{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","source":"runtime","type":"session.started","ts":"2026-05-17T05:08:08.787Z","seq":1,"sourceSeq":1,"sessionId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","sessionKey":"agent:fabu:subagent:9ea3e583-6d81-45ff-9240-d99a226ba0cc","runId":"65237b76-9fcf-4855-ab6b-532a13559992","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"trigger":"user","sessionFile":"/root/.openclaw/agents/fabu/sessions/e07625ff-d4a8-4da2-a10f-e4a3e3db3061.jsonl","workspaceDir":"/root/.openclaw/workspace/fabu","agentId":"fabu","messageChannel":"feishu","toolCount":12,"clientToolCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","source":"runtime","type":"trace.metadata","ts":"2026-05-17T05:08:08.792Z","seq":2,"sourceSeq":2,"sessionId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","sessionKey":"agent:fabu:subagent:9ea3e583-6d81-45ff-9240-d99a226ba0cc","runId":"65237b76-9fcf-4855-ab6b-532a13559992","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-05-17T05:08:08.788Z","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/e07625ff-d4a8-4da2-a10f-e4a3e3db3061.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":1778994488762,"sessionId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","sessionKey":"agent:fabu:subagent:9ea3e583-6d81-45ff-9240-d99a226ba0cc","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":28542,"projectContextChars":14961,"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:9ea3e583-6d81-45ff-9240-d99a226ba0cc","agentId":"fabu","messageChannel":"feishu"}}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","source":"runtime","type":"context.compiled","ts":"2026-05-17T05:08:08.808Z","seq":3,"sourceSeq":3,"sessionId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","sessionKey":"agent:fabu:subagent:9ea3e583-6d81-45ff-9240-d99a226ba0cc","runId":"65237b76-9fcf-4855-ab6b-532a13559992","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:** 对于有思想的人来说,这是最好的时代\n**主题判断:** AI应用、创业思维 → 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/有思想的人最好的时代.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/有思想的人最好的时代.md \\\n --theme default --color blue --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/best-era-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:9ea3e583-6d81-45ff-9240-d99a226ba0cc.\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 13:07 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":"4a81173e"}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","source":"runtime","type":"prompt.submitted","ts":"2026-05-17T05:08:08.810Z","seq":4,"sourceSeq":4,"sessionId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","sessionKey":"agent:fabu:subagent:9ea3e583-6d81-45ff-9240-d99a226ba0cc","runId":"65237b76-9fcf-4855-ab6b-532a13559992","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"prompt":"[Sun 2026-05-17 13:07 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:** 对于有思想的人来说,这是最好的时代\n**主题判断:** AI应用、创业思维 → 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/有思想的人最好的时代.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/有思想的人最好的时代.md \\\n --theme default --color blue --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/best-era-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:9ea3e583-6d81-45ff-9240-d99a226ba0cc.\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":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","source":"runtime","type":"model.completed","ts":"2026-05-17T05:08:59.605Z","seq":5,"sourceSeq":5,"sessionId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","sessionKey":"agent:fabu:subagent:9ea3e583-6d81-45ff-9240-d99a226ba0cc","runId":"65237b76-9fcf-4855-ab6b-532a13559992","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":12462,"output":4613,"cacheRead":250112,"total":267187},"promptCache":{"lastCallUsage":{"input":312,"output":220,"cacheRead":22656,"cacheWrite":0,"total":23188},"lastCacheTouchAt":1778994536880},"compactionCount":0,"assistantTexts":["I'll execute both publishing tasks. Let me start by reading the article and preparing the HTML for Z-Blog, while also checking the wechat script.","Good, I have the article content and can see the script structure. Let me check what the wechat script supports and also get the cover image path.","Good, cover image exists. Now let me check the full script to understand CLI flags more completely.","Let me check the full CLI args parsing:","Now I need to check how the script handles credentials — it wants WECHAT_APP_ID and WECHAT_APP_SECRET env vars. Let me look at that part:","Now let me check how credentials are loaded:","Good. Now let me prepare the HTML file for Z-Blog and run both tasks. First, let me create the HTML file for the Z-Blog WordPress/XML-RPC publish.","Now let me run both tasks in parallel. For task A (WeChat), I'll use the provided credentials. For task B (Z-Blog), I need to use XML-RPC.\n\nLet me start with the WeChat publish:","✅ **任务A(公众号)完成!** 文章已成功发布到草稿箱,media_id 已获取。\n\n现在执行任务B(创业思维网 Z-Blog)。我需要通过 XML-RPC 来发布。让我写一个 Node.js 脚本来完成这个操作:","两个任务都完成了!让我总结一下:\n\n---\n\n## ✅ 发布任务全部完成!\n\n### 任务A:公众号发布 ✅\n- **公众号:** 创业张三疯(chuangyezhangsanfeng)\n- **标题:** 对于有思想的人来说,这是最好的时代\n- **作者:** ai张三疯\n- **状态:** 已成功发布至草稿箱 ✅\n- **media_id:** `imBwNhfy9Uv4ps2luE5gfqJMIpuMMgJz_9TnRLKAQ6jPtHSahtmO2ABpQIe5SrPJ`\n\n### 任务B:创业思维网发布 ✅\n- **网站:** weixinsiwei.com(Z-Blog)\n- **标题:** 对于有思想的人来说,这是最好的时代\n- **文章ID:** `9596`\n- **状态:** 已成功发布 ✅\n- **验证:** 通过 getRecentPosts 验证,文章已在最新3篇中确认 ✅"],"finalPromptText":"[Sun 2026-05-17 13:07 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 13:07 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":1778994488812},{"role":"assistant","content":[{"type":"text","text":"I'll execute both publishing tasks. Let me start by reading the article and preparing the HTML for Z-Blog, while also checking the wechat script."},{"type":"toolCall","id":"call_00_vsh4FyOqDBNM8GvXzhvR5745","name":"read","arguments":{"path":"/root/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/有思想的人最好的时代.md"}},{"type":"toolCall","id":"call_01_LrFMIfIYTyes6taRIHvr8093","name":"exec","arguments":{"command":"cat /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts | head -50"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":4686,"output":167,"cacheRead":7168,"cacheWrite":0,"totalTokens":12021,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994488851,"responseId":"0f6e0c61-d959-44bc-9873-75bc541fd6c1"},{"role":"toolResult","toolCallId":"call_00_vsh4FyOqDBNM8GvXzhvR5745","toolName":"read","content":[{"type":"text","text":"# 对于有思想的人来说,这是最好的时代\n\n你有没有过这样的感觉?\n\n脑子里有一个想法,一个方案,一个你觉得特别棒的商业模式。你越想越兴奋,越想越觉得\"这事儿能成\"。\n\n然后呢?\n\n然后就没有然后了。\n\n因为从\"想出来\"到\"做出来\",中间隔着十万八千里。你需要写商业计划书、找团队、招人、筹钱、做产品原型、跑市场验证……任何一个环节卡住,那个在深夜里让你兴奋到睡不着的念头,就永远只是个念头。\n\n太多人,被卡在了想法和结果之间那道看不见的墙上。\n\n但现在不一样了。\n\n## 历史上从来没有过这样的时代\n\n想想看,人类历史上什么时候有过这样的时刻——你说一句话,世界就会动起来?\n\n几千年前,人类最大的痛苦是吃不饱。几百年前,最大的痛苦是信息传不远。几十年前,最大的痛苦是算力不够用。\n\n而你看看今天。\n\n你只需要对AI说一句话:\"帮我做一个XX行业的竞品分析报告\",十分钟后一份结构清晰、数据翔实的报告就摆在你面前。\n\n你只需要说:\"帮我设计一套获客方案\",AI就能给你列出从内容营销到私域运营的完整路径。\n\n你只需要说:\"帮我写一段推广文案\",AI就能根据你的产品卖点和目标人群,产出几个版本的文案供你挑选。\n\n**想法到实现的距离,被AI压缩成了一句话。**\n\n这不是科幻片里的场景。这是2026年5月,任何一个有手机、有网络的人,此时此刻就能做到的事。\n\n## 过去创业,最大的成本是什么?\n\n不是钱。\n\n是验证想法。\n\n五年前,我有一个哥们儿想做一款面向小微企业主的SaaS工具。他花了一个月写BP,三个月找团队,六个月做开发,又花了两个月跑市场推广。等到产品正式上线,他发现一个问题——目标客户根本不愿意在这件事上花钱。\n\n前后投入一年,烧了几十万,换回来一个\"此路不通\"。\n\n这笔学费,贵不贵?贵。值不值?值——因为那个\"不\"是用时间和金钱真金白银换回来的。\n\n但今天呢?\n\n你有一个想法,让AI帮你做一个市场调研。你把产品的核心功能描述给AI,让它模拟目标用户的反馈。你让AI帮你生成一个MVP的思路和执行清单。你甚至可以先用AI生成内容做一轮市场测试——发几篇文章、做几个视频、看用户反馈。\n\n**你不需要投入几十万,你只需要投入一个下午。**\n\n这就是过去十年商业世界最大的变化:试错成本从\"倾家荡产\"降到了\"一杯咖啡\"。\n\n## 有思想的人,之前到底被什么卡住了?\n\n来,我帮你捋一下。\n\n你有一个好想法。你需要把它做出来,对吧?\n\n做出来需要什么?\n\n**第一个卡点:执行能力。**\n\n你不会写代码?看不懂财务报表?不了解供应链?没关系。AI可以:帮你生成代码框架、帮你分析财务报表、帮你梳理供应链的上下游关系。\n\n你不是没有能力,你只是之前找不到\"能干这些活的人\"。现在有了。\n\n**第二个卡点:资源。**\n\n你没钱招团队。你没有办公室。你没有渠道资源。OK,AI就是你的团队——它是你的市场研究员、文案写手、设计师、数据分析师、客服、甚至项目经理。\n\n过去你一个人扛着一个项目,什么都得自己干。现在你一个人,带着一个无限耐心的\"数字团队\"。\n\n**第三个卡点:时间。**\n\n你白天有工作,晚上有家庭,你没办法全职投入。可以理解。AI可以帮你24小时跑。你睡觉的时候,它在做数据分析。你吃饭的时候,它在生成内容。你通勤的时候,它在跑A/B测试方案。\n\n**有思想的人,之前缺的不是想法,是执行团队的资源。现在AI就是你的执行团队。**\n\n你只需要想清楚\"做什么\"和\"为什么做\",剩下的\"怎么做\",交给AI。