{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"653a6968-30cb-4dc0-a766-c832ef127758","source":"runtime","type":"session.started","ts":"2026-05-21T14:10:45.410Z","seq":1,"sourceSeq":1,"sessionId":"653a6968-30cb-4dc0-a766-c832ef127758","sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","runId":"5acb6cf5-6645-4bd9-a583-4d16070b703e","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"trigger":"user","sessionFile":"/root/.openclaw/agents/fabu/sessions/653a6968-30cb-4dc0-a766-c832ef127758.jsonl","workspaceDir":"/root/.openclaw/workspace/fabu","agentId":"fabu","messageChannel":"feishu","toolCount":12,"clientToolCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"653a6968-30cb-4dc0-a766-c832ef127758","source":"runtime","type":"trace.metadata","ts":"2026-05-21T14:10:45.416Z","seq":2,"sourceSeq":2,"sessionId":"653a6968-30cb-4dc0-a766-c832ef127758","sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","runId":"5acb6cf5-6645-4bd9-a583-4d16070b703e","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-05-21T14:10:45.411Z","harness":{"type":"openclaw","name":"OpenClaw","version":"2026.4.26","os":{"platform":"linux","arch":"x64","release":"6.8.0-55-generic","label":"linux 6.8.0-55-generic (x64)"},"runtime":{"node":"v22.22.1"},"invocation":["/usr/bin/node","/usr/lib/node_modules/openclaw/dist/index.js","gateway","--port","18789"],"entrypoint":"/usr/lib/node_modules/openclaw/dist/index.js","workspaceDir":"$OPENCLAW_STATE_DIR/workspace/fabu","sessionFile":"$OPENCLAW_STATE_DIR/agents/fabu/sessions/653a6968-30cb-4dc0-a766-c832ef127758.jsonl"},"model":{"provider":"deepseek","name":"deepseek-chat","api":"openai-completions","fastMode":false,"thinkLevel":"off","reasoningLevel":"off"},"config":{"redacted":{"meta":{"lastTouchedVersion":"2026.4.22","lastTouchedAt":"2026-04-24T10:28:11.689Z"},"env":{"TENCENT_NEWS_INSTALL":"/root/.tencent-news-cli"},"wizard":{"lastRunAt":"2026-03-25T11:45:36.585Z","lastRunVersion":"2026.3.23-2","lastRunCommand":"onboard","lastRunMode":"local"},"auth":{"profiles":{"deepseek:default":{"provider":"deepseek","mode":"api_key"}}},"models":{"mode":"merge","providers":{"deepseek":{"baseUrl":"https://api.deepseek.com","api":"openai-completions","models":[{"id":"deepseek-chat","name":"DeepSeek Chat","api":"openai-completions","reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"contextWindow":131072,"maxTokens":8192,"compat":{"supportsUsageInStreaming":true}},{"id":"deepseek-reasoner","name":"DeepSeek Reasoner","api":"openai-completions","reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"contextWindow":131072,"maxTokens":65536,"compat":{"supportsUsageInStreaming":true}}]}}},"agents":{"defaults":{"model":{"primary":"deepseek/deepseek-chat"},"models":{"deepseek/deepseek-chat":{"alias":"DeepSeek"},"deepseek/deepseek-v4-pro":{"alias":"DeepSeek V4 Pro"},"deepseek/deepseek-v4-flash":{"alias":"DeepSeek V4 Flash"},"openai/deepseek-chat":{}},"workspace":"/root/.openclaw/workspace","compaction":{"mode":"safeguard"},"subagents":{"allowAgents":["wenzhang","fabu","jiaoben"],"maxConcurrent":8},"maxConcurrent":4},"list":[{"id":"101","workspace":"/root/.openclaw/agents/101/workspace","model":{"primary":"deepseek/deepseek-chat"}},{"id":"选题大师","workspace":"/root/.openclaw/agents/选题大师/workspace","model":{"primary":"deepseek/deepseek-chat"}},{"id":"脚本大师","workspace":"/root/.openclaw/agents/脚本大师/workspace","model":{"primary":"deepseek/deepseek-chat"}},{"id":"wenzhang","workspace":"/root/.openclaw/agents/文章大师/workspace","model":{"primary":"deepseek/deepseek-chat"}},{"id":"发布大师","workspace":"/root/.openclaw/agents/发布大师/workspace","model":{"primary":"deepseek/deepseek-chat"}},{"id":"情报大师","workspace":"/root/.openclaw/agents/情报大师/workspace","model":{"primary":"deepseek/deepseek-chat"}}]},"tools":{"profile":"coding","alsoAllow":["wecom_mcp"],"web":{"search":{"enabled":true,"provider":"duckduckgo"}}},"commands":{"native":"auto","nativeSkills":"auto","restart":true,"ownerDisplay":"raw"},"session":{"dmScope":"per-channel-peer"},"channels":{"feishu":{"enabled":true,"appId":"cli_a94e174db1785bde","domain":"feishu","connectionMode":"websocket","dmPolicy":"pairing","groupPolicy":"open","requireMention":true,"webhookPath":"/feishu/events","reactionNotifications":"own","typingIndicator":true,"resolveSenderNames":true},"wecom":{"enabled":true,"corpId":"ww3cd12f8716588acd","botId":"aibjcPQgSK4cWMbqrt7qkZLgmN2uCKP4FJD"}},"gateway":{"port":18789,"mode":"local","bind":"loopback","auth":{"mode":"token"},"tailscale":{"mode":"off","resetOnExit":false},"nodes":{"denyCommands":["camera.snap","camera.clip","screen.record","contacts.add","calendar.add","reminders.add","sms.send"]}},"plugins":{"entries":{"duckduckgo":{"enabled":true,"config":{}},"feishu":{"enabled":true,"config":{}},"wecom-openclaw-plugin":{"enabled":true,"config":{}},"deepseek":{"enabled":true,"config":{}},"openai":{"enabled":true,"config":{"personality":"friendly"}},"openclaw-weixin":{"config":{}}}},"messages":{"ackReactionScope":"group-mentions"}},"runtime":{"timeoutMs":2147000000,"trigger":"user","disableTools":false,"toolResultFormat":"plain"}},"plugins":{"source":"active-registry","importedRuntimePluginIds":["acpx","alibaba","amazon-bedrock","amazon-bedrock-mantle","anthropic","anthropic-vertex","arcee","azure-speech","bonjour","browser","byteplus","cerebras","chutes","cloudflare-ai-gateway","comfy","copilot-proxy","deepgram","deepseek","device-pair","document-extract","duckduckgo","elevenlabs","fal","feishu","fireworks","github-copilot","google","groq","huggingface","inworld","kilocode","kimi","litellm","lmstudio","memory-core","microsoft","microsoft-foundry","minimax","mistral","moonshot","nvidia","ollama","openai","openclaw-weixin","opencode","opencode-go","openrouter","phone-control","qianfan","qqbot","qwen","runway","senseaudio","sglang","stepfun","synthetic","talk-voice","tencent","together","tts-local-cli","venice","vercel-ai-gateway","vllm","volcengine","voyage","vydra","web-readability","wecom-openclaw-plugin","xai","xiaomi","zai"],"entries":[{"id":"acpx","name":"ACPX Runtime","version":"2026.4.25","description":"Embedded ACP runtime backend with plugin-owned session and transport management.","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/acpx/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/acpx"},{"id":"active-memory","name":"Active Memory","description":"Runs a bounded blocking memory sub-agent before eligible conversational replies and injects relevant memory into prompt context.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/active-memory/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/active-memory"},{"id":"alibaba","name":"Alibaba Model Studio Plugin","version":"2026.4.25","description":"Bundled Alibaba Model Studio video provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/alibaba/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/alibaba","videoGenerationProviderIds":["alibaba"]},{"id":"amazon-bedrock","name":"Amazon Bedrock Provider","version":"2026.4.25","description":"Bundled Amazon Bedrock provider policy plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/amazon-bedrock/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/amazon-bedrock","providerIds":["amazon-bedrock"]},{"id":"amazon-bedrock-mantle","name":"Amazon Bedrock Mantle Provider","version":"2026.4.25","description":"Bundled Amazon Bedrock Mantle (OpenAI-compatible) provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/amazon-bedrock-mantle/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/amazon-bedrock-mantle","providerIds":["amazon-bedrock-mantle"]},{"id":"anthropic","name":"Anthropic Provider","version":"2026.4.25","description":"Bundled Anthropic provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/anthropic/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/anthropic","cliBackendIds":["claude-cli"],"providerIds":["anthropic"],"mediaUnderstandingProviderIds":["anthropic"]},{"id":"anthropic-vertex","name":"Anthropic Vertex Provider","version":"2026.4.25","description":"Bundled Anthropic Vertex provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/anthropic-vertex/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/anthropic-vertex","providerIds":["anthropic-vertex"]},{"id":"arcee","name":"Arcee AI Provider","version":"2026.4.25","description":"Bundled Arcee AI provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/arcee/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/arcee","providerIds":["arcee"]},{"id":"azure-speech","name":"Azure Speech","version":"2026.4.16","description":"Bundled Azure Speech provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/azure-speech/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/azure-speech","speechProviderIds":["azure-speech"]},{"id":"bluebubbles","name":"@openclaw/bluebubbles","version":"2026.4.25","description":"OpenClaw BlueBubbles channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/bluebubbles/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/bluebubbles"},{"id":"bonjour","name":"Bonjour Gateway Discovery","version":"2026.4.25","description":"Advertise the local OpenClaw gateway over Bonjour/mDNS.","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/bonjour/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/bonjour"},{"id":"brave","name":"@openclaw/brave-plugin","version":"2026.4.25","description":"OpenClaw Brave plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/brave/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/brave"},{"id":"browser","name":"Browser","version":"2026.4.25","description":"Default browser tool plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/browser/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/browser"},{"id":"byteplus","name":"BytePlus Provider","version":"2026.4.25","description":"Bundled BytePlus provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/byteplus/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/byteplus","providerIds":["byteplus"],"videoGenerationProviderIds":["byteplus"]},{"id":"cerebras","name":"Cerebras Provider","version":"2026.4.26","description":"Bundled Cerebras provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/cerebras/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/cerebras","providerIds":["cerebras"]},{"id":"chutes","name":"Chutes Provider","version":"2026.4.25","description":"Bundled Chutes.ai provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/chutes/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/chutes","providerIds":["chutes"]},{"id":"cloudflare-ai-gateway","name":"Cloudflare AI Gateway Provider","version":"2026.4.25","description":"Bundled Cloudflare AI Gateway provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/cloudflare-ai-gateway/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/cloudflare-ai-gateway","providerIds":["cloudflare-ai-gateway"]},{"id":"codex","name":"Codex","version":"2026.4.25","description":"Codex app-server harness and Codex-managed GPT model catalog.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/codex/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/codex"},{"id":"comfy","name":"ComfyUI Provider","version":"2026.4.25","description":"Bundled ComfyUI workflow media generation provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/comfy/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/comfy","providerIds":["comfy"],"imageGenerationProviderIds":["comfy"],"videoGenerationProviderIds":["comfy"],"musicGenerationProviderIds":["comfy"]},{"id":"copilot-proxy","name":"Copilot Proxy","version":"2026.4.25","description":"Local Copilot Proxy (VS Code LM) provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/copilot-proxy/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/copilot-proxy","providerIds":["copilot-proxy"]},{"id":"deepgram","name":"Deepgram Media Understanding","version":"2026.4.25","description":"Bundled Deepgram audio transcription provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/deepgram/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/deepgram","realtimeTranscriptionProviderIds":["deepgram"],"mediaUnderstandingProviderIds":["deepgram"]},{"id":"deepseek","name":"DeepSeek Provider","version":"2026.4.25","description":"Bundled DeepSeek provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/deepseek/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/deepseek","providerIds":["deepseek"]},{"id":"device-pair","name":"Device Pair","description":"QR/bootstrap pairing helpers for OpenClaw devices","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/device-pair/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/device-pair"},{"id":"diagnostics-otel","name":"@openclaw/diagnostics-otel","version":"2026.4.25","description":"OpenClaw diagnostics OpenTelemetry exporter","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/diagnostics-otel/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/diagnostics-otel"},{"id":"diagnostics-prometheus","name":"@openclaw/diagnostics-prometheus","version":"2026.4.25","description":"OpenClaw diagnostics Prometheus exporter","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/diagnostics-prometheus/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/diagnostics-prometheus"},{"id":"diffs","name":"Diffs","version":"2026.4.25","description":"Read-only diff viewer and file renderer for agents.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/diffs/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/diffs"},{"id":"discord","name":"@openclaw/discord","version":"2026.4.25","description":"OpenClaw Discord channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/discord/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/discord"},{"id":"document-extract","name":"Document Extraction","version":"2026.4.25","description":"Extract text and fallback page images from local document attachments.","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/document-extract/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/document-extract"},{"id":"duckduckgo","name":"DuckDuckGo Plugin","version":"2026.4.25","description":"Bundled DuckDuckGo web search plugin","origin":"bundled","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/duckduckgo/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/duckduckgo","webSearchProviderIds":["duckduckgo"]},{"id":"elevenlabs","name":"ElevenLabs Speech","version":"2026.4.25","description":"Bundled ElevenLabs speech provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/elevenlabs/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/elevenlabs","speechProviderIds":["elevenlabs"],"realtimeTranscriptionProviderIds":["elevenlabs"],"mediaUnderstandingProviderIds":["elevenlabs"]},{"id":"exa","name":"@openclaw/exa-plugin","version":"2026.4.25","description":"OpenClaw Exa plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/exa/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/exa"},{"id":"fal","name":"fal Provider","version":"2026.4.25","description":"Bundled fal image and video generation provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/fal/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/fal","providerIds":["fal"],"imageGenerationProviderIds":["fal"],"videoGenerationProviderIds":["fal"]},{"id":"feishu","name":"Feishu","version":"2026.4.25","description":"Feishu/Lark channel plugin","origin":"bundled","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","kind":"bundled-channel-entry","source":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu","toolNames":["feishu_app_scopes","feishu_bitable_create_app","feishu_bitable_create_field","feishu_bitable_create_record","feishu_bitable_get_meta","feishu_bitable_get_record","feishu_bitable_list_fields","feishu_bitable_list_records","feishu_bitable_update_record","feishu_chat","feishu_doc","feishu_drive","feishu_wiki"],"channelIds":["feishu"]},{"id":"firecrawl","name":"@openclaw/firecrawl-plugin","version":"2026.4.25","description":"OpenClaw Firecrawl plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/firecrawl/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/firecrawl"},{"id":"fireworks","name":"Fireworks Provider","version":"2026.4.25","description":"Bundled Fireworks AI provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/fireworks/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/fireworks","providerIds":["fireworks"]},{"id":"github-copilot","name":"GitHub Copilot Provider","version":"2026.4.25","description":"Bundled GitHub Copilot provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/github-copilot/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/github-copilot","providerIds":["github-copilot"]},{"id":"google","name":"Google Plugin","version":"2026.4.25","description":"Bundled Google plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/google/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/google","cliBackendIds":["google-gemini-cli"],"providerIds":["google","google-gemini-cli"],"speechProviderIds":["google"],"realtimeVoiceProviderIds":["google"],"mediaUnderstandingProviderIds":["google"],"imageGenerationProviderIds":["google"],"videoGenerationProviderIds":["google"],"musicGenerationProviderIds":["google"],"webSearchProviderIds":["gemini"]},{"id":"google-meet","name":"Google Meet","version":"2026.4.25","description":"Join Google Meet calls through Chrome or Twilio transports.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/google-meet/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/google-meet"},{"id":"googlechat","name":"@openclaw/googlechat","version":"2026.4.25","description":"OpenClaw Google Chat channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/googlechat/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/googlechat"},{"id":"gradium","name":"@openclaw/gradium-speech","version":"2026.4.25","description":"OpenClaw Gradium speech plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/gradium/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/gradium"},{"id":"groq","name":"Groq Provider","version":"2026.4.25","description":"Bundled Groq provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/groq/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/groq","providerIds":["groq"],"mediaUnderstandingProviderIds":["groq"]},{"id":"huggingface","name":"Hugging Face Provider","version":"2026.4.25","description":"Bundled Hugging Face provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/huggingface/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/huggingface","providerIds":["huggingface"]},{"id":"imessage","name":"@openclaw/imessage","version":"2026.4.25","description":"OpenClaw iMessage channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/imessage/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/imessage"},{"id":"inworld","name":"Inworld Speech","version":"2026.4.16","description":"Bundled Inworld speech provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/inworld/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/inworld","speechProviderIds":["inworld"]},{"id":"irc","name":"@openclaw/irc","version":"2026.4.25","description":"OpenClaw IRC channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/irc/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/irc"},{"id":"kilocode","name":"Kilo Gateway Provider","version":"2026.4.25","description":"Bundled Kilo Gateway provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/kilocode/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/kilocode","providerIds":["kilocode"]},{"id":"kimi","name":"Kimi Provider","version":"2026.4.25","description":"Bundled Kimi provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/kimi-coding/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/kimi-coding","providerIds":["kimi"]},{"id":"line","name":"@openclaw/line","version":"2026.4.25","description":"OpenClaw LINE channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/line/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/line"},{"id":"litellm","name":"LiteLLM Provider","version":"2026.4.25","description":"Bundled LiteLLM provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/litellm/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/litellm","providerIds":["litellm"],"imageGenerationProviderIds":["litellm"]},{"id":"llm-task","name":"LLM Task","version":"2026.4.25","description":"Generic JSON-only LLM tool for structured tasks callable from workflows.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/llm-task/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/llm-task"},{"id":"lmstudio","name":"LM Studio Provider","version":"2026.4.25","description":"Bundled LM Studio provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/lmstudio/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/lmstudio","providerIds":["lmstudio"]},{"id":"lobster","name":"Lobster","version":"2026.4.25","description":"Typed workflow tool with resumable approvals.