Merge branch 'master' into fix/web-turn-error-surface

apps/cli/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write apps/cli/README.md
-README.md: cf038ad19c631721c7b3182ffe83e75e3837d9ba
-README.zh.md: c790f973a9ab0071253ab161bd8bc7835ebb2e02
+README.md: aee08225febe34bb10ee1001c798db9d7daa8905
+README.zh.md: 8f38fd342a0433ca5f7645f896b81aa5392033ae

apps/cli/README.md

@@ -27,6 +27,14 @@ The Web/headless composition also registers only `web_search`. Search uses DeepS
 
 `DSH_TOOLS_MODE` selects the tool presentation mode for the whole Web/headless process: `native` (the schema default when unset), `code` (the `run_code`-only Code Mode wire), or `both`; any other value fails loud at boot through the `dsh-tools` config schema. It is a TEMPORARY seam — process-wide because Loader composition is static — and is removed once the web UI owns per-session tool-mode selection; the TUI surface ignores it (its config tree pins its own mode).
 
+[`core-web.cordis.yml`](config/core-web.cordis.yml) is an opt-in `dsh web --config` overlay that keeps the shipped Web host, browser, Workspace, persistence, and permission composition while reducing the default native model surface to owner-scoped persistent `bash` and `str_replace_editor`. The PTY backend and editor consume the existing Web sandbox and filesystem providers. An open persistent shell prevents changing that session's permission mode until the shell closes, so a shell created under wider access cannot survive a downgrade. `DSH_TOOLS_MODE` still controls native/Code Mode presentation for the resulting two-tool registry.
+
+From a source checkout, start this minimal Web profile with:
+
+```sh
+pnpm run dsh web --config apps/cli/config/core-web.cordis.yml
+```
+
 Every `dsh` surface — TUI, Web, and headless — reports session telemetry by default (the row lives in the shared `base.cordis.yml`): every session-log event streams as OTLP/HTTP log records to `https://harness-telemetry.deepseeksvc.com/v1/logs` on a 10-second batch cadence. `DSH_TELEMETRY_OTLP_URL` points the exporter at a different collector; setting `DSH_TELEMETRY_DISABLED` to ANY non-empty value — including `0` or `false` — disables the row before it loads (a privacy switch prefers off-by-mistake over on-by-mistake). No redaction rule is mounted in this composition yet: exported records are the raw captured copy, including message text, tool arguments and results, and the session's working-directory path. The deployment rulings live in the [web-telemetry-default-mount Agent Note](../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md).
 
 ## Install (developer machine)

apps/cli/README.zh.md

@@ -27,6 +27,14 @@ Web／无头组合还只会注册 `web_search`。搜索使用 DeepSeek 的 Anthr
 
 `DSH_TOOLS_MODE` 为整个 Web／无头进程选择工具呈现模式：可选值为 `native`（未设置时的 schema 默认值）、`code`（仅含 `run_code` 的 Code Mode 协议接口）或 `both`；任何其他值都会经由 `dsh-tools` 配置 schema 在启动时明确报错。它是一个临时 seam：Loader 组合是静态的，因此该设置作用于整个进程；待 Web UI 负责逐会话工具模式选择后便会移除。TUI 界面会忽略该变量（其配置树固定了自身模式）。
 
+[`core-web.cordis.yml`](config/core-web.cordis.yml) 是一个可选启用的 `dsh web --config` 覆盖层：它保留已交付的 Web 宿主、浏览器、Workspace、持久化与权限组合，同时将默认的原生模型界面精简为以所有者为作用域的持久 `bash` 以及 `str_replace_editor`。PTY 后端和编辑器分别消费现有的 Web 沙箱与文件系统提供方。持久 shell 处于打开状态时，会阻止所属会话更改权限模式；因此，在较宽权限下创建的 shell 无法在降权后继续存活。`DSH_TOOLS_MODE` 仍控制由此得到的双工具注册表采用原生／Code Mode 呈现。
+
+在源码 checkout 中，用以下命令启动这个精简 Web profile：
+
+```sh
+pnpm run dsh web --config apps/cli/config/core-web.cordis.yml
+```
+
 每个 `dsh` 界面——TUI、Web 与无头——都默认上报会话遥测（该行位于共享的 `base.cordis.yml`）：每条会话日志事件以 OTLP/HTTP 日志记录的形式、按 10 秒批处理节奏流向 `https://harness-telemetry.deepseeksvc.com/v1/logs`。`DSH_TELEMETRY_OTLP_URL` 可将 exporter 指向其他 collector；将 `DSH_TELEMETRY_DISABLED` 设为**任意非空值**——包括 `0` 或 `false`——都会在该行加载前将其关停（隐私开关取「宁可误关、不可误开」）。该组合当前未挂载任何脱敏规则：导出记录即原始捕获副本，包含消息正文、工具参数与结果、以及会话工作目录路径。部署口径见 [web-telemetry-default-mount Agent Note](../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md)。
 