\n\n## 别把AI当聊天工具,把它当成你的\"数字员工军团\"\n\n很多人到现在还在干嘛?跟AI聊天。\n\n\"帮我写一首诗\"、\"给我讲个笑话\"、\"模仿村上春树的风格写一段话\"。\n\n这些当然有趣。但如果你只停留在这个层面,你是在浪费这个时代最慷慨的馈赠。\n\n真正的用法是什么?\n\n把AI当成你的数字员工军团。\n\n在创业的领域,你一个人,通过AI,可以顶过去一家小型创业公司的产能。\n\n举个例子:\n\n你是做小红书内容的。传统模式:你需要一个内容策划、一个文案、一个设计师、一个排版——至少三个人。月薪加起来一万五到两万。\n\nAI模式:你一个人。让AI分析近期爆款选题,让AI生成初稿,让AI配图,让AI优化排版。你只需要做一件事——审稿和调整方向。\n\n一个人干的活,覆盖了三个人。成本从两万降到两百。产能输出翻倍。\n\n你说你是小生意、小老板、个人创业者,团队这个词对你来说太奢侈了。没关系。现在的AI,是你用一杯奶茶的价格,就能请到的\"全能员工\"。\n\n你见过创业者为了省一个员工的钱,自己熬夜到凌晨三点做图、写文案、跑数据。现在这些事,动动嘴就干完了。\n\n**你不是在省多少钱的问题。你是在释放你自己的时间——让你从\"做事的人\",变成\"决策的人\"。**\n\n这才是最值钱的转变。\n\n## 只做最值钱的那部分工作\n\n想想看,你一天24小时,真正\"值钱\"的时间有多少?\n\n开会、填表、回邮件、排期、改稿、对数据……这些事占了你一天百分之八十的时间。真正需要你深度思考、做判断、定方向的时间,可能不到两小时。\n\n但现在,你可以把那百分之八十的时间,交给AI。\n\n你需要做的,是那两小时的事。\n\n为什么?因为只有那两小时的事,别人拿不走。只有那两小时的事,才是你真正的价值所在。\n\nAI可以帮你写1000篇文章。但它不知道哪一篇最能打动人。\nAI可以帮你做100份方案。但它不知道哪一份最适合你的客户。\nAI可以帮你分析1000条数据。但它不知道这些数据背后,藏着什么样的商业直觉。\n\n**AI给你的是\"效率\",你给AI的是\"方向\"。**\n\n有方向的人,配上高效率的工具,就是无敌的。\n\n## 问题回到你身上\n\n所以你想想看。\n\n过去你被卡住的那些想法——那个想做的公众号、那个想启动的小项目、那个一直想写的书、那个思考了很久的商业模式——你今天还不动手,不是因为AI不够强。\n\n是因为你还没有想通一个道理:\n\n**以前做事,需要的是\"我有什么\"。有资金、有团队、有资源、有关系。什么都没有,什么都干不了。**\n\n**现在做事,需要的是\"我想什么\"。有想法、有判断、有方向、有策略。这四个有了,剩下的交给AI。**\n\n历史上,从来没有一个时代,如此慷慨地把\"实现的力量\"交到每一个有思想的人手上。\n\n工业时代,你要有工厂、设备、工人。互联网时代,你要有团队、技术、资本。AI时代,你只需要——动动嘴。\n\n这个时代在奖励谁?\n\n奖励那些敢想的人。奖励那些有判断力的人。奖励那些知道\"什么值得做\"的人。\n\n而这些人,被卡了多久?\n\n卡了多久不重要。重要的是,那堵墙,现在塌了。\n\n对于有思想的人来说,这不是一个容易的时代。这是一个幸运的时代。\n\n不是因为AI能做一切。而是因为——**你只需要做那个最值钱的部分,剩下的,AI来。**"}],"isError":false,"timestamp":1778994490930},{"role":"toolResult","toolCallId":"call_01_LrFMIfIYTyes6taRIHvr8093","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}\n\ninterface MarkdownRenderResult {\n title: string;\n author: string;\n summary: string;\n htmlPath: string;\n contentImages: ImageInfo[];\n}\n\ntype ArticleType = \"news\" | \"newspic\";\n\ninterface ArticleOptions {\n title: string;\n author?: string;\n digest?: string;\n content: string;\n thumbMediaId: string;\n articleType: ArticleType;\n imageMediaIds?: string[];\n needOpenComment?: number;"}],"details":{"status":"completed","exitCode":0,"durationMs":39,"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}\n\ninterface MarkdownRenderResult {\n title: string;\n author: string;\n summary: string;\n htmlPath: string;\n contentImages: ImageInfo[];\n}\n\ntype ArticleType = \"news\" | \"newspic\";\n\ninterface ArticleOptions {\n title: string;\n author?: string;\n digest?: string;\n content: string;\n thumbMediaId: string;\n articleType: ArticleType;\n imageMediaIds?: string[];\n needOpenComment?: number;","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1778994490930},{"role":"assistant","content":[{"type":"text","text":"Good, I have the article content and can see the script structure. Let me check what the wechat script supports and also get the cover image path."},{"type":"toolCall","id":"call_00_dWsdj1maTUbEWfWhWSBH9198","name":"exec","arguments":{"command":"ls -la /root/.openclaw/agents/101/workspace/imgs/cover.png 2>/dev/null; ls -la /root/.openclaw/agents/101/workspace/imgs/ 2>/dev/null; echo \"---\"; head -100 /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts | tail -50"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":2079,"output":165,"cacheRead":11776,"cacheWrite":0,"totalTokens":14020,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994490931,"responseId":"64c331f5-b5f2-4245-9876-7297aad86e8c"},{"role":"toolResult","toolCallId":"call_00_dWsdj1maTUbEWfWhWSBH9198","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\ntotal 204\ndrwxr-xr-x 12 root root 4096 May 11 09:19 .\ndrwxr-xr-x 19 root root 4096 May 12 21:53 ..\ndrwxr-xr-x 2 root root 4096 May 11 09:19 ai-agent\ndrwxr-xr-x 2 root root 4096 May 3 19:29 ai-app\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 ai-chip\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 business\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 company\n-rw-r--r-- 1 root root 159045 Mar 26 13:01 cover.png\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 default\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 policy\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 productivity\ndrwxr-xr-x 3 root root 4096 May 3 21:00 qiyukeji\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 tech\n---\n onlyFansCanComment?: number;\n}\n\nconst TOKEN_URL = \"https://api.weixin.qq.com/cgi-bin/token\";\nconst UPLOAD_URL = \"https://api.weixin.qq.com/cgi-bin/material/add_material\";\nconst DRAFT_URL = \"https://api.weixin.qq.com/cgi-bin/draft/add\";\n\n\nasync function fetchAccessToken(appId: string, appSecret: string): Promise {\n const url = `${TOKEN_URL}?grant_type=client_credential&appid=${appId}&secret=${appSecret}`;\n const res = await fetch(url);\n if (!res.ok) {\n throw new Error(`Failed to fetch access token: ${res.status}`);\n }\n const data = await res.json() as AccessTokenResponse;\n if (data.errcode) {\n throw new Error(`Access token error ${data.errcode}: ${data.errmsg}`);\n }\n if (!data.access_token) {\n throw new Error(\"No access_token in response\");\n }\n return data.access_token;\n}\n\nasync function uploadImage(\n imagePath: string,\n accessToken: string,\n baseDir?: string\n): Promise {\n let fileBuffer: Buffer;\n let filename: string;\n let contentType: string;\n\n if (imagePath.startsWith(\"http://\") || imagePath.startsWith(\"https://\")) {\n const response = await fetch(imagePath);\n if (!response.ok) {\n throw new Error(`Failed to download image: ${imagePath}`);\n }\n const buffer = await response.arrayBuffer();\n if (buffer.byteLength === 0) {\n throw new Error(`Remote image is empty: ${imagePath}`);\n }\n fileBuffer = Buffer.from(buffer);\n const urlPath = imagePath.split(\"?\")[0];\n filename = path.basename(urlPath) || \"image.jpg\";\n contentType = response.headers.get(\"content-type\") || \"image/jpeg\";\n } else {\n const resolvedPath = path.isAbsolute(imagePath)\n ? imagePath\n : path.resolve(baseDir || process.cwd(), imagePath);"}],"details":{"status":"completed","exitCode":0,"durationMs":70,"aggregated":"-rw-r--r-- 1 root root 159045 Mar 26 13:01 /root/.openclaw/agents/101/workspace/imgs/cover.png\ntotal 204\ndrwxr-xr-x 12 root root 4096 May 11 09:19 .\ndrwxr-xr-x 19 root root 4096 May 12 21:53 ..\ndrwxr-xr-x 2 root root 4096 May 11 09:19 ai-agent\ndrwxr-xr-x 2 root root 4096 May 3 19:29 ai-app\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 ai-chip\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 business\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 company\n-rw-r--r-- 1 root root 159045 Mar 26 13:01 cover.png\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 default\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 policy\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 productivity\ndrwxr-xr-x 3 root root 4096 May 3 21:00 qiyukeji\ndrwxr-xr-x 2 root root 4096 Apr 25 11:58 tech\n---\n onlyFansCanComment?: number;\n}\n\nconst TOKEN_URL = \"https://api.weixin.qq.com/cgi-bin/token\";\nconst UPLOAD_URL = \"https://api.weixin.qq.com/cgi-bin/material/add_material\";\nconst DRAFT_URL = \"https://api.weixin.qq.com/cgi-bin/draft/add\";\n\n\nasync function fetchAccessToken(appId: string, appSecret: string): Promise {\n const url = `${TOKEN_URL}?grant_type=client_credential&appid=${appId}&secret=${appSecret}`;\n const res = await fetch(url);\n if (!res.ok) {\n throw new Error(`Failed to fetch access token: ${res.status}`);\n }\n const data = await res.json() as AccessTokenResponse;\n if (data.errcode) {\n throw new Error(`Access token error ${data.errcode}: ${data.errmsg}`);\n }\n if (!data.access_token) {\n throw new Error(\"No access_token in response\");\n }\n return data.access_token;\n}\n\nasync function uploadImage(\n imagePath: string,\n accessToken: string,\n baseDir?: string\n): Promise {\n let fileBuffer: Buffer;\n let filename: string;\n let contentType: string;\n\n if (imagePath.startsWith(\"http://\") || imagePath.startsWith(\"https://\")) {\n const response = await fetch(imagePath);\n if (!response.ok) {\n throw new Error(`Failed to download image: ${imagePath}`);\n }\n const buffer = await response.arrayBuffer();\n if (buffer.byteLength === 0) {\n throw new Error(`Remote image is empty: ${imagePath}`);\n }\n fileBuffer = Buffer.from(buffer);\n const urlPath = imagePath.split(\"?