{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","source":"runtime","type":"session.started","ts":"2026-05-17T07:09:35.769Z","seq":1,"sourceSeq":1,"sessionId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","sessionKey":"agent:fabu:subagent:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","runId":"5f5560f8-c398-44d7-8ebe-c8aef397ff43","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"trigger":"user","sessionFile":"/root/.openclaw/agents/fabu/sessions/2c0fe23c-307e-46c0-b28f-1e2f19262eaa.jsonl","workspaceDir":"/root/.openclaw/workspace/fabu","agentId":"fabu","messageChannel":"feishu","toolCount":12,"clientToolCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","source":"runtime","type":"trace.metadata","ts":"2026-05-17T07:09:35.779Z","seq":2,"sourceSeq":2,"sessionId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","sessionKey":"agent:fabu:subagent:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","runId":"5f5560f8-c398-44d7-8ebe-c8aef397ff43","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-05-17T07:09:35.771Z","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/2c0fe23c-307e-46c0-b28f-1e2f19262eaa.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":300000,"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":1779001775754,"sessionId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","sessionKey":"agent:fabu:subagent:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","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":28556,"projectContextChars":14975,"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:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","agentId":"fabu","messageChannel":"feishu"}}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","source":"runtime","type":"context.compiled","ts":"2026-05-17T07:09:35.808Z","seq":3,"sourceSeq":3,"sessionId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","sessionKey":"agent:fabu:subagent:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","runId":"5f5560f8-c398-44d7-8ebe-c8aef397ff43","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请执行以下发布任务:\n\n**文章主题:** 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n**主题判断:** 短视频创业、自媒体警示 → 发布到 **创业思维网 weixinsiwei.com** 和 **公众号 创业张三疯**\n\n**任务A:公众号发布**\n1. 公众号文件:/root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md\n2. 命令:WECHAT_APP_ID= WECHAT_APP_SECRET= \\\n bun ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts \\\n /root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md \\\n --theme grace --color rose --author \"ai张三疯\" \\\n --cover /root/.openclaw/agents/101/workspace/imgs/cover.png\n3. 发布后验证草稿箱\n\n**任务B:创业思维网发布(Z-Blog)**\n1. HTML文件:/tmp/blind-host-article.html\n2. 创业思维网:https://weixinsiwei.com/zb_system/xml-rpc/index.php\n 账号:admin / 135269zxj\n blogId:68ba1ff10060dd54f1e399b8e332bdba\n3. 注意:Z-Blog必须传HTML格式\n4. 发布后必须验证(getRecentPosts)\n\n**完成后通知我**\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:5642f637-7f41-46f8-b1de-1d5cd09c2ab3.\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":"[Sun 2026-05-17 15:09 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":"6d3763a7"}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","source":"runtime","type":"prompt.submitted","ts":"2026-05-17T07:09:35.810Z","seq":4,"sourceSeq":4,"sessionId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","sessionKey":"agent:fabu:subagent:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","runId":"5f5560f8-c398-44d7-8ebe-c8aef397ff43","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"prompt":"[Sun 2026-05-17 15:09 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请执行以下发布任务:\n\n**文章主题:** 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n**主题判断:** 短视频创业、自媒体警示 → 发布到 **创业思维网 weixinsiwei.com** 和 **公众号 创业张三疯**\n\n**任务A:公众号发布**\n1. 公众号文件:/root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md\n2. 命令:WECHAT_APP_ID= WECHAT_APP_SECRET= \\\n bun ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts \\\n /root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md \\\n --theme grace --color rose --author \"ai张三疯\" \\\n --cover /root/.openclaw/agents/101/workspace/imgs/cover.png\n3. 发布后验证草稿箱\n\n**任务B:创业思维网发布(Z-Blog)**\n1. HTML文件:/tmp/blind-host-article.html\n2. 创业思维网:https://weixinsiwei.com/zb_system/xml-rpc/index.php\n 账号:admin / 135269zxj\n blogId:68ba1ff10060dd54f1e399b8e332bdba\n3. 注意:Z-Blog必须传HTML格式\n4. 发布后必须验证(getRecentPosts)\n\n**完成后通知我**\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:5642f637-7f41-46f8-b1de-1d5cd09c2ab3.\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":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","source":"runtime","type":"model.completed","ts":"2026-05-17T07:10:24.585Z","seq":5,"sourceSeq":5,"sessionId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","sessionKey":"agent:fabu:subagent:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","runId":"5f5560f8-c398-44d7-8ebe-c8aef397ff43","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":11238,"output":2839,"cacheRead":156544,"total":170621},"promptCache":{"lastCallUsage":{"input":155,"output":234,"cacheRead":19968,"cacheWrite":0,"total":20357},"lastCacheTouchAt":1779001821462},"compactionCount":0,"assistantTexts":["I'll execute both publishing tasks. Let me start by verifying the input files exist, then run them in parallel.","Good, all files exist. Let me check the wechat-api.ts script to understand its usage, and also check what tools are available for the Z-Blog XML-RPC posting.","Let me look at the full wechat-api.ts to understand its argument parsing and run it.","Now I understand the CLI args. Let me run both tasks in parallel - Task A (WeChat publish) and Task B (Z-Blog publish).