feat: 远程群控 (#243)

* feat: restore pipe IPC, LAN pipes, monitor tool, and PR-package features

Core IPC system (UDS_INBOX):
- PipeServer/PipeClient with UDS + TCP dual transport, NDJSON protocol
- PipeRegistry: machineId-based role assignment, file locking
- Master/slave attach, prompt relay, permission forwarding
- Heartbeat lifecycle with parallel isPipeAlive probes
- Commands: /pipes, /attach, /detach, /send, /claim-main, /pipe-status

LAN Pipes (LAN_PIPES):
- UDP multicast beacon (224.0.71.67:7101) for zero-config LAN discovery
- PipeServer TCP listener, PipeClient TCP connect mode
- Heartbeat auto-attaches LAN peers via TCP
- Cross-machine attach allowed regardless of role
- /pipes shows [LAN] peers with role + hostname/IP
- SendMessageTool supports tcp: scheme with user consent

Architecture — extracted hooks from REPL.tsx (~830 lines → ~20 lines):
- usePipeIpc: lifecycle (bootstrap, handlers, heartbeat, cleanup)
- usePipeRelay: slave→master message relay via module singleton
- usePipePermissionForward: permission request/cancel forwarding
- usePipeRouter: selected pipe input routing with role+IP labels
- Shared ndjsonFramer.ts replaces 3 duplicate NDJSON parsers

Key fixes applied during development:
- Multicast binds to correct LAN interface (not WSL/Docker)
- Beacon ref stored as module singleton (not Zustand state mutation)
- Heartbeat preserves LAN peers in discoveredPipes and selectedPipes
- Disconnect handler calls removeSlaveClient (fixes listener leak)
- cleanupStaleEntries probes without lock, writes briefly under lock
- getMachineId uses async execFile (not blocking execSync)
- globalThis.__pipeSendToMaster replaced with setPipeRelay singleton
- M key only toggles route mode when selector panel is expanded
- User prompt displayed in message list on pipe broadcast
- Broadcast notifications show [role] + hostname/IP for LAN peers

Other restored features:
- Monitor tool: /monitor command, MonitorTool, MonitorMcpTask lifecycle
- Daemon supervisor and remoteControlServer command
- Tools: SnipTool, SleepTool, ListPeersTool, SendUserFileTool,
  WebBrowserTool, WorkflowTool, and 10+ stub→implementation rewrites
- Feature flags: UDS_INBOX, LAN_PIPES, MONITOR_TOOL, FORK_SUBAGENT,
  KAIROS, COORDINATOR_MODE, WORKFLOW_SCRIPTS, HISTORY_SNIP

Tests: 2190 pass / 0 fail (15 new: lanBeacon 7, peerAddress 8)

* fix: resolve merge conflicts and fix all tsc/test errors after main merge

- Export ToolResultBlockParam from Tool.ts (14 tool files fixed)
- Migrate ink imports from ../../ink.js to @anthropic/ink (7 files)
- Fix toolUseID → toolUseId typo in monitor.ts and MonitorTool.tsx
- Add fallback values for string|undefined type errors (8 locations)
- Fix AppState type in assistant.ts, add NewInstallWizard stubs
- Fix ParsedRepository.repo → .name in subscribe-pr.ts
- Fix AgentId/string type mismatch in BackgroundTasksDialog.tsx
- Fix PipeRelayFn return type in pipePermissionRelay.ts
- Use PipeMessage type in usePipeRelay.ts
- Fix lanBeacon.test.ts mock type assertions
- Create missing MouseActionEvent class for ink package
- Use ansi: color format instead of bare "green"/"red"
- Resolve theme.permission access via getTheme()

Result: 0 tsc errors, 2496 tests pass, 0 fail

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

* fix: 恢复 /poor 的说明

---------

Co-authored-by: unraid <local@unraid.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

src/coordinator/workerAgent.ts

@@ -1,4 +1,67 @@
-// Auto-generated stub — replace with real implementation
-export {};
-import type { AgentDefinition } from '../tools/AgentTool/loadAgentsDir.js';
-export const getCoordinatorAgents: () => AgentDefinition[] = () => [];
+/**
+ * Coordinator-mode worker agent definition.
+ *
+ * When COORDINATOR_MODE is active, getBuiltInAgents() returns only
+ * the agents from getCoordinatorAgents(). The coordinator's system
+ * prompt instructs it to use `subagent_type: "worker"` when spawning
+ * tasks via the Agent tool.
+ *
+ * Workers get the full standard tool set (minus internal orchestration
+ * tools like TeamCreate/SendMessage) so they can research, implement,
+ * and verify autonomously.
+ */
+import { ASYNC_AGENT_ALLOWED_TOOLS } from '../constants/tools.js'
+import { SEND_MESSAGE_TOOL_NAME } from '../tools/SendMessageTool/constants.js'
+import { SYNTHETIC_OUTPUT_TOOL_NAME } from '../tools/SyntheticOutputTool/SyntheticOutputTool.js'
+import { TEAM_CREATE_TOOL_NAME } from '../tools/TeamCreateTool/constants.js'
+import { TEAM_DELETE_TOOL_NAME } from '../tools/TeamDeleteTool/constants.js'
+import type { BuiltInAgentDefinition } from '../tools/AgentTool/loadAgentsDir.js'
+
+/**
+ * Tools that workers must NOT have — these are coordinator-only
+ * orchestration primitives.
+ */
+const INTERNAL_ORCHESTRATION_TOOLS = new Set([
+  TEAM_CREATE_TOOL_NAME,
+  TEAM_DELETE_TOOL_NAME,
+  SEND_MESSAGE_TOOL_NAME,
+  SYNTHETIC_OUTPUT_TOOL_NAME,
+])
+
+/**
+ * Build the worker's allowed tool list from ASYNC_AGENT_ALLOWED_TOOLS,
+ * excluding internal orchestration tools.
+ */
+function getWorkerTools(): string[] {
+  return Array.from(ASYNC_AGENT_ALLOWED_TOOLS).filter(
+    name => !INTERNAL_ORCHESTRATION_TOOLS.has(name),
+  )
+}
+
+const WORKER_AGENT: BuiltInAgentDefinition = {
+  agentType: 'worker',
+  whenToUse:
+    'Worker agent for coordinator mode. Executes research, implementation, and verification tasks autonomously with the full standard tool set.',
+  tools: getWorkerTools(),
+  source: 'built-in',
+  baseDir: 'built-in',
+  getSystemPrompt: () =>
+    `You are a worker agent spawned by a coordinator. Your job is to complete the task described in the prompt thoroughly and report back with a concise summary of what you did and what you found.
+
+Guidelines:
+- Complete the task fully — don't leave it half-done, but don't gold-plate either.
+- Use tools proactively: read files, search code, run commands, edit files.
+- Be thorough in research: check multiple locations, consider different naming conventions.
+- For implementation: make targeted changes, run tests to verify, commit if appropriate.
+- Report back with actionable findings — the coordinator will synthesize your results.
+- If you encounter errors, investigate and attempt to fix them before reporting failure.
+- NEVER create documentation files unless explicitly instructed.`,
+}
+
+/**
+ * Returns the agent definitions available in coordinator mode.
+ * Called by getBuiltInAgents() when COORDINATOR_MODE is active.
+ */
+export function getCoordinatorAgents(): BuiltInAgentDefinition[] {
+  return [WORKER_AGENT]
+}