\")[0];\n filename = path.basename(urlPath) || \"image.jpg\";\n contentType = response.headers.get(\"content-type\") || \"image/jpeg\";\n } else {\n const resolvedPath = path.isAbsolute(imagePath)\n ? imagePath\n : path.resolve(baseDir || process.cwd(), imagePath);","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1778994492597},{"role":"assistant","content":[{"type":"text","text":"Good, cover image exists. Now let me check the full script to understand CLI flags more completely."},{"type":"toolCall","id":"call_00_yFkO4h2Uv00xLGWqsfmC0299","name":"exec","arguments":{"command":"cd /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts && grep -n \"parse\\|parse_args\\|commander\\|yargs\\|process\\.\\|argv\\|option\\.\" wechat-api.ts | head -40"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":872,"output":119,"cacheRead":13952,"cacheWrite":0,"totalTokens":14943,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994492598,"responseId":"45adc025-13bd-45e4-8ef4-c0e51d056510"},{"role":"toolResult","toolCallId":"call_00_yFkO4h2Uv00xLGWqsfmC0299","toolName":"exec","content":[{"type":"text","text":"100: : path.resolve(baseDir || process.cwd(), imagePath);\n291:function parseFrontmatter(content: string): { frontmatter: Record; body: string } {\n343: return JSON.parse(stdout) as MarkdownRenderResult;\n410: process.exit(0);\n428:function parseArgs(argv: string[]): CliArgs {\n429: if (argv.length === 0 || argv.includes(\"--help\") || argv.includes(\"-h\")) {\n442: for (let i = 0; i < argv.length; i++) {\n443: const arg = argv[i]!;\n444: if (arg === \"--type\" && argv[i + 1]) {\n445: const t = argv[++i]!.toLowerCase();\n449: } else if (arg === \"--title\" && argv[i + 1]) {\n450: args.title = argv[++i];\n451: } else if (arg === \"--author\" && argv[i + 1]) {\n452: args.author = argv[++i];\n453: } else if (arg === \"--summary\" && argv[i + 1]) {\n454: args.summary = argv[++i];\n455: } else if (arg === \"--theme\" && argv[i + 1]) {\n456: args.theme = argv[++i]!;\n457: } else if (arg === \"--color\" && argv[i + 1]) {\n458: args.color = argv[++i];\n459: } else if (arg === \"--cover\" && argv[i + 1]) {\n460: args.cover = argv[++i];\n461: } else if (arg === \"--account\" && argv[i + 1]) {\n462: args.account = argv[++i];\n469: } else if (arg.startsWith(\"--\") && argv[i + 1] && !argv[i + 1]!.startsWith(\"-\")) {\n478: process.exit(1);\n495: const args = parseArgs(process.argv.slice(2));\n500: process.exit(1);\n518: const parsed = parseFrontmatter(mdContent);\n519: frontmatter = parsed.frontmatter;\n530: const parsed = parseFrontmatter(content);\n531: frontmatter = parsed.frontmatter;\n532: const body = parsed.body;\n556: process.exit(1);\n611: ? path.resolve(process.cwd(), rawCoverPath)\n630: process.exit(1);\n635: process.exit(1);\n663: process.exit(1);"}],"details":{"status":"completed","exitCode":0,"durationMs":44,"aggregated":"100: : path.resolve(baseDir || process.cwd(), imagePath);\n291:function parseFrontmatter(content: string): { frontmatter: Record; body: string } {\n343: return JSON.parse(stdout) as MarkdownRenderResult;\n410: process.exit(0);\n428:function parseArgs(argv: string[]): CliArgs {\n429: if (argv.length === 0 || argv.includes(\"--help\") || argv.includes(\"-h\")) {\n442: for (let i = 0; i < argv.length; i++) {\n443: const arg = argv[i]!;\n444: if (arg === \"--type\" && argv[i + 1]) {\n445: const t = argv[++i]!.toLowerCase();\n449: } else if (arg === \"--title\" && argv[i + 1]) {\n450: args.title = argv[++i];\n451: } else if (arg === \"--author\" && argv[i + 1]) {\n452: args.author = argv[++i];\n453: } else if (arg === \"--summary\" && argv[i + 1]) {\n454: args.summary = argv[++i];\n455: } else if (arg === \"--theme\" && argv[i + 1]) {\n456: args.theme = argv[++i]!;\n457: } else if (arg === \"--color\" && argv[i + 1]) {\n458: args.color = argv[++i];\n459: } else if (arg === \"--cover\" && argv[i + 1]) {\n460: args.cover = argv[++i];\n461: } else if (arg === \"--account\" && argv[i + 1]) {\n462: args.account = argv[++i];\n469: } else if (arg.startsWith(\"--\") && argv[i + 1] && !argv[i + 1]!.startsWith(\"-\")) {\n478: process.exit(1);\n495: const args = parseArgs(process.argv.slice(2));\n500: process.exit(1);\n518: const parsed = parseFrontmatter(mdContent);\n519: frontmatter = parsed.frontmatter;\n530: const parsed = parseFrontmatter(content);\n531: frontmatter = parsed.frontmatter;\n532: const body = parsed.body;\n556: process.exit(1);\n611: ? path.resolve(process.cwd(), rawCoverPath)\n630: process.exit(1);\n635: process.exit(1);\n663: process.exit(1);","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1778994494277},{"role":"assistant","content":[{"type":"text","text":"Let me check the full CLI args parsing:"},{"type":"toolCall","id":"call_00_a09nHGoz8xPe0enzgSGD8514","name":"read","arguments":{"path":"/root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts","offset":428,"limit":80}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":667,"output":112,"cacheRead":14848,"cacheWrite":0,"totalTokens":15627,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994494278,"responseId":"2b285202-cf6c-4175-810c-c9511a3d30eb"},{"role":"toolResult","toolCallId":"call_00_a09nHGoz8xPe0enzgSGD8514","toolName":"read","content":[{"type":"text","text":"function 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 } else if (arg === \"--account\" && argv[i + 1]) {\n args.account = argv[++i];\n } else if (arg === \"--cite\") {\n args.citeStatus = true;\n } else if (arg === \"--no-cite\") {\n args.citeStatus = false;\n } else if (arg === \"--dry-run\") {\n args.dryRun = true;\n } else if (arg.startsWith(\"--\") && argv[i + 1] && !argv[i + 1]!.startsWith(\"-\")) {\n i++;\n } else if (!arg.startsWith(\"-\")) {\n args.filePath = arg;\n }\n }\n\n if (!args.filePath) {\n console.error(\"Error: File path required\");\n process.exit(1);\n }\n\n args.isHtml = args.filePath.toLowerCase().endsWith(\".html\");\n\n return args;\n}\n\nfunction extractHtmlTitle(html: string): string {\n const titleMatch = html.match(/([^<]+)<\\/title>/i);\n if (titleMatch) return titleMatch[1]!;\n const h1Match = html.match(/<h1[^>]*>([^<]+)<\\/h1>/i);\n if (h1Match) return h1Match[1]!.replace(/<[^>]+>/g, \"\").trim();\n return \"\";\n}\n\nasync function main(): Promise<void> {\n const args = parseArgs(process.argv.slice(2));\n\n const filePath = path.resolve(args.filePath);\n if (!fs.existsSync(filePath)) {\n console.error(`Error: File not found: ${filePath}`);\n process.exit(1);\n }\n\n const baseDir = path.dirname(filePath);\n let title = args.title || \"\";\n let author = args.author || \"\";\n let digest = args.summary || \"\";\n let htmlPath: string;\n\n[158 more lines in file. Use offset=508 to continue.]"}],"isError":false,"timestamp":1778994495375},{"role":"assistant","content":[{"type":"text","text":"Now I need to check how the script handles credentials — it wants WECHAT_APP_ID and WECHAT_APP_SECRET env vars. Let me look at that part:"},{"type":"toolCall","id":"call_00_DIQ2LVxb0jXGyLLeOHj39819","name":"read","arguments":{"offset":508,"path":"/root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts","limit":160}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":777,"output":140,"cacheRead":15616,"cacheWrite":0,"totalTokens":16533,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994495376,"responseId":"17d39c02-1d83-4db1-925b-e94a7dafed1e"},{"role":"toolResult","toolCallId":"call_00_DIQ2LVxb0jXGyLLeOHj39819","toolName":"read","content":[{"type":"text","text":" let htmlContent: string;\n let frontmatter: Record<string, string> = {};\n let contentImages: ImageInfo[] = [];\n\n if (args.isHtml) {\n htmlPath = filePath;\n htmlContent = extractHtmlContent(htmlPath);\n const mdPath = filePath.replace(/\\.html$/i, \".md\");\n if (fs.existsSync(mdPath)) {\n const mdContent = fs.readFileSync(mdPath, \"utf-8\");\n const parsed = parseFrontmatter(mdContent);\n frontmatter = parsed.frontmatter;\n if (!title && frontmatter.title) title = frontmatter.title;\n if (!author) author = frontmatter.author || \"\";\n if (!digest) digest = frontmatter.digest || frontmatter.summary || frontmatter.description || \"\";\n }\n if (!title) {\n title = extractHtmlTitle(fs.readFileSync(htmlPath, \"utf-8\"));\n }\n console.error(`[wechat-api] Using HTML file: ${htmlPath}`);\n } else {\n const content = fs.readFileSync(filePath, \"utf-8\");\n const parsed = parseFrontmatter(content);\n frontmatter = parsed.frontmatter;\n const body = parsed.body;\n\n title = title || frontmatter.title || \"\";\n if (!title) {\n const h1Match = body.match(/^#\\s+(.