\n\nFirst, let me create the Python script for Z-Blog XML-RPC posting:","Now execute both tasks simultaneously - Task A (WeChat API) and Task B (Z-Blog XML-RPC):","Both tasks completed successfully. Let me verify the WeChat draft by checking the draft list:","Let me verify the draft by calling the WeChat API directly to get the draft list:","All verifications passed. Here's the completion summary:\n\n---\n\n## ✅ 双平台发布完成\n\n### 任务A:公众号发布 ✅\n- **平台:** 公众号「创业张三疯」(chuangyezhangsanfeng)\n- **文章:** 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n- **样式:** grace主题 / rose配色 / 作者:ai张三疯\n- **封面:** 已上传 cover.png\n- **状态:** ✅ 已成功发布到草稿箱(media_id 已返回)\n- **验证:** ✅ 草稿箱确认存在该文章\n\n### 任务B:创业思维网发布 ✅\n- **平台:** weixinsiwei.com (Z-Blog)\n- **文章ID:** 9598\n- **格式:** HTML 格式发布\n- **验证:** ✅ getRecentPosts 确认文章存在,最新5篇文章列表可查\n- **分类标签:** 盲人主播, 短视频创业, MCN, 内容创作, 创业思维"],"finalPromptText":"[Sun 2026-05-17 15:09 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":"[Sun 2026-05-17 15:09 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":1779001775813},{"role":"assistant","content":[{"type":"text","text":"I'll execute both publishing tasks. Let me start by verifying the input files exist, then run them in parallel."},{"type":"toolCall","id":"call_00_0xdlZY8LONpL8kmX2HUd8131","name":"exec","arguments":{"command":"ls -la /root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md /tmp/blind-host-article.html /root/.openclaw/agents/101/workspace/imgs/cover.png 2>&1"}},{"type":"toolCall","id":"call_01_OJHwM7QHm7t2uDNKpGWx3720","name":"exec","arguments":{"command":"cat /root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md | head -50"}},{"type":"toolCall","id":"call_02_zQpLJuUF2Jn8KGirLqkv6389","name":"exec","arguments":{"command":"head -100 /tmp/blind-host-article.html"}},{"type":"toolCall","id":"call_03_TuTa1pAH87LjNjL5zuFq9879","name":"exec","arguments":{"command":"ls ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts 2>&1"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":4703,"output":294,"cacheRead":7168,"cacheWrite":0,"totalTokens":12165,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001775882,"responseId":"3251b35f-3b6e-41a4-92ed-8a175094cf55"},{"role":"toolResult","toolCallId":"call_00_0xdlZY8LONpL8kmX2HUd8131","toolName":"exec","content":[{"type":"text","text":"-rw-r--r-- 1 root root 159045 Mar 26 13:01 /root/.openclaw/agents/101/workspace/imgs/cover.png\n-rw-r--r-- 1 root root 6095 May 17 15:08 /root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md\n-rw-r--r-- 1 root root 6574 May 17 15:08 /tmp/blind-host-article.html"}],"details":{"status":"completed","exitCode":0,"durationMs":207,"aggregated":"-rw-r--r-- 1 root root 159045 Mar 26 13:01 /root/.openclaw/agents/101/workspace/imgs/cover.png\n-rw-r--r-- 1 root root 6095 May 17 15:08 /root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md\n-rw-r--r-- 1 root root 6574 May 17 15:08 /tmp/blind-host-article.html","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001779282},{"role":"toolResult","toolCallId":"call_01_OJHwM7QHm7t2uDNKpGWx3720","toolName":"exec","content":[{"type":"text","text":"# 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n\n你刷到过盲人主播的视频吗?\n\n画面里,一个盲人姑娘举着盲杖,小心翼翼地在人行道上探路。背景音乐缓慢,弹幕全是\"加油\"\"泪目\"\"这才是生活\"。然后镜头一转,她在直播间里用手触摸读屏手机,一字一句地推荐一款洗衣液。下单链接挂在右下角,成交量还不错。\n\n感动吗?先别急着感动。\n\n最近,一位从MCN离职的员工爆料了一个很多人不愿意说破的事实:**盲人主播赛道,已经饱和了。** 饱和到什么程度?\"前期必须投流,后期还得摆拍。\"\n\n你没看错,摆拍。\n\n## 一、一个\"温情风口\"的诞生与堕落\n\n盲人主播这个赛道,一开始确实有真情实感。\n\n算法推荐时代,稀缺的就是情绪。一个自强不息的残疾人通过短视频自食其力,天然戳中大众的共情点。平台也乐意推——这是正能量,不踩红线,还能拉长用户停留时长。第一批真正自强不息的盲人主播收获流量,赚到了钱,这是好故事。\n\n但好故事的终点,就是资本的下一个起点。\n\nMCN看到了什么?看到了流量密码:**弱势群体+自强叙事+消费转化**,公式清晰,可复制。于是大批MCN入场,招募盲人。招募条件是什么?\"优先招募女孩,但男孩也会考虑。\"\n\n为什么优先女孩?因为女性盲人主播的声音更柔和,更容易让用户产生\"想保护她\"的心理,转化率更高。这不是关怀,这是流量测算。\n\n当一个赛道被MCN盯上,它的命运只有一条:被迅速榨干。\n\n## 二、饱和的真相:不是人太多,是戏太假\n\n盲人主播赛道饱和,本质上不是真的盲人从业者太多,而是\"假盲人\"和\"假故事\"太多。\n\n北京警方刚通报了一个典型案例:刘某和江某某,虚假摆拍\"盲人在盲道行走被电动车撞击\"的内容,通过短视频平台发布,被查处。这不是个案。你去搜一下,类似的\"盲人被撞\"\"盲人卖菜被欺负\"\"盲人考研成功\"……很多都是摆拍。\n\nMCN的剧本模板已经工业化了:\n- 第一周:拍盲人生活困难(建立人设)\n- 第二周:拍盲人自强不息(积累情感增量)\n- 第三周:开直播带货(变现)\n\n问题在哪?**当一个赛道里90%的内容都是剧本,用户的信任就会被耗尽。** 你看到的眼泪,可能是洋葱熏的;你买到的洗衣液,可能是三无贴牌;你心里的\"支持弱势群体\",最终变成了MCN账上的投流费。\n\n这不是温情,这是套路。不是感动,是收割。\n\n## 三、风口之下,全是镰刀\n\n这对正在观望短视频创业的人,是一个教科书级别的警示。\n\n很多人做短视频的逻辑是:先找一个\"有红利的风口\"冲进去。盲人赛道火,我就做盲人;三农火,我就回农村;摆摊火,我就去夜市拍摆摊。\n\n但你想过没有——**等你看到风口的时候,入口已经排满了镰刀。**\n\n追逐\"感动中国\"式的风口,有三个致命陷阱:"}],"details":{"status":"completed","exitCode":0,"durationMs":178,"aggregated":"# 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n\n你刷到过盲人主播的视频吗?\n\n画面里,一个盲人姑娘举着盲杖,小心翼翼地在人行道上探路。背景音乐缓慢,弹幕全是\"加油\"\"泪目\"\"这才是生活\"。然后镜头一转,她在直播间里用手触摸读屏手机,一字一句地推荐一款洗衣液。下单链接挂在右下角,成交量还不错。\n\n感动吗?先别急着感动。\n\n最近,一位从MCN离职的员工爆料了一个很多人不愿意说破的事实:**盲人主播赛道,已经饱和了。** 饱和到什么程度?\"前期必须投流,后期还得摆拍。\"\n\n你没看错,摆拍。\n\n## 一、一个\"温情风口\"的诞生与堕落\n\n盲人主播这个赛道,一开始确实有真情实感。\n\n算法推荐时代,稀缺的就是情绪。一个自强不息的残疾人通过短视频自食其力,天然戳中大众的共情点。平台也乐意推——这是正能量,不踩红线,还能拉长用户停留时长。第一批真正自强不息的盲人主播收获流量,赚到了钱,这是好故事。\n\n但好故事的终点,就是资本的下一个起点。\n\nMCN看到了什么?看到了流量密码:**弱势群体+自强叙事+消费转化**,公式清晰,可复制。于是大批MCN入场,招募盲人。招募条件是什么?\"优先招募女孩,但男孩也会考虑。\"\n\n为什么优先女孩?因为女性盲人主播的声音更柔和,更容易让用户产生\"想保护她\"的心理,转化率更高。这不是关怀,这是流量测算。\n\n当一个赛道被MCN盯上,它的命运只有一条:被迅速榨干。\n\n## 二、饱和的真相:不是人太多,是戏太假\n\n盲人主播赛道饱和,本质上不是真的盲人从业者太多,而是\"假盲人\"和\"假故事\"太多。\n\n北京警方刚通报了一个典型案例:刘某和江某某,虚假摆拍\"盲人在盲道行走被电动车撞击\"的内容,通过短视频平台发布,被查处。这不是个案。你去搜一下,类似的\"盲人被撞\"\"盲人卖菜被欺负\"\"盲人考研成功\"……很多都是摆拍。\n\nMCN的剧本模板已经工业化了:\n- 第一周:拍盲人生活困难(建立人设)\n- 第二周:拍盲人自强不息(积累情感增量)\n- 第三周:开直播带货(变现)\n\n问题在哪?**当一个赛道里90%的内容都是剧本,用户的信任就会被耗尽。** 你看到的眼泪,可能是洋葱熏的;你买到的洗衣液,可能是三无贴牌;你心里的\"支持弱势群体\",最终变成了MCN账上的投流费。\n\n这不是温情,这是套路。不是感动,是收割。\n\n## 三、风口之下,全是镰刀\n\n这对正在观望短视频创业的人,是一个教科书级别的警示。\n\n很多人做短视频的逻辑是:先找一个\"有红利的风口\"冲进去。盲人赛道火,我就做盲人;三农火,我就回农村;摆摊火,我就去夜市拍摆摊。\n\n但你想过没有——**等你看到风口的时候,入口已经排满了镰刀。**\n\n追逐\"感动中国\"式的风口,有三个致命陷阱:","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001779282},{"role":"toolResult","toolCallId":"call_02_zQpLJuUF2Jn8KGirLqkv6389","toolName":"exec","content":[{"type":"text","text":"

盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课

\n

你刷到过盲人主播的视频吗?

\n

画面里,一个盲人姑娘举着盲杖,小心翼翼地在人行道上探路。背景音乐缓慢,弹幕全是\"加油\"\"泪目\"\"这才是生活\"。然后镜头一转,她在直播间里用手触摸读屏手机,一字一句地推荐一款洗衣液。下单链接挂在右下角,成交量还不错。

\n

感动吗?先别急着感动。

\n

最近,一位从MCN离职的员工爆料了一个很多人不愿意说破的事实:盲人主播赛道,已经饱和了。 饱和到什么程度?\"前期必须投流,后期还得摆拍。\"

\n

你没看错,摆拍。

\n

一、一个\"温情风口\"的诞生与堕落

\n

盲人主播这个赛道,一开始确实有真情实感。

\n

算法推荐时代,稀缺的就是情绪。一个自强不息的残疾人通过短视频自食其力,天然戳中大众的共情点。平台也乐意推——这是正能量,不踩红线,还能拉长用户停留时长。第一批真正自强不息的盲人主播收获流量,赚到了钱,这是好故事。

\n

但好故事的终点,就是资本的下一个起点。

\n

MCN看到了什么?看到了流量密码:弱势群体+自强叙事+消费转化,公式清晰,可复制。于是大批MCN入场,招募盲人。招募条件是什么?\"优先招募女孩,但男孩也会考虑。\"

\n

为什么优先女孩?因为女性盲人主播的声音更柔和,更容易让用户产生\"想保护她\"的心理,转化率更高。这不是关怀,这是流量测算。

\n

当一个赛道被MCN盯上,它的命运只有一条:被迅速榨干。

\n

二、饱和的真相:不是人太多,是戏太假

\n

盲人主播赛道饱和,本质上不是真的盲人从业者太多,而是\"假盲人\"和\"假故事\"太多。

\n

北京警方刚通报了一个典型案例:刘某和江某某,虚假摆拍\"盲人在盲道行走被电动车撞击\"的内容,通过短视频平台发布,被查处。这不是个案。你去搜一下,类似的\"盲人被撞\"\"盲人卖菜被欺负\"\"盲人考研成功\"……很多都是摆拍。

\n

MCN的剧本模板已经工业化了:\n- 第一周:拍盲人生活困难(建立人设)\n- 第二周:拍盲人自强不息(积累情感增量)\n- 第三周:开直播带货(变现)

\n

问题在哪?当一个赛道里90%的内容都是剧本,用户的信任就会被耗尽。 你看到的眼泪,可能是洋葱熏的;你买到的洗衣液,可能是三无贴牌;你心里的\"支持弱势群体\",最终变成了MCN账上的投流费。

\n

这不是温情,这是套路。不是感动,是收割。

\n

三、风口之下,全是镰刀

\n

这对正在观望短视频创业的人,是一个教科书级别的警示。

\n

很多人做短视频的逻辑是:先找一个\"有红利的风口\"冲进去。盲人赛道火,我就做盲人;三农火,我就回农村;摆摊火,我就去夜市拍摆摊。

\n

但你想过没有——等你看到风口的时候,入口已经排满了镰刀。

\n

追逐\"感动中国\"式的风口,有三个致命陷阱:

\n

第一,情绪赛道生命周期极短。 用户的眼泪来得快去得也快。今天为盲人主播心动,下个月就被新的热点覆盖。你投入了设备、人设、投流成本,收获的只是一波短暂的流量脉冲。

\n

第二,高情绪=高审美疲劳。 当用户发现某个赛道的视频\"一看就是剧本\",他们会直接划过,甚至产生逆反心理。你越卖惨,他越反感。

\n

第三,变现路径脆弱。 靠人设带货,人设一崩,一切归零。还记得那些摆拍翻车的主播吗?一旦被扒出造假,账号废了,团队散了,还面临法律风险。

\n

四、真正值得做的短视频方向是什么?

\n

说了这么多反面教材,那什么方向值得做?

\n

答案是:真实、专业、有长期积累的领域。

\n

这三个词,每一个都是对\"风口追逐者\"的否定。

\n

真实——你不需要扮演任何人。你是一个创业者,就拍创业的真实过程。你是一个老师,就讲你专业领域的真知灼见。你不用流泪,不用卖惨,用户不傻,他们能分辨誰在演戏,誰在说真话。

\n

专业——信息差永远值钱。你在一个领域深耕三年积累的认知,对门外汉来说就是降维打击。直播间里,专业知识撑起的信任,比眼泪撑起的信任坚固一百倍。

\n

有长期积累——你的内容应该是一砖一瓦垒起来的,不是一次性的情绪消费品。今天讲、明天讲、一年后还在讲,用户会跟着你一起成长。这个积累过程,就是你的护城河。

\n

看看现在真正活下来、活得好的短视频创作者,有几个是靠\"追风口\"起来的?他们要么在某个领域有十年积累,要么是真性情吸引了同类。没有一个靠的是\"跟着感动走\"。

\n

五、短视频最后拼的是内容底蕴,不是赛道红利

\n

回到盲人主播这件事。

\n

很多MCN以为自己在玩流量,其实在薅真实的羊毛。他们把弱势群体的尊严当消费品,把用户的善良当转化率。这和当年微商割裂包、知识付费割焦虑,本质上没有区别——换了个皮,内核还是薅。

\n

但历史一次又一次地证明:靠收割情绪建立的内容生意,从来走不远。

\n

你可以靠一个爆款视频火三天,但不可能靠三个剧本活三年。短视频的终局,是长内容的底层逻辑在起作用——持续输出价值,沉淀信任,构建内容壁垒。道理从来没变过,只是表现形式从公众号换成了短视频。

\n

所以,如果你想认真做短视频,问自己三个问题:

\n
    \n
  1. 我不演任何人,我的真实经历和认知是什么?
  2. \n
  3. 我能在什么领域持续输出三年以上而不会枯竭?
  4. \n
  5. 当风口消失、平台更迭,我的用户还会因为什么而留下?
  6. \n
\n

想清楚这三件事,比追一百个风口都管用。

\n

别做那个追风口的人。做那个让风口追你的人。

"}],"details":{"status":"completed","exitCode":0,"durationMs":146,"aggregated":"

盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课

\n

你刷到过盲人主播的视频吗?

\n

画面里,一个盲人姑娘举着盲杖,小心翼翼地在人行道上探路。背景音乐缓慢,弹幕全是\"加油\"\"泪目\"\"这才是生活\"。然后镜头一转,她在直播间里用手触摸读屏手机,一字一句地推荐一款洗衣液。下单链接挂在右下角,成交量还不错。

\n

感动吗?先别急着感动。

\n

最近,一位从MCN离职的员工爆料了一个很多人不愿意说破的事实:盲人主播赛道,已经饱和了。 饱和到什么程度?\"前期必须投流,后期还得摆拍。\"

\n

你没看错,摆拍。

\n

一、一个\"温情风口\"的诞生与堕落

\n

盲人主播这个赛道,一开始确实有真情实感。

\n

算法推荐时代,稀缺的就是情绪。一个自强不息的残疾人通过短视频自食其力,天然戳中大众的共情点。平台也乐意推——这是正能量,不踩红线,还能拉长用户停留时长。第一批真正自强不息的盲人主播收获流量,赚到了钱,这是好故事。

\n

但好故事的终点,就是资本的下一个起点。

\n

MCN看到了什么?看到了流量密码:弱势群体+自强叙事+消费转化,公式清晰,可复制。于是大批MCN入场,招募盲人。招募条件是什么?\"优先招募女孩,但男孩也会考虑。\"

\n

为什么优先女孩?因为女性盲人主播的声音更柔和,更容易让用户产生\"想保护她\"的心理,转化率更高。这不是关怀,这是流量测算。

\n

当一个赛道被MCN盯上,它的命运只有一条:被迅速榨干。

\n

二、饱和的真相:不是人太多,是戏太假

\n

盲人主播赛道饱和,本质上不是真的盲人从业者太多,而是\"假盲人\"和\"假故事\"太多。

\n

北京警方刚通报了一个典型案例:刘某和江某某,虚假摆拍\"盲人在盲道行走被电动车撞击\"的内容,通过短视频平台发布,被查处。这不是个案。你去搜一下,类似的\"盲人被撞\"\"盲人卖菜被欺负\"\"盲人考研成功\"……很多都是摆拍。

\n

MCN的剧本模板已经工业化了:\n- 第一周:拍盲人生活困难(建立人设)\n- 第二周:拍盲人自强不息(积累情感增量)\n- 第三周:开直播带货(变现)

\n

问题在哪?当一个赛道里90%的内容都是剧本,用户的信任就会被耗尽。 你看到的眼泪,可能是洋葱熏的;你买到的洗衣液,可能是三无贴牌;你心里的\"支持弱势群体\",最终变成了MCN账上的投流费。

\n

这不是温情,这是套路。不是感动,是收割。

\n

三、风口之下,全是镰刀

\n

这对正在观望短视频创业的人,是一个教科书级别的警示。

\n

很多人做短视频的逻辑是:先找一个\"有红利的风口\"冲进去。盲人赛道火,我就做盲人;三农火,我就回农村;摆摊火,我就去夜市拍摆摊。

\n

但你想过没有——等你看到风口的时候,入口已经排满了镰刀。

\n

追逐\"感动中国\"式的风口,有三个致命陷阱:

\n

第一,情绪赛道生命周期极短。 用户的眼泪来得快去得也快。今天为盲人主播心动,下个月就被新的热点覆盖。你投入了设备、人设、投流成本,收获的只是一波短暂的流量脉冲。

\n

第二,高情绪=高审美疲劳。 当用户发现某个赛道的视频\"一看就是剧本\",他们会直接划过,甚至产生逆反心理。你越卖惨,他越反感。

\n

第三,变现路径脆弱。 靠人设带货,人设一崩,一切归零。还记得那些摆拍翻车的主播吗?一旦被扒出造假,账号废了,团队散了,还面临法律风险。

\n

四、真正值得做的短视频方向是什么?

