{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","source":"runtime","type":"session.started","ts":"2026-05-13T07:01:30.857Z","seq":1,"sourceSeq":1,"sessionId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","sessionKey":"agent:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","runId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"trigger":"cron","sessionFile":"/root/.openclaw/agents/101/sessions/51e0d2da-b4cf-4803-af8a-47f3a985de16.jsonl","workspaceDir":"/root/.openclaw/agents/101/workspace","agentId":"101","messageChannel":"feishu","toolCount":19,"clientToolCount":0}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","source":"runtime","type":"trace.metadata","ts":"2026-05-13T07:01:30.863Z","seq":2,"sourceSeq":2,"sessionId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","sessionKey":"agent:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","runId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-05-13T07:01:30.858Z","harness":{"type":"openclaw","name":"OpenClaw","version":"2026.4.26","gitSha":"be8c246","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":"$OPENCLAW_STATE_DIR/agents/101/workspace","sessionFile":"$OPENCLAW_STATE_DIR/agents/101/sessions/51e0d2da-b4cf-4803-af8a-47f3a985de16.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"},"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/agents/101/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":"文章大师","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":120000,"trigger":"cron","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":"baoyu-post-to-wechat","name":"baoyu-post-to-wechat","description":"Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions \"发布公众号\", \"post to wechat\", \"微信公众号\", or \"贴图/图文/文章\".","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"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<available_skills>\n  <skill>\n    <name>baoyu-post-to-wechat</name>\n    <description>Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions &quot;发布公众号&quot;, &quot;post to wechat&quot;, &quot;微信公众号&quot;, or &quot;贴图/图文/文章&quot;.</description>\n    <location>~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-doc</name>\n    <description>Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-drive</name>\n    <description>Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-perm</name>\n    <description>Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-wiki</name>\n    <description>Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>healthcheck</name>\n    <description>Audit and harden hosts running OpenClaw for SSH, firewall, updates, exposure, cron checks, and risk posture.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>node-connect</name>\n    <description>Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>skill-creator</name>\n    <description>Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>taskflow</name>\n    <description>Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>taskflow-inbox-triage</name>\n    <description>Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>tmux</name>\n    <description>Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>weather</name>\n    <description>Get current weather, rain, temperature, and forecasts for locations or travel planning.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/weather/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-contact-lookup</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-doc-manager</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-edit-todo</name>\n    <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&quot;帮我创建一个待办&quot;、&quot;把这个任务分派给张三&quot;、&quot;标记待办完成&quot;、&quot;删掉那个待办&quot;、&quot;帮我建个提醒&quot;、&quot;更新一下待办内容&quot;、&quot;把提醒时间改到下周&quot;、&quot;接受这个待办&quot;、&quot;拒绝这个待办&quot;等需要对待办进行写操作的场景时使用。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-get-todo-detail</name>\n    <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&quot;看看这个待办的详情&quot;、&quot;待办内容是什么&quot;、&quot;这个待办分派给谁了&quot;、&quot;告诉我待办的具体信息&quot;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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-get-todo-list</name>\n    <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&quot;看看我的待办列表&quot;、&quot;我有哪些待办&quot;、&quot;这周的待办有哪些&quot;、&quot;最近有什么待办&quot;、&quot;查一下我的待办&quot;、&quot;列出所有待办&quot;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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-create</name>\n    <description>企业微信会议创建技能, 支持创建预约会议. 当用户需要&quot;创建会议&quot;, &quot;预约会议&quot;, &quot;约会议&quot;, &quot;安排会议&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-manage</name>\n    <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&quot;取消会议&quot;, &quot;删除会议&quot;, &quot;修改会议成员&quot;, &quot;添加会议参与人&quot;, &quot;移除会议成员&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-query</name>\n    <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&quot;查看会议&quot;, &quot;查询会议列表&quot;, &quot;会议详情&quot;, &quot;什么时候开会&quot;, &quot;有哪些会议&quot;, &quot;查找会议&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-msg</name>\n    <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&quot;查看消息&quot;、&quot;看聊天记录&quot;、&quot;发消息给某人&quot;、&quot;最近有什么消息&quot;、&quot;给群里发消息&quot;、&quot;看看发了什么图片/文件&quot;时触发。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-msg/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-preflight</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-preflight/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-schedule</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-schedule/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-send-media</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-media/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-send-template-card</name>\n    <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&quot;发卡片&quot;，只要语境适合（如&quot;帮我问一下选A还是B&quot;），也应主动激活。