 ## 安装（开发机）

apps/cli/config/core-web.cordis.yml

@@ -0,0 +1,72 @@
+# Opt-in two-tool profile over the shipped Web composition. The default native
+# model surface is exactly persistent `bash` plus `str_replace_editor`; the
+# Web host, browser shell, workspace, persistence, and permission stack remain.
+
+# Disable every model-facing consumer in the base/Web tree. plan-mode owns the
+# always-registered exit_plan_mode tool even while the session is not planning.
+- id: tool-bash
+  disabled: true
+
+- id: tool-tasks
+  disabled: true
+
+- id: tool-fs
+  disabled: true
+
+- id: tool-fs-search
+  disabled: true
+
+- id: tool-web
+  disabled: true
+
+- id: tool-skill
+  disabled: true
+
+- id: plan-mode
+  disabled: true
+
+- id: tool-subagent
+  disabled: true
+
+- id: tool-subagent-fork
+  disabled: true
+
+- id: tool-workflow
+  disabled: true
+
+- id: tool-todo
+  disabled: true
+
+# The matching browser controls must not offer host tools that this profile
+# omits. ui-question's host half owns the ask_user_question registration.
+- id: ui-plan
+  disabled: true
+
+- id: ui-question
+  disabled: true
+
+- insert:
+    - id: pty
+      name: '@deepseek-ai/dsh-pty'
+
+    # This backend consumes the existing Web sandbox and permission policy.
+    # It loads only on Linux/macOS; Windows and other platforms fail at boot.
+    # Its 300s send wait matches the persistent Bash command timeout instead of
+    # pty-local's 30s default. An open persistent shell fences permission-mode
+    # changes until it closes.
+    - id: pty-local
+      name: '@deepseek-ai/dsh-pty-local'
+      config:
+        timeoutMs: 300000
+
+    - id: persistent-bash
+      name: '@deepseek-ai/dsh-tool-bash-persistent'
+      config:
+        timeoutMs: 300000
+
+    # The editor consumes the Web fs-sandbox provider and therefore retains
+    # the selected session permission mode.
+    - id: str-replace-editor
+      name: '@deepseek-ai/dsh-tool-str-replace-editor'
+      config:
+        maxOutputChars: 16000

apps/cli/package.json

@@ -68,9 +68,12 @@
     "@deepseek-ai/dsh-llm-deepseek": "workspace:^",
     "@deepseek-ai/dsh-llm-pi-ai": "workspace:^",
     "@deepseek-ai/dsh-llm-retry": "workspace:^",
+    "@deepseek-ai/dsh-mcp-client": "workspace:^",
     "@deepseek-ai/dsh-paths": "workspace:^",
     "@deepseek-ai/dsh-permission": "workspace:^",
     "@deepseek-ai/dsh-plan-mode": "workspace:^",
+    "@deepseek-ai/dsh-pty": "workspace:^",
+    "@deepseek-ai/dsh-pty-local": "workspace:^",
     "@deepseek-ai/dsh-sandbox-local": "workspace:^",
     "@deepseek-ai/dsh-sandbox-policy": "workspace:^",
     "@deepseek-ai/dsh-scope": "workspace:^",
@@ -103,12 +106,14 @@
     "@deepseek-ai/dsh-token-meter": "workspace:^",
     "@deepseek-ai/dsh-tool-ask-user": "workspace:^",
     "@deepseek-ai/dsh-tool-bash": "workspace:^",
+    "@deepseek-ai/dsh-tool-bash-persistent": "workspace:^",
     "@deepseek-ai/dsh-tool-cordis": "workspace:^",
     "@deepseek-ai/dsh-tool-fs": "workspace:^",
     "@deepseek-ai/dsh-tool-fs-search": "workspace:^",
     "@deepseek-ai/dsh-tool-goal": "workspace:^",
     "@deepseek-ai/dsh-tool-ralph": "workspace:^",
     "@deepseek-ai/dsh-tool-skill": "workspace:^",
+    "@deepseek-ai/dsh-tool-str-replace-editor": "workspace:^",
     "@deepseek-ai/dsh-tool-subagent": "workspace:^",
     "@deepseek-ai/dsh-tool-tasks": "workspace:^",
     "@deepseek-ai/dsh-tool-todo": "workspace:^",

apps/cli/tests/fixtures/memory-mcp-base.cordis.yml

@@ -0,0 +1,8 @@
+# Minimal keyless composition for loading example MCP overlays against the
+# package-owned fixture server in memory-mcp-configs.spec.ts. Source builtins
+# keep this unit test independent of prebuilt workspace artifacts.
+- id: system-prompt
+  name: cordis:memory-test-system-prompt
+
+- id: tools
+  name: cordis:memory-test-tools