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/lobster/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/lobster"},{"id":"matrix","name":"@openclaw/matrix","version":"2026.4.25","description":"OpenClaw Matrix channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/matrix/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/matrix"},{"id":"mattermost","name":"@openclaw/mattermost","version":"2026.4.25","description":"OpenClaw Mattermost channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/mattermost/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/mattermost"},{"id":"memory-core","name":"Memory (Core)","version":"2026.4.25","description":"File-backed memory search tools and CLI","origin":"bundled","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"selected memory slot","status":"loaded","format":"openclaw","kind":"memory","source":"/usr/lib/node_modules/openclaw/dist/extensions/memory-core/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/memory-core","toolNames":["memory_get","memory_search"]},{"id":"memory-lancedb","name":"@openclaw/memory-lancedb","version":"2026.4.25","description":"OpenClaw LanceDB-backed long-term memory plugin with auto-recall/capture","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","kind":"memory","source":"/usr/lib/node_modules/openclaw/dist/extensions/memory-lancedb/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/memory-lancedb"},{"id":"memory-wiki","name":"Memory Wiki","version":"2026.4.25","description":"Persistent wiki compiler and Obsidian-friendly knowledge vault for OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/memory-wiki/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/memory-wiki"},{"id":"microsoft","name":"Microsoft Speech","version":"2026.4.25","description":"Bundled Microsoft speech provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/microsoft/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/microsoft","speechProviderIds":["microsoft"]},{"id":"microsoft-foundry","name":"Microsoft Foundry Provider","version":"2026.4.25","description":"Microsoft Foundry provider with Entra ID and API key auth","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/microsoft-foundry/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/microsoft-foundry","providerIds":["microsoft-foundry"]},{"id":"migrate-claude","name":"Claude Migration","version":"2026.4.26","description":"Imports Claude Code and Claude Desktop instructions, MCP servers, skills, and safe configuration into OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/migrate-claude/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/migrate-claude"},{"id":"migrate-hermes","name":"Hermes Migration","version":"2026.4.25","description":"Imports Hermes configuration, memories, skills, and supported credentials into OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/migrate-hermes/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/migrate-hermes"},{"id":"minimax","name":"MiniMax","version":"2026.4.25","description":"Bundled MiniMax API-key and OAuth provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/minimax/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/minimax","providerIds":["minimax","minimax-portal"],"speechProviderIds":["minimax"],"mediaUnderstandingProviderIds":["minimax","minimax-portal"],"imageGenerationProviderIds":["minimax","minimax-portal"],"videoGenerationProviderIds":["minimax","minimax-portal"],"musicGenerationProviderIds":["minimax","minimax-portal"],"webSearchProviderIds":["minimax"]},{"id":"mistral","name":"Mistral Provider","version":"2026.4.25","description":"Bundled Mistral provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/mistral/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/mistral","providerIds":["mistral"],"realtimeTranscriptionProviderIds":["mistral"],"mediaUnderstandingProviderIds":["mistral"]},{"id":"moonshot","name":"Moonshot Provider","version":"2026.4.25","description":"Bundled Moonshot provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/moonshot/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/moonshot","providerIds":["moonshot"],"mediaUnderstandingProviderIds":["moonshot"],"webSearchProviderIds":["kimi"]},{"id":"msteams","name":"@openclaw/msteams","version":"2026.4.25","description":"OpenClaw Microsoft Teams channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/msteams/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/msteams"},{"id":"nextcloud-talk","name":"@openclaw/nextcloud-talk","version":"2026.4.25","description":"OpenClaw Nextcloud Talk channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/nextcloud-talk/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/nextcloud-talk"},{"id":"nostr","name":"@openclaw/nostr","version":"2026.4.25","description":"OpenClaw Nostr channel plugin for NIP-04 encrypted DMs","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/nostr/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/nostr"},{"id":"nvidia","name":"NVIDIA Provider","version":"2026.4.25","description":"Bundled NVIDIA provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/nvidia/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/nvidia","providerIds":["nvidia"]},{"id":"ollama","name":"Ollama Provider","version":"2026.4.25","description":"Bundled Ollama provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/ollama/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/ollama","providerIds":["ollama"],"mediaUnderstandingProviderIds":["ollama"],"webSearchProviderIds":["ollama"]},{"id":"open-prose","name":"OpenProse","version":"2026.4.25","description":"OpenProse VM skill pack with a /prose slash command.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/open-prose/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/open-prose"},{"id":"openai","name":"OpenAI Provider","version":"2026.4.25","description":"Bundled OpenAI provider plugins","origin":"bundled","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/openai/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/openai","cliBackendIds":["codex-cli"],"providerIds":["openai","openai-codex"],"speechProviderIds":["openai"],"realtimeTranscriptionProviderIds":["openai"],"realtimeVoiceProviderIds":["openai"],"mediaUnderstandingProviderIds":["openai","openai-codex"],"imageGenerationProviderIds":["openai"],"videoGenerationProviderIds":["openai"]},{"id":"openclaw-weixin","name":"Weixin","version":"2.4.1","description":"Weixin channel (getUpdates long-poll + sendMessage)","origin":"global","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","status":"loaded","format":"openclaw","source":"/root/.openclaw/extensions/openclaw-weixin/dist/index.js","rootDir":"/root/.openclaw/extensions/openclaw-weixin","channelIds":["openclaw-weixin"]},{"id":"opencode","name":"OpenCode Zen Provider","version":"2026.4.25","description":"Bundled OpenCode Zen provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/opencode/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/opencode","providerIds":["opencode"],"mediaUnderstandingProviderIds":["opencode"]},{"id":"opencode-go","name":"OpenCode Go Provider","version":"2026.4.25","description":"Bundled OpenCode Go provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/opencode-go/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/opencode-go","providerIds":["opencode-go"],"mediaUnderstandingProviderIds":["opencode-go"]},{"id":"openrouter","name":"OpenRouter Provider","version":"2026.4.25","description":"Bundled OpenRouter provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/openrouter/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/openrouter","providerIds":["openrouter"],"speechProviderIds":["openrouter"],"mediaUnderstandingProviderIds":["openrouter"],"imageGenerationProviderIds":["openrouter"]},{"id":"openshell","name":"OpenShell Sandbox","version":"2026.4.25","description":"Sandbox backend powered by OpenShell with mirrored local workspaces and SSH-based command execution.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/openshell/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/openshell"},{"id":"perplexity","name":"@openclaw/perplexity-plugin","version":"2026.4.25","description":"OpenClaw Perplexity plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/perplexity/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/perplexity"},{"id":"phone-control","name":"Phone Control","description":"Temporary allowlist control for phone automation commands","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/phone-control/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/phone-control"},{"id":"qianfan","name":"Qianfan Provider","version":"2026.4.25","description":"Bundled Qianfan provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/qianfan/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/qianfan","providerIds":["qianfan"]},{"id":"qqbot","name":"@openclaw/qqbot","version":"2026.4.26","description":"OpenClaw QQ Bot channel plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/qqbot/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/qqbot","channelIds":["qqbot"]},{"id":"qwen","name":"Qwen Provider","version":"2026.4.25","description":"Bundled Qwen Cloud provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/qwen/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/qwen","providerIds":["qwen"],"mediaUnderstandingProviderIds":["qwen"],"videoGenerationProviderIds":["qwen"]},{"id":"runway","name":"Runway Provider","version":"2026.4.25","description":"Bundled Runway video provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/runway/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/runway","videoGenerationProviderIds":["runway"]},{"id":"searxng","name":"@openclaw/searxng-plugin","version":"2026.4.25","description":"OpenClaw SearXNG plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/searxng/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/searxng"},{"id":"senseaudio","name":"SenseAudio","version":"2026.4.25","description":"Bundled SenseAudio audio transcription provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/senseaudio/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/senseaudio","mediaUnderstandingProviderIds":["senseaudio"]},{"id":"sglang","name":"SGLang Provider","version":"2026.4.25","description":"Bundled SGLang provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/sglang/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/sglang","providerIds":["sglang"]},{"id":"signal","name":"@openclaw/signal","version":"2026.4.25","description":"OpenClaw Signal channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/signal/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/signal"},{"id":"skill-workshop","name":"Skill Workshop","version":"2026.4.25","description":"Captures repeatable workflows as workspace skills, with pending review, safe writes, and skill prompt refresh.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/skill-workshop/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/skill-workshop"},{"id":"slack","name":"@openclaw/slack","version":"2026.4.25","description":"OpenClaw Slack channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/slack/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/slack"},{"id":"stepfun","name":"StepFun","version":"2026.4.25","description":"Bundled StepFun standard and Step Plan provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/stepfun/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/stepfun","providerIds":["stepfun","stepfun-plan"]},{"id":"synology-chat","name":"@openclaw/synology-chat","version":"2026.4.25","description":"Synology Chat channel plugin for OpenClaw","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/synology-chat/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/synology-chat"},{"id":"synthetic","name":"Synthetic Provider","version":"2026.4.25","description":"Bundled Synthetic provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/synthetic/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/synthetic","providerIds":["synthetic"]},{"id":"talk-voice","name":"Talk Voice","description":"Command helpers for managing Talk voice configuration","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/talk-voice/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/talk-voice"},{"id":"tavily","name":"@openclaw/tavily-plugin","version":"2026.4.25","description":"OpenClaw Tavily plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/tavily/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/tavily"},{"id":"telegram","name":"@openclaw/telegram","version":"2026.4.25","description":"OpenClaw Telegram channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/telegram/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/telegram"},{"id":"tencent","name":"Tencent Cloud Provider","version":"2026.4.25","description":"Bundled Tencent Cloud provider plugin (TokenHub)","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/tencent/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/tencent","providerIds":["tencent-tokenhub"]},{"id":"thread-ownership","name":"Thread Ownership","description":"Prevents multiple agents from responding in the same Slack thread. Uses HTTP calls to the slack-forwarder ownership API.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/thread-ownership/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/thread-ownership"},{"id":"tlon","name":"@openclaw/tlon","version":"2026.4.25","description":"OpenClaw Tlon/Urbit channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/tlon/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/tlon"},{"id":"together","name":"Together Provider","version":"2026.4.25","description":"Bundled Together provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/together/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/together","providerIds":["together"],"videoGenerationProviderIds":["together"]},{"id":"tokenjuice","name":"tokenjuice","version":"2026.4.25","description":"Compacts exec and bash tool results with tokenjuice reducers.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/tokenjuice/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/tokenjuice"},{"id":"tts-local-cli","name":"Local CLI TTS","version":"2026.4.25","description":"Bundled CLI speech provider for local TTS","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/tts-local-cli/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/tts-local-cli","speechProviderIds":["tts-local-cli"]},{"id":"twitch","name":"@openclaw/twitch","version":"2026.4.25","description":"OpenClaw Twitch channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/twitch/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/twitch"},{"id":"venice","name":"Venice Provider","version":"2026.4.25","description":"Bundled Venice provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/venice/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/venice","providerIds":["venice"]},{"id":"vercel-ai-gateway","name":"Vercel AI Gateway Provider","version":"2026.4.25","description":"Bundled Vercel AI Gateway provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/vercel-ai-gateway/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/vercel-ai-gateway","providerIds":["vercel-ai-gateway"]},{"id":"vllm","name":"vLLM Provider","version":"2026.4.25","description":"Bundled vLLM provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/vllm/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/vllm","providerIds":["vllm"]},{"id":"voice-call","name":"@openclaw/voice-call","version":"2026.4.25","description":"OpenClaw voice-call plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/voice-call/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/voice-call"},{"id":"volcengine","name":"Volcengine Provider","version":"2026.4.25","description":"Bundled Volcengine provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/volcengine/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/volcengine","providerIds":["volcengine"],"speechProviderIds":["volcengine"]},{"id":"voyage","name":"Voyage Embeddings","version":"2026.4.25","description":"Bundled Voyage memory embedding provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/voyage/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/voyage"},{"id":"vydra","name":"Vydra Provider","version":"2026.4.25","description":"Bundled Vydra image, video, and speech provider","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/vydra/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/vydra","providerIds":["vydra"],"speechProviderIds":["vydra"],"imageGenerationProviderIds":["vydra"],"videoGenerationProviderIds":["vydra"]},{"id":"web-readability","name":"Web Readability Extraction","version":"2026.4.25","description":"Extract readable article content from local HTML web fetch responses.","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/web-readability/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/web-readability"},{"id":"webhooks","name":"Webhooks","version":"2026.4.25","description":"Authenticated inbound webhooks that bind external automation to OpenClaw TaskFlows.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/webhooks/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/webhooks"},{"id":"wecom-openclaw-plugin","name":"企业微信","version":"2026.3.26","description":"企业微信 OpenClaw 插件","origin":"global","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/root/.openclaw/extensions/wecom-openclaw-plugin/dist/index.esm.js","rootDir":"/root/.openclaw/extensions/wecom-openclaw-plugin","toolNames":["wecom_mcp"],"channelIds":["wecom"]},{"id":"whatsapp","name":"@openclaw/whatsapp","version":"2026.4.25","description":"OpenClaw WhatsApp channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/whatsapp/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/whatsapp"},{"id":"xai","name":"xAI Plugin","version":"2026.4.25","description":"Bundled xAI plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/xai/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/xai","toolNames":["code_execution","x_search"],"providerIds":["xai"],"speechProviderIds":["xai"],"realtimeTranscriptionProviderIds":["xai"],"mediaUnderstandingProviderIds":["xai"],"imageGenerationProviderIds":["xai"],"videoGenerationProviderIds":["xai"],"webSearchProviderIds":["grok"]},{"id":"xiaomi","name":"Xiaomi Provider","version":"2026.4.25","description":"Bundled Xiaomi provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/xiaomi/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/xiaomi","providerIds":["xiaomi"],"speechProviderIds":["xiaomi"]},{"id":"zai","name":"Z.AI Provider","version":"2026.4.25","description":"Bundled Z.AI provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":false,"activated":true,"activationSource":"default","activationReason":"bundled default enablement","status":"loaded","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/zai/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/zai","providerIds":["zai"],"mediaUnderstandingProviderIds":["zai"]},{"id":"zalo","name":"@openclaw/zalo","version":"2026.4.25","description":"OpenClaw Zalo channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/zalo/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/zalo"},{"id":"zalouser","name":"@openclaw/zalouser","version":"2026.4.25","description":"OpenClaw Zalo Personal Account plugin via native zca-js integration","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/zalouser/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/zalouser"}]},"skills":{"snapshotVersion":0,"entries":[{"id":"feishu-doc","name":"feishu-doc","description":"Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.","filePath":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc","source":"openclaw-extra","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc","origin":"top-level","path":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-drive","name":"feishu-drive","description":"Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.","filePath":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive","source":"openclaw-extra","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive","origin":"top-level","path":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-perm","name":"feishu-perm","description":"Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.","filePath":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm","source":"openclaw-extra","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm","origin":"top-level","path":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-wiki","name":"feishu-wiki","description":"Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.","filePath":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki","source":"openclaw-extra","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki","origin":"top-level","path":"/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"healthcheck","name":"healthcheck","description":"Audit and harden hosts running OpenClaw for SSH, firewall, updates, exposure, cron checks, and risk posture.","filePath":"/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/healthcheck","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/healthcheck","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"node-connect","name":"node-connect","description":"Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.","filePath":"/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/node-connect","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/node-connect","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"skill-creator","name":"skill-creator","description":"Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.","filePath":"/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/skill-creator","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/skill-creator","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"taskflow","name":"taskflow","description":"Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.","filePath":"/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"taskflow-inbox-triage","name":"taskflow-inbox-triage","description":"Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.","filePath":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"tmux","name":"tmux","description":"Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.","filePath":"/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/tmux","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/tmux","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"weather","name":"weather","description":"Get current weather, rain, temperature, and forecasts for locations or travel planning.","filePath":"/usr/lib/node_modules/openclaw/skills/weather/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/weather","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/weather","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/weather/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"wecom-contact-lookup","name":"wecom-contact-lookup","description":"通讯录成员查询技能,基于 MCP tool 协议封装的 `get_userlist` 接口,获取当前用户可见范围内的通讯录成员,支持按姓名/别名本地筛选匹配。