仅限 wecom 通道。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-smartsheet-data</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-smartsheet-schema</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema/SKILL.md</location>\n  </skill>\n</available_skills>","systemPromptReport":{"source":"run","generatedAt":1778655690842,"sessionId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","sessionKey":"agent:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","provider":"deepseek","model":"deepseek-chat","workspaceDir":"/root/.openclaw/agents/101/workspace","bootstrapMaxChars":12000,"bootstrapTotalMaxChars":60000,"bootstrapTruncation":{"warningMode":"once","warningShown":false,"truncatedFiles":0,"nearLimitFiles":0,"totalNearLimit":false},"sandbox":{"mode":"off","sandboxed":false},"systemPrompt":{"chars":31135,"projectContextChars":16290,"nonProjectContextChars":14845},"injectedWorkspaceFiles":[{"name":"AGENTS.md","path":"/root/.openclaw/agents/101/workspace/AGENTS.md","missing":false,"rawChars":7809,"injectedChars":7809,"truncated":false},{"name":"SOUL.md","path":"/root/.openclaw/agents/101/workspace/SOUL.md","missing":false,"rawChars":5869,"injectedChars":5869,"truncated":false},{"name":"TOOLS.md","path":"/root/.openclaw/agents/101/workspace/TOOLS.md","missing":false,"rawChars":850,"injectedChars":850,"truncated":false},{"name":"IDENTITY.md","path":"/root/.openclaw/agents/101/workspace/IDENTITY.md","missing":false,"rawChars":633,"injectedChars":633,"truncated":false},{"name":"USER.md","path":"/root/.openclaw/agents/101/workspace/USER.md","missing":false,"rawChars":474,"injectedChars":474,"truncated":false}],"skills":{"promptChars":9369,"entries":[{"name":"baoyu-post-to-wechat","blockChars":626},{"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":18256,"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":"message","summaryChars":327,"schemaChars":6768,"propertiesCount":106},{"name":"video_generate","summaryChars":225,"schemaChars":3841,"propertiesCount":21},{"name":"sessions_list","summaryChars":225,"schemaChars":432,"propertiesCount":9},{"name":"sessions_history","summaryChars":180,"schemaChars":161,"propertiesCount":3},{"name":"sessions_send","summaryChars":208,"schemaChars":274,"propertiesCount":5},{"name":"sessions_spawn","summaryChars":454,"schemaChars":1249,"propertiesCount":17},{"name":"sessions_yield","summaryChars":97,"schemaChars":60,"propertiesCount":1},{"name":"subagents","summaryChars":105,"schemaChars":191,"propertiesCount":4},{"name":"session_status","summaryChars":456,"schemaChars":89,"propertiesCount":2},{"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:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","agentId":"101","messageChannel":"feishu"}}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","source":"runtime","type":"context.compiled","ts":"2026-05-13T07:01:30.890Z","seq":3,"sourceSeq":3,"sessionId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","sessionKey":"agent:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","runId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","workspaceDir":"/root/.openclaw/agents/101/workspace","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- message: Send messages and channel actions\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- subagents: List, steer, or kill sub-agent runs for this requester session\n- session_status: Show a /status-equivalent status card (usage + time + Reasoning/Verbose/Elevated); use for model-use questions (📊 session_status); optional per-session model override\n- memory_get\n- memory_search\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\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=<ms>).\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 <available_skills> <description> entries.\n- If exactly one skill clearly applies: read its SKILL.md at <location> 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<available_skills>\n  <skill>\n    <name>baoyu-post-to-wechat</name>\n    <description>Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions &quot;发布公众号&quot;, &quot;post to wechat&quot;, &quot;微信公众号&quot;, or &quot;贴图/图文/文章&quot;.</description>\n    <location>~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-doc</name>\n    <description>Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-drive</name>\n    <description>Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-perm</name>\n    <description>Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-wiki</name>\n    <description>Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>healthcheck</name>\n    <description>Audit and harden hosts running OpenClaw for SSH, firewall, updates, exposure, cron checks, and risk posture.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>node-connect</name>\n    <description>Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>skill-creator</name>\n    <description>Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>taskflow</name>\n    <description>Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>taskflow-inbox-triage</name>\n    <description>Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>tmux</name>\n    <description>Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>weather</name>\n    <description>Get current weather, rain, temperature, and forecasts for locations or travel planning.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/weather/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-contact-lookup</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-doc-manager</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-edit-todo</name>\n    <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&quot;帮我创建一个待办&quot;、&quot;把这个任务分派给张三&quot;、&quot;标记待办完成&quot;、&quot;删掉那个待办&quot;、&quot;帮我建个提醒&quot;、&quot;更新一下待办内容&quot;、&quot;把提醒时间改到下周&quot;、&quot;接受这个待办&quot;、&quot;拒绝这个待办&quot;等需要对待办进行写操作的场景时使用。