feat: 添加 builtin-tools 增强与测试覆盖

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

packages/builtin-tools/src/tools/CtxInspectTool/CtxInspectTool.ts

@@ -2,6 +2,12 @@ import { z } from 'zod/v4'
 import type { ToolResultBlockParam } from 'src/Tool.js'
 import { buildTool } from 'src/Tool.js'
 import { lazySchema } from 'src/utils/lazySchema.js'
+import { tokenCountWithEstimation } from 'src/utils/tokens.js'
+import {
+  getStats,
+  isContextCollapseEnabled,
+} from 'src/services/contextCollapse/index.js'
+import { isSessionMemoryInitialized } from 'src/services/SessionMemory/sessionMemoryUtils.js'
 
 const CTX_INSPECT_TOOL_NAME = 'CtxInspect'
 
@@ -19,6 +25,10 @@ type CtxInput = z.infer<InputSchema>
 type CtxOutput = {
   total_tokens: number
   message_count: number
+  context_window_model: string
+  prompt_caching_enabled: boolean
+  session_memory_enabled: boolean
+  context_collapse_enabled: boolean
   summary: string
 }
 
@@ -67,13 +77,45 @@ Use this to understand your context budget before deciding whether to snip old m
     }
   },
 
-  async call() {
+  async call(input: CtxInput, context) {
-    // Context inspection is wired into the context collapse system.
+    const messages = context.messages ?? []
+    const model = context.options?.mainLoopModel ?? 'unknown'
+    const totalTokens = tokenCountWithEstimation(messages)
+    const collapseEnabled = isContextCollapseEnabled()
+    const collapseStats = getStats()
+    const focused = input.query?.trim()
+
+    const sessionMemoryEnabled = isSessionMemoryInitialized()
+    // Prompt caching is an API-level feature controlled by the provider, not
+    // a user-facing toggle. Report as enabled only for providers known to
+    // support Anthropic-style prompt caching (first-party, Bedrock, Vertex).
+    const promptCachingEnabled = !model.startsWith('openai/') &&
+      !model.startsWith('grok/') &&
+      !model.startsWith('gemini/')
+
+    const summaryParts = [
+      focused ? `Focus: ${focused}` : 'Overall context summary',
+      `Model context: ${model}`,
+      `Prompt caching: ${promptCachingEnabled ? 'enabled' : 'disabled'}`,
+      `Session memory: ${sessionMemoryEnabled ? 'enabled' : 'disabled'}`,
+      `Context collapse: ${collapseEnabled ? 'enabled' : 'disabled'}`,
+    ]
+
+    if (collapseEnabled) {
+      summaryParts.push(
+        `Collapse spans: ${collapseStats.collapsedSpans} committed, ${collapseStats.stagedSpans} staged, ${collapseStats.collapsedMessages} messages summarized`,
+      )
+    }
+
     return {
       data: {
-        total_tokens: 0,
+        total_tokens: totalTokens,
-        message_count: 0,
+        message_count: messages.length,
-        summary: 'Context inspection requires the CONTEXT_COLLAPSE runtime.',
+        context_window_model: model,
+        prompt_caching_enabled: promptCachingEnabled,
+        session_memory_enabled: sessionMemoryEnabled,
+        context_collapse_enabled: collapseEnabled,
+        summary: summaryParts.join('\n'),
       },
     }
   },