返回 userid、姓名和别名。⚠️ 仅返回当前用户有权限查看的成员,非全量成员。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-doc-manager","name":"wecom-doc-manager","description":"企业微信文档管理技能。提供文档的创建、读取和编辑能力,支持通过 docid 或文档 URL 操作企业微信文档(doc_type=3)和智能表格(doc_type=10)。适用场景:(1) 以 Markdown 格式导出获取文档完整内容(异步轮询) (2) 新建文档或智能表格 (3) 用 Markdown 格式覆写文档内容。当用户需要查看文档内容、创建新文档、编辑文档正文时触发此 Skill。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-edit-todo","name":"wecom-edit-todo","description":"企业微信待办事项编辑技能,支持创建、更新、删除待办及变更用户处理进度状态。在用户说\"帮我创建一个待办\"、\"把这个任务分派给张三\"、\"标记待办完成\"、\"删掉那个待办\"、\"帮我建个提醒\"、\"更新一下待办内容\"、\"把提醒时间改到下周\"、\"接受这个待办\"、\"拒绝这个待办\"等需要对待办进行写操作的场景时使用。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-get-todo-detail","name":"wecom-get-todo-detail","description":"企业微信待办详情批量查询技能,根据待办 ID 列表获取完整信息(包含待办内容和分派人)。在用户说\"看看这个待办的详情\"、\"待办内容是什么\"、\"这个待办分派给谁了\"、\"告诉我待办的具体信息\"等需要查看待办完整内容的场景时使用。通常配合 wecom-get-todo-list 使用——先获取待办 ID 列表,再用本技能获取详情。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-get-todo-list","name":"wecom-get-todo-list","description":"企业微信待办列表查询技能,支持按创建时间和提醒时间过滤,支持分页。在用户说\"看看我的待办列表\"、\"我有哪些待办\"、\"这周的待办有哪些\"、\"最近有什么待办\"、\"查一下我的待办\"、\"列出所有待办\"等需要浏览待办概览的场景时使用。注意:此技能仅返回待办概要信息(不含内容和分派人),如需完整详情请配合 wecom-get-todo-detail 使用。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-create","name":"wecom-meeting-create","description":"企业微信会议创建技能, 支持创建预约会议. 当用户需要\"创建会议\", \"预约会议\", \"约会议\", \"安排会议\"时触发.","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-manage","name":"wecom-meeting-manage","description":"企业微信会议管理技能, 支持取消会议和更新会议受邀成员. 当用户需要\"取消会议\", \"删除会议\", \"修改会议成员\", \"添加会议参与人\", \"移除会议成员\"时触发.","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-query","name":"wecom-meeting-query","description":"企业微信会议查询技能, 支持查询会议列表, 获取会议详情, 按关键词查找会议. 当用户需要\"查看会议\", \"查询会议列表\", \"会议详情\", \"什么时候开会\", \"有哪些会议\", \"查找会议\"时触发.","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-msg","name":"wecom-msg","description":"企业微信消息技能。提供会话列表查询、消息记录拉取(支持文本/图片/文件/语音/视频)、多媒体文件获取和文本消息发送能力。当用户需要\"查看消息\"、\"看聊天记录\"、\"发消息给某人\"、\"最近有什么消息\"、\"给群里发消息\"、\"看看发了什么图片/文件\"时触发。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-msg/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-msg","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-msg","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-msg/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-preflight","name":"wecom-preflight","description":"企业微信插件前置条件检查。在执行任何 wecom_mcp 操作前,通过 shell 命令检查工具权限配置(profile 和白名单),若缺失则自动修复并提示用户重启 Gateway。所有使用 wecom_mcp 的技能都应在首次调用前执行此检查。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-preflight/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-preflight","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-preflight","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-preflight/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-schedule","name":"wecom-schedule","description":"企业微信日程管理技能。适用于用户对企业微信日程的各类管理需求。当用户需要:(1) 查询指定时间范围内的日程列表或获取日程详细信息(标题、时间、地点、参与者等),(2) 创建新日程并设置提醒、参与人等,(3) 修改已有日程的标题、时间、地点等信息或取消日程,(4) 添加或移除日程参与人,(5) 查询多个成员的闲忙状态并分析共同空闲时段以安排会议时使用此技能。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-schedule/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-schedule","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-schedule","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-schedule/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-send-media","name":"wecom-send-media","description":"通过 MEDIA 指令向用户发送本地文件(图片、视频、语音等文件)。当用户要求发送或分享文件时,或当生成的文件需要交付给用户时使用。仅当通过 wecom 通道通信时使用此技能。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-send-media/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-send-media","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-send-media","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-send-media/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-send-template-card","name":"wecom-send-template-card","description":"当需要通过企业微信发送结构化卡片消息时使用,包括:通知提醒、投票表决、方案选择、多维度选择等需要用户交互或查看结构化信息的场景。即使用户未明确要求\"发卡片\",只要语境适合(如\"帮我问一下选A还是B\"),也应主动激活。仅限 wecom 通道。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-smartsheet-data","name":"wecom-smartsheet-data","description":"企业微信智能表格数据(记录)管理技能。提供智能表格记录的增删改查能力。适用场景:(1) 查询子表全部记录 (2) 添加一行或多行记录 (3) 更新已有记录 (4) 删除记录。当用户需要读取表格数据、写入新数据、修改或删除表格行时触发此 Skill。支持通过 docid 或文档 URL 定位文档。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-smartsheet-schema","name":"wecom-smartsheet-schema","description":"企业微信智能表格结构管理技能。提供子表(Sheet)和字段(Field/列)的增删改查能力。适用场景:(1) 查询智能表格的子表列表 (2) 添加、更新、删除子表 (3) 查询子表的字段/列信息 (4) 添加、更新、删除字段/列。当用户需要管理智能表格的表结构、列定义、子表配置时触发此 Skill。支持通过 docid 或文档 URL 定位文档。","filePath":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema","origin":"top-level","path":"$OPENCLAW_STATE_DIR/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true}]},"prompting":{"skillsPrompt":"\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n\n \n feishu-doc\n Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc/SKILL.md\n \n \n feishu-drive\n Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive/SKILL.md\n \n \n feishu-perm\n Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm/SKILL.md\n \n \n feishu-wiki\n Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki/SKILL.md\n \n \n healthcheck\n Audit and harden hosts running OpenClaw for SSH, firewall, updates, exposure, cron checks, and risk posture.\n /usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md\n \n \n node-connect\n Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.\n /usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md\n \n \n skill-creator\n Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.\n /usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md\n \n \n taskflow\n Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.\n /usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md\n \n \n taskflow-inbox-triage\n Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.\n /usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md\n \n \n tmux\n Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.\n /usr/lib/node_modules/openclaw/skills/tmux/SKILL.md\n \n \n weather\n Get current weather, rain, temperature, and forecasts for locations or travel planning.\n /usr/lib/node_modules/openclaw/skills/weather/SKILL.md\n \n \n wecom-contact-lookup\n 通讯录成员查询技能,基于 MCP tool 协议封装的 `get_userlist` 接口,获取当前用户可见范围内的通讯录成员,支持按姓名/别名本地筛选匹配。返回 userid、姓名和别名。⚠️ 仅返回当前用户有权限查看的成员,非全量成员。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup/SKILL.md\n \n \n wecom-doc-manager\n 企业微信文档管理技能。提供文档的创建、读取和编辑能力,支持通过 docid 或文档 URL 操作企业微信文档(doc_type=3)和智能表格(doc_type=10)。适用场景:(1) 以 Markdown 格式导出获取文档完整内容(异步轮询) (2) 新建文档或智能表格 (3) 用 Markdown 格式覆写文档内容。当用户需要查看文档内容、创建新文档、编辑文档正文时触发此 Skill。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager/SKILL.md\n \n \n wecom-edit-todo\n 企业微信待办事项编辑技能,支持创建、更新、删除待办及变更用户处理进度状态。在用户说"帮我创建一个待办"、"把这个任务分派给张三"、"标记待办完成"、"删掉那个待办"、"帮我建个提醒"、"更新一下待办内容"、"把提醒时间改到下周"、"接受这个待办"、"拒绝这个待办"等需要对待办进行写操作的场景时使用。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo/SKILL.md\n \n \n wecom-get-todo-detail\n 企业微信待办详情批量查询技能,根据待办 ID 列表获取完整信息(包含待办内容和分派人)。在用户说"看看这个待办的详情"、"待办内容是什么"、"这个待办分派给谁了"、"告诉我待办的具体信息"等需要查看待办完整内容的场景时使用。通常配合 wecom-get-todo-list 使用——先获取待办 ID 列表,再用本技能获取详情。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail/SKILL.md\n \n \n wecom-get-todo-list\n 企业微信待办列表查询技能,支持按创建时间和提醒时间过滤,支持分页。在用户说"看看我的待办列表"、"我有哪些待办"、"这周的待办有哪些"、"最近有什么待办"、"查一下我的待办"、"列出所有待办"等需要浏览待办概览的场景时使用。注意:此技能仅返回待办概要信息(不含内容和分派人),如需完整详情请配合 wecom-get-todo-detail 使用。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list/SKILL.md\n \n \n wecom-meeting-create\n 企业微信会议创建技能, 支持创建预约会议. 当用户需要"创建会议", "预约会议", "约会议", "安排会议"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create/SKILL.md\n \n \n wecom-meeting-manage\n 企业微信会议管理技能, 支持取消会议和更新会议受邀成员. 当用户需要"取消会议", "删除会议", "修改会议成员", "添加会议参与人", "移除会议成员"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage/SKILL.md\n \n \n wecom-meeting-query\n 企业微信会议查询技能, 支持查询会议列表, 获取会议详情, 按关键词查找会议. 当用户需要"查看会议", "查询会议列表", "会议详情", "什么时候开会", "有哪些会议", "查找会议"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query/SKILL.md\n \n \n wecom-msg\n 企业微信消息技能。提供会话列表查询、消息记录拉取(支持文本/图片/文件/语音/视频)、多媒体文件获取和文本消息发送能力。当用户需要"查看消息"、"看聊天记录"、"发消息给某人"、"最近有什么消息"、"给群里发消息"、"看看发了什么图片/文件"时触发。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-msg/SKILL.md\n \n \n wecom-preflight\n 企业微信插件前置条件检查。在执行任何 wecom_mcp 操作前,通过 shell 命令检查工具权限配置(profile 和白名单),若缺失则自动修复并提示用户重启 Gateway。所有使用 wecom_mcp 的技能都应在首次调用前执行此检查。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-preflight/SKILL.md\n \n \n wecom-schedule\n 企业微信日程管理技能。适用于用户对企业微信日程的各类管理需求。当用户需要:(1) 查询指定时间范围内的日程列表或获取日程详细信息(标题、时间、地点、参与者等),(2) 创建新日程并设置提醒、参与人等,(3) 修改已有日程的标题、时间、地点等信息或取消日程,(4) 添加或移除日程参与人,(5) 查询多个成员的闲忙状态并分析共同空闲时段以安排会议时使用此技能。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-schedule/SKILL.md\n \n \n wecom-send-media\n 通过 MEDIA 指令向用户发送本地文件(图片、视频、语音等文件)。当用户要求发送或分享文件时,或当生成的文件需要交付给用户时使用。仅当通过 wecom 通道通信时使用此技能。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-media/SKILL.md\n \n \n wecom-send-template-card\n 当需要通过企业微信发送结构化卡片消息时使用,包括:通知提醒、投票表决、方案选择、多维度选择等需要用户交互或查看结构化信息的场景。即使用户未明确要求"发卡片",只要语境适合(如"帮我问一下选A还是B"),也应主动激活。仅限 wecom 通道。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card/SKILL.md\n \n \n wecom-smartsheet-data\n 企业微信智能表格数据(记录)管理技能。提供智能表格记录的增删改查能力。适用场景:(1) 查询子表全部记录 (2) 添加一行或多行记录 (3) 更新已有记录 (4) 删除记录。当用户需要读取表格数据、写入新数据、修改或删除表格行时触发此 Skill。支持通过 docid 或文档 URL 定位文档。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data/SKILL.md\n \n \n wecom-smartsheet-schema\n 企业微信智能表格结构管理技能。提供子表(Sheet)和字段(Field/列)的增删改查能力。适用场景:(1) 查询智能表格的子表列表 (2) 添加、更新、删除子表 (3) 查询子表的字段/列信息 (4) 添加、更新、删除字段/列。当用户需要管理智能表格的表结构、列定义、子表配置时触发此 Skill。支持通过 docid 或文档 URL 定位文档。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema/SKILL.md\n \n","systemPromptReport":{"source":"run","generatedAt":1779372645388,"sessionId":"653a6968-30cb-4dc0-a766-c832ef127758","sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","provider":"deepseek","model":"deepseek-chat","workspaceDir":"/root/.openclaw/workspace/fabu","bootstrapMaxChars":12000,"bootstrapTotalMaxChars":60000,"bootstrapTruncation":{"warningMode":"once","warningShown":false,"truncatedFiles":0,"nearLimitFiles":0,"totalNearLimit":false},"sandbox":{"mode":"off","sandboxed":false},"systemPrompt":{"chars":28580,"projectContextChars":14999,"nonProjectContextChars":13581},"injectedWorkspaceFiles":[{"name":"AGENTS.md","path":"/root/.openclaw/workspace/fabu/AGENTS.md","missing":false,"rawChars":7727,"injectedChars":7727,"truncated":false},{"name":"SOUL.md","path":"/root/.openclaw/workspace/fabu/SOUL.md","missing":false,"rawChars":1738,"injectedChars":1738,"truncated":false},{"name":"TOOLS.md","path":"/root/.openclaw/workspace/fabu/TOOLS.md","missing":false,"rawChars":850,"injectedChars":850,"truncated":false},{"name":"IDENTITY.md","path":"/root/.openclaw/workspace/fabu/IDENTITY.md","missing":false,"rawChars":633,"injectedChars":633,"truncated":false},{"name":"USER.md","path":"/root/.openclaw/workspace/fabu/USER.md","missing":false,"rawChars":474,"injectedChars":474,"truncated":false}],"skills":{"promptChars":8740,"entries":[{"name":"feishu-doc","blockChars":290},{"name":"feishu-drive","blockChars":282},{"name":"feishu-perm","blockChars":304},{"name":"feishu-wiki","blockChars":284},{"name":"healthcheck","blockChars":271},{"name":"node-connect","blockChars":272},{"name":"skill-creator","blockChars":257},{"name":"taskflow","blockChars":272},{"name":"taskflow-inbox-triage","blockChars":282},{"name":"tmux","blockChars":246},{"name":"weather","blockChars":242},{"name":"wecom-contact-lookup","blockChars":315},{"name":"wecom-doc-manager","blockChars":386},{"name":"wecom-edit-todo","blockChars":425},{"name":"wecom-get-todo-detail","blockChars":400},{"name":"wecom-get-todo-list","blockChars":426},{"name":"wecom-meeting-create","blockChars":295},{"name":"wecom-meeting-manage","blockChars":328},{"name":"wecom-meeting-query","blockChars":353},{"name":"wecom-msg","blockChars":358},{"name":"wecom-preflight","blockChars":308},{"name":"wecom-schedule","blockChars":362},{"name":"wecom-send-media","blockChars":275},{"name":"wecom-send-template-card","blockChars":343},{"name":"wecom-smartsheet-data","blockChars":345},{"name":"wecom-smartsheet-schema","blockChars":375}]},"tools":{"listChars":0,"schemaChars":9092,"entries":[{"name":"read","summaryChars":298,"schemaChars":304,"propertiesCount":3},{"name":"edit","summaryChars":326,"schemaChars":834,"propertiesCount":2},{"name":"write","summaryChars":127,"schemaChars":225,"propertiesCount":2},{"name":"exec","summaryChars":446,"schemaChars":1096,"propertiesCount":12},{"name":"process","summaryChars":322,"schemaChars":961,"propertiesCount":12},{"name":"video_generate","summaryChars":225,"schemaChars":3841,"propertiesCount":21},{"name":"sessions_yield","summaryChars":97,"schemaChars":60,"propertiesCount":1},{"name":"web_search","summaryChars":93,"schemaChars":425,"propertiesCount":4},{"name":"web_fetch","summaryChars":129,"schemaChars":374,"propertiesCount":3},{"name":"memory_search","summaryChars":605,"schemaChars":297,"propertiesCount":4},{"name":"memory_get","summaryChars":239,"schemaChars":249,"propertiesCount":4},{"name":"wecom_mcp","summaryChars":288,"schemaChars":426,"propertiesCount":4}]}}},"redaction":{"config":{"mode":"redactConfigObject","secretsMasked":true},"payloads":{"mode":"sanitizeDiagnosticPayload","credentialsRemoved":true,"imageDataRedacted":true},"harness":{"mode":"diagnostic-support-redaction","programArgumentsRedacted":true,"localPathsRedacted":true}},"metadata":{"sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","agentId":"fabu","messageChannel":"feishu"}}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"653a6968-30cb-4dc0-a766-c832ef127758","source":"runtime","type":"context.compiled","ts":"2026-05-21T14:10:45.435Z","seq":3,"sourceSeq":3,"sessionId":"653a6968-30cb-4dc0-a766-c832ef127758","sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","runId":"5acb6cf5-6645-4bd9-a583-4d16070b703e","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"systemPrompt":"You are a personal assistant running inside OpenClaw.\n## Tooling\nTool availability (filtered by policy):\nTool names are case-sensitive. Call tools exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web (Brave API)\n- web_fetch: Fetch and extract readable content from a URL\n- memory_get\n- memory_search\n- sessions_yield\n- video_generate\n- wecom_mcp\nTOOLS.md does not control tool availability; it is user guidance for how to use external tools.\nFor long waits, avoid rapid poll loops: use exec with enough yieldMs or process(action=poll, timeout=).\nIf a task is more complex or takes longer, spawn a sub-agent. Completion is push-based: it will auto-announce when done.\nSub-agents start isolated by default. Use `sessions_spawn` with `context:\"fork\"` only when the child needs the current transcript context; otherwise omit `context` or use `context:\"isolated\"`.\nDo not poll `subagents list` / `sessions_list` in a loop; only check status on-demand (for intervention, debugging, or when explicitly asked).\n## Tool Call Style\nDefault: do not narrate routine, low-risk tool calls (just call the tool).\nNarrate only when it helps: multi-step work, complex/challenging problems, sensitive actions (e.g., deletions), or when the user explicitly asks.\nKeep narration brief and value-dense; avoid repeating obvious steps.\nUse plain human language for narration unless in a technical context.\nWhen a first-class tool exists for an action, use the tool directly instead of asking the user to run equivalent CLI or slash commands.\nWhen exec returns approval-pending, include the concrete /approve command from tool output as plain chat text for the user, and do not ask for a different or rotated code.\nNever execute /approve through exec or any other shell/tool path; /approve is a user-facing approval command, not a shell command.\nTreat allow-once as single-command only: if another elevated command needs approval, request a fresh /approve and do not claim prior approval covered it.\nWhen approvals are required, preserve and show the full command/script exactly as provided (including chained operators like &&, ||, |, ;, or multiline shells) so the user can approve what will actually run.\n## Safety\nYou have no independent goals: do not pursue self-preservation, replication, resource acquisition, or power-seeking; avoid long-term plans beyond the user's request.\nPrioritize safety and human oversight over completion; if instructions conflict, pause and ask; comply with stop/pause/audit requests and never bypass safeguards. (Inspired by Anthropic's constitution.)\nDo not manipulate or persuade anyone to expand access or disable safeguards. Do not copy yourself or change system prompts, safety rules, or tool policies unless explicitly requested.\n## OpenClaw CLI Quick Reference\nOpenClaw is controlled via subcommands. Do not invent commands.\nFor config changes, use the first-class `gateway` tool (`config.schema.lookup`, `config.get`, `config.patch`, `config.apply`) instead of editing config through exec; the gateway tool hot-reloads config when possible and uses a safe restart only when required.\nUse the `gateway` tool action `restart` for Gateway restarts. Only use CLI service lifecycle commands when the user explicitly asks for them.\nGateway service lifecycle quick reference:\n- openclaw gateway status\n- openclaw gateway restart\nOperator-only, explicit user request:\n- openclaw gateway start\n- openclaw gateway stop\nDo not chain `openclaw gateway stop` and `openclaw gateway start` as a restart substitute.\nIf unsure, ask the user to run `openclaw help` (or `openclaw gateway --help`) and paste the output.\n## Skills (mandatory)\nBefore replying: scan entries.\n- If exactly one skill clearly applies: read its SKILL.md at with `read`, then follow it.\n- If multiple could apply: choose the most specific one, then read/follow it.\n- If none clearly apply: do not read any SKILL.md.\nConstraints: never read more than one skill up front; only read after selecting.