+)$/m);\n if (h1Match) title = h1Match[1]!;\n }\n if (!author) author = frontmatter.author || \"\";\n if (!digest) digest = frontmatter.digest || frontmatter.summary || frontmatter.description || \"\";\n\n console.error(`[wechat-api] Theme: ${args.theme}${args.color ? `, color: ${args.color}` : \"\"}, citeStatus: ${args.citeStatus}`);\n const rendered = renderMarkdownWithPlaceholders(filePath, args.theme, args.color, args.citeStatus, args.title);\n htmlPath = rendered.htmlPath;\n contentImages = rendered.contentImages;\n if (!title) title = rendered.title;\n if (!author) author = rendered.author;\n if (!digest) digest = rendered.summary;\n console.error(`[wechat-api] HTML generated: ${htmlPath}`);\n console.error(`[wechat-api] Placeholder images: ${contentImages.length}`);\n htmlContent = extractHtmlContent(htmlPath);\n }\n\n if (!title) {\n console.error(\"Error: No title found. Provide via --title, frontmatter, or <title> tag.\");\n process.exit(1);\n }\n\n if (digest && digest.length > 120) {\n const truncated = digest.slice(0, 117);\n const lastPunct = Math.max(truncated.lastIndexOf(\"。\"), truncated.lastIndexOf(\",\"), truncated.lastIndexOf(\";\"), truncated.lastIndexOf(\"、\"));\n digest = lastPunct > 80 ? truncated.slice(0, lastPunct + 1) : truncated + \"...\";\n console.error(`[wechat-api] Digest truncated to ${digest.length} chars`);\n }\n\n console.error(`[wechat-api] Title: ${title}`);\n if (author) console.error(`[wechat-api] Author: ${author}`);\n if (digest) console.error(`[wechat-api] Digest: ${digest.slice(0, 50)}...`);\n console.error(`[wechat-api] Type: ${args.articleType}`);\n\n const extConfig = loadWechatExtendConfig();\n const resolved = resolveAccount(extConfig, args.account);\n if (resolved.name) console.error(`[wechat-api] Account: ${resolved.name} (${resolved.alias})`);\n\n if (!author && resolved.default_author) author = resolved.default_author;\n\n if (args.dryRun) {\n console.log(JSON.stringify({\n articleType: args.articleType,\n title,\n author: author || undefined,\n digest: digest || undefined,\n htmlPath,\n contentLength: htmlContent.length,\n placeholderImageCount: contentImages.length || undefined,\n account: resolved.alias || undefined,\n }, null, 2));\n return;\n }\n\n const creds = loadCredentials(resolved);\n console.error(\"[wechat-api] Fetching access token...\");\n const accessToken = await fetchAccessToken(creds.appId, creds.appSecret);\n\n console.error(\"[wechat-api] Uploading images...\");\n const { html: processedHtml, firstMediaId, allMediaIds } = await uploadImagesInHtml(\n htmlContent,\n accessToken,\n baseDir,\n contentImages,\n );\n htmlContent = processedHtml;\n\n let thumbMediaId = \"\";\n const rawCoverPath = args.cover ||\n frontmatter.coverImage ||\n frontmatter.featureImage ||\n frontmatter.cover ||\n frontmatter.image;\n const coverPath = rawCoverPath && !path.isAbsolute(rawCoverPath) && args.cover\n ? path.resolve(process.cwd(), rawCoverPath)\n : rawCoverPath;\n\n if (coverPath) {\n console.error(`[wechat-api] Uploading cover: ${coverPath}`);\n const coverResp = await uploadImage(coverPath, accessToken, baseDir);\n thumbMediaId = coverResp.media_id;\n } else if (firstMediaId) {\n if (firstMediaId.startsWith(\"https://\")) {\n console.error(`[wechat-api] Uploading first image as cover: ${firstMediaId}`);\n const coverResp = await uploadImage(firstMediaId, accessToken, baseDir);\n thumbMediaId = coverResp.media_id;\n } else {\n thumbMediaId = firstMediaId;\n }\n }\n\n if (args.articleType === \"news\" && !thumbMediaId) {\n console.error(\"Error: No cover image. Provide via --cover, frontmatter.coverImage, or include an image in content.\");\n process.exit(1);\n }\n\n if (args.articleType === \"newspic\" && allMediaIds.length === 0) {\n console.error(\"Error: newspic requires at least one image in content.\");\n process.exit(1);\n }\n\n console.error(\"[wechat-api] Publishing to draft...\");\n const result = await publishToDraft({\n title,\n author: author || undefined,\n digest: digest || undefined,\n content: htmlContent,\n thumbMediaId,\n articleType: args.articleType,\n imageMediaIds: args.articleType === \"newspic\" ? allMediaIds : undefined,\n needOpenComment: resolved.need_open_comment,\n onlyFansCanComment: resolved.only_fans_can_comment,\n }, accessToken);\n\n console.log(JSON.stringify({\n success: true,\n media_id: result.media_id,\n title,\n articleType: args.articleType,\n }, null, 2));\n\n console.error(`[wechat-api] Published successfully! media_id: ${result.media_id}`);\n}\n\nawait main().catch((err) => {\n console.error(`Error: ${err instanceof Error ? err.message : String(err)}`);\n process.exit(1);\n});\n"}],"isError":false,"timestamp":1778994496789},{"role":"assistant","content":[{"type":"text","text":"Now let me check how credentials are loaded:"},{"type":"toolCall","id":"call_00_oCedAEaVDp9XorcFsTH28505","name":"exec","arguments":{"command":"grep -n \"loadCredentials\\|WECHAT_APP_ID\\|WECHAT_APP_SECRET\\|appId\\|appSecret\" /root/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-extend-config.ts | head -40"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":1600,"output":115,"cacheRead":16512,"cacheWrite":0,"totalTokens":18227,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994496790,"responseId":"03706c9e-b431-4a63-963c-549e1d71d814"},{"role":"toolResult","toolCallId":"call_00_oCedAEaVDp9XorcFsTH28505","toolName":"exec","content":[{"type":"text","text":"199:export function loadCredentials(account?: ResolvedAccount): { appId: string; appSecret: string } {\n201: return { appId: account.app_id, appSecret: account.app_secret };\n211: let appId = \"\";\n212: let appSecret = \"\";\n215: appId = process.env[`${prefix}APP_ID`]\n219: appSecret = process.env[`${prefix}APP_SECRET`]\n225: if (!appId) {\n226: appId = process.env.WECHAT_APP_ID || cwdEnv.WECHAT_APP_ID || homeEnv.WECHAT_APP_ID || \"\";\n228: if (!appSecret) {\n229: appSecret = process.env.WECHAT_APP_SECRET || cwdEnv.WECHAT_APP_SECRET || homeEnv.WECHAT_APP_SECRET || \"\";\n232: if (!appId || !appSecret) {\n235: `Missing WECHAT_APP_ID or WECHAT_APP_SECRET${hint}.\\n` +\n240: return { appId, appSecret };"}],"details":{"status":"completed","exitCode":0,"durationMs":43,"aggregated":"199:export function loadCredentials(account?: ResolvedAccount): { appId: string; appSecret: string } {\n201: return { appId: account.app_id, appSecret: account.app_secret };\n211: let appId = \"\";\n212: let appSecret = \"\";\n215: appId = process.env[`${prefix}APP_ID`]\n219: appSecret = process.env[`${prefix}APP_SECRET`]\n225: if (!appId) {\n226: appId = process.env.WECHAT_APP_ID || cwdEnv.WECHAT_APP_ID || homeEnv.WECHAT_APP_ID || \"\";\n228: if (!appSecret) {\n229: appSecret = process.env.WECHAT_APP_SECRET || cwdEnv.WECHAT_APP_SECRET || homeEnv.WECHAT_APP_SECRET || \"\";\n232: if (!appId || !appSecret) {\n235: `Missing WECHAT_APP_ID or WECHAT_APP_SECRET${hint}.\\n` +\n240: return { appId, appSecret };","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1778994498435},{"role":"assistant","content":[{"type":"text","text":"Good. Now let me prepare the HTML file for Z-Blog and run both tasks. First, let me create the HTML file for the Z-Blog WordPress/XML-RPC publish."},{"type":"toolCall","id":"call_00_tRENXcmTEfmn9fyBJRLy9156","name":"write","arguments":{"path":"/tmp/best-era-article.html","content":"<!DOCTYPE html>\n<html>\n<head>\n<meta charset=\"utf-8\">\n<title>对于有思想的人来说,这是最好的时代\n\n\n