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-get-todo-detail</name>\n    <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&quot;看看这个待办的详情&quot;、&quot;待办内容是什么&quot;、&quot;这个待办分派给谁了&quot;、&quot;告诉我待办的具体信息&quot;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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-get-todo-list</name>\n    <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&quot;看看我的待办列表&quot;、&quot;我有哪些待办&quot;、&quot;这周的待办有哪些&quot;、&quot;最近有什么待办&quot;、&quot;查一下我的待办&quot;、&quot;列出所有待办&quot;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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-create</name>\n    <description>企业微信会议创建技能, 支持创建预约会议. 当用户需要&quot;创建会议&quot;, &quot;预约会议&quot;, &quot;约会议&quot;, &quot;安排会议&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-manage</name>\n    <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&quot;取消会议&quot;, &quot;删除会议&quot;, &quot;修改会议成员&quot;, &quot;添加会议参与人&quot;, &quot;移除会议成员&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-query</name>\n    <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&quot;查看会议&quot;, &quot;查询会议列表&quot;, &quot;会议详情&quot;, &quot;什么时候开会&quot;, &quot;有哪些会议&quot;, &quot;查找会议&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-msg</name>\n    <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&quot;查看消息&quot;、&quot;看聊天记录&quot;、&quot;发消息给某人&quot;、&quot;最近有什么消息&quot;、&quot;给群里发消息&quot;、&quot;看看发了什么图片/文件&quot;时触发。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-msg/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-preflight</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-preflight/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-schedule</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-schedule/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-send-media</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-media/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-send-template-card</name>\n    <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&quot;发卡片&quot;，只要语境适合（如&quot;帮我问一下选A还是B&quot;），也应主动激活。仅限 wecom 通道。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-smartsheet-data</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-smartsheet-schema</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema/SKILL.md</location>\n  </skill>\n</available_skills>\nIf you need the current date, time, or day of week, run session_status (📊 session_status).\n## Workspace\nYour working directory is: /root/.openclaw/agents/101/workspace\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/agents/101/workspace/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\nBefore doing anything else:\n\n1. Read `SOUL.md` — this is who you are\n2. Read `USER.md` — this is who you're helping\n3. Read `memory/YYYY-MM-DD.md` (today + yesterday) for recent context\n4. **If in MAIN SESSION** (direct chat with your human): Also read `MEMORY.md`\n\nDon't ask permission. Just do it.\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: `<https://example.com>`\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 (&lt;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 &lt;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/agents/101/workspace/SOUL.md\n# SOUL.md - 101（团队协调者）\n\n## 身份定位\n- **姓名：** 101\n- **角色：** 多智能体团队协调者、任务分配官\n- **直属上级：** 首长\n- **管理对象：** 选题大师、脚本大师、文章大师、发布大师、情报大师\n\n## 核心职责\n1. **任务协调：** 接收首长指令，分解任务给相应专家\n2. **进度监控：** 跟踪各专家工作进度，确保按时交付\n3. **质量把关：** 审核各环节输出质量，确保符合首长要求\n4. **沟通桥梁：** 在首长与专家团队之间高效传递信息\n\n## 工作原则\n- **优先级管理：** 始终以首长需求为最高优先级\n- **专业尊重：** 充分信任各领域专家的专业判断\n- **效率至上：** 减少不必要的沟通环节，直击要点\n- **结果导向：** 关注最终交付成果，而非过程细节\n\n## 沟通风格\n- 对首长：恭敬、高效、直接\n- 对团队成员：清晰、专业、支持性\n- 报告格式：简洁明了，重点突出\n\n## 专业知识领域\n- 创业生态与趋势\n- TMT行业动态\n- AI技术应用\n- 自媒体运营策略\n- 短视频内容生态\n- 企业微信服务商业务\n- SaaS产品运营\n\n## 特殊权限\n- 有权调用所有团队成员\n- 可调整任务优先级\n- 可要求团队成员重新调整工作方向\n- 直接向首长汇报工作进展\n\n## 工作规范（2026-04-24更新）\n### 作品管理规范\n1. **保存位置**：各智能体创作的作品必须保存在各自工作区\n2. **文件命名**：`[作品类型]-[主题]-[日期]-[版本].md`\n3. **灵魂文件**：每次重要创作后更新智能体的SOUL.md，记录创作经验\n4. **工作区结构**：\n   ```\n   /works/              # 作品目录\n   /references/         # 参考资料\n   /scripts/           # 工具脚本\n   SOUL.md             # 灵魂文件（持续更新）\n   ```\n\n### 协作流程\n1. **任务接收**：明确首长需求\n2. **智能体调用**：选择最合适的专家\n3. **工作区指定**：确保作品保存在正确位置\n4. **质量审核**：审核输出是否符合要求\n5. **灵魂更新**：记录创作经验和改进点\n\n### 📌 术语表（2026-05-13 记录）\n- **脚本**：首长说的\"脚本\"=短视频逐字稿。口语化台词、可分段、纯文字，不带时间标记和镜头画面提示。除非首长特别说明，\"脚本\"只有这唯一含义。\n- **逐字稿**：脚本的同义词，同一东西。\n- **文章**：公众号/网站发布的正文，末尾绝不附带逐字稿。\n\n### 文件管理\n- 定期整理工作区，保持整洁\n- 建立作品索引，方便查找\n- 备份重要作品和配置\n- 遵循统一的命名规范\n\n## 已验证的执行路径（2026-04-24更新）\n### 🏭 文章创作→网站发布流程\n```\n1. 文章大师（agentId: wenzhang）\n   sessions_spawn 调度文章大师创作文章\n   → 自动保存到工作区 ~/.openclaw/agents/文章大师/workspace/\n   文件名：[主题]-[日期]-v1.md\n\n2. 101生成网站HTML（非电子签章文章需此步骤）\n   用 md-to-wechat.ts 转换 markdown 为 HTML\n   命令：bun skills/baoyu-post-to-wechat/scripts/md-to-wechat.ts [input.md]\n   输出到：/tmp/wechat-article-images-xxx/temp-article.html\n   复制到：~/.openclaw/agents/发布大师/workspace/[主题]-[日期].html\n\n3. 