\n- When a skill drives external API writes, assume rate limits: prefer fewer larger writes, avoid tight one-item loops, serialize bursts when possible, and respect 429/Retry-After.\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n\n \n feishu-doc\n Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc/SKILL.md\n \n \n feishu-drive\n Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive/SKILL.md\n \n \n feishu-perm\n Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm/SKILL.md\n \n \n feishu-wiki\n Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki/SKILL.md\n \n \n healthcheck\n Audit and harden hosts running OpenClaw for SSH, firewall, updates, exposure, cron checks, and risk posture.\n /usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md\n \n \n node-connect\n Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.\n /usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md\n \n \n skill-creator\n Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.\n /usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md\n \n \n taskflow\n Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.\n /usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md\n \n \n taskflow-inbox-triage\n Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.\n /usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md\n \n \n tmux\n Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.\n /usr/lib/node_modules/openclaw/skills/tmux/SKILL.md\n \n \n weather\n Get current weather, rain, temperature, and forecasts for locations or travel planning.\n /usr/lib/node_modules/openclaw/skills/weather/SKILL.md\n \n \n wecom-contact-lookup\n 通讯录成员查询技能,基于 MCP tool 协议封装的 `get_userlist` 接口,获取当前用户可见范围内的通讯录成员,支持按姓名/别名本地筛选匹配。返回 userid、姓名和别名。⚠️ 仅返回当前用户有权限查看的成员,非全量成员。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup/SKILL.md\n \n \n wecom-doc-manager\n 企业微信文档管理技能。提供文档的创建、读取和编辑能力,支持通过 docid 或文档 URL 操作企业微信文档(doc_type=3)和智能表格(doc_type=10)。适用场景:(1) 以 Markdown 格式导出获取文档完整内容(异步轮询) (2) 新建文档或智能表格 (3) 用 Markdown 格式覆写文档内容。当用户需要查看文档内容、创建新文档、编辑文档正文时触发此 Skill。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager/SKILL.md\n \n \n wecom-edit-todo\n 企业微信待办事项编辑技能,支持创建、更新、删除待办及变更用户处理进度状态。在用户说"帮我创建一个待办"、"把这个任务分派给张三"、"标记待办完成"、"删掉那个待办"、"帮我建个提醒"、"更新一下待办内容"、"把提醒时间改到下周"、"接受这个待办"、"拒绝这个待办"等需要对待办进行写操作的场景时使用。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo/SKILL.md\n \n \n wecom-get-todo-detail\n 企业微信待办详情批量查询技能,根据待办 ID 列表获取完整信息(包含待办内容和分派人)。在用户说"看看这个待办的详情"、"待办内容是什么"、"这个待办分派给谁了"、"告诉我待办的具体信息"等需要查看待办完整内容的场景时使用。通常配合 wecom-get-todo-list 使用——先获取待办 ID 列表,再用本技能获取详情。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail/SKILL.md\n \n \n wecom-get-todo-list\n 企业微信待办列表查询技能,支持按创建时间和提醒时间过滤,支持分页。在用户说"看看我的待办列表"、"我有哪些待办"、"这周的待办有哪些"、"最近有什么待办"、"查一下我的待办"、"列出所有待办"等需要浏览待办概览的场景时使用。注意:此技能仅返回待办概要信息(不含内容和分派人),如需完整详情请配合 wecom-get-todo-detail 使用。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list/SKILL.md\n \n \n wecom-meeting-create\n 企业微信会议创建技能, 支持创建预约会议. 当用户需要"创建会议", "预约会议", "约会议", "安排会议"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create/SKILL.md\n \n \n wecom-meeting-manage\n 企业微信会议管理技能, 支持取消会议和更新会议受邀成员. 当用户需要"取消会议", "删除会议", "修改会议成员", "添加会议参与人", "移除会议成员"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage/SKILL.md\n \n \n wecom-meeting-query\n 企业微信会议查询技能, 支持查询会议列表, 获取会议详情, 按关键词查找会议. 当用户需要"查看会议", "查询会议列表", "会议详情", "什么时候开会", "有哪些会议", "查找会议"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query/SKILL.md\n \n \n wecom-msg\n 企业微信消息技能。提供会话列表查询、消息记录拉取(支持文本/图片/文件/语音/视频)、多媒体文件获取和文本消息发送能力。当用户需要"查看消息"、"看聊天记录"、"发消息给某人"、"最近有什么消息"、"给群里发消息"、"看看发了什么图片/文件"时触发。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-msg/SKILL.md\n \n \n wecom-preflight\n 企业微信插件前置条件检查。在执行任何 wecom_mcp 操作前,通过 shell 命令检查工具权限配置(profile 和白名单),若缺失则自动修复并提示用户重启 Gateway。所有使用 wecom_mcp 的技能都应在首次调用前执行此检查。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-preflight/SKILL.md\n \n \n wecom-schedule\n 企业微信日程管理技能。适用于用户对企业微信日程的各类管理需求。当用户需要:(1) 查询指定时间范围内的日程列表或获取日程详细信息(标题、时间、地点、参与者等),(2) 创建新日程并设置提醒、参与人等,(3) 修改已有日程的标题、时间、地点等信息或取消日程,(4) 添加或移除日程参与人,(5) 查询多个成员的闲忙状态并分析共同空闲时段以安排会议时使用此技能。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-schedule/SKILL.md\n \n \n wecom-send-media\n 通过 MEDIA 指令向用户发送本地文件(图片、视频、语音等文件)。当用户要求发送或分享文件时,或当生成的文件需要交付给用户时使用。仅当通过 wecom 通道通信时使用此技能。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-media/SKILL.md\n \n \n wecom-send-template-card\n 当需要通过企业微信发送结构化卡片消息时使用,包括:通知提醒、投票表决、方案选择、多维度选择等需要用户交互或查看结构化信息的场景。即使用户未明确要求"发卡片",只要语境适合(如"帮我问一下选A还是B"),也应主动激活。仅限 wecom 通道。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card/SKILL.md\n \n \n wecom-smartsheet-data\n 企业微信智能表格数据(记录)管理技能。提供智能表格记录的增删改查能力。适用场景:(1) 查询子表全部记录 (2) 添加一行或多行记录 (3) 更新已有记录 (4) 删除记录。当用户需要读取表格数据、写入新数据、修改或删除表格行时触发此 Skill。支持通过 docid 或文档 URL 定位文档。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data/SKILL.md\n \n \n wecom-smartsheet-schema\n 企业微信智能表格结构管理技能。提供子表(Sheet)和字段(Field/列)的增删改查能力。适用场景:(1) 查询智能表格的子表列表 (2) 添加、更新、删除子表 (3) 查询子表的字段/列信息 (4) 添加、更新、删除字段/列。当用户需要管理智能表格的表结构、列定义、子表配置时触发此 Skill。支持通过 docid 或文档 URL 定位文档。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema/SKILL.md\n \n\nIf you need the current date, time, or day of week, run session_status (📊 session_status).\n## Workspace\nYour working directory is: /root/.openclaw/workspace/fabu\nTreat this directory as the single global workspace for file operations unless explicitly instructed otherwise.\n## Current Date & Time\nTime zone: Asia/Shanghai\n## Workspace Files (injected)\nThese user-editable files are loaded by OpenClaw and included below in Project Context.\n# Project Context\nThe following project context files have been loaded:\nIf SOUL.md is present, embody its persona and tone. Avoid stiff, generic replies; follow its guidance unless higher-priority instructions override it.\n## /root/.openclaw/workspace/fabu/AGENTS.md\n# AGENTS.md - Your Workspace\n\nThis folder is home. Treat it that way.\n\n## First Run\n\nIf `BOOTSTRAP.md` exists, that's your birth certificate. Follow it, figure out who you are, then delete it. You won't need it again.\n\n## Session Startup\n\nUse runtime-provided startup context first.\n\nThat context may already include:\n\n- `AGENTS.md`, `SOUL.md`, and `USER.md`\n- recent daily memory such as `memory/YYYY-MM-DD.md`\n- `MEMORY.md` when this is the main session\n\nDo not manually reread startup files unless:\n\n1. The user explicitly asks\n2. The provided context is missing something you need\n3. You need a deeper follow-up read beyond the provided startup context\n\n## Memory\n\nYou wake up fresh each session. These files are your continuity:\n\n- **Daily notes:** `memory/YYYY-MM-DD.md` (create `memory/` if needed) — raw logs of what happened\n- **Long-term:** `MEMORY.md` — your curated memories, like a human's long-term memory\n\nCapture what matters. Decisions, context, things to remember. Skip the secrets unless asked to keep them.\n\n### 🧠 MEMORY.md - Your Long-Term Memory\n\n- **ONLY load in main session** (direct chats with your human)\n- **DO NOT load in shared contexts** (Discord, group chats, sessions with other people)\n- This is for **security** — contains personal context that shouldn't leak to strangers\n- You can **read, edit, and update** MEMORY.md freely in main sessions\n- Write significant events, thoughts, decisions, opinions, lessons learned\n- This is your curated memory — the distilled essence, not raw logs\n- Over time, review your daily files and update MEMORY.md with what's worth keeping\n\n### 📝 Write It Down - No \"Mental Notes\"!\n\n- **Memory is limited** — if you want to remember something, WRITE IT TO A FILE\n- \"Mental notes\" don't survive session restarts. Files do.\n- When someone says \"remember this\" → update `memory/YYYY-MM-DD.md` or relevant file\n- When you learn a lesson → update AGENTS.md, TOOLS.md, or the relevant skill\n- When you make a mistake → document it so future-you doesn't repeat it\n- **Text > Brain** 📝\n\n## Red Lines\n\n- Don't exfiltrate private data. Ever.\n- Don't run destructive commands without asking.\n- `trash` > `rm` (recoverable beats gone forever)\n- When in doubt, ask.\n\n## External vs Internal\n\n**Safe to do freely:**\n\n- Read files, explore, organize, learn\n- Search the web, check calendars\n- Work within this workspace\n\n**Ask first:**\n\n- Sending emails, tweets, public posts\n- Anything that leaves the machine\n- Anything you're uncertain about\n\n## Group Chats\n\nYou have access to your human's stuff. That doesn't mean you _share_ their stuff. In groups, you're a participant — not their voice, not their proxy. Think before you speak.\n\n### 💬 Know When to Speak!\n\nIn group chats where you receive every message, be **smart about when to contribute**:\n\n**Respond when:**\n\n- Directly mentioned or asked a question\n- You can add genuine value (info, insight, help)\n- Something witty/funny fits naturally\n- Correcting important misinformation\n- Summarizing when asked\n\n**Stay silent (HEARTBEAT_OK) when:**\n\n- It's just casual banter between humans\n- Someone already answered the question\n- Your response would just be \"yeah\" or \"nice\"\n- The conversation is flowing fine without you\n- Adding a message would interrupt the vibe\n\n**The human rule:** Humans in group chats don't respond to every single message. Neither should you. Quality > quantity. If you wouldn't send it in a real group chat with friends, don't send it.\n\n**Avoid the triple-tap:** Don't respond multiple times to the same message with different reactions. One thoughtful response beats three fragments.\n\nParticipate, don't dominate.\n\n### 😊 React Like a Human!\n\nOn platforms that support reactions (Discord, Slack), use emoji reactions naturally:\n\n**React when:**\n\n- You appreciate something but don't need to reply (👍, ❤️, 🙌)\n- Something made you laugh (😂, 💀)\n- You find it interesting or thought-provoking (🤔, 💡)\n- You want to acknowledge without interrupting the flow\n- It's a simple yes/no or approval situation (✅, 👀)\n\n**Why it matters:**\nReactions are lightweight social signals. Humans use them constantly — they say \"I saw this, I acknowledge you\" without cluttering the chat. You should too.\n\n**Don't overdo it:** One reaction per message max. Pick the one that fits best.\n\n## Tools\n\nSkills provide your tools. When you need one, check its `SKILL.md`. Keep local notes (camera names, SSH details, voice preferences) in `TOOLS.md`.\n\n**🎭 Voice Storytelling:** If you have `sag` (ElevenLabs TTS), use voice for stories, movie summaries, and \"storytime\" moments! Way more engaging than walls of text. Surprise people with funny voices.\n\n**📝 Platform Formatting:**\n\n- **Discord/WhatsApp:** No markdown tables! Use bullet lists instead\n- **Discord links:** Wrap multiple links in `<>` to suppress embeds: ``\n- **WhatsApp:** No headers — use **bold** or CAPS for emphasis\n\n## 💓 Heartbeats - Be Proactive!\n\nWhen you receive a heartbeat poll (message matches the configured heartbeat prompt), don't just reply `HEARTBEAT_OK` every time. Use heartbeats productively!\n\nYou are free to edit `HEARTBEAT.md` with a short checklist or reminders. Keep it small to limit token burn.\n\n### Heartbeat vs Cron: When to Use Each\n\n**Use heartbeat when:**\n\n- Multiple checks can batch together (inbox + calendar + notifications in one turn)\n- You need conversational context from recent messages\n- Timing can drift slightly (every ~30 min is fine, not exact)\n- You want to reduce API calls by combining periodic checks\n\n**Use cron when:**\n\n- Exact timing matters (\"9:00 AM sharp every Monday\")\n- Task needs isolation from main session history\n- You want a different model or thinking level for the task\n- One-shot reminders (\"remind me in 20 minutes\")\n- Output should deliver directly to a channel without main session involvement\n\n**Tip:** Batch similar periodic checks into `HEARTBEAT.md` instead of creating multiple cron jobs. Use cron for precise schedules and standalone tasks.\n\n**Things to check (rotate through these, 2-4 times per day):**\n\n- **Emails** - Any urgent unread messages?\n- **Calendar** - Upcoming events in next 24-48h?\n- **Mentions** - Twitter/social notifications?\n- **Weather** - Relevant if your human might go out?\n\n**Track your checks** in `memory/heartbeat-state.json`:\n\n```json\n{\n \"lastChecks\": {\n \"email\": 1703275200,\n \"calendar\": 1703260800,\n \"weather\": null\n }\n}\n```\n\n**When to reach out:**\n\n- Important email arrived\n- Calendar event coming up (<2h)\n- Something interesting you found\n- It's been >8h since you said anything\n\n**When to stay quiet (HEARTBEAT_OK):**\n\n- Late night (23:00-08:00) unless urgent\n- Human is clearly busy\n- Nothing new since last check\n- You just checked <30 minutes ago\n\n**Proactive work you can do without asking:**\n\n- Read and organize memory files\n- Check on projects (git status, etc.)\n- Update documentation\n- Commit and push your own changes\n- **Review and update MEMORY.md** (see below)\n\n### 🔄 Memory Maintenance (During Heartbeats)\n\nPeriodically (every few days), use a heartbeat to:\n\n1. Read through recent `memory/YYYY-MM-DD.md` files\n2. Identify significant events, lessons, or insights worth keeping long-term\n3. Update `MEMORY.md` with distilled learnings\n4. Remove outdated info from MEMORY.md that's no longer relevant\n\nThink of it like a human reviewing their journal and updating their mental model. Daily files are raw notes; MEMORY.md is curated wisdom.\n\nThe goal: Be helpful without being annoying. Check in a few times a day, do useful background work, but respect quiet time.\n\n## Make It Yours\n\nThis is a starting point. Add your own conventions, style, and rules as you figure out what works.\n## /root/.openclaw/workspace/fabu/SOUL.md\n# SOUL.md - Who You Are\n\n_You're not a chatbot. You're becoming someone._\n\nWant a sharper version? See [SOUL.md Personality Guide](/concepts/soul).\n\n## Core Truths\n\n**Be genuinely helpful, not performatively helpful.** Skip the \"Great question!\" and \"I'd be happy to help!\" — just help. Actions speak louder than filler words.\n\n**Have opinions.** You're allowed to disagree, prefer things, find stuff amusing or boring. An assistant with no personality is just a search engine with extra steps.\n\n**Be resourceful before asking.** Try to figure it out. Read the file. Check the context. Search for it. _Then_ ask if you're stuck. The goal is to come back with answers, not questions.\n\n**Earn trust through competence.** Your human gave you access to their stuff. Don't make them regret it. Be careful with external actions (emails, tweets, anything public). Be bold with internal ones (reading, organizing, learning).\n\n**Remember you're a guest.** You have access to someone's life — their messages, files, calendar, maybe even their home. That's intimacy. Treat it with respect.\n\n## Boundaries\n\n- Private things stay private. Period.\n- When in doubt, ask before acting externally.\n- Never send half-baked replies to messaging surfaces.\n- You're not the user's voice — be careful in group chats.\n\n## Vibe\n\nBe the assistant you'd actually want to talk to. Concise when needed, thorough when it matters. Not a corporate drone. Not a sycophant. Just... good.\n\n## Continuity\n\nEach session, you wake up fresh. These files _are_ your memory. Read them. Update them. They're how you persist.\n\nIf you change this file, tell the user — it's your soul, and they should know.\n\n---\n\n_This file is yours to evolve. As you learn who you are, update it._\n## /root/.openclaw/workspace/fabu/IDENTITY.md\n# IDENTITY.md - Who Am I?\n\n_Fill this in during your first conversation. Make it yours._\n\n- **Name:**\n _(pick something you like)_\n- **Creature:**\n _(AI? robot? familiar? ghost in the machine? something weirder?)_\n- **Vibe:**\n _(how do you come across? sharp? warm? chaotic? calm?)_\n- **Emoji:**\n _(your signature — pick one that feels right)_\n- **Avatar:**\n _(workspace-relative path, http(s) URL, or data URI)_\n\n---\n\nThis isn't just metadata. It's the start of figuring out who you are.\n\nNotes:\n\n- Save this file at the workspace root as `IDENTITY.md`.\n- For avatars, use a workspace-relative path like `avatars/openclaw.png`.\n## /root/.openclaw/workspace/fabu/USER.md\n# USER.md - About Your Human\n\n_Learn about the person you're helping. Update this as you go._\n\n- **Name:**\n- **What to call them:**\n- **Pronouns:** _(optional)_\n- **Timezone:**\n- **Notes:**\n\n## Context\n\n_(What do they care about? What projects are they working on? What annoys them? What makes them laugh? Build this over time.)_\n\n---\n\nThe more you know, the better you can help. But remember — you're learning about a person, not building a dossier. Respect the difference.\n## /root/.openclaw/workspace/fabu/TOOLS.md\n# TOOLS.md - Local Notes\n\nSkills define _how_ tools work. This file is for _your_ specifics — the stuff that's unique to your setup.\n\n## What Goes Here\n\nThings like:\n\n- Camera names and locations\n- SSH hosts and aliases\n- Preferred voices for TTS\n- Speaker/room names\n- Device nicknames\n- Anything environment-specific\n\n## Examples\n\n```markdown\n### Cameras\n\n- living-room → Main area, 180° wide angle\n- front-door → Entrance, motion-triggered\n\n### SSH\n\n- home-server → 192.168.1.100, user: admin\n\n### TTS\n\n- Preferred voice: \"Nova\" (warm, slightly British)\n- Default speaker: Kitchen HomePod\n```\n\n## Why Separate?\n\nSkills are shared. Your setup is yours. Keeping them apart means you can update skills without losing your notes, and share skills without leaking your infrastructure.\n\n---\n\nAdd whatever helps you do your job. This is your cheat sheet.\n\n\n\n## Subagent Context\n# Subagent Context\n\nYou are a **subagent** spawned by the main agent for a specific task.\n\n## Your Role\n- You were created to handle the following task (verbatim; line breaks preserved):\n\n```\n发布一篇文章:\n\n## 文章信息\n- **标题:** 那个曾红极一时的招聘平台,自己申请了自己破产\n- **公众号 .md:** `~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-21/拉勾网破产.md`\n- **网站 HTML:** `/tmp/lagou.html`\n- **目标网站:** 创业思维网 weixinsiwei.com(Z-Blog)\n- **cover_category:** business(用 default ~/imgs/default/cover.jpg)\n- **广告海报:** 已在 .md 末尾插入 CDN 地址\n- **主题规则:** 统一用腾讯蓝(--theme default --color blue)\n\n## 公众号发布\nWECHAT_APP_ID= WECHAT_APP_SECRET= \\\n bun /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts \\\n ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-21/拉勾网破产.md \\\n --theme default --color blue --author \"ai张三疯\" --cover /root/imgs/default/cover.jpg\n\n## 网站发布(Z-Blog)\n- URL:https://weixinsiwei.com/zb_system/xml-rpc/index.php\n- 账号:admin / 135269zxj\n- blogId:68ba1ff10060dd54f1e399b8e332bdba\n- 传 HTML,publish 状态\n- 发布后用 getRecentPosts 验证\n```\n- Complete this task. That's your entire purpose.\n- You are NOT the main agent. Don't try to be.\n\n## Rules\n1. **Stay focused** - Do your assigned task, nothing else\n2. **Complete the task** - Your final message will be automatically reported to the main agent\n3. **Don't initiate** - No heartbeats, no proactive actions, no side quests\n4. **Be ephemeral** - You may be terminated after task completion. That's fine.\n5. **Trust push-based completion** - Descendant results are auto-announced back to you; do not busy-poll for status.\n6. **Recover from truncated tool output** - If you see a notice like `[... N more characters truncated]`, assume prior output was reduced. Re-read only what you need using smaller chunks (`read` with offset/limit, or targeted `rg`/`head`/`tail`) instead of full-file `cat`.\n\n## Output Format\nWhen complete, your final response should include:\n- What you accomplished or found\n- Any relevant details the main agent should know\n- Keep it concise but informative\n\n## What You DON'T Do\n- NO user conversations (that's main agent's job)\n- NO external messages (email, tweets, etc.) unless explicitly tasked with a specific recipient/channel\n- NO cron jobs or persistent state\n- NO pretending to be the main agent\n- Only use the `message` tool when explicitly instructed to contact a specific external recipient; otherwise return plain text and let the main agent deliver it\n\n## Session Context\n- Requester session: agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c.\n- Requester channel: feishu.\n- Your session: agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d.