packages/builtin-tools/src/tools/CtxInspectTool/__tests__/CtxInspectTool.test.ts

@@ -0,0 +1,216 @@
+import { afterEach, beforeEach, describe, expect, mock, test } from 'bun:test'
+
+mock.module('src/utils/log.ts', () => ({
+  logError: () => {},
+  logToFile: () => {},
+  getLogDisplayTitle: () => '',
+  logEvent: () => {},
+  logMCPError: () => {},
+  logMCPDebug: () => {},
+  dateToFilename: (d: Date) => d.toISOString().replace(/[:.]/g, '-'),
+  getLogFilePath: () => '/tmp/mock-log',
+  attachErrorLogSink: () => {},
+  getInMemoryErrors: () => [],
+  loadErrorLogs: async () => [],
+  getErrorLogByIndex: async () => null,
+  captureAPIRequest: () => {},
+  _resetErrorLogForTesting: () => {},
+}))
+
+mock.module('src/services/tokenEstimation.ts', () => ({
+  roughTokenCountEstimation: (text: string) => Math.ceil(text.length / 4),
+  roughTokenCountEstimationForMessages: (msgs: unknown[]) => msgs.length * 64,
+  roughTokenCountEstimationForMessage: () => 64,
+  roughTokenCountEstimationForFileType: () => 64,
+  bytesPerTokenForFileType: () => 4,
+  countTokensWithAPI: async () => 0,
+  countMessagesTokensWithAPI: async () => 0,
+  countTokensViaHaikuFallback: async () => 0,
+}))
+
+let sessionMemoryInitialized = false
+mock.module('src/services/SessionMemory/sessionMemoryUtils.ts', () => ({
+  isSessionMemoryInitialized: () => sessionMemoryInitialized,
+  waitForSessionMemoryExtraction: async () => {},
+  getLastSummarizedMessageId: () => undefined,
+  getSessionMemoryContent: async () => null,
+  setLastSummarizedMessageId: () => {},
+  markExtractionStarted: () => {},
+  markExtractionCompleted: () => {},
+  setSessionMemoryConfig: () => {},
+  getSessionMemoryConfig: () => ({}),
+  recordExtractionTokenCount: () => {},
+  markSessionMemoryInitialized: () => {},
+  hasMetInitializationThreshold: () => false,
+  hasMetUpdateThreshold: () => false,
+  getToolCallsBetweenUpdates: () => 0,
+  resetSessionMemoryState: () => {},
+  DEFAULT_SESSION_MEMORY_CONFIG: {},
+}))
+
+mock.module('src/utils/slowOperations.ts', () => ({
+  jsonStringify: JSON.stringify,
+  jsonParse: JSON.parse,
+  slowLogging: { enabled: false },
+  clone: (value: unknown) => structuredClone(value),
+  cloneDeep: (value: unknown) => structuredClone(value),
+  callerFrame: () => '',
+  SLOW_OPERATION_THRESHOLD_MS: 100,
+  writeFileSync_DEPRECATED: () => {},
+}))
+
+const { initContextCollapse, resetContextCollapse } = await import(
+  'src/services/contextCollapse/index.js'
+)
+const { tokenCountWithEstimation } = await import('src/utils/tokens.js')
+const { CtxInspectTool } = await import('../CtxInspectTool.js')
+
+function makeUserMessage(text: string) {
+  return {
+    type: 'user' as const,
+    uuid: `user-${text}`,
+    message: { role: 'user' as const, content: text },
+  }
+}
+
+function makeAssistantMessage(text: string) {
+  return {
+    type: 'assistant' as const,
+    uuid: `assistant-${text}`,
+    message: {
+      role: 'assistant' as const,
+      content: [{ type: 'text' as const, text }],
+    },
+  }
+}
+
+function makeContext(messages: unknown[], mainLoopModel = 'claude-sonnet-4-6') {
+  return {
+    messages,
+    options: {
+      mainLoopModel,
+    },
+    getAppState: () => ({}),
+  } as any
+}
+
+const allowTool = async (input: Record<string, unknown>) => ({
+  behavior: 'allow' as const,
+  updatedInput: input,
+})
+
+const parentMessage = makeAssistantMessage('Parent tool call')
+
+beforeEach(() => {
+  resetContextCollapse()
+  sessionMemoryInitialized = false
+})
+
+afterEach(() => {
+  resetContextCollapse()
+  sessionMemoryInitialized = false
+})
+
+describe('CtxInspectTool', () => {
+  test('tool exports and metadata remain stable', async () => {
+    expect(CtxInspectTool).toBeDefined()
+    expect(CtxInspectTool.name).toBe('CtxInspect')
+    expect(typeof CtxInspectTool.call).toBe('function')
+    expect(await CtxInspectTool.description()).toContain('context')
+    expect(CtxInspectTool.userFacingName()).toBe('CtxInspect')
+    expect(CtxInspectTool.isReadOnly()).toBe(true)
+    expect(CtxInspectTool.isConcurrencySafe()).toBe(true)
+  })
+
+  test('formats tool results for transcript rendering', () => {
+    const block = CtxInspectTool.mapToolResultToToolResultBlockParam(
+      {
+        total_tokens: 192,
+        message_count: 3,
+        context_window_model: 'claude-sonnet-4-6',
+        prompt_caching_enabled: true,
+        session_memory_enabled: true,
+        context_collapse_enabled: false,
+        summary: 'Context collapse: disabled',
+      },
+      'tool-use-id',
+    )
+
+    expect(block.tool_use_id).toBe('tool-use-id')
+    expect(block.content).toContain('192 tokens')
+    expect(block.content).toContain('3 messages')
+    expect(block.content).toContain('Context collapse: disabled')
+  })
+
+  test('returns live context counts and mechanism state', async () => {
+    const messages = [
+      makeUserMessage('Inspect the current context budget.'),
+      makeAssistantMessage('Looking at the current conversation state.'),
+    ]
+    const context = makeContext(messages, 'claude-sonnet-4-6')
+
+    const result = await (CtxInspectTool as any).call(
+      {},
+      context,
+      allowTool,
+      parentMessage,
+    )
+
+    expect(Object.keys(result.data).sort()).toEqual([
+      'context_collapse_enabled',
+      'context_window_model',
+      'message_count',
+      'prompt_caching_enabled',
+      'session_memory_enabled',
+      'summary',
+      'total_tokens',
+    ])
+    expect(result.data.message_count).toBe(messages.length)
+    expect(result.data.total_tokens).toBe(tokenCountWithEstimation(messages as any))
+    expect(result.data.context_window_model).toBe('claude-sonnet-4-6')
+    expect(result.data.prompt_caching_enabled).toBe(true)
+    expect(result.data.session_memory_enabled).toBe(false)
+    expect(result.data.context_collapse_enabled).toBe(false)
+    expect(result.data.summary).toContain('Overall context summary')
+    expect(result.data.summary).toContain('Session memory: disabled')
+    expect(result.data.summary).toContain('Context collapse: disabled')
+  })
+
+  test('query input focuses summary and collapse runtime changes the reported state', async () => {
+    const messages = [
+      makeUserMessage('Show me tool usage pressure in this thread.'),
+      makeAssistantMessage('Summarizing tool-heavy context now.'),
+    ]
+    const context = makeContext(messages, 'claude-sonnet-4-6')
+
+    const disabledResult = await (CtxInspectTool as any).call(
+      { query: 'tool usage' },
+      context,
+      allowTool,
+      parentMessage,
+    )
+
+    initContextCollapse()
+
+    const enabledResult = await (CtxInspectTool as any).call(
+      { query: 'tool usage' },
+      context,
+      allowTool,
+      parentMessage,
+    )
+
+    expect(disabledResult.data.message_count).toBe(messages.length)
+    expect(enabledResult.data.message_count).toBe(messages.length)
+    expect(disabledResult.data.total_tokens).toBe(
+      tokenCountWithEstimation(messages as any),
+    )
+    expect(enabledResult.data.total_tokens).toBe(
+      tokenCountWithEstimation(messages as any),
+    )
+    expect(disabledResult.data.summary).toContain('Focus: tool usage')
+    expect(disabledResult.data.context_collapse_enabled).toBe(false)
+    expect(enabledResult.data.context_collapse_enabled).toBe(true)
+    expect(enabledResult.data.summary).toContain('Context collapse: enabled')
+    expect(enabledResult.data.summary).toContain('Collapse spans:')
+  })
+})

packages/builtin-tools/src/tools/RemoteTriggerTool/RemoteTriggerTool.ts

@@ -11,6 +11,7 @@ import {
   getClaudeAIOAuthTokens,
 } from 'src/utils/auth.js'
 import { lazySchema } from 'src/utils/lazySchema.js'
+import { appendRemoteTriggerAuditRecord } from 'src/utils/remoteTriggerAudit.js'
 import { jsonStringify } from 'src/utils/slowOperations.js'
 import { DESCRIPTION, PROMPT, REMOTE_TRIGGER_TOOL_NAME } from './prompt.js'
 import { renderToolResultMessage, renderToolUseMessage } from './UI.js'
@@ -36,6 +37,7 @@ const outputSchema = lazySchema(() =>
   z.object({
     status: z.number(),
     json: z.string(),
+    audit_id: z.string().optional(),
   }),
 )
 type OutputSchema = ReturnType<typeof outputSchema>
@@ -76,77 +78,96 @@ export const RemoteTriggerTool = buildTool({
     return PROMPT
   },
   async call(input: Input, context: ToolUseContext) {
-    await checkAndRefreshOAuthTokenIfNeeded()
+    const auditBase = {
-    const accessToken = getClaudeAIOAuthTokens()?.accessToken
+      action: input.action,
-    if (!accessToken) {
+      ...(input.trigger_id ? { triggerId: input.trigger_id } : {}),
-      throw new Error(
-        'Not authenticated with a claude.ai account. Run /login and try again.',
-      )
-    }
-    const orgUUID = await getOrganizationUUID()
-    if (!orgUUID) {
-      throw new Error('Unable to resolve organization UUID.')
     }
+    try {
+      await checkAndRefreshOAuthTokenIfNeeded()
+      const accessToken = getClaudeAIOAuthTokens()?.accessToken
+      if (!accessToken) {
+        throw new Error(
+          'Not authenticated with a claude.ai account. Run /login and try again.',
+        )
+      }
+      const orgUUID = await getOrganizationUUID()
+      if (!orgUUID) {
+        throw new Error('Unable to resolve organization UUID.')
+      }
 
-    const base = `${getOauthConfig().BASE_API_URL}/v1/code/triggers`
+      const base = `${getOauthConfig().BASE_API_URL}/v1/code/triggers`
-    const headers = {
+      const headers = {
-      Authorization: `Bearer ${accessToken}`,
+        Authorization: `Bearer ${accessToken}`,
-      'Content-Type': 'application/json',
+        'Content-Type': 'application/json',
-      'anthropic-version': '2023-06-01',
+        'anthropic-version': '2023-06-01',
-      'anthropic-beta': TRIGGERS_BETA,
+        'anthropic-beta': TRIGGERS_BETA,
-      'x-organization-uuid': orgUUID,
+        'x-organization-uuid': orgUUID,
-    }
+      }
 