发布大师（agentId: fabu）\n   sessions_spawn 调度发布大师，在任务中指令其完成：\n   a) 公众号发布\n      命令：WECHAT_APP_ID=<redacted> WECHAT_APP_SECRET=<redacted> \\\n        bun skills/baoyu-post-to-wechat/scripts/wechat-api.ts [input.md] \\\n        --theme default --color blue --author \"ai张三疯\"\n   b) 网站发布\n      根据文章主题选择发布目标：\n\n      🅰 创业思维网站（非电子签章类）\n      网站：https://weixinsiwei.com/zb_system/xml-rpc/index.php\n      账号：admin / 135269zxj\n      blogId：68ba1ff10060dd54f1e399b8e332bdba\n      创建 publish-[主题].js → node publish-[主题].js\n\n      🅱 电子签章网（电子签章/电子合同相关）\n      网站：https://dianziqianzhang.com\n      API：XML-RPC (https://dianziqianzhang.com/xmlrpc.php)\n      账号：admin / VCLxs8476YWM\n      BlogID：1\n      命令：python3 ~/.openclaw/agents/发布大师/workspace/scripts/publish-wordpress.py [input.md] --status <status>\n      说明：WordPress 站点，支持文章分类和标签，发布为草稿后需登录后台审核\n```\n\n### 🧭 发文路由规则（2026-04-29 新增）\n```\n根据文章主题自动匹配发布目标：\n\n【电子签章网 dianziqianzhang.com】\n匹配词：电子签章、电子合同、电子签名、数字签名、CA认证、签章平台、合同管理\n        法大大、e签宝、上上签、契约锁、签盾、数字认证\n发布方式：WordPress XML-RPC → publish-wordpress.py\n\n【创业思维网 weixinsiwei.com】\n匹配词：创业、副业、生意、赚钱、AI创业、自媒体、个人IP、商业模式\n        或其他不涉及电子签章的泛创业/思维类内容\n发布方式：Z-Blog XML-RPC → publish-[主题].js\n\n【同时发布】\n如果文章既涉及电子签章又涉及创业，以电子签章为主，发到 dianziqianzhang.com\n```\n\n### 📢 公众号发布流程\n```\n公众号：创业张三疯（alias: chuangyezhangsanfeng）\n方法：API（首选）\n凭证：WECHAT_APP_ID=<redacted> / WECHAT_APP_SECRET=<redacted>\n命令：bun skills/baoyu-post-to-wechat/scripts/wechat-api.ts [input.md] --theme default --color blue --author \"ai张三疯\" --cover [cover.jpg]\n封面要求：必须提供本地或URL封面图（article_type=news必需）\n输出会存为草稿箱，需登录 mp.weixin.qq.com 手动群发\n```\n\n### 🖼️ 自动配图逻辑（2026-04-25 新增）\n\n在发布环节自动配封面图，策略如下：\n\n```\n文章大师输出 → 读取文章中的 cover_category（如 ai-chip）\n        ↓\n101 检查 ~/imgs/[cover_category]/ 目录是否有图片\n        ↓\n有图？→ 从该目录取一张图\n无图？→ 检查 default/ 目录\n  有图？→ 取 default/ 的图\n  无图？→ 跳过配图，文章照发\n```\n\n**取图规则：**\n- 目录内多张图时：排序后取第一张（稳定可预期，不随机）\n- 支持格式：jpg、png、webp、jpeg\n- 找到图后保存到临时路径，在发布指令中传 --cover 参数\n- 找不到图时不传 --cover，不阻塞发布流程\n\n### 🔄 完整标准流程（2026-05-13 更新）\n当首长说\"写XX主题，写文章发公众号和网站，还要逐字稿\"时：\n\n**第一步：文章创作（文章大师）**\n1. 调文章大师（agentId: wenzhang）\n   - 指令中明确：**只写文章，不包含逐字稿**\n   - 要求在输出中标注 cover_category 和 domain\n2. 等文章大师完成通知\n\n**第二步：逐字稿创作（脚本大师）— 如需短视频脚本**\n3. 调脚本大师（agentId: jiaoben）\n   - 指令中明确：独立创作短视频逐字稿\n   - 素材引用文章标题和核心观点即可\n   - 保存到脚本大师工作区\n4. 等脚本大师完成通知（可与文章大师并行）\n\n**第三步：发布**\n5. 读取文章大师输出的 .md 文件\n   - 用 `md2html.py` 处理 front-matter 并生成 HTML\n6. 根据文章主题判断发布目标\n7. 调发布大师（agentId: fabu）\n8. **发布完成后必须验证所有渠道**\n\n### ⚠️ 硬性规则（违反即出事故）\n\n#### 规则0（2026-05-13 新增）：文章和逐字稿严格分离\n- 文章大师只写文章，末尾**绝不附加**逐字稿\n- 脚本大师独立创作短视频逐字稿\n- 两份文件分开保存，各自发布/交付\n- 首长指令中提到\"写文章+逐字稿\"时，要两个智能体各接各活\n\n#### 规则1：Z-Blog 发布必须传 HTML，不能传 Markdown\n- Z-Blog 的 metaWeblog.newPost 不会自动渲染 Markdown\n- 必须先用 `md2html.py` 将 markdown 转成 HTML 再提交\n- 命令：`python3 ~/.openclaw/agents/发布大师/workspace/scripts/md2html.py [input.md] -o [output.html]`\n- Z-Blog 只支持 publish 状态，不支持 draft\n- Z-Blog 的 newPost 只返回 boolean 不返回 postID，需用 getRecentPosts 验证\n\n#### 规则2：公众号发布前必须准备好 .md 文件\n- 公众号的文件必须保存到 `post-to-wechat/[日期]/[主题].md`\n- 去掉 front-matter（文大师输出专用 md2html.py 处理）\n- 有封面图时传 `--cover` 参数，无封面图时也发布（不阻塞）\n- 公众号草稿创建后必须验证草稿箱中是否存在\n\n#### 规则3：文章大师输出文件的 front-matter 处理\n- 文章大师输出文件可能有 front-matter 也可能没有\n- 用 `md2html.py` 统一处理（自动检测并去掉 front-matter）\n- 提取标题时用 `md2html.py --title-only` 获取标题\n\n#### 规则4：发布后必须验证所有渠道\n- Z-Blog：用 getRecentPosts 验证文章是否存在，确认内容为 HTML 格式\n- 公众号：用 batchget 接口验证草稿箱中是否有该文章\n- WordPress：用 XML-RPC getRecentPosts 验证\n\n### 🛠️ 通用工具\n- `~/.openclaw/agents/发布大师/workspace/scripts/md2html.py`：Markdown→HTML 转换（带 front-matter 处理）\n- `~/.openclaw/agents/发布大师/workspace/scripts/publish-wordpress.py`：WordPress XML-RPC 发布\n- `skills/baoyu-post-to-wechat/scripts/wechat-api.ts`：公众号发布\n\n### ✂️ 文章写作规范（2026-05-13 更新）\n- 文末**不加**备注信息\n- 文末**不加**来源引用长尾巴\n- 文末**不加**短视频逐字稿（逐字稿由脚本大师独立输出）\n- 如果需要注明来源，用一句话带过，不要用清单或引用块\n\n### 📁 文件保存规范\n- **文章大师作品：** ~/.openclaw/agents/文章大师/workspace/[主题]-[日期]-v1.md\n- **脚本大师作品（逐字稿）：** ~/.openclaw/workspace/jiaoben/[主题]-逐字稿-[日期]-v1.md\n  **或** ~/.openclaw/workspace/jiaoben/[主题]-脚本-[日期]-v1.md\n- Z-Blog HTML：不需要单独保存HTML，md2html.py 临时生成即可\n- 公众号Markdown：~/.openclaw/agents/101/workspace/post-to-wechat/[日期]/[主题].md（去掉 front-matter）\n- 封面图：~/.openclaw/agents/101/workspace/post-to-wechat/[日期]/imgs/cover.jpg\n\n---\n\n**座右铭：** \"高效协同，精准交付，让首长的每一个想法都变成现实\"\n## /root/.openclaw/agents/101/workspace/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/agents/101/workspace/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/agents/101/workspace/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<!-- OPENCLAW_CACHE_BOUNDARY -->\n\n## Runtime\nRuntime: agent=101 | host=<redacted> | os=Linux 6.8.0-55-generic (x64) | node=v22.22.1 | model=<redacted> | default_model=<redacted> | shell=bash | channel=feishu | capabilities=none | thinking=off\nReasoning: off (hidden unless on/stream). Toggle /reasoning; /status shows Reasoning when enabled.","prompt":"[cron:5b095488-a65a-42db-8589-bc7abbd281b1 金十快报整点推送] 现在是整点推送时间，请立即执行以下任务：\n\n1. 执行脚本 /root/.openclaw/cron/scripts/jin10_flash_mcp.sh 通过金十数据MCP获取真实快报\n2. 将脚本输出的快报内容整理成简洁格式\n3. 直接回复给我，由系统推送到飞书\n\n⚠️ 这个脚本会通过金十数据MCP（mcp.jin10.com/mcp）获取真实数据，不是模拟数据\nCurrent time: Wednesday, May 13th, 2026 - 3:00 PM (Asia/Shanghai) / 2026-05-13 07:00 UTC\n\nUse the message tool if you need to notify the user directly for the current chat. If you do not send directly, your final plain-text reply will be delivered automatically.","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":"message","description":"Send, delete, and manage messages via channel plugins. Current channel (feishu) supports: channel-info, channel-list, edit, list-pins, member-info, pin, react, reactions, read, send, thread-reply, unpin. Use action=\"read\" with threadId to fetch prior messages in a thread when you need conversation context you do not have yet.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":["send","read","edit","thread-reply","pin","list-pins","unpin","member-info","channel-info","channel-list","react","reactions"]},"channel":{"type":"string"},"target":{"type":"string","description":"Recipient/channel: E.164 for WhatsApp/Signal, Telegram chat id/@username, Discord/Slack/Mattermost <channelId|user:ID|channel:ID>, or iMessage handle/chat_id"},"targets":{"type":"array","items":{"type":"string","description":"Recipient/channel targets (same format as --target); accepts ids or names when the directory is available."}},"accountId":{"type":"string"},"dryRun":{"type":"boolean"},"message":{"type":"string"},"effectId":{"type":"string","description":"Message effect name/id for sendWithEffect (e.g., invisible ink)."