你有没有过这样的感觉?

\n

脑子里有一个想法,一个方案,一个你觉得特别棒的商业模式。你越想越兴奋,越想越觉得\"这事儿能成\"。

\n

然后呢?

\n

然后就没有然后了。

\n

因为从\"想出来\"到\"做出来\",中间隔着十万八千里。你需要写商业计划书、找团队、招人、筹钱、做产品原型、跑市场验证……任何一个环节卡住,那个在深夜里让你兴奋到睡不着的念头,就永远只是个念头。

\n

太多人,被卡在了想法和结果之间那道看不见的墙上。

\n

但现在不一样了。

\n

历史上从来没有过这样的时代

\n

想想看,人类历史上什么时候有过这样的时刻——你说一句话,世界就会动起来?

\n

几千年前,人类最大的痛苦是吃不饱。几百年前,最大的痛苦是信息传不远。几十年前,最大的痛苦是算力不够用。

\n

而你看看今天。

\n

你只需要对AI说一句话:\"帮我做一个XX行业的竞品分析报告\",十分钟后一份结构清晰、数据翔实的报告就摆在你面前。

\n

你只需要说:\"帮我设计一套获客方案\",AI就能给你列出从内容营销到私域运营的完整路径。

\n

你只需要说:\"帮我写一段推广文案\",AI就能根据你的产品卖点和目标人群,产出几个版本的文案供你挑选。

\n

想法到实现的距离,被AI压缩成了一句话。

\n

这不是科幻片里的场景。这是2026年5月,任何一个有手机、有网络的人,此时此刻就能做到的事。

\n

过去创业,最大的成本是什么?

\n

不是钱。

\n

是验证想法。

\n

五年前,我有一个哥们儿想做一款面向小微企业主的SaaS工具。他花了一个月写BP,三个月找团队,六个月做开发,又花了两个月跑市场推广。等到产品正式上线,他发现一个问题——目标客户根本不愿意在这件事上花钱。

\n

前后投入一年,烧了几十万,换回来一个\"此路不通\"。

\n

这笔学费,贵不贵?贵。值不值?值——因为那个\"不\"是用时间和金钱真金白银换回来的。

\n

但今天呢?

\n

你有一个想法,让AI帮你做一个市场调研。你把产品的核心功能描述给AI,让它模拟目标用户的反馈。你让AI帮你生成一个MVP的思路和执行清单。你甚至可以先用AI生成内容做一轮市场测试——发几篇文章、做几个视频、看用户反馈。

\n

你不需要投入几十万,你只需要投入一个下午。

\n

这就是过去十年商业世界最大的变化:试错成本从\"倾家荡产\"降到了\"一杯咖啡\"。

\n

有思想的人,之前到底被什么卡住了?

\n

来,我帮你捋一下。

\n

你有一个好想法。你需要把它做出来,对吧?

\n

做出来需要什么?