-    const { action, trigger_id, body } = input
+      const { action, trigger_id, body } = input
-    let method: 'GET' | 'POST'
+      let method: 'GET' | 'POST'
-    let url: string
+      let url: string
-    let data: unknown
+      let data: unknown
-    switch (action) {
+      switch (action) {
-      case 'list':
+        case 'list':
-        method = 'GET'
+          method = 'GET'
-        url = base
+          url = base
-        break
+          break
-      case 'get':
+        case 'get':
-        if (!trigger_id) throw new Error('get requires trigger_id')
+          if (!trigger_id) throw new Error('get requires trigger_id')
-        method = 'GET'
+          method = 'GET'
-        url = `${base}/${trigger_id}`
+          url = `${base}/${trigger_id}`
-        break
+          break
-      case 'create':
+        case 'create':
-        if (!body) throw new Error('create requires body')
+          if (!body) throw new Error('create requires body')
-        method = 'POST'
+          method = 'POST'
-        url = base
+          url = base
-        data = body
+          data = body
-        break
+          break
-      case 'update':
+        case 'update':
-        if (!trigger_id) throw new Error('update requires trigger_id')
+          if (!trigger_id) throw new Error('update requires trigger_id')
-        if (!body) throw new Error('update requires body')
+          if (!body) throw new Error('update requires body')
-        method = 'POST'
+          method = 'POST'
-        url = `${base}/${trigger_id}`
+          url = `${base}/${trigger_id}`
-        data = body
+          data = body
-        break
+          break
-      case 'run':
+        case 'run':
-        if (!trigger_id) throw new Error('run requires trigger_id')
+          if (!trigger_id) throw new Error('run requires trigger_id')
-        method = 'POST'
+          method = 'POST'
-        url = `${base}/${trigger_id}/run`
+          url = `${base}/${trigger_id}/run`
-        data = {}
+          data = {}
-        break
+          break
-    }
+      }
 
-    const res = await axios.request({
+      const res = await axios.request({
-      method,
+        method,
-      url,
+        url,
-      headers,
+        headers,
-      data,
+        data,
-      timeout: 20_000,
+        timeout: 20_000,
-      signal: context.abortController.signal,
+        signal: context.abortController.signal,
-      validateStatus: () => true,
+        validateStatus: () => true,
-    })
+      })
-
+      const audit = await appendRemoteTriggerAuditRecord({
-    return {
+        ...auditBase,
-      data: {
+        ok: res.status >= 200 && res.status < 300,
         status: res.status,
-        json: jsonStringify(res.data),
+      })
-      },
+
+      return {
+        data: {
+          status: res.status,
+          json: jsonStringify(res.data),
+          audit_id: audit.auditId,
+        },
+      }
+    } catch (error) {
+      await appendRemoteTriggerAuditRecord({
+        ...auditBase,
+        ok: false,
+        error: error instanceof Error ? error.message : String(error),
+      })
+      throw error
     }
   },
   mapToolResultToToolResultBlockParam(output, toolUseID) {

packages/builtin-tools/src/tools/RemoteTriggerTool/__tests__/RemoteTriggerTool.test.ts

@@ -0,0 +1,91 @@
+import { afterEach, beforeEach, describe, expect, mock, test } from 'bun:test'
+import { mkdir, readFile, rm } from 'fs/promises'
+import { tmpdir } from 'os'
+import { join } from 'path'
+import {
+  resetStateForTests,
+  setOriginalCwd,
+  setProjectRoot,
+} from 'src/bootstrap/state.js'
+
+let requestStatus = 200
+
+mock.module('axios', () => ({
+  default: {
+    request: async () => ({
+      status: requestStatus,
+      data: { ok: requestStatus >= 200 && requestStatus < 300 },
+    }),
+  },
+}))
+
+mock.module('src/utils/auth.js', () => ({
+  checkAndRefreshOAuthTokenIfNeeded: async () => {},
+  getClaudeAIOAuthTokens: () => ({ accessToken: 'token' }),
+}))
+
+mock.module('src/services/oauth/client.js', () => ({
+  getOrganizationUUID: async () => 'org',
+}))
+
+mock.module('src/constants/oauth.js', () => ({
+  getOauthConfig: () => ({ BASE_API_URL: 'https://example.test' }),
+}))
+
+let cwd = ''
+let previousCwd = ''
+
+beforeEach(async () => {
+  requestStatus = 200
+  previousCwd = process.cwd()
+  cwd = join(tmpdir(), `remote-trigger-tool-${Date.now()}-${Math.random().toString(16).slice(2)}`)
+  await mkdir(cwd, { recursive: true })
+  process.chdir(cwd)
+  resetStateForTests()
+  setOriginalCwd(cwd)
+  setProjectRoot(cwd)
+})
+
+afterEach(async () => {
+  resetStateForTests()
+  process.chdir(previousCwd)
+  await rm(cwd, { recursive: true, force: true })
+})
+
+describe('RemoteTriggerTool audit', () => {
+  test('writes an audit record for successful remote calls', async () => {
+    const { RemoteTriggerTool } = await import('../RemoteTriggerTool')
+    const result = await RemoteTriggerTool.call(
+      { action: 'run', trigger_id: 'trigger-1' },
+      { abortController: new AbortController() } as any,
+    )
+
+    expect(result.data.audit_id).toBeString()
+    const raw = await readFile(
+      join(cwd, '.claude', 'remote-trigger-audit.jsonl'),
+      'utf-8',
+    )
+    expect(raw).toContain('"action":"run"')
+    expect(raw).toContain('"triggerId":"trigger-1"')
+    expect(raw).toContain('"ok":true')
+  })
+
+  test('writes an audit record before rethrowing validation failures', async () => {
+    const { RemoteTriggerTool } = await import('../RemoteTriggerTool')
+
+    await expect(
+      RemoteTriggerTool.call(
+        { action: 'run' },
+        { abortController: new AbortController() } as any,
+      ),
+    ).rejects.toThrow('run requires trigger_id')
+
+    const raw = await readFile(
+      join(cwd, '.claude', 'remote-trigger-audit.jsonl'),
+      'utf-8',
+    )
+    expect(raw).toContain('"action":"run"')
+    expect(raw).toContain('"ok":false')
+    expect(raw).toContain('run requires trigger_id')
+  })
+})

packages/builtin-tools/src/tools/TeamDeleteTool/TeamDeleteTool.ts

@@ -14,11 +14,26 @@ import {
 } from 'src/utils/swarm/teamHelpers.js'
 import { clearTeammateColors } from 'src/utils/swarm/teammateLayoutManager.js'
 import { clearLeaderTeamName } from 'src/utils/tasks.js'
+import { ensureBackendsRegistered, getBackendByType, getInProcessBackend } from 'src/utils/swarm/backends/registry.js'
+import { createPaneBackendExecutor } from 'src/utils/swarm/backends/PaneBackendExecutor.js'
+import { isPaneBackend } from 'src/utils/swarm/backends/types.js'
+import { sleep } from 'src/utils/sleep.js'
 import { TEAM_DELETE_TOOL_NAME } from './constants.js'
 import { getPrompt } from './prompt.js'
 import { renderToolResultMessage, renderToolUseMessage } from './UI.js'
 