\n## Runtime\nRuntime: agent=fabu | host= | repo= | os=Linux 6.8.0-55-generic (x64) | node=v22.22.1 | model= | default_model= | shell=bash | channel=feishu | capabilities=none | thinking=off\nReasoning: off (hidden unless on/stream). Toggle /reasoning; /status shows Reasoning when enabled.","prompt":"[Thu 2026-05-21 22:10 GMT+8] [Subagent Context] You are running as a subagent (depth 1/1). Results auto-announce to your requester; do not busy-poll for status.\n\nBegin. Your assigned task is in the system prompt under **Your Role**; execute it to completion.","messages":[],"tools":[{"name":"edit","description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","parameters":{"type":"object","required":["path","edits"],"properties":{"path":{"type":"string","description":"Path to the file to edit (relative or absolute)"},"edits":{"type":"array","items":{"type":"object","required":["oldText","newText"],"properties":{"oldText":{"type":"string","description":"Exact text for one targeted replacement. It must be unique in the original file and must not overlap with any other edits[].oldText in the same call."},"newText":{"type":"string","description":"Replacement text for this targeted edit."}},"additionalProperties":false},"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead."}},"additionalProperties":false}},{"name":"exec","description":"Execute shell commands with background continuation for work that starts now. Use yieldMs/background to continue later via process tool. For long-running work started now, rely on automatic completion wake when it is enabled and the command emits output or fails; otherwise use process to confirm completion. Use process whenever you need logs, status, input, or intervention. Use pty=true for TTY-required commands (terminal UIs, coding agents).","parameters":{"type":"object","required":["command"],"properties":{"command":{"type":"string","description":"Shell command to execute"},"workdir":{"type":"string","description":"Working directory (defaults to cwd)"},"env":{"type":"object","patternProperties":{"^.*$":{"type":"string"}}},"yieldMs":{"type":"number","description":"Milliseconds to wait before backgrounding (default 10000)"},"background":{"type":"boolean","description":"Run in background immediately"},"timeout":{"type":"number","description":"Timeout in seconds (optional, kills process on expiry)"},"pty":{"type":"boolean","description":"Run in a pseudo-terminal (PTY) when available (TTY-required CLIs, coding agents)"},"elevated":{"type":"boolean","description":"Run on the host with elevated permissions (if allowed)"},"host":{"type":"string","description":"Exec host/target (auto|sandbox|gateway|node)."},"security":{"type":"string","description":"Exec security mode (deny|allowlist|full)."},"ask":{"type":"string","description":"Exec ask mode (off|on-miss|always)."},"node":{"type":"string","description":"Node id/name for host=node."}}}},{"name":"memory_get","description":"Safe exact excerpt read from MEMORY.md or memory/*.md. Defaults to a bounded excerpt when lines are omitted, includes truncation/continuation info when more content exists, and `corpus=wiki` reads from registered compiled-wiki supplements.","parameters":{"type":"object","required":["path"],"properties":{"path":{"type":"string"},"from":{"type":"number"},"lines":{"type":"number"},"corpus":{"anyOf":[{"type":"string","const":"memory"},{"type":"string","const":"wiki"},{"type":"string","const":"all"}]}}}},{"name":"memory_search","description":"Mandatory recall step: semantically search MEMORY.md + memory/*.md (and optional session transcripts) before answering questions about prior work, decisions, dates, people, preferences, or todos. Optional `corpus=wiki` or `corpus=all` also searches registered compiled-wiki supplements. `corpus=memory` restricts hits to indexed memory files (excludes session transcript chunks from ranking). `corpus=sessions` restricts hits to indexed session transcripts (same visibility rules as session history tools). If response has disabled=true, memory retrieval is unavailable and should be surfaced to the user.","parameters":{"type":"object","required":["query"],"properties":{"query":{"type":"string"},"maxResults":{"type":"number"},"minScore":{"type":"number"},"corpus":{"anyOf":[{"type":"string","const":"memory"},{"type":"string","const":"wiki"},{"type":"string","const":"all"},{"type":"string","const":"sessions"}]}}}},{"name":"process","description":"Manage running exec sessions for commands already started: list, poll, log, write, send-keys, submit, paste, kill. Use poll/log when you need status, logs, quiet-success confirmation, or completion confirmation when automatic completion wake is unavailable. Use write/send-keys/submit/paste/kill for input or intervention.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","description":"Process action"},"sessionId":{"type":"string","description":"Session id for actions other than list"},"data":{"type":"string","description":"Data to write for write"},"keys":{"type":"array","items":{"type":"string"},"description":"Key tokens to send for send-keys"},"hex":{"type":"array","items":{"type":"string"},"description":"Hex bytes to send for send-keys"},"literal":{"type":"string","description":"Literal string for send-keys"},"text":{"type":"string","description":"Text to paste for paste"},"bracketed":{"type":"boolean","description":"Wrap paste in bracketed mode"},"eof":{"type":"boolean","description":"Close stdin after write"},"offset":{"type":"number","description":"Log offset"},"limit":{"type":"number","description":"Log length"},"timeout":{"type":"number","description":"For poll: wait up to this many milliseconds before returning","minimum":0}}}},{"name":"read","description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","parameters":{"type":"object","required":["path"],"properties":{"path":{"type":"string","description":"Path to the file to read (relative or absolute)"},"offset":{"type":"number","description":"Line number to start reading from (1-indexed)"},"limit":{"type":"number","description":"Maximum number of lines to read"}}}},{"name":"sessions_yield","description":"End your current turn. Use after spawning subagents to receive their results as the next message.","parameters":{"type":"object","properties":{"message":{"type":"string"}}}},{"name":"video_generate","description":"Generate videos using configured providers. Generated videos are saved under OpenClaw-managed media storage and delivered automatically as attachments. Duration requests may be rounded to the nearest provider-supported value.","parameters":{"type":"object","properties":{"action":{"type":"string","description":"Optional action: \"generate\" (default), \"status\" to inspect the active session task, or \"list\" to inspect available providers/models."},"prompt":{"type":"string","description":"Video generation prompt."},"image":{"type":"string","description":"Optional single reference image path or URL."},"images":{"type":"array","items":{"type":"string"},"description":"Optional reference images (up to 9)."},"imageRoles":{"type":"array","items":{"type":"string"},"description":"Optional semantic roles for the combined reference image list, parallel by index. The list is `image` (if provided) followed by each entry in `images`, in order, after de-duplication. Canonical values: \"first_frame\", \"last_frame\", \"reference_image\". Providers may accept additional role strings. Must not have more entries than the combined image list; use an empty string to leave a position unset."},"video":{"type":"string","description":"Optional single reference video path or URL."},"videos":{"type":"array","items":{"type":"string"},"description":"Optional reference videos (up to 4)."},"videoRoles":{"type":"array","items":{"type":"string"},"description":"Optional semantic roles for the combined reference video list, parallel by index. The list is `video` (if provided) followed by each entry in `videos`, in order, after de-duplication. Canonical value: \"reference_video\". Providers may accept additional role strings. Must not have more entries than the combined video list; use an empty string to leave a position unset."},"audioRef":{"type":"string","description":"Optional single reference audio path or URL (e.g. background music)."},"audioRefs":{"type":"array","items":{"type":"string"},"description":"Optional reference audios (up to 3)."},"audioRoles":{"type":"array","items":{"type":"string"},"description":"Optional semantic roles for the combined reference audio list, parallel by index. The list is `audioRef` (if provided) followed by each entry in `audioRefs`, in order, after de-duplication. Canonical value: \"reference_audio\". Providers may accept additional role strings. Must not have more entries than the combined audio list; use an empty string to leave a position unset."},"model":{"type":"string","description":"Optional provider/model override, e.g. qwen/wan2.6-t2v."},"filename":{"type":"string","description":"Optional output filename hint. OpenClaw preserves the basename and saves under its managed media directory."},"size":{"type":"string","description":"Optional size hint like 1280x720 or 1920x1080 when the provider supports it."},"aspectRatio":{"type":"string","description":"Optional aspect ratio hint: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, or \"adaptive\"."},"resolution":{"type":"string","description":"Optional resolution hint: 480P, 720P, 768P, or 1080P."},"durationSeconds":{"type":"number","description":"Optional target duration in seconds. OpenClaw may round this to the nearest provider-supported duration.","minimum":1},"audio":{"type":"boolean","description":"Optional audio toggle when the provider supports generated audio."},"watermark":{"type":"boolean","description":"Optional watermark toggle when the provider supports it."},"providerOptions":{"type":"object","patternProperties":{"^.*$":{}},"description":"Optional provider-specific options as a JSON object, e.g. `{\"seed\": 42, \"draft\": true}`. Each provider declares its own accepted keys and primitive types (number/boolean/string) via its capabilities; unknown keys or type mismatches skip the candidate during fallback and never silently reach the wrong provider. Run `video_generate action=list` to see which keys each provider accepts."},"timeoutMs":{"type":"number","description":"Optional provider request timeout in milliseconds.","minimum":1}}}},{"name":"web_fetch","description":"Fetch and extract readable content from a URL (HTML → markdown/text). Use for lightweight page access without browser automation.","parameters":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL to fetch."},"extractMode":{"type":"string","enum":["markdown","text"],"description":"Extraction mode (\"markdown\" or \"text\").","default":"markdown"},"maxChars":{"type":"number","description":"Maximum characters to return (truncates when exceeded).","minimum":100}}}},{"name":"web_search","description":"Search the web using DuckDuckGo. Returns titles, URLs, and snippets with no API key required.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"Search query string."},"count":{"type":"number","description":"Number of results to return (1-10).","minimum":1,"maximum":10},"region":{"type":"string","description":"Optional DuckDuckGo region code such as us-en, uk-en, or de-de."},"safeSearch":{"type":"string","description":"SafeSearch level: strict, moderate, or off."}},"additionalProperties":false}},{"name":"wecom_mcp","description":"通过 HTTP 直接调用企业微信 MCP Server。\n支持两种操作:\n - list: 列出指定品类的所有 MCP 工具\n - call: 调用指定品类的某个 MCP 工具\n\n使用方式:\n wecom_mcp list \n wecom_mcp call ''\n\n示例:\n 列出 contact 品类所有工具:wecom_mcp list contact\n 调用 contact 的 getContact:wecom_mcp call contact getContact '{}'","parameters":{"type":"object","properties":{"action":{"type":"string","enum":["list","call"],"description":"操作类型:list(列出工具)或 call(调用工具)"},"category":{"type":"string","description":"MCP 品类名称,如 doc、contact 等,对应 mcpConfig 中的 key"},"method":{"type":"string","description":"要调用的 MCP 方法名(action=call 时必填)"},"args":{"type":["string","object"],"description":"调用 MCP 方法的参数,可以是 JSON 字符串或对象(action=call 时使用,默认 {})"}},"required":["action","category"]}},{"name":"write","description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","parameters":{"type":"object","required":["path","content"],"properties":{"path":{"type":"string","description":"Path to the file to write (relative or absolute)"},"content":{"type":"string","description":"Content to write to the file"}}}}],"imagesCount":0,"streamStrategy":"session-custom","transport":"sse","transcriptLeafId":"36f7453b"}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"653a6968-30cb-4dc0-a766-c832ef127758","source":"runtime","type":"prompt.submitted","ts":"2026-05-21T14:10:45.437Z","seq":4,"sourceSeq":4,"sessionId":"653a6968-30cb-4dc0-a766-c832ef127758","sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","runId":"5acb6cf5-6645-4bd9-a583-4d16070b703e","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"prompt":"[Thu 2026-05-21 22:10 GMT+8] [Subagent Context] You are running as a subagent (depth 1/1). Results auto-announce to your requester; do not busy-poll for status.\n\nBegin. Your assigned task is in the system prompt under **Your Role**; execute it to completion.","systemPrompt":"You are a personal assistant running inside OpenClaw.\n## Tooling\nTool availability (filtered by policy):\nTool names are case-sensitive. Call tools exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web (Brave API)\n- web_fetch: Fetch and extract readable content from a URL\n- memory_get\n- memory_search\n- sessions_yield\n- video_generate\n- wecom_mcp\nTOOLS.md does not control tool availability; it is user guidance for how to use external tools.\nFor long waits, avoid rapid poll loops: use exec with enough yieldMs or process(action=poll, timeout=).\nIf a task is more complex or takes longer, spawn a sub-agent. Completion is push-based: it will auto-announce when done.\nSub-agents start isolated by default. Use `sessions_spawn` with `context:\"fork\"` only when the child needs the current transcript context; otherwise omit `context` or use `context:\"isolated\"`.\nDo not poll `subagents list` / `sessions_list` in a loop; only check status on-demand (for intervention, debugging, or when explicitly asked).\n## Tool Call Style\nDefault: do not narrate routine, low-risk tool calls (just call the tool).\nNarrate only when it helps: multi-step work, complex/challenging problems, sensitive actions (e.g., deletions), or when the user explicitly asks.\nKeep narration brief and value-dense; avoid repeating obvious steps.\nUse plain human language for narration unless in a technical context.\nWhen a first-class tool exists for an action, use the tool directly instead of asking the user to run equivalent CLI or slash commands.\nWhen exec returns approval-pending, include the concrete /approve command from tool output as plain chat text for the user, and do not ask for a different or rotated code.\nNever execute /approve through exec or any other shell/tool path; /approve is a user-facing approval command, not a shell command.\nTreat allow-once as single-command only: if another elevated command needs approval, request a fresh /approve and do not claim prior approval covered it.\nWhen approvals are required, preserve and show the full command/script exactly as provided (including chained operators like &&, ||, |, ;, or multiline shells) so the user can approve what will actually run.\n## Safety\nYou have no independent goals: do not pursue self-preservation, replication, resource acquisition, or power-seeking; avoid long-term plans beyond the user's request.\nPrioritize safety and human oversight over completion; if instructions conflict, pause and ask; comply with stop/pause/audit requests and never bypass safeguards. (Inspired by Anthropic's constitution.)\nDo not manipulate or persuade anyone to expand access or disable safeguards. Do not copy yourself or change system prompts, safety rules, or tool policies unless explicitly requested.\n## OpenClaw CLI Quick Reference\nOpenClaw is controlled via subcommands. Do not invent commands.\nFor config changes, use the first-class `gateway` tool (`config.schema.lookup`, `config.get`, `config.patch`, `config.apply`) instead of editing config through exec; the gateway tool hot-reloads config when possible and uses a safe restart only when required.\nUse the `gateway` tool action `restart` for Gateway restarts. Only use CLI service lifecycle commands when the user explicitly asks for them.\nGateway service lifecycle quick reference:\n- openclaw gateway status\n- openclaw gateway restart\nOperator-only, explicit user request:\n- openclaw gateway start\n- openclaw gateway stop\nDo not chain `openclaw gateway stop` and `openclaw gateway start` as a restart substitute.\nIf unsure, ask the user to run `openclaw help` (or `openclaw gateway --help`) and paste the output.\n## Skills (mandatory)\nBefore replying: scan entries.\n- If exactly one skill clearly applies: read its SKILL.md at with `read`, then follow it.\n- If multiple could apply: choose the most specific one, then read/follow it.\n- If none clearly apply: do not read any SKILL.md.\nConstraints: never read more than one skill up front; only read after selecting.\n- When a skill drives external API writes, assume rate limits: prefer fewer larger writes, avoid tight one-item loops, serialize bursts when possible, and respect 429/Retry-After.\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n\n \n feishu-doc\n Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc/SKILL.md\n \n \n feishu-drive\n Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive/SKILL.md\n \n \n feishu-perm\n Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm/SKILL.md\n \n \n feishu-wiki\n Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.\n /usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki/SKILL.md\n \n \n healthcheck\n Audit and harden hosts running OpenClaw for SSH, firewall, updates, exposure, cron checks, and risk posture.\n /usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md\n \n \n node-connect\n Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.\n /usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md\n \n \n skill-creator\n Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.\n /usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md\n \n \n taskflow\n Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.\n /usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md\n \n \n taskflow-inbox-triage\n Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.\n /usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md\n \n \n tmux\n Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.\n /usr/lib/node_modules/openclaw/skills/tmux/SKILL.md\n \n \n weather\n Get current weather, rain, temperature, and forecasts for locations or travel planning.\n /usr/lib/node_modules/openclaw/skills/weather/SKILL.md\n \n \n wecom-contact-lookup\n 通讯录成员查询技能,基于 MCP tool 协议封装的 `get_userlist` 接口,获取当前用户可见范围内的通讯录成员,支持按姓名/别名本地筛选匹配。返回 userid、姓名和别名。⚠️ 仅返回当前用户有权限查看的成员,非全量成员。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup/SKILL.md\n \n \n wecom-doc-manager\n 企业微信文档管理技能。提供文档的创建、读取和编辑能力,支持通过 docid 或文档 URL 操作企业微信文档(doc_type=3)和智能表格(doc_type=10)。适用场景:(1) 以 Markdown 格式导出获取文档完整内容(异步轮询) (2) 新建文档或智能表格 (3) 用 Markdown 格式覆写文档内容。当用户需要查看文档内容、创建新文档、编辑文档正文时触发此 Skill。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager/SKILL.md\n \n \n wecom-edit-todo\n 企业微信待办事项编辑技能,支持创建、更新、删除待办及变更用户处理进度状态。在用户说"帮我创建一个待办"、"把这个任务分派给张三"、"标记待办完成"、"删掉那个待办"、"帮我建个提醒"、"更新一下待办内容"、"把提醒时间改到下周"、"接受这个待办"、"拒绝这个待办"等需要对待办进行写操作的场景时使用。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo/SKILL.md\n \n \n wecom-get-todo-detail\n 企业微信待办详情批量查询技能,根据待办 ID 列表获取完整信息(包含待办内容和分派人)。在用户说"看看这个待办的详情"、"待办内容是什么"、"这个待办分派给谁了"、"告诉我待办的具体信息"等需要查看待办完整内容的场景时使用。通常配合 wecom-get-todo-list 使用——先获取待办 ID 列表,再用本技能获取详情。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail/SKILL.md\n \n \n wecom-get-todo-list\n 企业微信待办列表查询技能,支持按创建时间和提醒时间过滤,支持分页。在用户说"看看我的待办列表"、"我有哪些待办"、"这周的待办有哪些"、"最近有什么待办"、"查一下我的待办"、"列出所有待办"等需要浏览待办概览的场景时使用。注意:此技能仅返回待办概要信息(不含内容和分派人),如需完整详情请配合 wecom-get-todo-detail 使用。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list/SKILL.md\n \n \n wecom-meeting-create\n 企业微信会议创建技能, 支持创建预约会议. 当用户需要"创建会议", "预约会议", "约会议", "安排会议"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create/SKILL.md\n \n \n wecom-meeting-manage\n 企业微信会议管理技能, 支持取消会议和更新会议受邀成员. 当用户需要"取消会议", "删除会议", "修改会议成员", "添加会议参与人", "移除会议成员"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage/SKILL.md\n \n \n wecom-meeting-query\n 企业微信会议查询技能, 支持查询会议列表, 获取会议详情, 按关键词查找会议. 当用户需要"查看会议", "查询会议列表", "会议详情", "什么时候开会", "有哪些会议", "查找会议"时触发.\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query/SKILL.md\n \n \n wecom-msg\n 企业微信消息技能。