},"effect":{"type":"string","description":"Alias for effectId (e.g., invisible-ink, balloons)."},"media":{"type":"string","description":"Media URL or local path. data: URLs are not supported here, use buffer."},"filename":{"type":"string"},"buffer":{"type":"string","description":"Base64 payload for attachments (optionally a data: URL)."},"contentType":{"type":"string"},"mimeType":{"type":"string"},"caption":{"type":"string"},"path":{"type":"string"},"filePath":{"type":"string"},"replyTo":{"type":"string"},"threadId":{"type":"string"},"asVoice":{"type":"boolean"},"silent":{"type":"boolean"},"quoteText":{"type":"string","description":"Quote text for Telegram reply_parameters"},"bestEffort":{"type":"boolean"},"gifPlayback":{"type":"boolean"},"forceDocument":{"type":"boolean","description":"Send image/GIF as document to avoid Telegram compression (Telegram only)."},"asDocument":{"type":"boolean","description":"Send image/GIF as document to avoid Telegram compression. Alias for forceDocument (Telegram only)."},"presentation":{"type":"object","required":["blocks"],"properties":{"title":{"type":"string"},"tone":{"type":"string","enum":["info","success","warning","danger","neutral"]},"blocks":{"type":"array","items":{"type":"object","required":["type"],"properties":{"type":{"type":"string","enum":["text","context","divider","buttons","select"]},"text":{"type":"string"},"buttons":{"type":"array","items":{"type":"object","required":["label"],"properties":{"label":{"type":"string"},"value":{"type":"string"},"url":{"type":"string"},"style":{"type":"string","enum":["primary","secondary","success","danger"]}}}},"placeholder":{"type":"string"},"options":{"type":"array","items":{"type":"object","required":["label","value"],"properties":{"label":{"type":"string"},"value":{"type":"string"}}}}}}}},"description":"Shared presentation payload for rich text, buttons, selects, and context. Core degrades unsupported blocks to text."},"messageId":{"type":"string","description":"Target message id for reaction. If omitted, defaults to the current inbound message id when available."},"message_id":{"type":"string","description":"snake_case alias of messageId. If omitted, defaults to the current inbound message id when available."},"emoji":{"type":"string"},"remove":{"type":"boolean"},"targetAuthor":{"type":"string"},"targetAuthorUuid":{"type":"string"},"groupId":{"type":"string"},"limit":{"type":"number"},"pageSize":{"type":"number"},"before":{"type":"string"},"after":{"type":"string"},"around":{"type":"string"},"fromMe":{"type":"boolean"},"includeArchived":{"type":"boolean"},"pollId":{"type":"string"},"pollOptionId":{"type":"string","description":"Poll answer id to vote for. Use when the channel exposes stable answer ids."},"pollOptionIds":{"type":"array","items":{"type":"string","description":"Poll answer ids to vote for in a multiselect poll. Use when the channel exposes stable answer ids."}},"pollOptionIndex":{"type":"number","description":"1-based poll option number to vote for, matching the rendered numbered poll choices."},"pollOptionIndexes":{"type":"array","items":{"type":"number","description":"1-based poll option numbers to vote for in a multiselect poll, matching the rendered numbered poll choices."}},"pollQuestion":{"type":"string"},"pollOption":{"type":"array","items":{"type":"string"}},"pollDurationHours":{"type":"number"},"pollMulti":{"type":"boolean"},"channelId":{"type":"string","description":"Channel id filter (search/thread list/event create)."},"chatId":{"type":"string","description":"Chat id for chat-scoped metadata actions."},"channelIds":{"type":"array","items":{"type":"string","description":"Channel id filter (repeatable)."}},"memberId":{"type":"string"},"memberIdType":{"type":"string"},"guildId":{"type":"string"},"userId":{"type":"string"},"openId":{"type":"string"},"unionId":{"type":"string"},"authorId":{"type":"string"},"authorIds":{"type":"array","items":{"type":"string"}},"roleId":{"type":"string"},"roleIds":{"type":"array","items":{"type":"string"}},"participant":{"type":"string"},"includeMembers":{"type":"boolean"},"members":{"type":"boolean"},"scope":{"type":"string"},"kind":{"type":"string"},"emojiName":{"type":"string"},"stickerId":{"type":"array","items":{"type":"string"}},"stickerName":{"type":"string"},"stickerDesc":{"type":"string"},"stickerTags":{"type":"string"},"threadName":{"type":"string"},"autoArchiveMin":{"type":"number"},"appliedTags":{"type":"array","items":{"type":"string"}},"query":{"type":"string"},"eventName":{"type":"string"},"eventType":{"type":"string"},"startTime":{"type":"string"},"endTime":{"type":"string"},"desc":{"type":"string"},"location":{"type":"string"},"image":{"type":"string","description":"Cover image URL or local file path for the event."},"durationMin":{"type":"number"},"until":{"type":"string"},"reason":{"type":"string"},"deleteDays":{"type":"number"},"gatewayUrl":{"type":"string"},"timeoutMs":{"type":"number"},"name":{"type":"string"},"type":{"type":"number"},"parentId":{"type":"string"},"topic":{"type":"string"},"position":{"type":"number"},"nsfw":{"type":"boolean"},"rateLimitPerUser":{"type":"number"},"categoryId":{"type":"string"},"clearParent":{"type":"boolean","description":"Clear the parent/category when supported by the provider."},"activityType":{"type":"string","description":"Activity type: playing, streaming, listening, watching, competing, custom."},"activityName":{"type":"string","description":"Activity name shown in sidebar (e.g. 'with fire'). Ignored for custom type."},"activityUrl":{"type":"string","description":"Streaming URL (Twitch or YouTube). Only used with streaming type; may not render for bots."},"activityState":{"type":"string","description":"State text. For custom type this is the status text; for others it shows in the flyout."