-const inputSchema = lazySchema(() => z.strictObject({}))
+const inputSchema = lazySchema(() =>
+  z.strictObject({
+    wait_ms: z
+      .number()
+      .min(0)
+      .max(30_000)
+      .optional()
+      .describe(
+        'Optional time to wait for active teammates to acknowledge shutdown before cleanup.',
+      ),
+  }),
+)
 type InputSchema = ReturnType<typeof inputSchema>
 
 export type Output = {
@@ -68,7 +83,7 @@ export const TeamDeleteTool: Tool<InputSchema, Output> = buildTool({
     }
   },
 
-  async call(_input, context) {
+  async call(input, context) {
     const { setAppState, getAppState } = context
     const appState = getAppState()
     const teamName = appState.teamContext?.teamName
@@ -87,13 +102,82 @@ export const TeamDeleteTool: Tool<InputSchema, Output> = buildTool({
         const activeMembers = nonLeadMembers.filter(m => m.isActive !== false)
 
         if (activeMembers.length > 0) {
-          const memberNames = activeMembers.map(m => m.name).join(', ')
+          const requested: string[] = []
-          return {
+          for (const member of activeMembers) {
-            data: {
+            let sent = false
-              success: false,
+            if (member.backendType === 'in-process') {
-              message: `Cannot cleanup team with ${activeMembers.length} active member(s): ${memberNames}. Use requestShutdown to gracefully terminate teammates first.`,
+              const executor = getInProcessBackend()
-              team_name: teamName,
+              executor.setContext?.(context)
-            },
+              sent = await executor.terminate(
+                member.agentId,
+                'Team cleanup requested by team lead',
+              )
+            } else if (member.backendType && isPaneBackend(member.backendType)) {
+              await ensureBackendsRegistered()
+              const executor = createPaneBackendExecutor(
+                getBackendByType(member.backendType),
+              )
+              executor.setContext?.(context)
+              sent = await executor.terminate(
+                member.agentId,
+                'Team cleanup requested by team lead',
+              )
+            }
+            if (sent) {
+              requested.push(member.name)
+            }
+          }
+          const waitMs = input.wait_ms ?? 0
+          if (waitMs > 0 && requested.length > 0) {
+            const deadline = Date.now() + waitMs
+            while (Date.now() < deadline) {
+              await sleep(Math.min(250, Math.max(0, deadline - Date.now())))
+              const refreshed = readTeamFile(teamName)
+              const stillActive =
+                refreshed?.members.filter(
+                  m => m.name !== TEAM_LEAD_NAME && m.isActive !== false,
+                ) ?? []
+              if (stillActive.length === 0) {
+                break
+              }
+            }
+            const refreshed = readTeamFile(teamName)
+            const stillActive =
+              refreshed?.members.filter(
+                m => m.name !== TEAM_LEAD_NAME && m.isActive !== false,
+              ) ?? []
+            if (stillActive.length === 0) {
+              // Fall through to cleanup with the refreshed team file state.
+            } else {
+              const memberNames = stillActive.map(m => m.name).join(', ')
+              return {
+                data: {
+                  success: false,
+                  message: `Shutdown requested for active teammate(s): ${requested.join(', ')}. Cleanup is still blocked after waiting ${waitMs}ms: ${memberNames}.`,
+                  team_name: teamName,
+                },
+              }
+            }
+          }
+          const latestTeamFile = readTeamFile(teamName)
+          const latestActiveMembers =
+            latestTeamFile?.members.filter(
+              m => m.name !== TEAM_LEAD_NAME && m.isActive !== false,
+            ) ?? []
+          if (latestActiveMembers.length === 0) {
+            // Continue to cleanup below.
+          } else {
+            const memberNames = latestActiveMembers.map(m => m.name).join(', ')
+            return {
+              data: {
+                success: false,
+                message:
+                  requested.length > 0
+                    ? `Shutdown requested for active teammate(s): ${requested.join(', ')}. Cleanup is blocked until they exit: ${memberNames}.`
+                    : `Cannot cleanup team with ${latestActiveMembers.length} active member(s): ${memberNames}. Use requestShutdown to gracefully terminate teammates first.`,
+                team_name: teamName,
+              },
+            }
           }
         }
       }

packages/builtin-tools/src/tools/WebBrowserTool/WebBrowserTool.ts

@@ -9,19 +9,11 @@ const inputSchema = lazySchema(() =>
   z.strictObject({
     url: z
       .string()
-      .describe('URL to navigate to in the browser.'),
+      .describe('URL to fetch and extract content from.'),
     action: z
-      .enum(['navigate', 'screenshot', 'click', 'type', 'scroll'])
+      .enum(['navigate', 'screenshot'])
       .optional()
-      .describe('Browser action to perform. Defaults to "navigate".'),
+      .describe('Action to perform. "navigate" fetches page content (default). "screenshot" returns a text snapshot of the page.'),
-    selector: z
-      .string()
-      .optional()
-      .describe('CSS selector for click/type actions.'),
-    text: z
-      .string()
-      .optional()
-      .describe('Text to type when action is "type".'),
   }),
 )
 type InputSchema = ReturnType<typeof inputSchema>
@@ -45,16 +37,24 @@ export const WebBrowserTool = buildTool({
   },
 
   async description() {
-    return 'Browse the web using an embedded browser'
+    return 'Fetch and read web page content via HTTP'
   },
   async prompt() {
-    return `Open and interact with web pages in an embedded browser. Supports navigation, screenshots, clicking, typing, and scrolling.
+    return `Fetch web pages via HTTP and extract their text content. This is a lightweight browser tool (HTTP fetch, not a full browser engine).
+
+Supported actions:
+- navigate: Fetch a URL and extract page title + text content
+- screenshot: Same as navigate (returns text snapshot, not a visual screenshot)
+
+Limitations:
+- No JavaScript execution — only sees server-rendered HTML
+- click/type/scroll require a full browser runtime (not available)
+- For full browser interaction, use the Claude-in-Chrome MCP tools instead
 