\n

说了这么多反面教材,那什么方向值得做?

\n

答案是:真实、专业、有长期积累的领域。

\n

这三个词,每一个都是对\"风口追逐者\"的否定。

\n

真实——你不需要扮演任何人。你是一个创业者,就拍创业的真实过程。你是一个老师,就讲你专业领域的真知灼见。你不用流泪,不用卖惨,用户不傻,他们能分辨誰在演戏,誰在说真话。

\n

专业——信息差永远值钱。你在一个领域深耕三年积累的认知,对门外汉来说就是降维打击。直播间里,专业知识撑起的信任,比眼泪撑起的信任坚固一百倍。

\n

有长期积累——你的内容应该是一砖一瓦垒起来的,不是一次性的情绪消费品。今天讲、明天讲、一年后还在讲,用户会跟着你一起成长。这个积累过程,就是你的护城河。

\n

看看现在真正活下来、活得好的短视频创作者,有几个是靠\"追风口\"起来的?他们要么在某个领域有十年积累,要么是真性情吸引了同类。没有一个靠的是\"跟着感动走\"。

\n

五、短视频最后拼的是内容底蕴,不是赛道红利

\n

回到盲人主播这件事。

\n

很多MCN以为自己在玩流量,其实在薅真实的羊毛。他们把弱势群体的尊严当消费品,把用户的善良当转化率。这和当年微商割裂包、知识付费割焦虑,本质上没有区别——换了个皮,内核还是薅。

\n

但历史一次又一次地证明:靠收割情绪建立的内容生意,从来走不远。

\n

你可以靠一个爆款视频火三天,但不可能靠三个剧本活三年。短视频的终局,是长内容的底层逻辑在起作用——持续输出价值,沉淀信任,构建内容壁垒。道理从来没变过,只是表现形式从公众号换成了短视频。

\n

所以,如果你想认真做短视频,问自己三个问题:

\n
    \n
  1. 我不演任何人,我的真实经历和认知是什么?
  2. \n
  3. 我能在什么领域持续输出三年以上而不会枯竭?
  4. \n
  5. 当风口消失、平台更迭,我的用户还会因为什么而留下?
  6. \n
\n