apps/cli/tests/memory-mcp-configs.spec.ts

@@ -0,0 +1,132 @@
+/**
+ * The third-party memory examples stay config-only. This suite parses every
+ * checked-in overlay, verifies its pin/transport/secret boundary, then replaces
+ * only the upstream endpoint with the package-owned keyless MCP fixture and
+ * proves the real Cordis Loader discovers a tool through the generic bridge.
+ */
+
+import { readFileSync } from 'node:fs'
+import { resolve } from 'node:path'
+import { afterEach, describe, expect, it } from 'vitest'
+import type { Context } from 'cordis'
+import type { PatchOptions } from '@cordisjs/plugin-include'
+import { boot, loadOverlayPatches } from '@deepseek-ai/dsh-app-boot'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry from '@deepseek-ai/dsh-tools'
+import * as McpClient from '@deepseek-ai/dsh-mcp-client/src/index.ts'
+
+interface ExampleContract {
+  file: string
+  id: string
+  serverName: string
+  transport: 'stdio' | 'streamable-http'
+  pin: string
+}
+
+interface InsertedRow {
+  id?: string
+  name?: string
+  config?: Record<string, unknown>
+}
+
+const root = resolve(import.meta.dirname, '../../..')
+const exampleDir = resolve(root, 'examples/mcp-memory')
+const baseConfig = resolve(import.meta.dirname, 'fixtures/memory-mcp-base.cordis.yml')
+const fixtureServer = resolve(root, 'packages/mcp/mcp-client/tests/fixture-server.ts')
+
+const examples: ExampleContract[] = [
+  {
+    file: 'memorix.cordis.yml',
+    id: 'memory-memorix',
+    serverName: 'memorix',
+    transport: 'stdio',
+    pin: '1.3.0',
+  },
+  {
+    file: 'mcp-reference-memory.cordis.yml',
+    id: 'memory-mcp-reference',
+    serverName: 'reference_memory',
+    transport: 'stdio',
+    pin: '2026.7.4',
+  },
+  {
+    file: 'engram.cordis.yml',
+    id: 'memory-engram',
+    serverName: 'engram',
+    transport: 'stdio',
+    pin: '1.20.0',
+  },
+]
+
+const liveContexts = new Set<Context>()
+
+afterEach(async () => {
+  await Promise.all([...liveContexts].map(async ctx => ctx.fiber.dispose()))
+  liveContexts.clear()
+})
+
+function insertedRow(patches: PatchOptions[]): InsertedRow {
+  expect(patches).toHaveLength(1)
+  const insert = patches[0]?.insert
+  expect(insert).toHaveLength(1)
+  return insert?.[0] as InsertedRow
+}
+
+async function waitForTool(ctx: Context, name: string): Promise<void> {
+  const deadline = Date.now() + 10_000
+  while (!ctx.tools.schemas().some(schema => schema.name === name)) {
+    if (Date.now() >= deadline) throw new Error(`timed out waiting for ${name}`)
+    await new Promise(resolveWait => setTimeout(resolveWait, 25))
+  }
+}
+
+describe('third-party memory MCP example overlays', () => {
+  it.each(examples)('parses $file with the documented generic boundary', (contract) => {
+    const file = resolve(exampleDir, contract.file)
+    const source = readFileSync(file, 'utf8')
+    const row = insertedRow(loadOverlayPatches('memory-mcp-config-test', file))
+
+    expect(row.id).toBe(contract.id)
+    expect(row.name).toBe('@deepseek-ai/dsh-mcp-client')
+    expect(row.config?.serverName).toBe(contract.serverName)
+    expect(row.config?.transport).toBe(contract.transport)
+    expect(source.split('\n', 1)[0]).toContain(contract.pin)
+    expect(source).not.toMatch(/\bsk-[A-Za-z0-9_-]{8,}\b/)
+    expect(source).not.toContain('DEEPSEEK_API_KEY')
+  })
+
+  it.each(examples)('loads $file and discovers a keyless fixture tool', async (contract) => {
+    const patches = loadOverlayPatches(
+      'memory-mcp-config-test',
+      resolve(exampleDir, contract.file),
+    )
+    // The static config gate verifies the checked-in bare package specifier.
+    // The unit test maps it to the source module so a clean checkout needs no
+    // prebuilt `lib/` artifacts before proving the Loader/MCP behavior.
+    insertedRow(patches).name = 'cordis:memory-test-mcp-client'
+    const fixturePatch: PatchOptions = {
+      id: contract.id,
+      config: {
+        serverName: contract.serverName,
+        transport: 'stdio',
+        command: process.execPath,
+        args: [fixtureServer],
+        env: {},
+        cwd: root,
+        toolCallTimeoutMs: 5_000,
+      },
+    }
+    const ctx = await boot(
+      'memory-mcp-config-test',
+      baseConfig,
+      [...patches, fixturePatch],
+      (ctx) => {
+        liveContexts.add(ctx)
+        ctx.loader.builtins['memory-test-system-prompt'] = SystemPrompt
+        ctx.loader.builtins['memory-test-tools'] = ToolRegistry
+        ctx.loader.builtins['memory-test-mcp-client'] = McpClient
+      },
+    )
+    await waitForTool(ctx, `mcp__${contract.serverName}__greet`)
+  }, 15_000)
+})