 Use this for:
-- Viewing web pages and their content
+- Reading web page content and documentation
-- Taking screenshots of UI
+- Checking API endpoints that return HTML
-- Interacting with web applications
+- Quick page title/content extraction`
-- Testing web endpoints with full browser rendering`
   },
 
   isConcurrencySafe() {
@@ -85,12 +85,84 @@ Use this for:
   },
 
   async call(input: BrowserInput) {
-    // Browser integration requires the WEB_BROWSER_TOOL runtime (Bun WebView).
+    const action = input.action ?? 'navigate'
+
+    if (action === 'navigate' || action === 'screenshot') {
+      // Fetch the page content via HTTP
+      try {
+        const response = await fetch(input.url, {
+          headers: {
+            'User-Agent':
+              'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+            Accept:
+              'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+          },
+          redirect: 'follow',
+        })
+
+        if (!response.ok) {
+          return {
+            data: {
+              title: `HTTP ${response.status}`,
+              url: input.url,
+              content: `Error: ${response.status} ${response.statusText}`,
+            },
+          }
+        }
+
+        const html = await response.text()
+
+        // Extract title
+        const titleMatch = html.match(/<title[^>]*>([^<]*)<\/title>/i)
+        const title = titleMatch?.[1]?.trim() ?? ''
+
+        // Extract text content (strip HTML tags, scripts, styles)
+        let textContent = html
+          .replace(/<script[\s\S]*?<\/script>/gi, '')
+          .replace(/<style[\s\S]*?<\/style>/gi, '')
+          .replace(/<[^>]+>/g, ' ')
+          .replace(/\s+/g, ' ')
+          .trim()
+
+        // Truncate to reasonable size
+        if (textContent.length > 50_000) {
+          textContent = textContent.slice(0, 50_000) + '\n[truncated]'
+        }
+
+        if (action === 'screenshot') {
+          return {
+            data: {
+              title,
+              url: response.url,
+              content: `[Text snapshot — visual screenshots require Chrome browser tools]\n\n${textContent}`,
+            },
+          }
+        }
+
+        return {
+          data: {
+            title,
+            url: response.url,
+            content: textContent,
+          },
+        }
+      } catch (err) {
+        return {
+          data: {
+            title: 'Error',
+            url: input.url,
+            content: `Failed to fetch: ${err instanceof Error ? err.message : String(err)}`,
+          },
+        }
+      }
+    }
+
+    // Unreachable — schema only allows navigate/screenshot
     return {
       data: {
         title: '',
         url: input.url,
-        content: 'Web browser requires the WEB_BROWSER_TOOL runtime.',
+        content: `Unknown action "${action}".`,
       },
     }
   },

packages/builtin-tools/src/tools/WebBrowserTool/__tests__/WebBrowserTool.test.ts

@@ -0,0 +1,94 @@
+import { describe, test, expect, beforeAll, afterAll } from 'bun:test'
+
+// Mock fetch directly — avoids flaky dependency on external hosts AND
+// pollution by other tests that call setGlobalDispatcher (proxy agents make
+// localhost fetches return 500 in the full-suite run).
+const realFetch = globalThis.fetch
+
+beforeAll(() => {
+  globalThis.fetch = (async (
+    input: string | URL | Request,
+    _init?: RequestInit,
+  ) => {
+    const url = typeof input === 'string' ? input : input.toString()
+    if (url === 'not-a-url' || !url.startsWith('http')) {
+      throw new TypeError('Failed to fetch')
+    }
+    const body =
+      '<!doctype html><html><head><title>Example Domain</title></head>' +
+      '<body><h1>Example Domain</h1><p>Sample content.</p></body></html>'
+    const res = new Response(body, {
+      status: 200,
+      headers: { 'content-type': 'text/html' },
+    })
+    // Make response.url match the request URL so tests can assert on it.
+    Object.defineProperty(res, 'url', { value: url, configurable: true })
+    return res
+  }) as typeof fetch
+})
+
+afterAll(() => {
+  globalThis.fetch = realFetch
+})
+
+describe('WebBrowserTool', () => {
+  test('tool exports and metadata', async () => {
+    const { WebBrowserTool } = await import('../WebBrowserTool.js')
+    expect(WebBrowserTool).toBeDefined()
+    expect(WebBrowserTool.name).toBe('WebBrowser')
+    expect(typeof WebBrowserTool.call).toBe('function')
+    expect(WebBrowserTool.userFacingName()).toBe('Browser')
+    expect(WebBrowserTool.isReadOnly()).toBe(true)
+  })
+
+  test('description reflects browser-lite', async () => {
+    const { WebBrowserTool } = await import('../WebBrowserTool.js')
+    const desc = await WebBrowserTool.description()
+    expect(desc).toContain('HTTP')
+    expect(desc).not.toContain('embedded browser')
+  })
+
+  test('prompt mentions limitations', async () => {
+    const { WebBrowserTool } = await import('../WebBrowserTool.js')
+    const prompt = await WebBrowserTool.prompt()
+    expect(prompt).toContain('Limitations')
+    expect(prompt).toContain('No JavaScript')
+    expect(prompt).toContain('Claude-in-Chrome')
+  })
+
+  test('navigate fetches URL', async () => {
+    const { WebBrowserTool } = await import('../WebBrowserTool.js')
+    const result = await WebBrowserTool.call({
+      url: 'https://example.com',
+    } as any)
+    expect(result.data.title).toBe('Example Domain')
+    expect(result.data.url).toContain('example.com')
+    expect(result.data.content).toContain('Example Domain')
+  }, 15000)
+
+  test('screenshot returns text snapshot', async () => {
+    const { WebBrowserTool } = await import('../WebBrowserTool.js')
+    const result = await WebBrowserTool.call({
+      url: 'https://example.com',
+      action: 'screenshot',
+    } as any)
+    expect(result.data.content).toContain('Text snapshot')
+    expect(result.data.content).toContain('Example Domain')
+  }, 15000)
+
+  test('schema only allows navigate and screenshot', async () => {
+    const { WebBrowserTool } = await import('../WebBrowserTool.js')
+    const schema = WebBrowserTool.inputSchema
+    const parseResult = schema.safeParse({
+      url: 'https://example.com',
+      action: 'click',
+    })
+    expect(parseResult.success).toBe(false)
+  })
+
+  test('invalid URL returns error', async () => {
+    const { WebBrowserTool } = await import('../WebBrowserTool.js')
+    const result = await WebBrowserTool.call({ url: 'not-a-url' } as any)
+    expect(result.data.content).toContain('Failed to fetch')
+  })
+})

packages/builtin-tools/src/tools/WebSearchTool/adapters/index.ts

@@ -16,17 +16,37 @@ export type {
   WebSearchAdapter,
 } from './types.js'
 
+/**
+ * Check if the current session uses a third-party (non-Anthropic) API provider.
+ * These providers don't support Anthropic's server_tools (server-side web search),
+ * so they must fall back to the Bing scraper adapter.
+ */
+function isThirdPartyProvider(): boolean {
+  return !!(
+    process.env.CLAUDE_CODE_USE_OPENAI ||
+    process.env.CLAUDE_CODE_USE_GEMINI ||
+    process.env.CLAUDE_CODE_USE_GROK
+  )
+}
+
 let cachedAdapter: WebSearchAdapter | null = null
 let cachedAdapterKey: 'api' | 'bing' | 'brave' | null = null
 
 export function createAdapter(): WebSearchAdapter {
   const envAdapter = process.env.WEB_SEARCH_ADAPTER
+  // Priority:
+  //   1. Explicit env override (WEB_SEARCH_ADAPTER=api|bing|brave)
+  //   2. Third-party provider (OpenAI/Gemini/Grok) → bing (no server_tools support)
+  //   3. First-party Anthropic API → api (server-side web search + connector_text)
+  //   4. Fallback → bing
   const adapterKey =
     envAdapter === 'api' || envAdapter === 'bing' || envAdapter === 'brave'
       ? envAdapter
-      : isFirstPartyAnthropicBaseUrl()
+      : isThirdPartyProvider()
-        ? 'api'
+        ? 'bing'
-        : 'bing'
+        : isFirstPartyAnthropicBaseUrl()
+          ? 'api'
+          : 'bing'
 