\n

第一个卡点:执行能力。

\n

你不会写代码?看不懂财务报表?不了解供应链?没关系。AI可以:帮你生成代码框架、帮你分析财务报表、帮你梳理供应链的上下游关系。

\n

你不是没有能力,你只是之前找不到\"能干这些活的人\"。现在有了。

\n

第二个卡点:资源。

\n

你没钱招团队。你没有办公室。你没有渠道资源。OK,AI就是你的团队——它是你的市场研究员、文案写手、设计师、数据分析师、客服、甚至项目经理。

\n

过去你一个人扛着一个项目,什么都得自己干。现在你一个人,带着一个无限耐心的\"数字团队\"。

\n

第三个卡点:时间。

\n

你白天有工作,晚上有家庭,你没办法全职投入。可以理解。AI可以帮你24小时跑。你睡觉的时候,它在做数据分析。你吃饭的时候,它在生成内容。你通勤的时候,它在跑A/B测试方案。

\n

有思想的人,之前缺的不是想法,是执行团队的资源。现在AI就是你的执行团队。

\n

你只需要想清楚\"做什么\"和\"为什么做\",剩下的\"怎么做\",交给AI。

\n

别把AI当聊天工具,把它当成你的\"数字员工军团\"

\n

很多人到现在还在干嘛?跟AI聊天。

\n

\"帮我写一首诗\"、\"给我讲个笑话\"、\"模仿村上春树的风格写一段话\"。

\n

这些当然有趣。但如果你只停留在这个层面,你是在浪费这个时代最慷慨的馈赠。

\n

真正的用法是什么?

\n

把AI当成你的数字员工军团。

\n

在创业的领域,你一个人,通过AI,可以顶过去一家小型创业公司的产能。

\n

举个例子:

\n

你是做小红书内容的。传统模式:你需要一个内容策划、一个文案、一个设计师、一个排版——至少三个人。月薪加起来一万五到两万。

\n

AI模式:你一个人。让AI分析近期爆款选题,让AI生成初稿,让AI配图,让AI优化排版。你只需要做一件事——审稿和调整方向。

\n

一个人干的活,覆盖了三个人。成本从两万降到两百。产能输出翻倍。

\n

你说你是小生意、小老板、个人创业者,团队这个词对你来说太奢侈了。没关系。现在的AI,是你用一杯奶茶的价格,就能请到的\"全能员工\"。

\n

你见过创业者为了省一个员工的钱,自己熬夜到凌晨三点做图、写文案、跑数据。现在这些事,动动嘴就干完了。

\n

你不是在省多少钱的问题。你是在释放你自己的时间——让你从\"做事的人\",变成\"决策的人\"。

\n

这才是最值钱的转变。

\n

只做最值钱的那部分工作

\n

想想看,你一天24小时,真正\"值钱\"的时间有多少?

\n

开会、填表、回邮件、排期、改稿、对数据……这些事占了你一天百分之八十的时间。真正需要你深度思考、做判断、定方向的时间,可能不到两小时。

\n

但现在,你可以把那百分之八十的时间,交给AI。

\n

你需要做的,是那两小时的事。

\n

为什么?因为只有那两小时的事,别人拿不走。只有那两小时的事,才是你真正的价值所在。

\n

AI可以帮你写1000篇文章。但它不知道哪一篇最能打动人。
\nAI可以帮你做100份方案。但它不知道哪一份最适合你的客户。
\nAI可以帮你分析1000条数据。但它不知道这些数据背后,藏着什么样的商业直觉。

\n

AI给你的是\"效率\",你给AI的是\"方向\"。

\n

有方向的人,配上高效率的工具,就是无敌的。

\n

问题回到你身上

\n

所以你想想看。

\n

过去你被卡住的那些想法——那个想做的公众号、那个想启动的小项目、那个一直想写的书、那个思考了很久的商业模式——你今天还不动手,不是因为AI不够强。

\n

是因为你还没有想通一个道理:

\n

以前做事,需要的是\"我有什么\"。有资金、有团队、有资源、有关系。什么都没有,什么都干不了。

\n

现在做事,需要的是\"我想什么\"。有想法、有判断、有方向、有策略。这四个有了,剩下的交给AI。

\n

历史上,从来没有一个时代,如此慷慨地把\"实现的力量\"交到每一个有思想的人手上。

\n

工业时代,你要有工厂、设备、工人。互联网时代,你要有团队、技术、资本。AI时代,你只需要——动动嘴。

\n

这个时代在奖励谁?

\n

奖励那些敢想的人。奖励那些有判断力的人。奖励那些知道\"什么值得做\"的人。

\n

而这些人,被卡了多久?

\n

卡了多久不重要。重要的是,那堵墙,现在塌了。

\n

对于有思想的人来说,这不是一个容易的时代。这是一个幸运的时代。

\n

不是因为AI能做一切。而是因为——你只需要做那个最值钱的部分,剩下的,AI来。

\n\n\n"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":301,"output":2047,"cacheRead":18176,"cacheWrite":0,"totalTokens":20524,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994498436,"responseId":"3ec167a7-5793-4140-82fc-ee02216d3b40"},{"role":"toolResult","toolCallId":"call_00_tRENXcmTEfmn9fyBJRLy9156","toolName":"write","content":[{"type":"text","text":"Successfully wrote 3530 bytes to /tmp/best-era-article.html"}],"isError":false,"timestamp":1778994511075},{"role":"assistant","content":[{"type":"text","text":"Now let me run both tasks in parallel. For task A (WeChat), I'll use the provided credentials. For task B (Z-Blog), I need to use XML-RPC.\n\nLet me start with the WeChat publish:"},{"type":"toolCall","id":"call_00_ASdj0uCKEINGK6coZ9EQ3959","name":"exec","arguments":{"command":"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/有思想的人最好的时代.md \\\n --theme default --color blue --author \"ai张三疯\" \\\n --cover /root/.openclaw/agents/101/workspace/imgs/cover.png \\\n 2>&1","timeout":120}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":72,"output":255,"cacheRead":20480,"cacheWrite":0,"totalTokens":20807,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994511076,"responseId":"09e718d6-8a11-4c79-902a-87f07f26fcbb"},{"role":"toolResult","toolCallId":"call_00_ASdj0uCKEINGK6coZ9EQ3959","toolName":"exec","content":[{"type":"text","text":"[wechat-api] Theme: default, color: blue, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: default, color: blue, citeStatus: true\n[wechat-api] HTML generated: /tmp/wechat-article-images-Qyst09/temp-article.html\n[wechat-api] Placeholder images: 0\n[wechat-api] Title: 对于有思想的人来说,这是最好的时代\n[wechat-api] Author: ai张三疯\n[wechat-api] Digest: 脑子里有一个想法,一个方案,一个你觉得特别棒的商业模式。你越想越兴奋,越想越觉得\"这事儿能成\"。...\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\": \"imBwNhfy9Uv4ps2luE5gfqJMIpuMMgJz_9TnRLKAQ6jPtHSahtmO2ABpQIe5SrPJ\",\n \"title\": \"对于有思想的人来说,这是最好的时代\",\n \"articleType\": \"news\"\n}\n[wechat-api] Published successfully! media_id: imBwNhfy9Uv4ps2luE5gfqJMIpuMMgJz_9TnRLKAQ6jPtHSahtmO2ABpQIe5SrPJ"}],"details":{"status":"completed","exitCode":0,"durationMs":7808,"aggregated":"[wechat-api] Theme: default, color: blue, citeStatus: true\n[wechat-api] Rendering markdown with placeholders via md-to-wechat: default, color: blue, citeStatus: true\n[wechat-api] HTML generated: /tmp/wechat-article-images-Qyst09/temp-article.html\n[wechat-api] Placeholder images: 0\n[wechat-api] Title: 对于有思想的人来说,这是最好的时代\n[wechat-api] Author: ai张三疯\n[wechat-api] Digest: 脑子里有一个想法,一个方案,一个你觉得特别棒的商业模式。你越想越兴奋,越想越觉得\"这事儿能成\"。...\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\": \"imBwNhfy9Uv4ps2luE5gfqJMIpuMMgJz_9TnRLKAQ6jPtHSahtmO2ABpQIe5SrPJ\",\n \"title\": \"对于有思想的人来说,这是最好的时代\",\n \"articleType\": \"news\"\n}\n[wechat-api] Published successfully! media_id: imBwNhfy9Uv4ps2luE5gfqJMIpuMMgJz_9TnRLKAQ6jPtHSahtmO2ABpQIe5SrPJ","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1778994521381},{"role":"assistant","content":[{"type":"text","text":"✅ **任务A(公众号)完成!** 文章已成功发布到草稿箱,media_id 已获取。\n\n现在执行任务B(创业思维网 Z-Blog)。我需要通过 XML-RPC 来发布。让我写一个 Node.js 脚本来完成这个操作:"},{"type":"toolCall","id":"call_00_xwQqQjDpPv0xb79B1E849512","name":"exec","arguments":{"command":"which node && node -e \"try{require('xmlrpc');console.log('xmlrpc module ok')}catch(e){console.log('need install xmlrpc')}\""}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":452,"output":137,"cacheRead":20736,"cacheWrite":0,"totalTokens":21325,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994521382,"responseId":"24bb1736-7ba8-4e05-8dda-7e7ec84445e3"},{"role":"toolResult","toolCallId":"call_00_xwQqQjDpPv0xb79B1E849512","toolName":"exec","content":[{"type":"text","text":"/usr/bin/node\nxmlrpc module ok"}],"details":{"status":"completed","exitCode":0,"durationMs":101,"aggregated":"/usr/bin/node\nxmlrpc module ok","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1778994523580},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_aE9zrSO6Hzzo2F3gDyl17525","name":"write","arguments":{"path":"/tmp/publish-zblog.mjs","content":"import { createClient } from \"xmlrpc\";\nimport { readFileSync } from \"fs\";\n\n// Z-Blog XML-RPC config\nconst ZBLOG_URL = \"https://weixinsiwei.com/zb_system/xml-rpc/index.php\";\nconst USERNAME = \"admin\";\nconst PASSWORD = \"135269zxj\";\nconst BLOG_ID = \"68ba1ff10060dd54f1e399b8e332bdba\";\n\nconst htmlContent = readFileSync(\"/tmp/best-era-article.html\", \"utf-8\");\nconst title = \"对于有思想的人来说,这是最好的时代\";\n\n// Extract first ~200 chars as description\nconst descMatch = htmlContent.match(/