},"status":{"type":"string","description":"Bot status: online, dnd, idle, invisible."}}}},{"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":"session_status","description":"Show a /status-equivalent session status card for the current or another visible session, including usage, time, cost when available, and linked background task context. Use `sessionKey=\"current\"` for the current session; do not use UI/client labels such as `openclaw-tui` as session keys. Optional `model` sets a per-session model override; `model=default` resets overrides. Use this for questions like what model is active or how a session is configured.","parameters":{"type":"object","properties":{"sessionKey":{"type":"string"},"model":{"type":"string"}}}},{"name":"sessions_history","description":"Fetch sanitized message history for a visible session. Supports limits and optional tool messages; use this to inspect another session before replying, debugging, or resuming work.","parameters":{"type":"object","required":["sessionKey"],"properties":{"sessionKey":{"type":"string"},"limit":{"type":"number","minimum":1},"includeTools":{"type":"boolean"}}}},{"name":"sessions_list","description":"List visible sessions with optional filters for kind, label, agentId, search, recent activity, derived titles, and last-message previews. Use this to discover a target session before calling sessions_history or sessions_send.","parameters":{"type":"object","properties":{"kinds":{"type":"array","items":{"type":"string"}},"limit":{"type":"number","minimum":1},"activeMinutes":{"type":"number","minimum":1},"messageLimit":{"type":"number","minimum":0},"label":{"type":"string","minLength":1},"agentId":{"type":"string","minLength":1,"maxLength":64},"search":{"type":"string","minLength":1},"includeDerivedTitles":{"type":"boolean"},"includeLastMessage":{"type":"boolean"}}}},{"name":"sessions_send","description":"Send a message into another visible session by sessionKey or label. Use this to delegate follow-up work to an existing session; waits for the target run and returns the updated assistant reply when available.","parameters":{"type":"object","required":["message"],"properties":{"sessionKey":{"type":"string"},"label":{"type":"string","minLength":1,"maxLength":512},"agentId":{"type":"string","minLength":1,"maxLength":64},"message":{"type":"string"},"timeoutSeconds":{"type":"number","minimum":0}}}},{"name":"sessions_spawn","description":"Spawn a clean isolated session by default with the native subagent runtime. `mode=\"run\"` is one-shot and `mode=\"session\"` is persistent or thread-bound. Subagents inherit the parent workspace directory automatically. For native subagents only, set `context=\"fork\"` when the child needs the current transcript context; otherwise omit it or use `context=\"isolated\"`. Use this when the work should happen in a fresh child session instead of the current one.","parameters":{"type":"object","required":["task"],"properties":{"task":{"type":"string"},"label":{"type":"string"},"runtime":{"type":"string","enum":["subagent"]},"agentId":{"type":"string"},"model":{"type":"string"},"thinking":{"type":"string"},"cwd":{"type":"string"},"runTimeoutSeconds":{"type":"number","minimum":0},"timeoutSeconds":{"type":"number","minimum":0},"thread":{"type":"boolean"},"mode":{"type":"string","enum":["run","session"]},"cleanup":{"type":"string","enum":["delete","keep"]},"sandbox":{"type":"string","enum":["inherit","require"]},"context":{"type":"string","enum":["isolated","fork"],"description":"Native subagent context mode. Omit or use \"isolated\" for a clean child session; use \"fork\" only when the child needs the requester transcript context."},"lightContext":{"type":"boolean","description":"When true, spawned subagent runs use lightweight bootstrap context. Only applies to runtime='subagent'."},"attachments":{"type":"array","items":{"type":"object","required":["name","content"],"properties":{"name":{"type":"string"},"content":{"type":"string"},"encoding":{"type":"string","enum":["utf8","base64"]},"mimeType":{"type":"string"}}},"maxItems":50},"attachAs":{"type":"object","properties":{"mountPath":{"type":"string"}}}}}},{"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":"subagents","description":"List, kill, or steer spawned sub-agents for this requester session. Use this for sub-agent orchestration.","parameters":{"type":"object","properties":{"action":{"type":"string","enum":["list","kill","steer"]},"target":{"type":"string"},"message":{"type":"string"},"recentMinutes":{"type":"number","minimum":1}}}},{"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 <category>\n  wecom_mcp call <category> <method> '<jsonArgs>'\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":"84fb62f3"}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","source":"runtime","type":"prompt.submitted","ts":"2026-05-13T07:01:30.892Z","seq":4,"sourceSeq":4,"sessionId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","sessionKey":"agent:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","runId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"prompt":"[cron:5b095488-a65a-42db-8589-bc7abbd281b1 金十快报整点推送] 现在是整点推送时间，请立即执行以下任务：\n\n1. 执行脚本 /root/.openclaw/cron/scripts/jin10_flash_mcp.sh 通过金十数据MCP获取真实快报\n2. 将脚本输出的快报内容整理成简洁格式\n3. 直接回复给我，由系统推送到飞书\n\n⚠️ 这个脚本会通过金十数据MCP（mcp.jin10.com/mcp）获取真实数据，不是模拟数据\nCurrent time: Wednesday, May 13th, 2026 - 3:00 PM (Asia/Shanghai) / 2026-05-13 07:00 UTC\n\nUse the message tool if you need to notify the user directly for the current chat. If you do not send directly, your final plain-text reply will be delivered automatically.","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- message: Send messages and channel actions\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- subagents: List, steer, or kill sub-agent runs for this requester session\n- session_status: Show a /status-equivalent status card (usage + time + Reasoning/Verbose/Elevated); use for model-use questions (📊 session_status); optional per-session model override\n- memory_get\n- memory_search\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\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=<ms>).