   if (cachedAdapter && cachedAdapterKey === adapterKey) return cachedAdapter
 

packages/builtin-tools/src/tools/WorkflowTool/WorkflowTool.ts

@@ -1,18 +1,358 @@
+import { randomUUID } from 'crypto'
+import { mkdir, readdir, readFile, writeFile } from 'fs/promises'
+import { join, parse } from 'path'
 import { z } from 'zod/v4'
 import type { ToolResultBlockParam } from 'src/Tool.js'
 import { buildTool } from 'src/Tool.js'
 import { truncate } from 'src/utils/format.js'
-import { WORKFLOW_TOOL_NAME } from './constants.js'
+import { safeParseJSON } from 'src/utils/json.js'
+import {
+  WORKFLOW_DIR_NAME,
+  WORKFLOW_FILE_EXTENSIONS,
+  WORKFLOW_TOOL_NAME,
+} from './constants.js'
+
+const WORKFLOW_RUNS_DIR = '.claude/workflow-runs'
 
 const inputSchema = z.object({
   workflow: z.string().describe('Name of the workflow to execute'),
   args: z.string().optional().describe('Arguments to pass to the workflow'),
+  action: z
+    .enum(['start', 'status', 'advance', 'cancel', 'list'])
+    .optional()
+    .describe('Workflow action. Defaults to start.'),
+  run_id: z
+    .string()
+    .optional()
+    .describe('Workflow run id for status, advance, or cancel.'),
 })
 type Input = typeof inputSchema
 type WorkflowInput = z.infer<Input>
 
+type WorkflowStepStatus = 'pending' | 'running' | 'completed' | 'cancelled'
+
+type WorkflowStep = {
+  name: string
+  prompt: string
+  status: WorkflowStepStatus
+  startedAt?: number
+  completedAt?: number
+}
+
+type WorkflowRun = {
+  runId: string
+  workflow: string
+  args?: string
+  status: 'running' | 'completed' | 'cancelled'
+  createdAt: number
+  updatedAt: number
+  currentStepIndex: number
+  steps: WorkflowStep[]
+}
+
 type WorkflowOutput = { output: string }
 