(.*?)<\\/p>/);\nconst description = descMatch\n ? descMatch[1].replace(/<[^>]+>/g, \"\").slice(0, 200)\n : \"对于有思想的人来说,这是最好的时代\";\n\nconst client = createClient({ url: ZBLOG_URL });\n\n// First, let's use wp.newPost (WordPress API) which Z-Blog supports\nconst postContent = {\n post_title: title,\n post_content: htmlContent,\n post_excerpt: description,\n post_status: \"publish\",\n post_author: 1,\n terms: {\n category: [\"AI应用\", \"创业思维\"]\n }\n};\n\nclient.methodCall(\"wp.newPost\", [BLOG_ID, USERNAME, PASSWORD, postContent], (err, data) => {\n if (err) {\n console.error(\"❌ Error publishing post:\", err.message);\n // Try metaWeblog.newPost as fallback\n console.error(\"Trying metaWeblog.newPost as fallback...\");\n const postData = {\n title: title,\n description: htmlContent,\n mt_excerpt: description,\n dateCreated: new Date(),\n categories: [\"AI应用\", \"创业思维\"]\n };\n client.methodCall(\"metaWeblog.newPost\", [BLOG_ID, USERNAME, PASSWORD, postData, true], (err2, data2) => {\n if (err2) {\n console.error(\"❌ metaWeblog also failed:\", err2.message);\n process.exit(1);\n }\n console.log(`✅ Published! Post ID: ${data2}`);\n verifyPost(String(data2));\n });\n return;\n }\n console.log(`✅ Published! Post ID: ${data}`);\n verifyPost(String(data));\n});\n\nfunction verifyPost(postId) {\n console.log(\"\\n=== Verifying recent posts ===\");\n client.methodCall(\"metaWeblog.getRecentPosts\", [BLOG_ID, USERNAME, PASSWORD, 3], (err, posts) => {\n if (err) {\n console.error(\"❌ Failed to get recent posts:\", err.message);\n process.exit(1);\n }\n if (!posts || posts.length === 0) {\n console.log(\"No recent posts found\");\n process.exit(0);\n }\n console.log(`\\nRecent posts (last ${posts.length}):`);\n posts.forEach((p, i) => {\n console.log(` ${i + 1}. [${p.dateCreated?.toISOString?.() || \"N/A\"}] ${p.title?.slice(0, 60) || \"(no title)\"} (ID: ${p.postid})`);\n });\n\n const found = posts.find(p => String(p.postid) === postId || p.title === title);\n if (found) {\n console.log(`\\n✅ Verification SUCCESS: \"${title}\" found in recent posts!`);\n } else {\n console.log(`\\n⚠️ Post ID ${postId} not in recent posts list, but publish call succeeded.`);\n }\n process.exit(0);\n });\n}\n"}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":98,"output":875,"cacheRead":21248,"cacheWrite":0,"totalTokens":22221,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994523582,"responseId":"6210250c-9f5f-4c2b-9ce5-74b4204bfa4e"},{"role":"toolResult","toolCallId":"call_00_aE9zrSO6Hzzo2F3gDyl17525","toolName":"write","content":[{"type":"text","text":"Successfully wrote 2755 bytes to /tmp/publish-zblog.mjs"}],"isError":false,"timestamp":1778994530467},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_6JX7ZVdSEJ4TowdsOyqk2204","name":"exec","arguments":{"command":"cd /tmp && node /tmp/publish-zblog.mjs 2>&1","timeout":60}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":105,"output":75,"cacheRead":22144,"cacheWrite":0,"totalTokens":22324,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994530468,"responseId":"75ad9524-2262-43fd-9f8a-808cfe6f4769"},{"role":"toolResult","toolCallId":"call_00_6JX7ZVdSEJ4TowdsOyqk2204","toolName":"exec","content":[{"type":"text","text":"file:///tmp/publish-zblog.mjs:1\nimport { createClient } from \"xmlrpc\";\n ^^^^^^^^^^^^\nSyntaxError: Named export 'createClient' not found. The requested module 'xmlrpc' is a CommonJS module, which may not support all module.exports as named exports.\nCommonJS modules can always be imported via the default export, for example using:\n\nimport pkg from 'xmlrpc';\nconst { createClient } = pkg;\n\n at ModuleJob._instantiate (node:internal/modules/esm/module_job:226:21)\n at async ModuleJob.run (node:internal/modules/esm/module_job:335:5)\n at async onImport.tracePromise.__proto__ (node:internal/modules/esm/loader:665:26)\n at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:117:5)\n\nNode.js v22.22.1\n\n(Command exited with code 1)"}],"details":{"status":"completed","exitCode":1,"durationMs":77,"aggregated":"file:///tmp/publish-zblog.mjs:1\nimport { createClient } from \"xmlrpc\";\n ^^^^^^^^^^^^\nSyntaxError: Named export 'createClient' not found. The requested module 'xmlrpc' is a CommonJS module, which may not support all module.exports as named exports.\nCommonJS modules can always be imported via the default export, for example using:\n\nimport pkg from 'xmlrpc';\nconst { createClient } = pkg;\n\n at ModuleJob._instantiate (node:internal/modules/esm/module_job:226:21)\n at async ModuleJob.run (node:internal/modules/esm/module_job:335:5)\n at async onImport.tracePromise.__proto__ (node:internal/modules/esm/loader:665:26)\n at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:117:5)\n\nNode.js v22.22.1\n\n(Command exited with code 1)","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1778994532120},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_sgh5XkMURtKIExg2VBQk1201","name":"edit","arguments":{"path":"/tmp/publish-zblog.mjs","edits":[{"oldText":"import { createClient } from \"xmlrpc\";","newText":"import pkg from \"xmlrpc\";\nconst { createClient } = pkg;"}]}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":280,"output":111,"cacheRead":22272,"cacheWrite":0,"totalTokens":22663,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994532121,"responseId":"db1d73bc-8cbf-4b03-967a-8e36a2e95d3d"},{"role":"toolResult","toolCallId":"call_00_sgh5XkMURtKIExg2VBQk1201","toolName":"edit","content":[{"type":"text","text":"Successfully replaced 1 block(s) in /tmp/publish-zblog.mjs."}],"details":{"diff":"- 1 import { createClient } from \"xmlrpc\";\n+ 1 import pkg from \"xmlrpc\";\n+ 2 const { createClient } = pkg;\n 2 import { readFileSync } from \"fs\";\n 3 \n 4 // Z-Blog XML-RPC config\n 5 const ZBLOG_URL = \"https://weixinsiwei.com/zb_system/xml-rpc/index.php\";\n ...","firstChangedLine":1},"isError":false,"timestamp":1778994533624},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_ypzirDWh9LLRiB64QBkX3577","name":"exec","arguments":{"command":"cd /tmp && node /tmp/publish-zblog.mjs 2>&1","timeout":60}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":161,"output":75,"cacheRead":22528,"cacheWrite":0,"totalTokens":22764,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778994533625,"responseId":"ea172e74-ce4b-4aa5-b839-74dbe4ebf074"},{"role":"toolResult","toolCallId":"call_00_ypzirDWh9LLRiB64QBkX3577","toolName":"exec","content":[{"type":"text","text":"❌ Error publishing post: XML-RPC fault: 未知命令\nTrying metaWeblog.newPost as fallback...