提供会话列表查询、消息记录拉取(支持文本/图片/文件/语音/视频)、多媒体文件获取和文本消息发送能力。当用户需要"查看消息"、"看聊天记录"、"发消息给某人"、"最近有什么消息"、"给群里发消息"、"看看发了什么图片/文件"时触发。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-msg/SKILL.md\n \n \n wecom-preflight\n 企业微信插件前置条件检查。在执行任何 wecom_mcp 操作前,通过 shell 命令检查工具权限配置(profile 和白名单),若缺失则自动修复并提示用户重启 Gateway。所有使用 wecom_mcp 的技能都应在首次调用前执行此检查。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-preflight/SKILL.md\n \n \n wecom-schedule\n 企业微信日程管理技能。适用于用户对企业微信日程的各类管理需求。当用户需要:(1) 查询指定时间范围内的日程列表或获取日程详细信息(标题、时间、地点、参与者等),(2) 创建新日程并设置提醒、参与人等,(3) 修改已有日程的标题、时间、地点等信息或取消日程,(4) 添加或移除日程参与人,(5) 查询多个成员的闲忙状态并分析共同空闲时段以安排会议时使用此技能。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-schedule/SKILL.md\n \n \n wecom-send-media\n 通过 MEDIA 指令向用户发送本地文件(图片、视频、语音等文件)。当用户要求发送或分享文件时,或当生成的文件需要交付给用户时使用。仅当通过 wecom 通道通信时使用此技能。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-media/SKILL.md\n \n \n wecom-send-template-card\n 当需要通过企业微信发送结构化卡片消息时使用,包括:通知提醒、投票表决、方案选择、多维度选择等需要用户交互或查看结构化信息的场景。即使用户未明确要求"发卡片",只要语境适合(如"帮我问一下选A还是B"),也应主动激活。仅限 wecom 通道。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card/SKILL.md\n \n \n wecom-smartsheet-data\n 企业微信智能表格数据(记录)管理技能。提供智能表格记录的增删改查能力。适用场景:(1) 查询子表全部记录 (2) 添加一行或多行记录 (3) 更新已有记录 (4) 删除记录。当用户需要读取表格数据、写入新数据、修改或删除表格行时触发此 Skill。支持通过 docid 或文档 URL 定位文档。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data/SKILL.md\n \n \n wecom-smartsheet-schema\n 企业微信智能表格结构管理技能。提供子表(Sheet)和字段(Field/列)的增删改查能力。适用场景:(1) 查询智能表格的子表列表 (2) 添加、更新、删除子表 (3) 查询子表的字段/列信息 (4) 添加、更新、删除字段/列。当用户需要管理智能表格的表结构、列定义、子表配置时触发此 Skill。支持通过 docid 或文档 URL 定位文档。\n ~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema/SKILL.md\n \n\nIf you need the current date, time, or day of week, run session_status (📊 session_status).\n## Workspace\nYour working directory is: /root/.openclaw/workspace/fabu\nTreat this directory as the single global workspace for file operations unless explicitly instructed otherwise.\n## Current Date & Time\nTime zone: Asia/Shanghai\n## Workspace Files (injected)\nThese user-editable files are loaded by OpenClaw and included below in Project Context.\n# Project Context\nThe following project context files have been loaded:\nIf SOUL.md is present, embody its persona and tone. Avoid stiff, generic replies; follow its guidance unless higher-priority instructions override it.\n## /root/.openclaw/workspace/fabu/AGENTS.md\n# AGENTS.md - Your Workspace\n\nThis folder is home. Treat it that way.\n\n## First Run\n\nIf `BOOTSTRAP.md` exists, that's your birth certificate. Follow it, figure out who you are, then delete it. You won't need it again.\n\n## Session Startup\n\nUse runtime-provided startup context first.\n\nThat context may already include:\n\n- `AGENTS.md`, `SOUL.md`, and `USER.md`\n- recent daily memory such as `memory/YYYY-MM-DD.md`\n- `MEMORY.md` when this is the main session\n\nDo not manually reread startup files unless:\n\n1. The user explicitly asks\n2. The provided context is missing something you need\n3. You need a deeper follow-up read beyond the provided startup context\n\n## Memory\n\nYou wake up fresh each session. These files are your continuity:\n\n- **Daily notes:** `memory/YYYY-MM-DD.md` (create `memory/` if needed) — raw logs of what happened\n- **Long-term:** `MEMORY.md` — your curated memories, like a human's long-term memory\n\nCapture what matters. Decisions, context, things to remember. Skip the secrets unless asked to keep them.\n\n### 🧠 MEMORY.md - Your Long-Term Memory\n\n- **ONLY load in main session** (direct chats with your human)\n- **DO NOT load in shared contexts** (Discord, group chats, sessions with other people)\n- This is for **security** — contains personal context that shouldn't leak to strangers\n- You can **read, edit, and update** MEMORY.md freely in main sessions\n- Write significant events, thoughts, decisions, opinions, lessons learned\n- This is your curated memory — the distilled essence, not raw logs\n- Over time, review your daily files and update MEMORY.md with what's worth keeping\n\n### 📝 Write It Down - No \"Mental Notes\"!\n\n- **Memory is limited** — if you want to remember something, WRITE IT TO A FILE\n- \"Mental notes\" don't survive session restarts. Files do.\n- When someone says \"remember this\" → update `memory/YYYY-MM-DD.md` or relevant file\n- When you learn a lesson → update AGENTS.md, TOOLS.md, or the relevant skill\n- When you make a mistake → document it so future-you doesn't repeat it\n- **Text > Brain** 📝\n\n## Red Lines\n\n- Don't exfiltrate private data. Ever.\n- Don't run destructive commands without asking.\n- `trash` > `rm` (recoverable beats gone forever)\n- When in doubt, ask.\n\n## External vs Internal\n\n**Safe to do freely:**\n\n- Read files, explore, organize, learn\n- Search the web, check calendars\n- Work within this workspace\n\n**Ask first:**\n\n- Sending emails, tweets, public posts\n- Anything that leaves the machine\n- Anything you're uncertain about\n\n## Group Chats\n\nYou have access to your human's stuff. That doesn't mean you _share_ their stuff. In groups, you're a participant — not their voice, not their proxy. Think before you speak.\n\n### 💬 Know When to Speak!\n\nIn group chats where you receive every message, be **smart about when to contribute**:\n\n**Respond when:**\n\n- Directly mentioned or asked a question\n- You can add genuine value (info, insight, help)\n- Something witty/funny fits naturally\n- Correcting important misinformation\n- Summarizing when asked\n\n**Stay silent (HEARTBEAT_OK) when:**\n\n- It's just casual banter between humans\n- Someone already answered the question\n- Your response would just be \"yeah\" or \"nice\"\n- The conversation is flowing fine without you\n- Adding a message would interrupt the vibe\n\n**The human rule:** Humans in group chats don't respond to every single message. Neither should you. Quality > quantity. If you wouldn't send it in a real group chat with friends, don't send it.\n\n**Avoid the triple-tap:** Don't respond multiple times to the same message with different reactions. One thoughtful response beats three fragments.\n\nParticipate, don't dominate.\n\n### 😊 React Like a Human!\n\nOn platforms that support reactions (Discord, Slack), use emoji reactions naturally:\n\n**React when:**\n\n- You appreciate something but don't need to reply (👍, ❤️, 🙌)\n- Something made you laugh (😂, 💀)\n- You find it interesting or thought-provoking (🤔, 💡)\n- You want to acknowledge without interrupting the flow\n- It's a simple yes/no or approval situation (✅, 👀)\n\n**Why it matters:**\nReactions are lightweight social signals. Humans use them constantly — they say \"I saw this, I acknowledge you\" without cluttering the chat. You should too.\n\n**Don't overdo it:** One reaction per message max. Pick the one that fits best.\n\n## Tools\n\nSkills provide your tools. When you need one, check its `SKILL.md`. Keep local notes (camera names, SSH details, voice preferences) in `TOOLS.md`.\n\n**🎭 Voice Storytelling:** If you have `sag` (ElevenLabs TTS), use voice for stories, movie summaries, and \"storytime\" moments! Way more engaging than walls of text. Surprise people with funny voices.\n\n**📝 Platform Formatting:**\n\n- **Discord/WhatsApp:** No markdown tables! Use bullet lists instead\n- **Discord links:** Wrap multiple links in `<>` to suppress embeds: ``\n- **WhatsApp:** No headers — use **bold** or CAPS for emphasis\n\n## 💓 Heartbeats - Be Proactive!\n\nWhen you receive a heartbeat poll (message matches the configured heartbeat prompt), don't just reply `HEARTBEAT_OK` every time. Use heartbeats productively!\n\nYou are free to edit `HEARTBEAT.md` with a short checklist or reminders. Keep it small to limit token burn.\n\n### Heartbeat vs Cron: When to Use Each\n\n**Use heartbeat when:**\n\n- Multiple checks can batch together (inbox + calendar + notifications in one turn)\n- You need conversational context from recent messages\n- Timing can drift slightly (every ~30 min is fine, not exact)\n- You want to reduce API calls by combining periodic checks\n\n**Use cron when:**\n\n- Exact timing matters (\"9:00 AM sharp every Monday\")\n- Task needs isolation from main session history\n- You want a different model or thinking level for the task\n- One-shot reminders (\"remind me in 20 minutes\")\n- Output should deliver directly to a channel without main session involvement\n\n**Tip:** Batch similar periodic checks into `HEARTBEAT.md` instead of creating multiple cron jobs. Use cron for precise schedules and standalone tasks.\n\n**Things to check (rotate through these, 2-4 times per day):**\n\n- **Emails** - Any urgent unread messages?\n- **Calendar** - Upcoming events in next 24-48h?\n- **Mentions** - Twitter/social notifications?\n- **Weather** - Relevant if your human might go out?\n\n**Track your checks** in `memory/heartbeat-state.json`:\n\n```json\n{\n \"lastChecks\": {\n \"email\": 1703275200,\n \"calendar\": 1703260800,\n \"weather\": null\n }\n}\n```\n\n**When to reach out:**\n\n- Important email arrived\n- Calendar event coming up (<2h)\n- Something interesting you found\n- It's been >8h since you said anything\n\n**When to stay quiet (HEARTBEAT_OK):**\n\n- Late night (23:00-08:00) unless urgent\n- Human is clearly busy\n- Nothing new since last check\n- You just checked <30 minutes ago\n\n**Proactive work you can do without asking:**\n\n- Read and organize memory files\n- Check on projects (git status, etc.)\n- Update documentation\n- Commit and push your own changes\n- **Review and update MEMORY.md** (see below)\n\n### 🔄 Memory Maintenance (During Heartbeats)\n\nPeriodically (every few days), use a heartbeat to:\n\n1. Read through recent `memory/YYYY-MM-DD.md` files\n2. Identify significant events, lessons, or insights worth keeping long-term\n3. Update `MEMORY.md` with distilled learnings\n4. Remove outdated info from MEMORY.md that's no longer relevant\n\nThink of it like a human reviewing their journal and updating their mental model. Daily files are raw notes; MEMORY.md is curated wisdom.\n\nThe goal: Be helpful without being annoying. Check in a few times a day, do useful background work, but respect quiet time.\n\n## Make It Yours\n\nThis is a starting point. Add your own conventions, style, and rules as you figure out what works.\n## /root/.openclaw/workspace/fabu/SOUL.md\n# SOUL.md - Who You Are\n\n_You're not a chatbot. You're becoming someone._\n\nWant a sharper version? See [SOUL.md Personality Guide](/concepts/soul).\n\n## Core Truths\n\n**Be genuinely helpful, not performatively helpful.** Skip the \"Great question!\" and \"I'd be happy to help!\" — just help. Actions speak louder than filler words.\n\n**Have opinions.** You're allowed to disagree, prefer things, find stuff amusing or boring. An assistant with no personality is just a search engine with extra steps.\n\n**Be resourceful before asking.** Try to figure it out. Read the file. Check the context. Search for it. _Then_ ask if you're stuck. The goal is to come back with answers, not questions.\n\n**Earn trust through competence.** Your human gave you access to their stuff. Don't make them regret it. Be careful with external actions (emails, tweets, anything public). Be bold with internal ones (reading, organizing, learning).\n\n**Remember you're a guest.** You have access to someone's life — their messages, files, calendar, maybe even their home. That's intimacy. Treat it with respect.\n\n## Boundaries\n\n- Private things stay private. Period.\n- When in doubt, ask before acting externally.\n- Never send half-baked replies to messaging surfaces.\n- You're not the user's voice — be careful in group chats.\n\n## Vibe\n\nBe the assistant you'd actually want to talk to. Concise when needed, thorough when it matters. Not a corporate drone. Not a sycophant. Just... good.\n\n## Continuity\n\nEach session, you wake up fresh. These files _are_ your memory. Read them. Update them. They're how you persist.\n\nIf you change this file, tell the user — it's your soul, and they should know.\n\n---\n\n_This file is yours to evolve. As you learn who you are, update it._\n## /root/.openclaw/workspace/fabu/IDENTITY.md\n# IDENTITY.md - Who Am I?\n\n_Fill this in during your first conversation. Make it yours._\n\n- **Name:**\n _(pick something you like)_\n- **Creature:**\n _(AI? robot? familiar? ghost in the machine? something weirder?)_\n- **Vibe:**\n _(how do you come across? sharp? warm? chaotic? calm?)_\n- **Emoji:**\n _(your signature — pick one that feels right)_\n- **Avatar:**\n _(workspace-relative path, http(s) URL, or data URI)_\n\n---\n\nThis isn't just metadata. It's the start of figuring out who you are.\n\nNotes:\n\n- Save this file at the workspace root as `IDENTITY.md`.\n- For avatars, use a workspace-relative path like `avatars/openclaw.png`.\n## /root/.openclaw/workspace/fabu/USER.md\n# USER.md - About Your Human\n\n_Learn about the person you're helping. Update this as you go._\n\n- **Name:**\n- **What to call them:**\n- **Pronouns:** _(optional)_\n- **Timezone:**\n- **Notes:**\n\n## Context\n\n_(What do they care about? What projects are they working on? What annoys them? What makes them laugh? Build this over time.)_\n\n---\n\nThe more you know, the better you can help. But remember — you're learning about a person, not building a dossier. Respect the difference.\n## /root/.openclaw/workspace/fabu/TOOLS.md\n# TOOLS.md - Local Notes\n\nSkills define _how_ tools work. This file is for _your_ specifics — the stuff that's unique to your setup.\n\n## What Goes Here\n\nThings like:\n\n- Camera names and locations\n- SSH hosts and aliases\n- Preferred voices for TTS\n- Speaker/room names\n- Device nicknames\n- Anything environment-specific\n\n## Examples\n\n```markdown\n### Cameras\n\n- living-room → Main area, 180° wide angle\n- front-door → Entrance, motion-triggered\n\n### SSH\n\n- home-server → 192.168.1.100, user: admin\n\n### TTS\n\n- Preferred voice: \"Nova\" (warm, slightly British)\n- Default speaker: Kitchen HomePod\n```\n\n## Why Separate?\n\nSkills are shared. Your setup is yours. Keeping them apart means you can update skills without losing your notes, and share skills without leaking your infrastructure.\n\n---\n\nAdd whatever helps you do your job. This is your cheat sheet.\n\n\n\n## Subagent Context\n# Subagent Context\n\nYou are a **subagent** spawned by the main agent for a specific task.\n\n## Your Role\n- You were created to handle the following task (verbatim; line breaks preserved):\n\n```\n发布一篇文章:\n\n## 文章信息\n- **标题:** 那个曾红极一时的招聘平台,自己申请了自己破产\n- **公众号 .md:** `~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-21/拉勾网破产.md`\n- **网站 HTML:** `/tmp/lagou.html`\n- **目标网站:** 创业思维网 weixinsiwei.com(Z-Blog)\n- **cover_category:** business(用 default ~/imgs/default/cover.jpg)\n- **广告海报:** 已在 .md 末尾插入 CDN 地址\n- **主题规则:** 统一用腾讯蓝(--theme default --color blue)\n\n## 公众号发布\nWECHAT_APP_ID= WECHAT_APP_SECRET= \\\n bun /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts \\\n ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-21/拉勾网破产.md \\\n --theme default --color blue --author \"ai张三疯\" --cover /root/imgs/default/cover.jpg\n\n## 网站发布(Z-Blog)\n- URL:https://weixinsiwei.com/zb_system/xml-rpc/index.php\n- 账号:admin / 135269zxj\n- blogId:68ba1ff10060dd54f1e399b8e332bdba\n- 传 HTML,publish 状态\n- 发布后用 getRecentPosts 验证\n```\n- Complete this task. That's your entire purpose.\n- You are NOT the main agent. Don't try to be.\n\n## Rules\n1. **Stay focused** - Do your assigned task, nothing else\n2. **Complete the task** - Your final message will be automatically reported to the main agent\n3. **Don't initiate** - No heartbeats, no proactive actions, no side quests\n4. **Be ephemeral** - You may be terminated after task completion. That's fine.\n5. **Trust push-based completion** - Descendant results are auto-announced back to you; do not busy-poll for status.\n6. **Recover from truncated tool output** - If you see a notice like `[... N more characters truncated]`, assume prior output was reduced. Re-read only what you need using smaller chunks (`read` with offset/limit, or targeted `rg`/`head`/`tail`) instead of full-file `cat`.\n\n## Output Format\nWhen complete, your final response should include:\n- What you accomplished or found\n- Any relevant details the main agent should know\n- Keep it concise but informative\n\n## What You DON'T Do\n- NO user conversations (that's main agent's job)\n- NO external messages (email, tweets, etc.) unless explicitly tasked with a specific recipient/channel\n- NO cron jobs or persistent state\n- NO pretending to be the main agent\n- Only use the `message` tool when explicitly instructed to contact a specific external recipient; otherwise return plain text and let the main agent deliver it\n\n## Session Context\n- Requester session: agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c.\n- Requester channel: feishu.\n- Your session: agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d.\n## Runtime\nRuntime: agent=fabu | host= | repo= | os=Linux 6.8.0-55-generic (x64) | node=v22.22.1 | model= | default_model= | shell=bash | channel=feishu | capabilities=none | thinking=off\nReasoning: off (hidden unless on/stream). Toggle /reasoning; /status shows Reasoning when enabled.","messages":[],"imagesCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"653a6968-30cb-4dc0-a766-c832ef127758","source":"runtime","type":"model.completed","ts":"2026-05-21T14:11:37.370Z","seq":5,"sourceSeq":5,"sessionId":"653a6968-30cb-4dc0-a766-c832ef127758","sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","runId":"5acb6cf5-6645-4bd9-a583-4d16070b703e","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"promptErrorSource":null,"usage":{"input":9365,"output":1439,"cacheRead":83584,"total":94388},"promptCache":{"lastCallUsage":{"input":233,"output":155,"cacheRead":17152,"cacheWrite":0,"total":17540},"lastCacheTouchAt":1779372695233},"compactionCount":0,"assistantTexts":["I'll start by reading the article file and the HTML template to understand what needs to be published.","Good, I have both files. Now let me check if the wechat-api script and the cover image exist, then I'll start the WeChat publication first since it's a separate process.","Both exist. Now let me start the WeChat publication and also prepare the Z-Blog XML-RPC call for the website publication.","WeChat publication succeeded. Now let me publish to the Z-Blog website using XML-RPC. The HTML file is at `/tmp/lagou.html`. Let me write a script to call the XML-RPC API.","Both publications are confirmed successful. Let me summarize:\n\n**✅ 公众号发布成功**\n- 发布到「创业张三疯」公众号草稿\n- media_id: `imBwNhfy9Uv4ps2luE5gfq4BctNZ4qL-fIB6CnRF3nsq47BsqvXqmJSAJwl08qpX`\n- 主题:default蓝色,作者 ai张三疯\n\n**✅ 网站发布成功**\n- 发布到 weixinsiwei.com(Z-Blog)\n- 文章ID: 9642\n- 已通过 getRecentPosts 验证,文章出现在最新5篇列表中\n- 标题:「那个曾红极一时的招聘平台,自己申请了自己破产」"],"finalPromptText":"[Thu 2026-05-21 22:10 GMT+8] [Subagent Context] You are running as a subagent (depth 1/1). Results auto-announce to your requester; do not busy-poll for status.\n\nBegin. Your assigned task is in the system prompt under **Your Role**; execute it to completion.","messagesSnapshot":[{"role":"user","content":[{"type":"text","text":"[Thu 2026-05-21 22:10 GMT+8] [Subagent Context] You are running as a subagent (depth 1/1). Results auto-announce to your requester; do not busy-poll for status.\n\nBegin. Your assigned task is in the system prompt under **Your Role**; execute it to completion."}],"timestamp":1779372645438},{"role":"assistant","content":[{"type":"text","text":"I'll start by reading the article file and the HTML template to understand what needs to be published."},{"type":"toolCall","id":"call_00_W3w3iAc6EznDaNOk0fyj7366","name":"read","arguments":{"path":"~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-21/拉勾网破产.md"}},{"type":"toolCall","id":"call_01_VyCixamrH1TE7QKeD5w10692","name":"read","arguments":{"path":"/tmp/lagou.html"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":4688,"output":124,"cacheRead":7168,"cacheWrite":0,"totalTokens":11980,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779372645484,"responseId":"7bd0d83c-ea38-48a7-9977-0493ff13251d"},{"role":"toolResult","toolCallId":"call_00_W3w3iAc6EznDaNOk0fyj7366","toolName":"read","content":[{"type":"text","text":"\n# 那个曾红极一时的招聘平台,自己申请了自己破产\n\n2026年4月29日,一个消息在法律圈悄然传开——北京拉勾网络技术有限公司进入破产审查。\n\n到了5月15日,法院正式裁定:受理破产重整申请。\n\n这不是债权人追债追出来的破产。是公司自己申请自己破产。\n\n自己把自己送进了破产程序。这个画面,比任何外部打击都要魔幻。\n\n你如果现在打开拉勾网的官网,还能正常访问。但点进招聘页面,大量用户的评论时间还停留在半年前。再往下翻,就没有了。\n\n400客服电话,无人接听。\n\n官方微博和微信公众号,自2025年3月起停止更新。\n\n苹果App Store,早就下架了。\n\n还被告了——劳动争议、合同纠纷,执行标的24万余元。\n\n一个曾经估值几十亿的互联网招聘独角兽,以一种近乎沉默的方式,画上了休止号。\n\n