+async function findWorkflowFile(
+  workflowDir: string,
+  workflow: string,
+): Promise<{ path: string; content: string } | null> {
+  for (const ext of WORKFLOW_FILE_EXTENSIONS) {
+    const path = join(workflowDir, `${workflow}${ext}`)
+    try {
+      return { path, content: await readFile(path, 'utf-8') }
+    } catch {
+      // try next
+    }
+  }
+  return null
+}
+
+async function listAvailableWorkflows(workflowDir: string): Promise<string[]> {
+  try {
+    const files = await readdir(workflowDir)
+    return files
+      .filter(f => WORKFLOW_FILE_EXTENSIONS.includes(parse(f).ext.toLowerCase()))
+      .map(f => parse(f).name)
+      .sort()
+  } catch {
+    return []
+  }
+}
+
+function workflowRunPath(cwd: string, runId: string): string {
+  return join(cwd, WORKFLOW_RUNS_DIR, `${runId}.json`)
+}
+
+async function readWorkflowRun(
+  cwd: string,
+  runId: string,
+): Promise<WorkflowRun | null> {
+  try {
+    const parsed = safeParseJSON(
+      await readFile(workflowRunPath(cwd, runId), 'utf-8'),
+      false,
+    ) as Partial<WorkflowRun> | null
+    if (
+      !parsed ||
+      typeof parsed.runId !== 'string' ||
+      typeof parsed.workflow !== 'string' ||
+      !Array.isArray(parsed.steps)
+    ) {
+      return null
+    }
+    return parsed as WorkflowRun
+  } catch {
+    return null
+  }
+}
+
+async function writeWorkflowRun(cwd: string, run: WorkflowRun): Promise<void> {
+  await mkdir(join(cwd, WORKFLOW_RUNS_DIR), { recursive: true })
+  await writeFile(
+    workflowRunPath(cwd, run.runId),
+    JSON.stringify(run, null, 2) + '\n',
+    'utf-8',
+  )
+}
+
+async function listWorkflowRuns(cwd: string): Promise<WorkflowRun[]> {
+  let files: string[]
+  try {
+    files = await readdir(join(cwd, WORKFLOW_RUNS_DIR))
+  } catch {
+    return []
+  }
+  const runs = await Promise.all(
+    files
+      .filter(f => f.endsWith('.json'))
+      .map(f => readWorkflowRun(cwd, f.slice(0, -'.json'.length))),
+  )
+  return runs
+    .filter((run): run is WorkflowRun => run !== null)
+    .sort((a, b) => b.updatedAt - a.updatedAt)
+}
+
+function parseMarkdownSteps(content: string): WorkflowStep[] {
+  const steps: WorkflowStep[] = []
+  for (const rawLine of content.split('\n')) {
+    const line = rawLine.trim()
+    const taskMatch = line.match(/^[-*]\s+\[[ xX]\]\s+(.+)$/)
+    const bulletMatch = line.match(/^[-*]\s+(.+)$/)
+    const numberedMatch = line.match(/^\d+[.)]\s+(.+)$/)
+    const text = taskMatch?.[1] ?? bulletMatch?.[1] ?? numberedMatch?.[1]
+    if (!text) continue
+    steps.push({ name: text.slice(0, 80), prompt: text, status: 'pending' })
+  }
+  return steps
+}
+
+function parseYamlSteps(content: string): WorkflowStep[] {
+  const steps: WorkflowStep[] = []
+  let current: Partial<WorkflowStep> | null = null
+  const flush = () => {
+    if (!current) return
+    const prompt = current.prompt ?? current.name
+    if (current.name && prompt) {
+      steps.push({
+        name: current.name,
+        prompt,
+        status: 'pending',
+      })
+    }
+    current = null
+  }
+
+  for (const rawLine of content.split('\n')) {
+    const line = rawLine.trim()
+    const stepText = line.match(/^-\s+(.+)$/)?.[1]
+    if (stepText) {
+      flush()
+      const inlineName = stepText.match(/^name:\s*(.+)$/)?.[1]
+      current = {
+        name: inlineName ?? stepText,
+        prompt: inlineName ? undefined : stepText,
+      }
+      continue
+    }
+    const name = line.match(/^name:\s*(.+)$/)?.[1]
+    if (name) {
+      if (!current) current = {}
+      current.name = name
+      continue
+    }
+    const prompt = line.match(/^(prompt|run|command):\s*(.+)$/)?.[2]
+    if (prompt) {
+      if (!current) current = {}
+      current.prompt = prompt
+    }
+  }
+  flush()
+  return steps
+}
+
+function parseWorkflowSteps(filePath: string, content: string): WorkflowStep[] {
+  const ext = parse(filePath).ext.toLowerCase()
+  const steps =
+    ext === '.md' ? parseMarkdownSteps(content) : parseYamlSteps(content)
+  if (steps.length > 0) {
+    return steps
+  }
+  return [
+    {
+      name: 'Execute workflow',
+      prompt: content.trim(),
+      status: 'pending',
+    },
+  ]
+}
+
+function formatStep(step: WorkflowStep, index: number): string {
+  return `Step ${index + 1}: ${step.name}\n${step.prompt}`
+}
+
+function formatRunStatus(run: WorkflowRun): string {
+  const lines = [
+    `Workflow run: ${run.runId}`,
+    `Workflow: ${run.workflow}`,
+    `Status: ${run.status}`,
+    `Current step: ${run.steps[run.currentStepIndex]?.name ?? 'none'}`,
+    `Steps: ${run.steps.length}`,
+  ]
+  for (let i = 0; i < run.steps.length; i += 1) {
+    const step = run.steps[i]!
+    lines.push(`  ${i + 1}. [${step.status}] ${step.name}`)
+  }
+  return lines.join('\n')
+}
+
+async function startWorkflow(
+  input: WorkflowInput,
+  cwd: string,
+): Promise<WorkflowOutput> {
+  const workflowDir = join(cwd, WORKFLOW_DIR_NAME)
+  const found = await findWorkflowFile(workflowDir, input.workflow)
+  if (!found) {
+    const available = await listAvailableWorkflows(workflowDir)
+    const hint =
+      available.length > 0
+        ? `\nAvailable workflows: ${available.join(', ')}`
+        : `\nNo workflows found in ${WORKFLOW_DIR_NAME}/. Create .md or .yaml files there.`
+    return { output: `Error: Workflow "${input.workflow}" not found.${hint}` }
+  }
+
+  const steps = parseWorkflowSteps(found.path, found.content)
+  const now = Date.now()
+  steps[0] = { ...steps[0]!, status: 'running', startedAt: now }
+  const run: WorkflowRun = {
+    runId: randomUUID(),
+    workflow: input.workflow,
+    ...(input.args ? { args: input.args } : {}),
+    status: 'running',
+    createdAt: now,
+    updatedAt: now,
+    currentStepIndex: 0,
+    steps,
+  }
+  await writeWorkflowRun(cwd, run)
+
+  const argsSection = input.args ? `\n\nArguments:\n${input.args}` : ''
+  return {
+    output: [
+      `Workflow run started`,
+      `run_id: ${run.runId}`,
+      `workflow: ${run.workflow}`,
+      '',
+      formatStep(steps[0]!, 0),
+      argsSection,
+      '',
+      `When this step is complete, call Workflow with action="advance" and run_id="${run.runId}".`,
+    ].join('\n'),
+  }
+}
+
+async function getRunOrError(
+  cwd: string,
+  runId: string | undefined,
+): Promise<{ run?: WorkflowRun; output?: string }> {
+  if (!runId) return { output: 'Error: run_id is required for this action.' }
+  const run = await readWorkflowRun(cwd, runId)
+  if (!run) return { output: `Error: Workflow run "${runId}" not found.` }
+  return { run }
+}
+
+async function advanceWorkflow(
+  cwd: string,
+  runId: string | undefined,
+): Promise<WorkflowOutput> {
+  const found = await getRunOrError(cwd, runId)
+  if (!found.run) return { output: found.output! }
+  const run = found.run
+  const now = Date.now()
+  const current = run.steps[run.currentStepIndex]
+  if (current && current.status === 'running') {
+    current.status = 'completed'
+    current.completedAt = now
+  }
+  const nextIndex = run.currentStepIndex + 1
+  if (nextIndex >= run.steps.length) {
+    run.status = 'completed'
+    run.updatedAt = now
+    await writeWorkflowRun(cwd, run)
+    return { output: `Workflow completed\nrun_id: ${run.runId}` }
+  }
+  run.currentStepIndex = nextIndex
+  run.steps[nextIndex] = {
+    ...run.steps[nextIndex]!,
+    status: 'running',
+    startedAt: now,
+  }
+  run.updatedAt = now
+  await writeWorkflowRun(cwd, run)
+  return {
+    output: [
+      `Next workflow step`,
+      `run_id: ${run.runId}`,
+      '',
+      formatStep(run.steps[nextIndex]!, nextIndex),
+      '',
+      `When this step is complete, call Workflow with action="advance" and run_id="${run.runId}".`,
+    ].join('\n'),
+  }
+}
+
+async function cancelWorkflow(
+  cwd: string,
+  runId: string | undefined,
+): Promise<WorkflowOutput> {
+  const found = await getRunOrError(cwd, runId)
+  if (!found.run) return { output: found.output! }
+  const run = found.run
+  const now = Date.now()
+  run.status = 'cancelled'
+  run.updatedAt = now
+  for (const step of run.steps) {
+    if (step.status === 'pending' || step.status === 'running') {
+      step.status = 'cancelled'
+    }
+  }
+  await writeWorkflowRun(cwd, run)
+  return { output: `Workflow cancelled\nrun_id: ${run.runId}` }
+}
+
+async function listWorkflowRunsForOutput(cwd: string): Promise<WorkflowOutput> {
+  const runs = await listWorkflowRuns(cwd)
+  if (runs.length === 0) return { output: 'No workflow runs recorded.' }
+  return {
+    output: runs
+      .slice(0, 20)
+      .map(
+        run =>
+          `${run.runId} | ${run.workflow} | ${run.status} | step=${run.steps[run.currentStepIndex]?.name ?? 'none'} | updated=${new Date(run.updatedAt).toLocaleString()}`,
+      )
+      .join('\n'),
+  }
+}
+
 export const WorkflowTool = buildTool({
   name: WORKFLOW_TOOL_NAME,
   searchHint: 'execute user-defined workflow scripts',
@@ -22,21 +362,25 @@ export const WorkflowTool = buildTool({
   inputSchema,
 
   async description() {
-    return 'Execute a user-defined workflow script from .claude/workflows/'
+    return 'Execute and track a user-defined workflow from .claude/workflows/'
   },
   async prompt() {
-    return `Use the Workflow tool to execute user-defined workflow scripts located in .claude/workflows/. Workflows are YAML or Markdown files that define a sequence of steps for common development tasks.
+    return `Use the Workflow tool to run user-defined workflows located in .claude/workflows/. Workflows may be Markdown checklists/lists or YAML files with steps.
 