\n✅ Published! Post ID: true\n\n=== Verifying recent posts ===\n\nRecent posts (last 3):\n 1. [2026-05-17T13:08:55.080Z] 对于有思想的人来说,这是最好的时代 (ID: 9596)\n 2. [2026-05-17T11:30:00.080Z] 未来已来:大多数人还在聊天,少数人已经在赚钱了 (ID: 9595)\n 3. [2026-05-17T02:29:30.080Z] 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 (ID: 9594)\n\n✅ Verification SUCCESS: \"对于有思想的人来说,这是最好的时代\" found in recent posts!"}],"details":{"status":"completed","exitCode":0,"durationMs":1861,"aggregated":"❌ Error publishing post: XML-RPC fault: 未知命令\nTrying metaWeblog.newPost as fallback...\n✅ Published! Post ID: true\n\n=== Verifying recent posts ===\n\nRecent posts (last 3):\n 1. [2026-05-17T13:08:55.080Z] 对于有思想的人来说,这是最好的时代 (ID: 9596)\n 2. [2026-05-17T11:30:00.080Z] 未来已来:大多数人还在聊天,少数人已经在赚钱了 (ID: 9595)\n 3. [2026-05-17T02:29:30.080Z] 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 (ID: 9594)\n\n✅ Verification SUCCESS: \"对于有思想的人来说,这是最好的时代\" found in recent posts!","cwd":"/root/.openclaw/workspace/fabu"},"isError":false,"timestamp":1778994536878},{"role":"assistant","content":[{"type":"text","text":"两个任务都完成了!让我总结一下:\n\n---\n\n## ✅ 发布任务全部完成!\n\n### 任务A:公众号发布 ✅\n- **公众号:** 创业张三疯(chuangyezhangsanfeng)\n- **标题:** 对于有思想的人来说,这是最好的时代\n- **作者:** ai张三疯\n- **状态:** 已成功发布至草稿箱 ✅\n- **media_id:** `imBwNhfy9Uv4ps2luE5gfqJMIpuMMgJz_9TnRLKAQ6jPtHSahtmO2ABpQIe5SrPJ`\n\n### 任务B:创业思维网发布 ✅\n- **网站:** weixinsiwei.com(Z-Blog)\n- **标题:** 对于有思想的人来说,这是最好的时代\n- **文章ID:** `9596`\n- **状态:** 已成功发布 ✅\n- **验证:** 通过 getRecentPosts 验证,文章已在最新3篇中确认 ✅"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":312,"output":220,"cacheRead":22656,"cacheWrite":0,"totalTokens":23188,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1778994536880,"responseId":"f5ac5c88-d9b9-41ce-9f76-9883a2a6db24"}]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","source":"runtime","type":"trace.artifacts","ts":"2026-05-17T05:08:59.607Z","seq":6,"sourceSeq":6,"sessionId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","sessionKey":"agent:fabu:subagent:9ea3e583-6d81-45ff-9240-d99a226ba0cc","runId":"65237b76-9fcf-4855-ab6b-532a13559992","workspaceDir":"/root/.openclaw/workspace/fabu","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-05-17T05:08:59.607Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"promptErrorSource":null,"usage":{"input":12462,"output":4613,"cacheRead":250112,"total":267187},"promptCache":{"lastCallUsage":{"input":312,"output":220,"cacheRead":22656,"cacheWrite":0,"total":23188},"lastCacheTouchAt":1778994536880},"compactionCount":0,"assistantTexts":["I'll execute both publishing tasks. Let me start by reading the article and preparing the HTML for Z-Blog, while also checking the wechat script.","Good, I have the article content and can see the script structure. Let me check what the wechat script supports and also get the cover image path.","Good, cover image exists. Now let me check the full script to understand CLI flags more completely.","Let me check the full CLI args parsing:","Now I need to check how the script handles credentials — it wants WECHAT_APP_ID and WECHAT_APP_SECRET env vars. Let me look at that part:","Now let me check how credentials are loaded:","Good. Now let me prepare the HTML file for Z-Blog and run both tasks. First, let me create the HTML file for the Z-Blog WordPress/XML-RPC publish.","Now let me run both tasks in parallel. For task A (WeChat), I'll use the provided credentials. For task B (Z-Blog), I need to use XML-RPC.\n\nLet me start with the WeChat publish:","✅ **任务A(公众号)完成!** 文章已成功发布到草稿箱,media_id 已获取。\n\n现在执行任务B(创业思维网 Z-Blog)。我需要通过 XML-RPC 来发布。让我写一个 Node.js 脚本来完成这个操作:","两个任务都完成了!让我总结一下:\n\n---\n\n## ✅ 发布任务全部完成!\n\n### 任务A:公众号发布 ✅\n- **公众号:** 创业张三疯(chuangyezhangsanfeng)\n- **标题:** 对于有思想的人来说,这是最好的时代\n- **作者:** ai张三疯\n- **状态:** 已成功发布至草稿箱 ✅\n- **media_id:** `imBwNhfy9Uv4ps2luE5gfqJMIpuMMgJz_9TnRLKAQ6jPtHSahtmO2ABpQIe5SrPJ`\n\n### 任务B:创业思维网发布 ✅\n- **网站:** weixinsiwei.com(Z-Blog)\n- **标题:** 对于有思想的人来说,这是最好的时代\n- **文章ID:** `9596`\n- **状态:** 已成功发布 ✅\n- **验证:** 通过 getRecentPosts 验证,文章已在最新3篇中确认 ✅"],"finalPromptText":"[Sun 2026-05-17 13:07 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":22,"completedCount":22,"activeCount":0},"toolMetas":[{"toolName":"exec","meta":"show ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts -> show first 50 lines, `cat ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts | head -50`"},{"toolName":"read","meta":"from ~/.openclaw/agents/101/workspace/post-to-wechat/2026-05-17/有思想的人最好的时代.md"},{"toolName":"exec","meta":"list files in ~/.openclaw/agents/101/workspace/imgs/cover.png → list files in ~/.openclaw/agents/101/workspace/imgs/ → print text → show first 100 lines of ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts -> show last 50 lines, `ls -la ~/.openclaw/agents/101/workspace/imgs/cover.png 2>/dev/null; ls -la ~/.openclaw/agents/101/workspace/img…`"},{"toolName":"exec","meta":"search \"parse|parse_args|commander|yargs|process.|argv|option.\" in wechat-api.ts -> show first 40 lines (in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts), `cd ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts && grep -n \"parse\\|parse_args\\|commander\\|y…`"},{"toolName":"read","meta":"lines 428-507 from ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts"},{"toolName":"read","meta":"lines 508-667 from ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-api.ts"},{"toolName":"exec","meta":"search \"loadCredentials|WECHAT_APP_ID|WECHAT_APP_SECRET|appId|appSecret\" in ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/scripts/wechat-extend-config.ts -> show first 40 lines, `grep -n \"loadCredentials\\|WECHAT_APP_ID\\|WECHAT_APP_SECRET\\|appId\\|appSecret\" ~/.openclaw/agents/101/workspace/skil…`"},{"toolName":"write","meta":"to /tmp/best-era-article.html (3530 chars)"},{"toolName":"exec","meta":"WECHAT_APP_ID= WECHAT_APP_SECRET=b2d47e…192f \\ bun ~/.openclaw/agents/101/worksp…"},{"toolName":"exec","meta":"run which node → run node inline script, `which node && node -e \"try{require('xmlrpc');console.log('xmlrpc module ok')}catch(e){console.log('need install xmlrpc'…`"},{"toolName":"write","meta":"to /tmp/publish-zblog.mjs (2755 chars)"},{"toolName":"exec","meta":"run node script /tmp/publish-zblog.mjs (in /tmp), `cd /tmp && node /tmp/publish-zblog.mjs 2>&1`"},{"toolName":"edit","meta":"in /tmp/publish-zblog.mjs"},{"toolName":"exec","meta":"run node script /tmp/publish-zblog.mjs (in /tmp), `cd /tmp && node /tmp/publish-zblog.mjs 2>&1`"}],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","source":"runtime","type":"session.ended","ts":"2026-05-17T05:08:59.607Z","seq":7,"sourceSeq":7,"sessionId":"e07625ff-d4a8-4da2-a10f-e4a3e3db3061","sessionKey":"agent:fabu:subagent:9ea3e583-6d81-45ff-9240-d99a226ba0cc","runId":"65237b76-9fcf-4855-ab6b-532a13559992","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}}