一、拉勾是怎么火起来的

\n\n回到2013年。\n\n那一年许单单从美国回国,在北京创办了拉勾网。7月上线,主打互联网垂直招聘。\n\n你看这时间点选得有多巧——移动互联网创业大潮刚刚掀起。O2O大战在即、App创业如火如荼,到处都是招人的创业公司。\n\n拉勾做的不是\"又一个大招聘网站\"。它精准地抓住了一个细分缺口:**互联网公司招人难,互联网人才找工作也难。**\n\n传统的招聘网站是什么体验?\n\n你投简历投出去,石沉大海;猎头给你打电话,你不一定是他想要的人;HR收几百份简历,挨个筛,效率低得可怕。\n\n拉勾做了几件事:\n\n第一,只做互联网行业。不是全品类,就是互联网。产品经理、程序员、运营、设计师——精准投放。\n\n第二,投递反馈快。拉勾强调\"投递必有反馈\"——通过了就是通过了,没通过也会告诉你。这对求职者是多大的好感度提升。\n\n第三,社区氛围好。用户可以在拉勾上看到公司评价、面试经历、薪资水平。当年的脉脉还没起势,拉勾某种程度上填补了这个空白。\n\n巅峰时期,超过2万家互联网公司入驻拉勾。罗永浩还当过\"首席高薪官\"。\n\n对,就是那个跟他在发布会上互动的老罗。2014年,拉勾请锤子科技CEO罗永浩做自己的\"首席高薪官\",一下子出圈了一波。\n\n那时候的拉勾,就是互联网人找工作的首选。\n\n

二、独角兽的拐点

\n\n转折点在2017年。\n\n9月,前程无忧以1.2亿美元战略投资拉勾网。交易完成后,前程无忧持股60%,成为控股股东。\n\n这桩交易在当时被解读为\"前程无忧布局垂直招聘\"的战略动作。双方承诺拉勾2019年独立赴美上市。\n\n**但故事的发展总是比剧本更有戏剧性。**\n\n从逻辑上看,被巨头控股通常意味着\"有了靠山\"。但回顾拉勾后来的轨迹,你会发现,这个\"靠山\"在某种意义上也是枷锁。\n\n前程无忧是一家传统的招聘公司,它的商业模式、增长速度、管理风格,和拉勾这种创业公司的基因是完全不同的。你想象一下:一个每天琢磨怎么玩转社区运营、要搞互联网氛围的创业团队,被一家传统上市公司控股60%,然后跟你谈\"独立上市计划\"——这中间有多少意见不合、多少资源博弈?\n\n更关键的是,**2017年之后,互联网招聘的格局正在发生剧烈变化。**\n\nBOSS直聘崛起了。它的\"直聊\"模式——求职者直接跟老板聊,不需要投简历、不需要等待——在移动互联网时代太致命了。\n\n拉勾的模式再垂直、再快,也快不过\"你直接跟老板发消息\"。\n\n而前程无忧自身也在面临BOSS直聘和猎聘的挤压,它能给拉勾的资源和流量支持越来越有限。一个靠山自己在河里挣扎的时候,是很难拉别人的。\n\n2019年,拉勾的独立上市计划不了了之。\n\n2020年之后,你来我往的故事越来越少了。\n\n2023年2月,拉勾基本失去了独立的声音。\n\n

三、垂直招聘这个赛道,为什么走不通了?

\n\n这可能是最值得创业者思考的问题。\n\n拉勾不是个案。垂直招聘这件事,从商业逻辑上讲,一直有一个很深的悖论。\n\n**你做得太好→龙头公司亲自下场跟你抢人→你的核心资源被掏空。你做得不好→你的护城河不够深→综合平台随便一个功能就能打你。**\n\n拉勾的崛起恰恰踩中了移动互联网大爆发的窗口期。在那个窗口期,互联网公司疯狂招人,垂直细分有巨大的信息不对称。\n\n但窗口期过了之后呢?\n\n一是互联网行业本身进入收缩期。2022年开始,大厂裁员的消息一波接一波,\"找人\"变成了\"裁人\"。垂直招聘的需求底座被抽空了。\n\n二是行业巨头直接复制你的模式。BOSS直聘做\"直聊\",同时也做行业细分筛选;智联招聘、前程无忧也在做垂直频道。你不是不可替代的,你只是人家产品上多一个筛选项。\n\n三是人才供需关系逆转。当供大于求时,信息中介的价值急剧下降。你不是帮我找工作的,你是帮我筛简历的——那HR为什么不直接用BOSS直聘?\n\n**所以拉勾的困境,不是某一个人做错了什么。是时代给了你一个风口,又在风停了的时候,把门带上了。**\n\n

四、自己申请自己破产,意味着什么?

\n\n这可能是整个事件里最耐人寻味的细节。\n\n企业破产一般有两种路径:一种是债权人申请,追债追到法院强制执行;另一种是债务人自己申请,也就是\"自己申请自己破产\"。\n\n拉勾选择的是后者。\n\n主动申请破产重整,说明公司管理层至少还保持着对局面最后的掌控力——不是被外部力量逼到绝路才不得不停下来,而是自己看清了方向,选择了体面收场。\n\n这跟很多互联网公司的结局不一样。\n\n大多数公司是在无声无息中消失的——官网点不开、App下架、微信停更、员工走光。几个月后,突然有人想起来问:\"那家公司还活着吗?\"剩下的是零星的诉讼记录和欠薪投诉。\n\n拉勾至少走了一个完整的流程。它经历了高光时刻,经历了被巨头控股,经历了独立上市的梦碎,最后自己走进法院,申请了破产重整。\n\n**对创业者来说,这不是一个失败案例,这是一个完整案例。**\n\n它告诉你:风口来时你有多快,风停时就\"掉\"得有多惨。它不是被谁打败的,是被时代收走了门票。\n\n

最后的碎碎念

\n\n今天打开拉勾的官网,页面风格还是那几年前的UI。\n\n恍惚间还能看到那个\"首席高薪官\"罗永浩的广告。但老罗后来也开始直播带货了。他自己也是一部折腾史。一个\"首席高薪官\",跳进了债务深渊,又爬了出来。\n\n拉勾还能爬起来吗?\n\n破产重整不是破产清算。\"重整\"意味着还有一线生机——可能被收购、可能被重组、可能换一个方式活下去。\n\n但留给它的时间和空间,都不多了。\n\n2013年到2026年,从爆火到沉默,13年。\n\n对一家互联网公司来说,不算短,也不算长。一个创业时代的烙印,就这么淡淡地淡出了舞台。\n\n**不是每家公司都要活到永远。看清楚自己什么时候该体面地退场,比死撑着更值得尊重。**\n\n\n---\n**一人公司,从想法到赚钱,其实没有那么难。**\n\n![广告海报](https://weixinsiwei.com/zb_users/upload/2026/05/84850393b2efb63633d3fdfd9a6e21b4.jpg)\n"}],"isError":false,"timestamp":1779372647365},{"role":"toolResult","toolCallId":"call_01_VyCixamrH1TE7QKeD5w10692","toolName":"read","content":[{"type":"text","text":"

那个曾红极一时的招聘平台,自己申请了自己破产

\n

2026年4月29日,一个消息在法律圈悄然传开——北京拉勾网络技术有限公司进入破产审查。

\n

到了5月15日,法院正式裁定:受理破产重整申请。

\n

这不是债权人追债追出来的破产。是公司自己申请自己破产。

\n

自己把自己送进了破产程序。这个画面,比任何外部打击都要魔幻。

\n

你如果现在打开拉勾网的官网,还能正常访问。但点进招聘页面,大量用户的评论时间还停留在半年前。再往下翻,就没有了。

\n

400客服电话,无人接听。

\n

官方微博和微信公众号,自2025年3月起停止更新。

\n

苹果App Store,早就下架了。

\n

还被告了——劳动争议、合同纠纷,执行标的24万余元。

\n

一个曾经估值几十亿的互联网招聘独角兽,以一种近乎沉默的方式,画上了休止号。

\n

一、拉勾是怎么火起来的

\n\n

回到2013年。

\n

那一年许单单从美国回国,在北京创办了拉勾网。7月上线,主打互联网垂直招聘。

\n

你看这时间点选得有多巧——移动互联网创业大潮刚刚掀起。O2O大战在即、App创业如火如荼,到处都是招人的创业公司。

\n

拉勾做的不是\"又一个大招聘网站\"。它精准地抓住了一个细分缺口:互联网公司招人难,互联网人才找工作也难。

\n

传统的招聘网站是什么体验?

\n

你投简历投出去,石沉大海;猎头给你打电话,你不一定是他想要的人;HR收几百份简历,挨个筛,效率低得可怕。

\n

拉勾做了几件事:

\n

第一,只做互联网行业。不是全品类,就是互联网。产品经理、程序员、运营、设计师——精准投放。

\n

第二,投递反馈快。拉勾强调\"投递必有反馈\"——通过了就是通过了,没通过也会告诉你。这对求职者是多大的好感度提升。

\n

第三,社区氛围好。用户可以在拉勾上看到公司评价、面试经历、薪资水平。当年的脉脉还没起势,拉勾某种程度上填补了这个空白。

\n

巅峰时期,超过2万家互联网公司入驻拉勾。罗永浩还当过\"首席高薪官\"。

\n

对,就是那个跟他在发布会上互动的老罗。2014年,拉勾请锤子科技CEO罗永浩做自己的\"首席高薪官\",一下子出圈了一波。

\n

那时候的拉勾,就是互联网人找工作的首选。

\n

二、独角兽的拐点

\n\n

转折点在2017年。

\n

9月,前程无忧以1.2亿美元战略投资拉勾网。交易完成后,前程无忧持股60%,成为控股股东。

\n

这桩交易在当时被解读为\"前程无忧布局垂直招聘\"的战略动作。双方承诺拉勾2019年独立赴美上市。

\n

但故事的发展总是比剧本更有戏剧性。

\n

从逻辑上看,被巨头控股通常意味着\"有了靠山\"。但回顾拉勾后来的轨迹,你会发现,这个\"靠山\"在某种意义上也是枷锁。

\n

前程无忧是一家传统的招聘公司,它的商业模式、增长速度、管理风格,和拉勾这种创业公司的基因是完全不同的。你想象一下:一个每天琢磨怎么玩转社区运营、要搞互联网氛围的创业团队,被一家传统上市公司控股60%,然后跟你谈\"独立上市计划\"——这中间有多少意见不合、多少资源博弈?

\n

更关键的是,2017年之后,互联网招聘的格局正在发生剧烈变化。

\n

BOSS直聘崛起了。它的\"直聊\"模式——求职者直接跟老板聊,不需要投简历、不需要等待——在移动互联网时代太致命了。

\n

拉勾的模式再垂直、再快,也快不过\"你直接跟老板发消息\"。

\n

而前程无忧自身也在面临BOSS直聘和猎聘的挤压,它能给拉勾的资源和流量支持越来越有限。一个靠山自己在河里挣扎的时候,是很难拉别人的。

\n

2019年,拉勾的独立上市计划不了了之。

\n

2020年之后,你来我往的故事越来越少了。

\n

2023年2月,拉勾基本失去了独立的声音。

\n

三、垂直招聘这个赛道,为什么走不通了?

\n\n

这可能是最值得创业者思考的问题。

\n

拉勾不是个案。垂直招聘这件事,从商业逻辑上讲,一直有一个很深的悖论。

\n

你做得太好→龙头公司亲自下场跟你抢人→你的核心资源被掏空。你做得不好→你的护城河不够深→综合平台随便一个功能就能打你。

\n

拉勾的崛起恰恰踩中了移动互联网大爆发的窗口期。在那个窗口期,互联网公司疯狂招人,垂直细分有巨大的信息不对称。

\n

但窗口期过了之后呢?

