关于我.md')
+    expect(await chips.nth(1).innerText()).toBe('index.html')
+    expect(await row.getByText('+ 8 files', { exact: true }).count()).toBe(1)
+    const showFolder = page.getByRole('button', { name: 'Show in folder', exact: true })
+    expect(await showFolder.count()).toBe(1)
+    expect(await page.getByText('Produced', { exact: true }).count()).toBe(1)
+
+    const openPath = vi.spyOn(scaffold.ctx.apiProxy.host, 'openPath')
+      .mockImplementation(async (request, _signal) => ({
+        rpcId: request.rpcId,
+        result: { ok: true, value: { opened: true as const } },
+      }))
+    try {
+      const [response] = await Promise.all([
+        page.waitForResponse(response => new URL(response.url()).pathname === '/api/host.openPath'),
+        showFolder.click({ clickCount: 1 }),
+      ])
+      expect(response.status()).toBe(200)
+      expect(openPath).toHaveBeenCalledTimes(1)
+      expect(openPath.mock.calls[0]![0].payload).toEqual({ path: `${scaffold.workspaceCwd}/.` })
+    } finally {
+      openPath.mockRestore()
+    }
+
+    const tops = await row.locator(':scope > *').evaluateAll(elements =>
+      elements.map(element => element.getBoundingClientRect().top))
+    expect(new Set(tops.map(top => Math.round(top))).size).toBe(1)
+    const geometry = await row.evaluate(element => ({
+      clientWidth: element.clientWidth, scrollWidth: element.scrollWidth,
+    }))
+    expect(geometry.scrollWidth).toBeLessThanOrEqual(geometry.clientWidth)
 
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])

apps/web/tests/produced-files.overlay.yml

@@ -0,0 +1,6 @@
+# The summary test asserts the native-folder action without launching it. Pin
+# the capability so headless Linux CI and desktop developer hosts expose the
+# same UI branch; platform opener behavior belongs to the Host unit tests.
+- id: api-gateway
+  config:
+    nativeOpen: true

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

@@ -13,7 +13,6 @@
   - img
   - img
   - text: Context injection @deepseek-ai/dsh-system-prompt
-- text: Running
 - button "Think The user wants me to ask them a checkpoint question first, then continue with whatever they interject. Let me do exactly that.":
   - img
   - img

apps/web/tests/steering.e2e.ts

@@ -354,10 +354,10 @@ describe('web e2e: empty-draft Cmd+Enter steers the whole queue', () => {
       { timeout: 10_000 },
     ).toBe(2)
     expect(await page.locator('[data-queue-dock]').count()).toBe(0)
-    // The reasoning row streams independently of the steering handoff; wait
-    // for it so the mid snapshot pins the assistant step, not the pre-render
-    // gap a fast machine can catch between steering acceptance and the block.
-    await page.locator('[data-variant="think"]').first().waitFor({ timeout: 10_000 })
+    // The reasoning row streams independently of the steering handoff. Wait
+    // for the block to settle so the mid snapshot does not race its transient
+    // visually-hidden Running label while the question keeps the turn open.
+    await page.locator('[data-variant="think"][data-state="ok"]').first().waitFor({ timeout: 10_000 })
     const mid = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
     await compareOrRefreshGolden(STEER_ALL_MID, mid, MODE)