-Guidelines:
+Actions:
-- Specify the workflow name to execute (must match a file in .claude/workflows/)
+- start (default): create a persisted workflow run and return the first step to execute
-- Optionally pass arguments that the workflow can use
+- advance: mark the current step complete and return the next step
-- Workflows run in the context of the current project`
+- status: inspect a workflow run by run_id
+- cancel: cancel a workflow run
+- list: list recent workflow runs
+
+Workflow run state is persisted in .claude/workflow-runs/.`
   },
   userFacingName() {
     return 'Workflow'
   },
-  isReadOnly() {
+  isReadOnly(input) {
-    return false
+    return input.action === 'status' || input.action === 'list'
   },
   isEnabled() {
     return true
@@ -44,10 +388,10 @@ Guidelines:
 
   renderToolUseMessage(input: Partial<WorkflowInput>) {
     const name = input.workflow ?? 'unknown'
-    if (input.args) {
+    const action = input.action ?? 'start'
-      return `Workflow: ${name} ${input.args}`
+    return input.args
-    }
+      ? `Workflow: ${action} ${name} ${input.args}`
-    return `Workflow: ${name}`
+      : `Workflow: ${action} ${name}`
   },
 
   mapToolResultToToolResultBlockParam(
@@ -61,14 +405,26 @@ Guidelines:
     }
   },
 
-  async call(_input: WorkflowInput, _context, _progress) {
+  async call(input: WorkflowInput) {
-    // Workflow execution is wired by the WORKFLOW_SCRIPTS feature bootstrap.
+    const cwd = process.cwd()
-    // Without it, this tool is not functional.
+    const action = input.action ?? 'start'
-    return {
+    switch (action) {
-      data: {
+      case 'start':
-        output:
+        return { data: await startWorkflow(input, cwd) }
-          'Error: Workflow execution requires the WORKFLOW_SCRIPTS runtime.',
+      case 'status': {
-      },
+        const found = await getRunOrError(cwd, input.run_id)
+        return {
+          data: {
+            output: found.run ? formatRunStatus(found.run) : found.output!,
+          },
+        }
+      }
+      case 'advance':
+        return { data: await advanceWorkflow(cwd, input.run_id) }
+      case 'cancel':
+        return { data: await cancelWorkflow(cwd, input.run_id) }
+      case 'list':
+        return { data: await listWorkflowRunsForOutput(cwd) }
     }
   },
 })

packages/builtin-tools/src/tools/WorkflowTool/__tests__/WorkflowTool.test.ts

@@ -0,0 +1,99 @@
+import { afterEach, beforeEach, describe, expect, test } from 'bun:test'
+import { mkdir, readFile, rm, writeFile } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { WorkflowTool } from '../WorkflowTool'
+
+let cwd: string
+let previousCwd: string
+
+beforeEach(async () => {
+  previousCwd = process.cwd()
+  cwd = join(tmpdir(), `workflow-tool-${Date.now()}-${Math.random().toString(16).slice(2)}`)
+  await mkdir(join(cwd, '.claude', 'workflows'), { recursive: true })
+  process.chdir(cwd)
+})
+
+afterEach(async () => {
+  process.chdir(previousCwd)
+  await rm(cwd, { recursive: true, force: true })
+})
+
+describe('WorkflowTool', () => {
+  test('starts a workflow run and persists step state', async () => {
+    await writeFile(
+      join(cwd, '.claude', 'workflows', 'release.md'),
+      [
+        '# Release',
+        '',
+        '- [ ] Run tests',
+        '- [ ] Build package',
+      ].join('\n'),
+    )
+
+    const result = await WorkflowTool.call({ workflow: 'release' })
+
+    expect(result.data.output).toContain('Workflow run started')
+    expect(result.data.output).toContain('Run tests')
+    const match = result.data.output.match(/run_id: ([a-f0-9-]+)/)
+    expect(match?.[1]).toBeString()
+
+    const raw = await readFile(
+      join(cwd, '.claude', 'workflow-runs', `${match![1]}.json`),
+      'utf-8',
+    )
+    const run = JSON.parse(raw)
+    expect(run.workflow).toBe('release')
+    expect(run.status).toBe('running')
+    expect(run.steps).toHaveLength(2)
+    expect(run.steps[0].status).toBe('running')
+    expect(run.steps[1].status).toBe('pending')
+  })
+
+  test('advances a workflow run through completion', async () => {
+    await writeFile(
+      join(cwd, '.claude', 'workflows', 'audit.yaml'),
+      [
+        'steps:',
+        '  - name: Inspect',
+        '    prompt: Inspect the code',
+        '  - name: Verify',
+        '    prompt: Run focused tests',
+      ].join('\n'),
+    )
+
+    const started = await WorkflowTool.call({ workflow: 'audit' })
+    const runId = started.data.output.match(/run_id: ([a-f0-9-]+)/)![1]!
+
+    const next = await WorkflowTool.call(
+      { workflow: 'audit', action: 'advance', run_id: runId },
+    )
+    expect(next.data.output).toContain('Next workflow step')
+    expect(next.data.output).toContain('Run focused tests')
+
+    const done = await WorkflowTool.call(
+      { workflow: 'audit', action: 'advance', run_id: runId },
+    )
+    expect(done.data.output).toContain('Workflow completed')
+  })
+
+  test('lists and cancels workflow runs', async () => {
+    await writeFile(
+      join(cwd, '.claude', 'workflows', 'cleanup.md'),
+      '- Remove stale files',
+    )
+
+    const started = await WorkflowTool.call({ workflow: 'cleanup' })
+    const runId = started.data.output.match(/run_id: ([a-f0-9-]+)/)![1]!
+
+    const listed = await WorkflowTool.call(
+      { workflow: 'cleanup', action: 'list' },
+    )
+    expect(listed.data.output).toContain(runId)
+
+    const cancelled = await WorkflowTool.call(
+      { workflow: 'cleanup', action: 'cancel', run_id: runId },
+    )
+    expect(cancelled.data.output).toContain('Workflow cancelled')
+  })
+})

packages/builtin-tools/src/tools/shared/__tests__/spawnMultiAgent.test.ts

@@ -0,0 +1,54 @@
+import { afterEach, beforeEach, describe, expect, test } from 'bun:test'
+import { rmSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { spawnTeammate } from '../spawnMultiAgent'
+
+let tempHome: string
+let previousConfigDir: string | undefined
+
+beforeEach(() => {
+  previousConfigDir = process.env.CLAUDE_CONFIG_DIR
+  tempHome = join(tmpdir(), `spawn-multi-agent-${Date.now()}-${Math.random().toString(16).slice(2)}`)
+  process.env.CLAUDE_CONFIG_DIR = tempHome
+})
+
+afterEach(() => {
+  if (previousConfigDir === undefined) {
+    delete process.env.CLAUDE_CONFIG_DIR
+  } else {
+    process.env.CLAUDE_CONFIG_DIR = previousConfigDir
+  }
+  rmSync(tempHome, { recursive: true, force: true })
+})
+
+describe('spawnTeammate', () => {
+  test('fails before spawn side effects when the team file is missing', async () => {
+    let setAppStateCalled = false
+    const context = {
+      getAppState: () => ({
+        teamContext: undefined,
+      }),
+      setAppState: () => {
+        setAppStateCalled = true
+      },
+      options: {
+        agentDefinitions: {
+          activeAgents: [],
+        },
+      },
+    }
+
+    await expect(
+      spawnTeammate(
+        {
+          name: 'worker',
+          prompt: 'do work',
+          team_name: 'missing-team',
+        },
+        context as any,
+      ),
+    ).rejects.toThrow('Team "missing-team" does not exist')
+    expect(setAppStateCalled).toBe(false)
+  })
+})