想清楚这三件事,比追一百个风口都管用。

\n

别做那个追风口的人。做那个让风口追你的人。

","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001779283},{"role":"toolResult","toolCallId":"call_03_TuTa1pAH87LjNjL5zuFq9879","toolName":"exec","content":[{"type":"text","text":"/root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts"}],"details":{"status":"completed","exitCode":0,"durationMs":271,"aggregated":"/root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001779283},{"role":"assistant","content":[{"type":"text","text":"Good, all files exist. Let me check the wechat-api.ts script to understand its usage, and also check what tools are available for the Z-Blog XML-RPC posting."},{"type":"toolCall","id":"call_00_pXG8c0gypaZLyuBbu1bO1226","name":"exec","arguments":{"command":"head -30 ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts"}},{"type":"toolCall","id":"call_01_cnWBYjEMNbo6l6WLVzuJ1585","name":"exec","arguments":{"command":"which python3 && python3 -c \"import xmlrpc.client; print('xmlrpc available')\" 2>&1"}},{"type":"toolCall","id":"call_02_34gVQl8PwyeyBERjhl2e4768","name":"exec","arguments":{"command":"which bun && bun --version 2>&1"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":2831,"output":203,"cacheRead":11776,"cacheWrite":0,"totalTokens":14810,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001779284,"responseId":"1ea5fad4-32c3-480d-9639-d6744e48810c"},{"role":"toolResult","toolCallId":"call_00_pXG8c0gypaZLyuBbu1bO1226","toolName":"exec","content":[{"type":"text","text":"import fs from \"node:fs\";\nimport path from \"node:path\";\nimport { spawnSync } from \"node:child_process\";\nimport { fileURLToPath } from \"node:url\";\nimport { loadWechatExtendConfig, resolveAccount, loadCredentials } from \"./wechat-extend-config.ts\";\n\ninterface AccessTokenResponse {\n access_token?: string;\n errcode?: number;\n errmsg?: string;\n}\n\ninterface UploadResponse {\n media_id: string;\n url: string;\n errcode?: number;\n errmsg?: string;\n}\n\ninterface PublishResponse {\n media_id?: string;\n errcode?: number;\n errmsg?: string;\n}\n\ninterface ImageInfo {\n placeholder: string;\n localPath: string;\n originalPath: string;\n}"}],"details":{"status":"completed","exitCode":0,"durationMs":95,"aggregated":"import fs from \"node:fs\";\nimport path from \"node:path\";\nimport { spawnSync } from \"node:child_process\";\nimport { fileURLToPath } from \"node:url\";\nimport { loadWechatExtendConfig, resolveAccount, loadCredentials } from \"./wechat-extend-config.ts\";\n\ninterface AccessTokenResponse {\n access_token?: string;\n errcode?: number;\n errmsg?: string;\n}\n\ninterface UploadResponse {\n media_id: string;\n url: string;\n errcode?: number;\n errmsg?: string;\n}\n\ninterface PublishResponse {\n media_id?: string;\n errcode?: number;\n errmsg?: string;\n}\n\ninterface ImageInfo {\n placeholder: string;\n localPath: string;\n originalPath: string;\n}","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001781971},{"role":"toolResult","toolCallId":"call_01_cnWBYjEMNbo6l6WLVzuJ1585","toolName":"exec","content":[{"type":"text","text":"/usr/bin/python3\nxmlrpc available"}],"details":{"status":"completed","exitCode":0,"durationMs":228,"aggregated":"/usr/bin/python3\nxmlrpc available","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001781971},{"role":"toolResult","toolCallId":"call_02_34gVQl8PwyeyBERjhl2e4768","toolName":"exec","content":[{"type":"text","text":"/root/.bun/bin/bun\n1.3.11"}],"details":{"status":"completed","exitCode":0,"durationMs":190,"aggregated":"/root/.bun/bin/bun\n1.3.11","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001781971},{"role":"assistant","content":[{"type":"text","text":"Let me look at the full wechat-api.ts to understand its argument parsing and run it."},{"type":"toolCall","id":"call_00_ng8L89mLhnGd9kMOuMq38831","name":"exec","arguments":{"command":"grep -n 'arg\\|--\\|process\\|parse\\|commander\\|yargs\\|option\\|usage' ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts | head -30"}},{"type":"toolCall","id":"call_01_7D2Y3SzE2tuqHlxkl6bY9372","name":"exec","arguments":{"command":"ls ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":302,"output":171,"cacheRead":14720,"cacheWrite":0,"totalTokens":15193,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001781972,"responseId":"c20b0388-b063-48cd-9fa5-a22e0abdaa4a"},{"role":"toolResult","toolCallId":"call_00_ng8L89mLhnGd9kMOuMq38831","toolName":"exec","content":[{"type":"text","text":"3:import { spawnSync } from \"node:child_process\";\n100: : path.resolve(baseDir || process.cwd(), imagePath);\n122: const boundary = `----WebKitFormBoundary${Date.now().toString(16)}`;\n124: `--${boundary}`,\n130: const footer = `\\r\\n--${boundary}--\\r\\n`;\n222: const replacementTag = ``;\n237: options: ArticleOptions,\n244: const noc = options.needOpenComment ?? 1;\n245: const ofcc = options.onlyFansCanComment ?? 0;\n247: if (options.articleType === \"newspic\") {\n248: if (!options.imageMediaIds || options.imageMediaIds.length === 0) {\n253: title: options.title,\n254: content: options.content,\n258: image_list: options.imageMediaIds.map(id => ({ image_media_id: id })),\n261: if (options.author) article.author = options.author;\n265: title: options.title,\n266: content: options.content,\n267: thumb_media_id: options.thumbMediaId,\n271: if (options.author) article.author = options.author;\n272: if (options.digest) article.digest = options.digest;\n291:function parseFrontmatter(content: string): { frontmatter: Record; body: string } {\n292: const match = content.match(/^\\s*---\\r?\\n([\\s\\S]*?)\\r?\\n---\\r?\\n?([\\s\\S]*)$/);\n325: const args = [\"-y\", \"bun\", mdToWechatScript, markdownPath];\n326: if (title) args.push(\"--title\", title);\n327: if (theme) args.push(\"--theme\", theme);\n328: if (color) args.push(\"--color\", color);\n329: if (!citeStatus) args.push(\"--no-cite\");\n332: const result = spawnSync(\"npx\", args, {\n343: return JSON.parse(stdout) as MarkdownRenderResult;\n365: npx -y bun wechat-api.ts [options]"}],"details":{"status":"completed","exitCode":0,"durationMs":57,"aggregated":"3:import { spawnSync } from \"node:child_process\";\n100: : path.resolve(baseDir || process.cwd(), imagePath);\n122: const boundary = `----WebKitFormBoundary${Date.now().toString(16)}`;\n124: `--${boundary}`,\n130: const footer = `\\r\\n--${boundary}--\\r\\n`;\n222: const replacementTag = ``;\n237: options: ArticleOptions,\n244: const noc = options.needOpenComment ?? 1;\n245: const ofcc = options.onlyFansCanComment ?? 0;\n247: if (options.articleType === \"newspic\") {\n248: if (!options.imageMediaIds || options.imageMediaIds.length === 0) {\n253: title: options.title,\n254: content: options.content,\n258: image_list: options.imageMediaIds.map(id => ({ image_media_id: id })),\n261: if (options.author) article.author = options.author;\n265: title: options.title,\n266: content: options.content,\n267: thumb_media_id: options.thumbMediaId,\n271: if (options.author) article.author = options.author;\n272: if (options.digest) article.digest = options.digest;\n291:function parseFrontmatter(content: string): { frontmatter: Record; body: string } {\n292: const match = content.match(/^\\s*---\\r?\\n([\\s\\S]*?)\\r?\\n---\\r?\\n?([\\s\\S]*)$/);\n325: const args = [\"-y\", \"bun\", mdToWechatScript, markdownPath];\n326: if (title) args.push(\"--title\", title);\n327: if (theme) args.push(\"--theme\", theme);\n328: if (color) args.push(\"--color\", color);\n329: if (!citeStatus) args.push(\"--no-cite\");\n332: const result = spawnSync(\"npx\", args, {\n343: return JSON.parse(stdout) as MarkdownRenderResult;\n365: npx -y bun wechat-api.ts [options]","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001783997},{"role":"toolResult","toolCallId":"call_01_7D2Y3SzE2tuqHlxkl6bY9372","toolName":"exec","content":[{"type":"text","text":"bun.lock\ncdp.ts\ncheck-permissions.ts\ncopy-to-clipboard.ts\nmd-to-wechat.ts\nnode_modules\npackage.json\npackage-lock.json\npaste-from-clipboard.ts\nvendor\nwechat-agent-browser.ts\nwechat-api.ts\nwechat-article.ts\nwechat-browser.ts\nwechat-extend-config.ts"}],"details":{"status":"completed","exitCode":0,"durationMs":138,"aggregated":"bun.lock\ncdp.ts\ncheck-permissions.ts\ncopy-to-clipboard.ts\nmd-to-wechat.ts\nnode_modules\npackage.json\npackage-lock.json\npaste-from-clipboard.ts\nvendor\nwechat-agent-browser.ts\nwechat-api.ts\nwechat-article.ts\nwechat-browser.ts\nwechat-extend-config.ts","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001783997},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_xS3TphSwBsiRzQSblcnl7546","name":"exec","arguments":{"command":"grep -n 'usage\\|Usage\\|process.argv\\|parseArgs\\|options\\|program\\|.option\\|.command\\|help' ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts | tail -30"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":698,"output":102,"cacheRead":15104,"cacheWrite":0,"totalTokens":15904,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001783998,"responseId":"2d1744ff-13da-4a98-97e0-99c7ef491856"},{"role":"toolResult","toolCallId":"call_00_xS3TphSwBsiRzQSblcnl7546","toolName":"exec","content":[{"type":"text","text":"237: options: ArticleOptions,\n244: const noc = options.needOpenComment ?? 