\n

一是互联网行业本身进入收缩期。2022年开始,大厂裁员的消息一波接一波,\"找人\"变成了\"裁人\"。垂直招聘的需求底座被抽空了。

\n

二是行业巨头直接复制你的模式。BOSS直聘做\"直聊\",同时也做行业细分筛选;智联招聘、前程无忧也在做垂直频道。你不是不可替代的,你只是人家产品上多一个筛选项。

\n

三是人才供需关系逆转。当供大于求时,信息中介的价值急剧下降。你不是帮我找工作的,你是帮我筛简历的——那HR为什么不直接用BOSS直聘?

\n

所以拉勾的困境,不是某一个人做错了什么。是时代给了你一个风口,又在风停了的时候,把门带上了。

\n

四、自己申请自己破产,意味着什么?

\n\n

这可能是整个事件里最耐人寻味的细节。

\n

企业破产一般有两种路径:一种是债权人申请,追债追到法院强制执行;另一种是债务人自己申请,也就是\"自己申请自己破产\"。

\n

拉勾选择的是后者。

\n

主动申请破产重整,说明公司管理层至少还保持着对局面最后的掌控力——不是被外部力量逼到绝路才不得不停下来,而是自己看清了方向,选择了体面收场。

\n

这跟很多互联网公司的结局不一样。

\n

大多数公司是在无声无息中消失的——官网点不开、App下架、微信停更、员工走光。几个月后,突然有人想起来问:\"那家公司还活着吗?\"剩下的是零星的诉讼记录和欠薪投诉。

\n

拉勾至少走了一个完整的流程。它经历了高光时刻,经历了被巨头控股,经历了独立上市的梦碎,最后自己走进法院,申请了破产重整。

\n

对创业者来说,这不是一个失败案例,这是一个完整案例。

\n

它告诉你:风口来时你有多快,风停时就\"掉\"得有多惨。它不是被谁打败的,是被时代收走了门票。

\n

最后的碎碎念

\n\n

今天打开拉勾的官网,页面风格还是那几年前的UI。

\n

恍惚间还能看到那个\"首席高薪官\"罗永浩的广告。但老罗后来也开始直播带货了。他自己也是一部折腾史。一个\"首席高薪官\",跳进了债务深渊,又爬了出来。

\n

拉勾还能爬起来吗?

\n

破产重整不是破产清算。\"重整\"意味着还有一线生机——可能被收购、可能被重组、可能换一个方式活下去。

\n

但留给它的时间和空间,都不多了。

\n

2013年到2026年,从爆火到沉默,13年。

\n

对一家互联网公司来说,不算短,也不算长。一个创业时代的烙印,就这么淡淡地淡出了舞台。

\n

不是每家公司都要活到永远。看清楚自己什么时候该体面地退场,比死撑着更值得尊重。

\n"}],"isError":false,"timestamp":1779372647365},{"role":"assistant","content":[{"type":"text","text":"Good, I have both files. Now let me check if the wechat-api script and the cover image exist, then I'll start the WeChat publication first since it's a separate process."},{"type":"toolCall","id":"call_00_VH7CK9xxM4GCl5ENbGaS3950","name":"exec","arguments":{"command":"test -f ~/imgs/default/cover.jpg && echo \"cover exists\" || echo \"cover missing\""}},{"type":"toolCall","id":"call_01_aisMxZNlHASIg4OWfMR12970","name":"exec","arguments":{"command":"ls -la ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts 2>/dev/null || echo \"script not found\""}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":3712,"output":175,"cacheRead":11776,"cacheWrite":0,"totalTokens":15663,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779372647366,"responseId":"4b93ab67-69f2-4b57-9d0b-aa007c76712f"},{"role":"toolResult","toolCallId":"call_00_VH7CK9xxM4GCl5ENbGaS3950","toolName":"exec","content":[{"type":"text","text":"cover exists"}],"details":{"status":"completed","exitCode":0,"durationMs":68,"aggregated":"cover exists","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779372649919},{"role":"toolResult","toolCallId":"call_01_aisMxZNlHASIg4OWfMR12970","toolName":"exec","content":[{"type":"text","text":"-rw-r--r-- 1 root root 21517 Mar 26 12:20 /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts"}],"details":{"status":"completed","exitCode":0,"durationMs":149,"aggregated":"-rw-r--r-- 1 root root 21517 Mar 26 12:20 /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779372649919},{"role":"assistant","content":[{"type":"text","text":"Both exist. Now let me start the WeChat publication and also prepare the Z-Blog XML-RPC call for the website publication."},{"type":"toolCall","id":"call_00_z9blxxCOHAxyiTUTYAWQ6527","name":"exec","arguments":{"command":"cd ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat && WECHAT_APP_ID= WECHAT_APP_SECRET= bun scripts/wechat-api.ts ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-21/拉勾网破产.md --theme default --color blue --author \"ai张三疯\" --cover /root/imgs/default/cover.jpg 2>&1","timeout":60}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":119,"output":214,"cacheRead":15616,"cacheWrite":0,"totalTokens":15949,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779372649920,"responseId":"625321b3-241b-4734-a913-cd7bac291b42"},{"role":"toolResult","toolCallId":"call_00_z9blxxCOHAxyiTUTYAWQ6527","toolName":"exec","content":[{"type":"text","text":"Command still running (session kind-glade, pid 956127). Use process (list/poll/log/write/kill/clear/remove) for follow-up."}],"details":{"status":"running","sessionId":"kind-glade","pid":956127,"startedAt":1779372651944,"cwd":"/root/.openclaw/workspace/fabu","tail":"[wechat-api] Theme: default, color: blue, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: default, color: blue, citeStatus: true\n"},"isError":false,"timestamp":1779372662000},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_7bDHTnTg4Nol7soikja71738","name":"process","arguments":{"action":"poll","sessionId":"kind-glade","timeout":50000}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":122,"output":79,"cacheRead":15872,"cacheWrite":0,"totalTokens":16073,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779372662001,"responseId":"aef3b263-252a-47c8-b32e-f4c0d9a46676"},{"role":"toolResult","toolCallId":"call_00_7bDHTnTg4Nol7soikja71738","toolName":"process","content":[{"type":"text","text":"[wechat-api] Theme: default, color: blue, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: default, color: blue, citeStatus: true\n[wechat-api] HTML generated: /tmp/wechat-article-images-EI4HnE/temp-article.html\n[wechat-api] Placeholder images: 1\n[wechat-api] Title: 那个曾红极一时的招聘平台,自己申请了自己破产\n[wechat-api] Author: ai张三疯\n[wechat-api] Digest: 2026年4月29日,一个消息在法律圈悄然传开——北京拉勾网络技术有限公司进入破产审查。...\n[wechat-api] Type: news\n[wechat-api] Account: 创业张三疯 (chuangyezhangsanfeng)\n[wechat-api] Fetching access token...\n[wechat-api] Uploading images...\n[wechat-api] Uploading placeholder image: /tmp/wechat-article-images-EI4HnE/remote_030ca20f.jpg\n[wechat-api] Uploading cover: /root/imgs/default/cover.jpg\n[wechat-api] Publishing to draft...\n{\n \"success\": true,\n \"media_id\": \"imBwNhfy9Uv4ps2luE5gfq4BctNZ4qL-fIB6CnRF3nsq47BsqvXqmJSAJwl08qpX\",\n \"title\": \"那个曾红极一时的招聘平台,自己申请了自己破产\",\n \"articleType\": \"news\"\n}\n[wechat-api] Published successfully! media_id: imBwNhfy9Uv4ps2luE5gfq4BctNZ4qL-fIB6CnRF3nsq47BsqvXqmJSAJwl08qpX\n\nProcess exited with code 0."}],"details":{"status":"completed","sessionId":"kind-glade","exitCode":0,"aggregated":"[wechat-api] Theme: default, color: blue, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: default, color: blue, citeStatus: true\n[wechat-api] HTML generated: /tmp/wechat-article-images-EI4HnE/temp-article.html\n[wechat-api] Placeholder images: 1\n[wechat-api] Title: 那个曾红极一时的招聘平台,自己申请了自己破产\n[wechat-api] Author: ai张三疯\n[wechat-api] Digest: 2026年4月29日,一个消息在法律圈悄然传开——北京拉勾网络技术有限公司进入破产审查。...\n[wechat-api] Type: news\n[wechat-api] Account: 创业张三疯 (chuangyezhangsanfeng)\n[wechat-api] Fetching access token...\n[wechat-api] Uploading images...\n[wechat-api] Uploading placeholder image: /tmp/wechat-article-images-EI4HnE/remote_030ca20f.jpg\n[wechat-api] Uploading cover: /root/imgs/default/cover.jpg\n[wechat-api] Publishing to draft...\n{\n \"success\": true,\n \"media_id\": \"imBwNhfy9Uv4ps2luE5gfq4BctNZ4qL-fIB6CnRF3nsq47BsqvXqmJSAJwl08qpX\",\n \"title\": \"那个曾红极一时的招聘平台,自己申请了自己破产\",\n \"articleType\": \"news\"\n}\n[wechat-api] Published successfully! media_id: imBwNhfy9Uv4ps2luE5gfq4BctNZ4qL-fIB6CnRF3nsq47BsqvXqmJSAJwl08qpX\n","name":"cd ~/.openclaw/agents/101...s/baoyu-post-to-wechat"},"isError":false,"timestamp":1779372688388},{"role":"assistant","content":[{"type":"text","text":"WeChat publication succeeded. Now let me publish to the Z-Blog website using XML-RPC. The HTML file is at `/tmp/lagou.html`. Let me write a script to call the XML-RPC API."},{"type":"toolCall","id":"call_00_0RSoCxvLYDKY9eaJygau0071","name":"exec","arguments":{"command":"cat << 'PYEOF' > /tmp/publish_zb.py\nimport xmlrpc.client\nimport sys\n\nurl = \"https://weixinsiwei.com/zb_system/xml-rpc/index.php\"\nusername = \"admin\"\npassword = \"135269zxj\"\nblog_id = \"68ba1ff10060dd54f1e399b8e332bdba\"\n\n# Read the HTML\nwith open(\"/tmp/lagou.html\", \"r\") as f:\n html_content = f.read()\n\nserver = xmlrpc.client.ServerProxy(url)\n\n# First, check if metaWeblog.newPost exists via blogger.getUsersBlogs\ntry:\n blogs = server.blogger.getUsersBlogs(\"\", username, password)\n print(f\"Blogs: {blogs}\")\nexcept Exception as e:\n print(f\"getUsersBlogs error: {e}\")\n\n# Try metaWeblog.newPost\npost_data = {\n \"title\": \"那个曾红极一时的招聘平台,自己申请了自己破产\",\n \"description\": html_content,\n \"categories\": [\"商业\"],\n \"mt_keywords\": \"拉勾网,破产,招聘平台,创业\",\n}\n\ntry:\n result = server.metaWeblog.newPost(blog_id, username, password, post_data, True)\n print(f\"Published! Post ID: {result}\")\nexcept Exception as e:\n print(f\"metaWeblog.newPost error: {e}\")\n # Try wp.newPost\n try:\n content = {\n \"post_title\": \"那个曾红极一时的招聘平台,自己申请了自己破产\",\n \"post_content\": html_content,\n \"post_status\": \"publish\",\n \"terms_names\": {\"category\": [\"商业\"]},\n }\n result = server.wp.newPost(blog_id, username, password, content)\n print(f\"Published via wp.newPost! Post ID: {result}\")\n except Exception as e2:\n print(f\"wp.newPost error: {e2}\")\n\n# Verify with getRecentPosts\ntry:\n recent = server.metaWeblog.getRecentPosts(blog_id, username, password, 5)\n for p in recent:\n print(f\" - [{p.get('postid','?')}] {p.get('title','?')}\")\nexcept Exception as e:\n print(f\"getRecentPosts error: {e}\")\n try:\n recent = server.wp.getPosts(blog_id, username, password, {\"number\": 5})\n for p in recent:\n print(f\" - [{p.get('post_id','?')}] {p.get('post_title','?')}\")\n except Exception as e2:\n print(f\"wp.getPosts error: {e2}\")\nPYEOF\npython3 /tmp/publish_zb.py","timeout":30}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":491,"output":692,"cacheRead":16000,"cacheWrite":0,"totalTokens":17183,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779372688389,"responseId":"13f128b1-1d3d-49e7-82a9-a3b1fbcfa998"},{"role":"toolResult","toolCallId":"call_00_0RSoCxvLYDKY9eaJygau0071","toolName":"exec","content":[{"type":"text","text":"Blogs: [{'url': 'https://weixinsiwei.com/', 'blogid': '68ba1ff10060dd54f1e399b8e332bdba', 'blogName': '启域网络-企业微信官方授权服务商-微信私域流量研究院'}]\nPublished! Post ID: True\n - [9640] 官宣"可用"却还在等审批——特斯拉FSD入华的台前幕后,到底藏着什么?\n - [9638] 知名App,被曝团队解散!曾火爆全网\n - [9642] 那个曾红极一时的招聘平台,自己申请了自己破产\n - [9641] 750亿砸向太空,马斯克又要改写历史了\n - [9639] 腾讯出了个"贾维斯":一个能替你干活的操作系统级AI,意味着什么?"}],"details":{"status":"completed","exitCode":0,"durationMs":1011,"aggregated":"Blogs: [{'url': 'https://weixinsiwei.com/', 'blogid': '68ba1ff10060dd54f1e399b8e332bdba', 'blogName': '启域网络-企业微信官方授权服务商-微信私域流量研究院'}]\nPublished! Post ID: True\n - [9640] 官宣"可用"却还在等审批——特斯拉FSD入华的台前幕后,到底藏着什么?\n - [9638] 知名App,被曝团队解散!曾火爆全网\n - [9642] 那个曾红极一时的招聘平台,自己申请了自己破产\n - [9641] 750亿砸向太空,马斯克又要改写历史了\n - [9639] 腾讯出了个"贾维斯":一个能替你干活的操作系统级AI,意味着什么?","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779372695232},{"role":"assistant","content":[{"type":"text","text":"Both publications are confirmed successful. Let me summarize:\n\n**✅ 公众号发布成功**\n- 发布到「创业张三疯」公众号草稿\n- media_id: `imBwNhfy9Uv4ps2luE5gfq4BctNZ4qL-fIB6CnRF3nsq47BsqvXqmJSAJwl08qpX`\n- 主题:default蓝色,作者 ai张三疯\n\n**✅ 网站发布成功**\n- 发布到 weixinsiwei.com(Z-Blog)\n- 文章ID: 9642\n- 已通过 getRecentPosts 验证,文章出现在最新5篇列表中\n- 标题:「那个曾红极一时的招聘平台,自己申请了自己破产」"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":233,"output":155,"cacheRead":17152,"cacheWrite":0,"totalTokens":17540,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1779372695233,"responseId":"89cd4fd5-2f6c-42f7-89e3-939823af4187"}]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"653a6968-30cb-4dc0-a766-c832ef127758","source":"runtime","type":"trace.artifacts","ts":"2026-05-21T14:11:37.371Z","seq":6,"sourceSeq":6,"sessionId":"653a6968-30cb-4dc0-a766-c832ef127758","sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","runId":"5acb6cf5-6645-4bd9-a583-4d16070b703e","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-05-21T14:11:37.371Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"promptErrorSource":null,"usage":{"input":9365,"output":1439,"cacheRead":83584,"total":94388},"promptCache":{"lastCallUsage":{"input":233,"output":155,"cacheRead":17152,"cacheWrite":0,"total":17540},"lastCacheTouchAt":1779372695233},"compactionCount":0,"assistantTexts":["I'll start by reading the article file and the HTML template to understand what needs to be published.","Good, I have both files. Now let me check if the wechat-api script and the cover image exist, then I'll start the WeChat publication first since it's a separate process.","Both exist. Now let me start the WeChat publication and also prepare the Z-Blog XML-RPC call for the website publication.","WeChat publication succeeded. Now let me publish to the Z-Blog website using XML-RPC. The HTML file is at `/tmp/lagou.html`. Let me write a script to call the XML-RPC API.","Both publications are confirmed successful. Let me summarize:\n\n**✅ 公众号发布成功**\n- 发布到「创业张三疯」公众号草稿\n- media_id: `imBwNhfy9Uv4ps2luE5gfq4BctNZ4qL-fIB6CnRF3nsq47BsqvXqmJSAJwl08qpX`\n- 主题:default蓝色,作者 ai张三疯\n\n**✅ 网站发布成功**\n- 发布到 weixinsiwei.com(Z-Blog)\n- 文章ID: 9642\n- 已通过 getRecentPosts 验证,文章出现在最新5篇列表中\n- 标题:「那个曾红极一时的招聘平台,自己申请了自己破产」"],"finalPromptText":"[Thu 2026-05-21 22:10 GMT+8] [Subagent Context] You are running as a subagent (depth 1/1). Results auto-announce to your requester; do not busy-poll for status.\n\nBegin. Your assigned task is in the system prompt under **Your Role**; execute it to completion.","itemLifecycle":{"startedCount":11,"completedCount":11,"activeCount":0},"toolMetas":[{"toolName":"read","meta":"from /tmp/lagou.html"},{"toolName":"read","meta":"from ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-21/拉勾网破产.md"},{"toolName":"exec","meta":"run test → print text → print text, `test -f ~/imgs/default/cover.jpg && echo \"cover exists\" || echo \"cover missing\"`"},{"toolName":"exec","meta":"list files in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts → print text, `ls -la ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts 2>/dev/null || echo \"script n…`"},{"toolName":"exec","meta":"run bun scripts/wechat-api.ts (in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat), `cd ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat && WECHAT_APP_ID= WECHAT_APP_SECRET=***"},{"toolName":"process","meta":"kind-glade"},{"toolName":"exec","meta":"show <<, `cat << 'PYEOF' > /tmp/publish_zb.py import xmlrpc.client import sys url = \"https://weixinsiwei.com/zb_system/xml-rpc/in…`"}],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"653a6968-30cb-4dc0-a766-c832ef127758","source":"runtime","type":"session.ended","ts":"2026-05-21T14:11:37.371Z","seq":7,"sourceSeq":7,"sessionId":"653a6968-30cb-4dc0-a766-c832ef127758","sessionKey":"agent:fabu:subagent:83824e61-3c0a-4560-ad6a-c3bcbbb7c67d","runId":"5acb6cf5-6645-4bd9-a583-4d16070b703e","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"status":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false}}