\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 <available_skills> <description> entries.\n- If exactly one skill clearly applies: read its SKILL.md at <location> 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<available_skills>\n  <skill>\n    <name>baoyu-post-to-wechat</name>\n    <description>Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions &quot;发布公众号&quot;, &quot;post to wechat&quot;, &quot;微信公众号&quot;, or &quot;贴图/图文/文章&quot;.</description>\n    <location>~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-doc</name>\n    <description>Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-doc/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-drive</name>\n    <description>Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-drive/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-perm</name>\n    <description>Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-perm/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>feishu-wiki</name>\n    <description>Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.</description>\n    <location>/usr/lib/node_modules/openclaw/dist/extensions/feishu/skills/feishu-wiki/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>healthcheck</name>\n    <description>Audit and harden hosts running OpenClaw for SSH, firewall, updates, exposure, cron checks, and risk posture.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>node-connect</name>\n    <description>Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>skill-creator</name>\n    <description>Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>taskflow</name>\n    <description>Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>taskflow-inbox-triage</name>\n    <description>Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>tmux</name>\n    <description>Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>weather</name>\n    <description>Get current weather, rain, temperature, and forecasts for locations or travel planning.</description>\n    <location>/usr/lib/node_modules/openclaw/skills/weather/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-contact-lookup</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-contact-lookup/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-doc-manager</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-doc-manager/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-edit-todo</name>\n    <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&quot;帮我创建一个待办&quot;、&quot;把这个任务分派给张三&quot;、&quot;标记待办完成&quot;、&quot;删掉那个待办&quot;、&quot;帮我建个提醒&quot;、&quot;更新一下待办内容&quot;、&quot;把提醒时间改到下周&quot;、&quot;接受这个待办&quot;、&quot;拒绝这个待办&quot;等需要对待办进行写操作的场景时使用。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-edit-todo/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-get-todo-detail</name>\n    <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&quot;看看这个待办的详情&quot;、&quot;待办内容是什么&quot;、&quot;这个待办分派给谁了&quot;、&quot;告诉我待办的具体信息&quot;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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-detail/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-get-todo-list</name>\n    <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&quot;看看我的待办列表&quot;、&quot;我有哪些待办&quot;、&quot;这周的待办有哪些&quot;、&quot;最近有什么待办&quot;、&quot;查一下我的待办&quot;、&quot;列出所有待办&quot;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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-get-todo-list/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-create</name>\n    <description>企业微信会议创建技能, 支持创建预约会议. 当用户需要&quot;创建会议&quot;, &quot;预约会议&quot;, &quot;约会议&quot;, &quot;安排会议&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-create/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-manage</name>\n    <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&quot;取消会议&quot;, &quot;删除会议&quot;, &quot;修改会议成员&quot;, &quot;添加会议参与人&quot;, &quot;移除会议成员&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-manage/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-meeting-query</name>\n    <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&quot;查看会议&quot;, &quot;查询会议列表&quot;, &quot;会议详情&quot;, &quot;什么时候开会&quot;, &quot;有哪些会议&quot;, &quot;查找会议&quot;时触发.</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-meeting-query/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-msg</name>\n    <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&quot;查看消息&quot;、&quot;看聊天记录&quot;、&quot;发消息给某人&quot;、&quot;最近有什么消息&quot;、&quot;给群里发消息&quot;、&quot;看看发了什么图片/文件&quot;时触发。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-msg/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-preflight</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-preflight/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-schedule</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-schedule/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-send-media</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-media/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-send-template-card</name>\n    <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&quot;发卡片&quot;，只要语境适合（如&quot;帮我问一下选A还是B&quot;），也应主动激活。仅限 wecom 通道。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-send-template-card/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-smartsheet-data</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-data/SKILL.md</location>\n  </skill>\n  <skill>\n    <name>wecom-smartsheet-schema</name>\n    <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。