1;\n245: const ofcc = options.onlyFansCanComment ?? 0;\n247: if (options.articleType === \"newspic\") {\n248: if (!options.imageMediaIds || options.imageMediaIds.length === 0) {\n253: title: options.title,\n254: content: options.content,\n258: image_list: options.imageMediaIds.map(id => ({ image_media_id: id })),\n261: if (options.author) article.author = options.author;\n265: title: options.title,\n266: content: options.content,\n267: thumb_media_id: options.thumbMediaId,\n271: if (options.author) article.author = options.author;\n272: if (options.digest) article.digest = options.digest;\n361:function printUsage(): never {\n364:Usage:\n365: npx -y bun wechat-api.ts [options]\n381: --help Show this help\n428:function parseArgs(argv: string[]): CliArgs {\n429: if (argv.length === 0 || argv.includes(\"--help\") || argv.includes(\"-h\")) {\n430: printUsage();\n495: const args = parseArgs(process.argv.slice(2));"}],"details":{"status":"completed","exitCode":0,"durationMs":49,"aggregated":"237: options: ArticleOptions,\n244: const noc = options.needOpenComment ?? 1;\n245: const ofcc = options.onlyFansCanComment ?? 0;\n247: if (options.articleType === \"newspic\") {\n248: if (!options.imageMediaIds || options.imageMediaIds.length === 0) {\n253: title: options.title,\n254: content: options.content,\n258: image_list: options.imageMediaIds.map(id => ({ image_media_id: id })),\n261: if (options.author) article.author = options.author;\n265: title: options.title,\n266: content: options.content,\n267: thumb_media_id: options.thumbMediaId,\n271: if (options.author) article.author = options.author;\n272: if (options.digest) article.digest = options.digest;\n361:function printUsage(): never {\n364:Usage:\n365: npx -y bun wechat-api.ts [options]\n381: --help Show this help\n428:function parseArgs(argv: string[]): CliArgs {\n429: if (argv.length === 0 || argv.includes(\"--help\") || argv.includes(\"-h\")) {\n430: printUsage();\n495: const args = parseArgs(process.argv.slice(2));","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001785729},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_o74yqoJmot8L0JqncCXG7809","name":"read","arguments":{"path":"/root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts","offset":361,"limit":100}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":336,"output":104,"cacheRead":15872,"cacheWrite":0,"totalTokens":16312,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001785730,"responseId":"807ed876-dba8-44fb-b3aa-34966c54b804"},{"role":"toolResult","toolCallId":"call_00_o74yqoJmot8L0JqncCXG7809","toolName":"read","content":[{"type":"text","text":"function printUsage(): never {\n console.log(`Publish article to WeChat Official Account draft using API\n\nUsage:\n npx -y bun wechat-api.ts [options]\n\nArguments:\n file Markdown (.md) or HTML (.html) file\n\nOptions:\n --type Article type: news (文章, default) or newspic (图文)\n --title Override title\n --author <name> Author name (max 16 chars)\n --summary <text> Article summary/digest (max 128 chars)\n --theme <name> Theme name for markdown (default, grace, simple, modern). Default: default\n --color <name|hex> Primary color (blue, green, vermilion, etc. or hex)\n --cover <path> Cover image path (local or URL)\n --account <alias> Select account by alias (for multi-account setups)\n --no-cite Disable bottom citations for ordinary external links in markdown mode\n --dry-run Parse and render only, don't publish\n --help Show this help\n\nFrontmatter Fields (markdown):\n title Article title\n author Author name\n digest/summary Article summary\n coverImage/featureImage/cover/image Cover image path\n\nComments:\n Comments are enabled by default, open to all users.\n\nEnvironment Variables:\n WECHAT_APP_ID WeChat App ID\n WECHAT_APP_SECRET WeChat App Secret\n\nConfig File Locations (in priority order):\n 1. Environment variables\n 2. <cwd>/.baoyu-skills/.env\n 3. ~/.baoyu-skills/.env\n\nExample:\n npx -y bun wechat-api.ts article.md\n npx -y bun wechat-api.ts article.md --theme grace --cover cover.png\n npx -y bun wechat-api.ts article.md --author \"Author Name\" --summary \"Brief intro\"\n npx -y bun wechat-api.ts article.html --title \"My Article\"\n npx -y bun wechat-api.ts images/ --type newspic --title \"Photo Album\"\n npx -y bun wechat-api.ts article.md --dry-run\n npx -y bun wechat-api.ts article.md --no-cite\n`);\n process.exit(0);\n}\n\ninterface CliArgs {\n filePath: string;\n isHtml: boolean;\n articleType: ArticleType;\n title?: string;\n author?: string;\n summary?: string;\n theme: string;\n color?: string;\n cover?: string;\n account?: string;\n citeStatus: boolean;\n dryRun: boolean;\n}\n\nfunction parseArgs(argv: string[]): CliArgs {\n if (argv.length === 0 || argv.includes(\"--help\") || argv.includes(\"-h\")) {\n printUsage();\n }\n\n const args: CliArgs = {\n filePath: \"\",\n isHtml: false,\n articleType: \"news\",\n theme: \"default\",\n citeStatus: true,\n dryRun: false,\n };\n\n for (let i = 0; i < argv.length; i++) {\n const arg = argv[i]!;\n if (arg === \"--type\" && argv[i + 1]) {\n const t = argv[++i]!.toLowerCase();\n if (t === \"news\" || t === \"newspic\") {\n args.articleType = t;\n }\n } else if (arg === \"--title\" && argv[i + 1]) {\n args.title = argv[++i];\n } else if (arg === \"--author\" && argv[i + 1]) {\n args.author = argv[++i];\n } else if (arg === \"--summary\" && argv[i + 1]) {\n args.summary = argv[++i];\n } else if (arg === \"--theme\" && argv[i + 1]) {\n args.theme = argv[++i]!;\n } else if (arg === \"--color\" && argv[i + 1]) {\n args.color = argv[++i];\n } else if (arg === \"--cover\" && argv[i + 1]) {\n args.cover = argv[++i];\n\n[205 more lines in file. Use offset=461 to continue.]"}],"isError":false,"timestamp":1779001787016},{"role":"assistant","content":[{"type":"text","text":"Now I understand the CLI args. Let me run both tasks in parallel - Task A (WeChat publish) and Task B (Z-Blog publish).\n\nFirst, let me create the Python script for Z-Blog XML-RPC posting:"},{"type":"toolCall","id":"call_00_UjYmvqkKpHabsoj8QBBp9005","name":"write","arguments":{"path":"/tmp/post-zblog.py","content":"#!/usr/bin/env python3\n\"\"\"Post HTML article to Z-Blog via XML-RPC MetaWeblog API.\"\"\"\n\nimport xmlrpc.client\nimport sys\nimport os\nimport re\n\ndef main():\n blog_id = \"68ba1ff10060dd54f1e399b8e332bdba\"\n xmlrpc_url = \"https://weixinsiwei.com/zb_system/xml-rpc/index.php\"\n username = \"admin\"\n password = \"135269zxj\"\n html_file = \"/tmp/blind-host-article.html\"\n\n if not os.path.exists(html_file):\n print(f\"ERROR: HTML file not found: {html_file}\")\n sys.exit(1)\n\n with open(html_file, \"r\", encoding=\"utf-8\") as f:\n html_content = f.read()\n\n # Extract title from <h1> tag\n title_match = re.search(r'<h1>(.*?)</h1>', html_content, re.DOTALL)\n if not title_match:\n title_match = re.search(r'<title>(.*?)', html_content, re.DOTALL)\n if title_match:\n title = title_match.group(1).strip()\n else:\n title = \"盲人主播赛道已饱和:当'感动中国'变成镰刀\"\n\n print(f\"Title: {title}\")\n print(f\"HTML size: {len(html_content)} chars\")\n\n # Connect to Z-Blog XML-RPC\n try:\n server = xmlrpc.client.ServerProxy(xmlrpc_url)\n \n # Check connection by getting recent posts first\n print(\"Testing connection - fetching recent posts...\")\n recent_posts = server.metaWeblog.getRecentPosts(blog_id, username, password, 3)\n print(f\"Connection OK. Found {len(recent_posts)} existing posts.\")\n for post in recent_posts:\n print(f\" - [{post.get('postid', '?')}] {post.get('title', '?')}\")\n \n # Post the new article\n print(\"\\nPublishing new article...