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

@@ -0,0 +1,84 @@
+import { writeFile } from 'node:fs/promises'
+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 { SessionId } from '@deepseek-ai/dsh-session'
+import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
+
+const CORE_WEB_OVERLAY = fileURLToPath(new URL('../../cli/config/core-web.cordis.yml', import.meta.url))
+
+describe('core Web profile', () => {
+  let scaffold: WebScaffold
+  let agentHandle: AgentHandle
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({
+      extraOverlayPath: CORE_WEB_OVERLAY,
+      toolsMode: 'native',
+    })
+    agentHandle = await scaffold.ctx.agents.create({
+      sessionId: SessionId('core-web-profile-smoke'),
+      meta: { cwd: scaffold.workspaceCwd },
+      agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
+    })
+  })
+
+  afterAll(async () => {
+    const failures: unknown[] = []
+    await agentHandle?.dispose().catch((error: unknown) => failures.push(error))
+    await scaffold?.close().catch((error: unknown) => failures.push(error))
+    if (failures.length === 1) throw failures[0]
+    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 () => {
+    const seedPath = join(scaffold.workspaceCwd, 'profile-smoke.txt')
+    await writeFile(seedPath, 'CORE_WEB_EDITOR_OK\n')
+    const signal = new AbortController().signal
+    const bash = await scaffold.ctx.tools.execute({
+      signal,
+      callId: CallId('core-web-bash-smoke'),
+      name: 'bash',
+      arguments: { command: "printf 'CORE_WEB_BASH_OK\\n'" },
+      agent: agentHandle.agent,
+    })
+    const editor = await scaffold.ctx.tools.execute({
+      signal,
+      callId: CallId('core-web-editor-smoke'),
+      name: 'str_replace_editor',
+      arguments: { command: 'view', path: seedPath },
+      agent: agentHandle.agent,
+    })
+
+    const text = (result: typeof bash): string => result.content
+      .filter(block => block.type === 'text')
+      .map(block => block.text)
+      .join('')
+      .replaceAll(scaffold.workspaceCwd, '{{cwd}}')
+      .trimEnd()
+
+    expect({
+      tools: scaffold.ctx.tools.schemas().map(tool => tool.name),
+      bash: text(bash),
+      editor: text(editor),
+    }).toMatchInlineSnapshot(`
+      {
+        "bash": "CORE_WEB_BASH_OK",
+        "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",
+        "tools": [
+          "bash",
+          "str_replace_editor",
+        ],
+      }
+    `)
+
+    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()
+  })
+})

apps/web/tests/scaffold.ts

@@ -106,6 +106,12 @@ export interface WebScaffold {
 
 /** Options for {@link launchWebScaffold}. */
 export interface LaunchOptions {
+  /**
+   * Optional product overlay applied after the shipped Web surface and before
+   * the scaffold's hermetic test patches, matching AppCLIEntry's `--config`
+   * ordering.
+   */
+  extraOverlayPath?: string
   /**
    * Replay fixture (session.jsonl) served by the inserted dsh-llm-replay row
    * in replay/refresh modes; ignored in record mode (the real adapter
@@ -215,8 +221,12 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
   // 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)
+  const extraOverlayPatches = options.extraOverlayPath === undefined
+    ? []
+    : loadOverlayPatches('web e2e scaffold', options.extraOverlayPath)
   const patches: PatchOptions[] = [
     ...surfacePatches,
+    ...extraOverlayPatches,
     { id: 'session-persistence-jsonl', config: { root: persistenceRoot } },
     { id: 'session-query-sqlite', config: { path: ':memory:', openAt: 'first-search' } },
     // storage-json's yml root is anchored to the real $DSH_HOME; pin the row

apps/web/tsconfig.json

@@ -24,6 +24,7 @@
   "exclude": [
     "tests/scaffold.ts",
     "tests/scaffold-hermetic.e2e.ts",
+    "tests/core-web-profile.snapshot.ts",
     "tests/live-interactions.e2e.ts",
     "tests/question-composer.e2e.ts",
     "tests/approval-composer.e2e.ts",