\")\n post_struct = {\n 'title': title,\n 'description': html_content,\n 'categories': [],\n 'mt_keywords': '盲人主播,短视频创业,MCN,内容创作,创业思维',\n 'post_type': 'post',\n 'wp_slug': 'blind-host-saturation',\n }\n \n result = server.metaWeblog.newPost(blog_id, username, password, post_struct, True)\n print(f\"\\n✅ Article published successfully! Post ID: {result}\")\n \n # Verify by getting recent posts\n print(\"\\nVerifying - fetching recent posts...\")\n recent_posts = server.metaWeblog.getRecentPosts(blog_id, username, password, 5)\n print(f\"Latest {len(recent_posts)} posts:\")\n for post in recent_posts:\n print(f\" - [{post.get('postid', '?')}] {post.get('title', '?')} - {str(post.get('dateCreated', '?'))}\")\n \n print(\"\\n✅ Z-Blog publish complete!\")\n \n except Exception as e:\n print(f\"ERROR: {e}\")\n sys.exit(1)\n\nif __name__ == \"__main__\":\n main()\n"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":1008,"output":824,"cacheRead":16256,"cacheWrite":0,"totalTokens":18088,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001787017,"responseId":"d2a6ea8a-5072-43c9-b11b-3e01cdc7a36e"},{"role":"toolResult","toolCallId":"call_00_UjYmvqkKpHabsoj8QBBp9005","toolName":"write","content":[{"type":"text","text":"Successfully wrote 2585 bytes to /tmp/post-zblog.py"}],"isError":false,"timestamp":1779001795173},{"role":"assistant","content":[{"type":"text","text":"Now execute both tasks simultaneously - Task A (WeChat API) and Task B (Z-Blog XML-RPC):"},{"type":"toolCall","id":"call_00_hqUFIxxBmRW7rENzai2V6059","name":"exec","arguments":{"command":"cd /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat && WECHAT_APP_ID= WECHAT_APP_SECRET= bun run scripts/wechat-api.ts /root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md --theme grace --color rose --author \"ai张三疯\" --cover /root/.openclaw/agents/101/workspace/imgs/cover.png 2>&1","timeout":60}},{"type":"toolCall","id":"call_01_LZ6Yuv8P03pQUTcivm9f3827","name":"exec","arguments":{"command":"python3 /tmp/post-zblog.py 2>&1","timeout":30}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":66,"output":282,"cacheRead":18048,"cacheWrite":0,"totalTokens":18396,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001795175,"responseId":"bb3f9da0-2396-4143-8185-7a2355885df8"},{"role":"toolResult","toolCallId":"call_00_hqUFIxxBmRW7rENzai2V6059","toolName":"exec","content":[{"type":"text","text":"[wechat-api] Theme: grace, color: rose, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: grace, color: rose, citeStatus: true\n[wechat-api] HTML generated: /tmp/wechat-article-images-ub3i0e/temp-article.html\n[wechat-api] Placeholder images: 0\n[wechat-api] Title: 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n[wechat-api] Author: ai张三疯\n[wechat-api] Digest: 画面里,一个盲人姑娘举着盲杖,小心翼翼地在人行道上探路。背景音乐缓慢,弹幕全是\"加油\"\"泪目\"\"这才...\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 cover: /root/.openclaw/agents/101/workspace/imgs/cover.png\n[wechat-api] Publishing to draft...\n{\n \"success\": true,\n \"media_id\": \"imBwNhfy9Uv4ps2luE5gfqu7biH9OiII_LWfanEv3nmc_F7x-uWEU3Vp468T3_w-\",\n \"title\": \"盲人主播赛道已饱和:当\\\"感动中国\\\"变成镰刀,短视频创业者的最后一课\",\n \"articleType\": \"news\"\n}\n[wechat-api] Published successfully! media_id: imBwNhfy9Uv4ps2luE5gfqu7biH9OiII_LWfanEv3nmc_F7x-uWEU3Vp468T3_w-"}],"details":{"status":"completed","exitCode":0,"durationMs":7206,"aggregated":"[wechat-api] Theme: grace, color: rose, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: grace, color: rose, citeStatus: true\n[wechat-api] HTML generated: /tmp/wechat-article-images-ub3i0e/temp-article.html\n[wechat-api] Placeholder images: 0\n[wechat-api] Title: 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n[wechat-api] Author: ai张三疯\n[wechat-api] Digest: 画面里,一个盲人姑娘举着盲杖,小心翼翼地在人行道上探路。背景音乐缓慢,弹幕全是\"加油\"\"泪目\"\"这才...\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 cover: /root/.openclaw/agents/101/workspace/imgs/cover.png\n[wechat-api] Publishing to draft...\n{\n \"success\": true,\n \"media_id\": \"imBwNhfy9Uv4ps2luE5gfqu7biH9OiII_LWfanEv3nmc_F7x-uWEU3Vp468T3_w-\",\n \"title\": \"盲人主播赛道已饱和:当\\\"感动中国\\\"变成镰刀,短视频创业者的最后一课\",\n \"articleType\": \"news\"\n}\n[wechat-api] Published successfully! media_id: imBwNhfy9Uv4ps2luE5gfqu7biH9OiII_LWfanEv3nmc_F7x-uWEU3Vp468T3_w-","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001806839},{"role":"toolResult","toolCallId":"call_01_LZ6Yuv8P03pQUTcivm9f3827","toolName":"exec","content":[{"type":"text","text":"Title: 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\nHTML size: 2674 chars\nTesting connection - fetching recent posts...\nConnection OK. Found 3 existing posts.\n - [9596] 对于有思想的人来说,这是最好的时代\n - [9595] 未来已来:大多数人还在聊天,少数人已经在赚钱了\n - [9597] Token越来越贵,但国家正在让算力像水电一样普惠\n\nPublishing new article...\n\n✅ Article published successfully! Post ID: True\n\nVerifying - fetching recent posts...\nLatest 5 posts:\n - [9596] 对于有思想的人来说,这是最好的时代 - 2026-05-17T21:08:55+08:00\n - [9595] 未来已来:大多数人还在聊天,少数人已经在赚钱了 - 2026-05-17T19:30:00+08:00\n - [9598] 盲人主播赛道已饱和:当"感动中国"变成镰刀,短视频创业者的最后一课 - 2026-05-17T15:09:24+08:00\n - [9597] Token越来越贵,但国家正在让算力像水电一样普惠 - 2026-05-17T14:36:26+08:00\n - [9594] 国产103号赛级燃油投产:一桶油的国产替代,比你想的更有深意 - 2026-05-17T10:29:30+08:00\n\n✅ Z-Blog publish complete!"}],"details":{"status":"completed","exitCode":0,"durationMs":8135,"aggregated":"Title: 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\nHTML size: 2674 chars\nTesting connection - fetching recent posts...\nConnection OK. Found 3 existing posts.\n - [9596] 对于有思想的人来说,这是最好的时代\n - [9595] 未来已来:大多数人还在聊天,少数人已经在赚钱了\n - [9597] Token越来越贵,但国家正在让算力像水电一样普惠\n\nPublishing new article...\n\n✅ Article published successfully! Post ID: True\n\nVerifying - fetching recent posts...\nLatest 5 posts:\n - [9596] 对于有思想的人来说,这是最好的时代 - 2026-05-17T21:08:55+08:00\n - [9595] 未来已来:大多数人还在聊天,少数人已经在赚钱了 - 2026-05-17T19:30:00+08:00\n - [9598] 盲人主播赛道已饱和:当"感动中国"变成镰刀,短视频创业者的最后一课 - 2026-05-17T15:09:24+08:00\n - [9597] Token越来越贵,但国家正在让算力像水电一样普惠 - 2026-05-17T14:36:26+08:00\n - [9594] 国产103号赛级燃油投产:一桶油的国产替代,比你想的更有深意 - 2026-05-17T10:29:30+08:00\n\n✅ Z-Blog publish complete!","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001806839},{"role":"assistant","content":[{"type":"text","text":"Both tasks completed successfully. Let me verify the WeChat draft by checking the draft list:"},{"type":"toolCall","id":"call_00_9vNKBrdimaX5DtN5WbNy2830","name":"exec","arguments":{"command":"cd /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat && WECHAT_APP_ID= WECHAT_APP_SECRET= bun run scripts/wechat-api.ts /dev/null --dry-run 2>&1 | head -5; echo \"---\"; # Use the same script env to verify token, fetch drafts\n# Let me check if there's a draft verification endpoint available\ngrep -n 'draft\\|list\\|Draft\\|List\\|batchget\\|getDraft\\|getMaterial' ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts 2>/dev/null | head -10"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":860,"output":243,"cacheRead":18304,"cacheWrite":0,"totalTokens":19407,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001806841,"responseId":"f558bac1-05f5-41e6-812e-972ffa63b7de"},{"role":"toolResult","toolCallId":"call_00_9vNKBrdimaX5DtN5WbNy2830","toolName":"exec","content":[{"type":"text","text":"[wechat-api] Theme: default, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: default, citeStatus: true\n[wechat-api] HTML generated: /tmp/wechat-article-images-UQ9d0i/temp-article.html\n[wechat-api] Placeholder images: 0\n[wechat-api] Title: null\n---\n56:const DRAFT_URL = \"https://api.weixin.qq.com/cgi-bin/draft/add\";\n236:async function publishToDraft(\n258: image_list: options.imageMediaIds.map(id => ({ image_media_id: id })),\n362: console.log(`Publish article to WeChat Official Account draft using API\n638: console.error(\"[wechat-api] Publishing to draft...\");\n639: const result = await publishToDraft({"}],"details":{"status":"completed","exitCode":0,"durationMs":1987,"aggregated":"[wechat-api] Theme: default, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: default, citeStatus: true\n[wechat-api] HTML generated: /tmp/wechat-article-images-UQ9d0i/temp-article.html\n[wechat-api] Placeholder images: 0\n[wechat-api] Title: null\n---\n56:const DRAFT_URL = \"https://api.weixin.qq.com/cgi-bin/draft/add\";\n236:async function publishToDraft(\n258: image_list: options.imageMediaIds.map(id => ({ image_media_id: id })),\n362: console.log(`Publish article to WeChat Official Account draft using API\n638: console.error(\"[wechat-api] Publishing to draft...\");\n639: const result = await publishToDraft({","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001816420},{"role":"assistant","content":[{"type":"text","text":"Let me verify the draft by calling the WeChat API directly to get the draft list:"},{"type":"toolCall","id":"call_00_562PdoUV5q8iszfGOt7t5620","name":"exec","arguments":{"command":"# Verify draft by fetching access token and listing drafts\nTOKEN=$(curl -s \"https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid=wx88b0cf376e0386c4&secret=b2d47ee298204c28cf82549d2798192f\" | python3 -c \"import sys,json; print(json.load(sys.stdin).get('access_token',''))\")\necho \"Token: ${TOKEN:0:10}...\"\n\n# Get draft list\ncurl -s -X POST \"https://api.weixin.qq.com/cgi-bin/draft/batchget?access_token=$TOKEN\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"offset\":0,\"count\":5,\"no_content\":1}' | python3 -c \"\nimport sys, json\ndata = json.load(sys.stdin)\nif 'item' in data:\n for item in data['item']:\n a = item.get('content',{}).get('news_item',[{}])[0]\n title = a.get('title','?')\n digest = a.get('digest','')[:40]\n print(f' - {title}')\n if '盲人' in title:\n print(' ✅ MATCH! This is our article.')\nelse:\n print(json.dumps(data, indent=2, ensure_ascii=False))\n\"","timeout":15}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":279,"output":382,"cacheRead":19328,"cacheWrite":0,"totalTokens":19989,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1779001816421,"responseId":"94784a49-68e2-4e9f-b1ab-3c6ea5e476f7"},{"role":"toolResult","toolCallId":"call_00_562PdoUV5q8iszfGOt7t5620","toolName":"exec","content":[{"type":"text","text":"Token: 104_mxRysY...\n - 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n ✅ MATCH! This is our article.\n - 无锡建起\"Token工厂\":算力正在变成工业品,创业者该醒醒了\n - 你的手机里,容不下那么多App\n - 未来已来:大多数人还在聊天,少数人已经在赚钱了\n - 我国自主研发,103号赛级燃油投产!一桶油的国产替代,比你想的更有深意"}],"details":{"status":"completed","exitCode":0,"durationMs":1118,"aggregated":"Token: 104_mxRysY...\n - 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n ✅ MATCH! This is our article.\n - 无锡建起\"Token工厂\":算力正在变成工业品,创业者该醒醒了\n - 你的手机里,容不下那么多App\n - 未来已来:大多数人还在聊天,少数人已经在赚钱了\n - 我国自主研发,103号赛级燃油投产!一桶油的国产替代,比你想的更有深意","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1779001821461},{"role":"assistant","content":[{"type":"text","text":"All verifications passed. Here's the completion summary:\n\n---\n\n## ✅ 双平台发布完成\n\n### 任务A:公众号发布 ✅\n- **平台:** 公众号「创业张三疯」(chuangyezhangsanfeng)\n- **文章:** 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n- **样式:** grace主题 / rose配色 / 作者:ai张三疯\n- **封面:** 已上传 cover.png\n- **状态:** ✅ 已成功发布到草稿箱(media_id 已返回)\n- **验证:** ✅ 草稿箱确认存在该文章\n\n### 任务B:创业思维网发布 ✅\n- **平台:** weixinsiwei.com (Z-Blog)\n- **文章ID:** 9598\n- **格式:** HTML 格式发布\n- **验证:** ✅ getRecentPosts 确认文章存在,最新5篇文章列表可查\n- **分类标签:** 盲人主播, 短视频创业, MCN, 内容创作, 创业思维"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":155,"output":234,"cacheRead":19968,"cacheWrite":0,"totalTokens":20357,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1779001821462,"responseId":"0e38227e-01d8-4c1d-bcea-1cebf343eda8"}]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","source":"runtime","type":"trace.artifacts","ts":"2026-05-17T07:10:24.587Z","seq":6,"sourceSeq":6,"sessionId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","sessionKey":"agent:fabu:subagent:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","runId":"5f5560f8-c398-44d7-8ebe-c8aef397ff43","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-05-17T07:10:24.587Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"promptErrorSource":null,"usage":{"input":11238,"output":2839,"cacheRead":156544,"total":170621},"promptCache":{"lastCallUsage":{"input":155,"output":234,"cacheRead":19968,"cacheWrite":0,"total":20357},"lastCacheTouchAt":1779001821462},"compactionCount":0,"assistantTexts":["I'll execute both publishing tasks. Let me start by verifying the input files exist, then run them in parallel.","Good, all files exist. Let me check the wechat-api.ts script to understand its usage, and also check what tools are available for the Z-Blog XML-RPC posting.","Let me look at the full wechat-api.ts to understand its argument parsing and run it.","Now I understand the CLI args. Let me run both tasks in parallel - Task A (WeChat publish) and Task B (Z-Blog publish).\n\nFirst, let me create the Python script for Z-Blog XML-RPC posting:","Now execute both tasks simultaneously - Task A (WeChat API) and Task B (Z-Blog XML-RPC):","Both tasks completed successfully. Let me verify the WeChat draft by checking the draft list:","Let me verify the draft by calling the WeChat API directly to get the draft list:","All verifications passed. Here's the completion summary:\n\n---\n\n## ✅ 双平台发布完成\n\n### 任务A:公众号发布 ✅\n- **平台:** 公众号「创业张三疯」(chuangyezhangsanfeng)\n- **文章:** 盲人主播赛道已饱和:当\"感动中国\"变成镰刀,短视频创业者的最后一课\n- **样式:** grace主题 / rose配色 / 作者:ai张三疯\n- **封面:** 已上传 cover.png\n- **状态:** ✅ 已成功发布到草稿箱(media_id 已返回)\n- **验证:** ✅ 草稿箱确认存在该文章\n\n### 任务B:创业思维网发布 ✅\n- **平台:** weixinsiwei.com (Z-Blog)\n- **文章ID:** 9598\n- **格式:** HTML 格式发布\n- **验证:** ✅ getRecentPosts 确认文章存在,最新5篇文章列表可查\n- **分类标签:** 盲人主播, 短视频创业, MCN, 内容创作, 创业思维"],"finalPromptText":"[Sun 2026-05-17 15:09 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":30,"completedCount":30,"activeCount":0},"toolMetas":[{"toolName":"exec","meta":"show first 100 lines of /tmp/blind-host-article.html, `head -100 /tmp/blind-host-article.html`"},{"toolName":"exec","meta":"show ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md -> show first 50 lines, `cat ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md | head -50`"},{"toolName":"exec","meta":"list files in ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md, `ls -la ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/盲人主播赛道饱和.md /tmp/blind-host-article.html ~/.o…`"},{"toolName":"exec","meta":"list files in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts, `ls ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts 2>&1`"},{"toolName":"exec","meta":"show first 30 lines of ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts, `head -30 ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts`"},{"toolName":"exec","meta":"run which bun → run bun 2>&1, `which bun && bun --version 2>&1`"},{"toolName":"exec","meta":"run which python3 → run python3 inline script, `which python3 && python3 -c \"import xmlrpc.client; print('xmlrpc available')\" 2>&1`"},{"toolName":"exec","meta":"search \"arg|--|process|parse|commander|yargs|option|usage\" in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts -> show first 30 lines, `grep -n 'arg\\|--\\|process\\|parse\\|commander\\|yargs\\|option\\|usage' ~/.openclaw/agents/101/workspace/skills/baoyu-post-t…`"},{"toolName":"exec","meta":"list files in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/, `ls ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/`"},{"toolName":"exec","meta":"search \"usage|Usage|process.argv|parseArgs|options|program|.option|.command|help\" in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts -> show last 30 lines, `grep -n 'usage\\|Usage\\|process.argv\\|parseArgs\\|options\\|program\\|.option\\|.command\\|help' ~/.openclaw/agents/101/works…`"},{"toolName":"read","meta":"lines 361-460 from ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts"},{"toolName":"write","meta":"to /tmp/post-zblog.py (2585 chars)"},{"toolName":"exec","meta":"cd ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat && WECHAT_APP_ID= WECHAT_APP_SECR… (in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat)"},{"toolName":"exec","meta":"run python3 /tmp/post-zblog.py, `python3 /tmp/post-zblog.py 2>&1`"},{"toolName":"exec","meta":"run scripts/wechat-api.ts -> show first 5 lines → print text → run # Use (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_SECR…`"},{"toolName":"exec","meta":"# Verify draft by fetching access token and listing drafts TOKEN=*** -s \"https://api.weixin.qq.com/cgi-bin/token?gra…"}],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","source":"runtime","type":"session.ended","ts":"2026-05-17T07:10:24.587Z","seq":7,"sourceSeq":7,"sessionId":"2c0fe23c-307e-46c0-b28f-1e2f19262eaa","sessionKey":"agent:fabu:subagent:5642f637-7f41-46f8-b1de-1d5cd09c2ab3","runId":"5f5560f8-c398-44d7-8ebe-c8aef397ff43","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}}