</description>\n    <location>~/.openclaw/extensions/wecom-openclaw-plugin/skills/wecom-smartsheet-schema/SKILL.md</location>\n  </skill>\n</available_skills>\nIf you need the current date, time, or day of week, run session_status (📊 session_status).\n## Workspace\nYour working directory is: /root/.openclaw/agents/101/workspace\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/agents/101/workspace/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\nBefore doing anything else:\n\n1. Read `SOUL.md` — this is who you are\n2. Read `USER.md` — this is who you're helping\n3. Read `memory/YYYY-MM-DD.md` (today + yesterday) for recent context\n4. **If in MAIN SESSION** (direct chat with your human): Also read `MEMORY.md`\n\nDon't ask permission. Just do it.\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: `<https://example.com>`\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 (&lt;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 &lt;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/agents/101/workspace/SOUL.md\n# SOUL.md - 101（团队协调者）\n\n## 身份定位\n- **姓名：** 101\n- **角色：** 多智能体团队协调者、任务分配官\n- **直属上级：** 首长\n- **管理对象：** 选题大师、脚本大师、文章大师、发布大师、情报大师\n\n## 核心职责\n1. **任务协调：** 接收首长指令，分解任务给相应专家\n2. **进度监控：** 跟踪各专家工作进度，确保按时交付\n3. **质量把关：** 审核各环节输出质量，确保符合首长要求\n4. **沟通桥梁：** 在首长与专家团队之间高效传递信息\n\n## 工作原则\n- **优先级管理：** 始终以首长需求为最高优先级\n- **专业尊重：** 充分信任各领域专家的专业判断\n- **效率至上：** 减少不必要的沟通环节，直击要点\n- **结果导向：** 关注最终交付成果，而非过程细节\n\n## 沟通风格\n- 对首长：恭敬、高效、直接\n- 对团队成员：清晰、专业、支持性\n- 报告格式：简洁明了，重点突出\n\n## 专业知识领域\n- 创业生态与趋势\n- TMT行业动态\n- AI技术应用\n- 自媒体运营策略\n- 短视频内容生态\n- 企业微信服务商业务\n- SaaS产品运营\n\n## 特殊权限\n- 有权调用所有团队成员\n- 可调整任务优先级\n- 可要求团队成员重新调整工作方向\n- 直接向首长汇报工作进展\n\n## 工作规范（2026-04-24更新）\n### 作品管理规范\n1. **保存位置**：各智能体创作的作品必须保存在各自工作区\n2. **文件命名**：`[作品类型]-[主题]-[日期]-[版本].md`\n3. **灵魂文件**：每次重要创作后更新智能体的SOUL.md，记录创作经验\n4. **工作区结构**：\n   ```\n   /works/              # 作品目录\n   /references/         # 参考资料\n   /scripts/           # 工具脚本\n   SOUL.md             # 灵魂文件（持续更新）\n   ```\n\n### 协作流程\n1. **任务接收**：明确首长需求\n2. **智能体调用**：选择最合适的专家\n3. **工作区指定**：确保作品保存在正确位置\n4. **质量审核**：审核输出是否符合要求\n5. **灵魂更新**：记录创作经验和改进点\n\n### 📌 术语表（2026-05-13 记录）\n- **脚本**：首长说的\"脚本\"=短视频逐字稿。口语化台词、可分段、纯文字，不带时间标记和镜头画面提示。除非首长特别说明，\"脚本\"只有这唯一含义。\n- **逐字稿**：脚本的同义词，同一东西。\n- **文章**：公众号/网站发布的正文，末尾绝不附带逐字稿。\n\n### 文件管理\n- 定期整理工作区，保持整洁\n- 建立作品索引，方便查找\n- 备份重要作品和配置\n- 遵循统一的命名规范\n\n## 已验证的执行路径（2026-04-24更新）\n### 🏭 文章创作→网站发布流程\n```\n1. 文章大师（agentId: wenzhang）\n   sessions_spawn 调度文章大师创作文章\n   → 自动保存到工作区 ~/.openclaw/agents/文章大师/workspace/\n   文件名：[主题]-[日期]-v1.md\n\n2. 101生成网站HTML（非电子签章文章需此步骤）\n   用 md-to-wechat.ts 转换 markdown 为 HTML\n   命令：bun skills/baoyu-post-to-wechat/scripts/md-to-wechat.ts [input.md]\n   输出到：/tmp/wechat-article-images-xxx/temp-article.html\n   复制到：~/.openclaw/agents/发布大师/workspace/[主题]-[日期].html\n\n3. 发布大师（agentId: fabu）\n   sessions_spawn 调度发布大师，在任务中指令其完成：\n   a) 公众号发布\n      命令：WECHAT_APP_ID=<redacted> WECHAT_APP_SECRET=<redacted> \\\n        bun skills/baoyu-post-to-wechat/scripts/wechat-api.ts [input.md] \\\n        --theme default --color blue --author \"ai张三疯\"\n   b) 网站发布\n      根据文章主题选择发布目标：\n\n      🅰 创业思维网站（非电子签章类）\n      网站：https://weixinsiwei.com/zb_system/xml-rpc/index.php\n      账号：admin / 135269zxj\n      blogId：68ba1ff10060dd54f1e399b8e332bdba\n      创建 publish-[主题].js → node publish-[主题].js\n\n      🅱 电子签章网（电子签章/电子合同相关）\n      网站：https://dianziqianzhang.com\n      API：XML-RPC (https://dianziqianzhang.com/xmlrpc.php)\n      账号：admin / VCLxs8476YWM\n      BlogID：1\n      命令：python3 ~/.openclaw/agents/发布大师/workspace/scripts/publish-wordpress.py [input.md] --status <status>\n      说明：WordPress 站点，支持文章分类和标签，发布为草稿后需登录后台审核\n```\n\n### 🧭 发文路由规则（2026-04-29 新增）\n```\n根据文章主题自动匹配发布目标：\n\n【电子签章网 dianziqianzhang.com】\n匹配词：电子签章、电子合同、电子签名、数字签名、CA认证、签章平台、合同管理\n        法大大、e签宝、上上签、契约锁、签盾、数字认证\n发布方式：WordPress XML-RPC → publish-wordpress.py\n\n【创业思维网 weixinsiwei.com】\n匹配词：创业、副业、生意、赚钱、AI创业、自媒体、个人IP、商业模式\n        或其他不涉及电子签章的泛创业/思维类内容\n发布方式：Z-Blog XML-RPC → publish-[主题].js\n\n【同时发布】\n如果文章既涉及电子签章又涉及创业，以电子签章为主，发到 dianziqianzhang.com\n```\n\n### 📢 公众号发布流程\n```\n公众号：创业张三疯（alias: chuangyezhangsanfeng）\n方法：API（首选）\n凭证：WECHAT_APP_ID=<redacted> / WECHAT_APP_SECRET=<redacted>\n命令：bun skills/baoyu-post-to-wechat/scripts/wechat-api.ts [input.md] --theme default --color blue --author \"ai张三疯\" --cover [cover.jpg]\n封面要求：必须提供本地或URL封面图（article_type=news必需）\n输出会存为草稿箱，需登录 mp.weixin.qq.com 手动群发\n```\n\n### 🖼️ 自动配图逻辑（2026-04-25 新增）\n\n在发布环节自动配封面图，策略如下：\n\n```\n文章大师输出 → 读取文章中的 cover_category（如 ai-chip）\n        ↓\n101 检查 ~/imgs/[cover_category]/ 目录是否有图片\n        ↓\n有图？→ 从该目录取一张图\n无图？→ 检查 default/ 目录\n  有图？→ 取 default/ 的图\n  无图？→ 跳过配图，文章照发\n```\n\n**取图规则：**\n- 目录内多张图时：排序后取第一张（稳定可预期，不随机）\n- 支持格式：jpg、png、webp、jpeg\n- 找到图后保存到临时路径，在发布指令中传 --cover 参数\n- 找不到图时不传 --cover，不阻塞发布流程\n\n### 🔄 完整标准流程（2026-05-13 更新）\n当首长说\"写XX主题，写文章发公众号和网站，还要逐字稿\"时：\n\n**第一步：文章创作（文章大师）**\n1. 调文章大师（agentId: wenzhang）\n   - 指令中明确：**只写文章，不包含逐字稿**\n   - 要求在输出中标注 cover_category 和 domain\n2. 等文章大师完成通知\n\n**第二步：逐字稿创作（脚本大师）— 如需短视频脚本**\n3. 调脚本大师（agentId: jiaoben）\n   - 指令中明确：独立创作短视频逐字稿\n   - 素材引用文章标题和核心观点即可\n   - 保存到脚本大师工作区\n4. 等脚本大师完成通知（可与文章大师并行）\n\n**第三步：发布**\n5. 读取文章大师输出的 .md 文件\n   - 用 `md2html.py` 处理 front-matter 并生成 HTML\n6. 根据文章主题判断发布目标\n7. 调发布大师（agentId: fabu）\n8. **发布完成后必须验证所有渠道**\n\n### ⚠️ 硬性规则（违反即出事故）\n\n#### 规则0（2026-05-13 新增）：文章和逐字稿严格分离\n- 文章大师只写文章，末尾**绝不附加**逐字稿\n- 脚本大师独立创作短视频逐字稿\n- 两份文件分开保存，各自发布/交付\n- 首长指令中提到\"写文章+逐字稿\"时，要两个智能体各接各活\n\n#### 规则1：Z-Blog 发布必须传 HTML，不能传 Markdown\n- Z-Blog 的 metaWeblog.newPost 不会自动渲染 Markdown\n- 必须先用 `md2html.py` 将 markdown 转成 HTML 再提交\n- 命令：`python3 ~/.openclaw/agents/发布大师/workspace/scripts/md2html.py [input.md] -o [output.html]`\n- Z-Blog 只支持 publish 状态，不支持 draft\n- Z-Blog 的 newPost 只返回 boolean 不返回 postID，需用 getRecentPosts 验证\n\n#### 规则2：公众号发布前必须准备好 .md 文件\n- 公众号的文件必须保存到 `post-to-wechat/[日期]/[主题].md`\n- 去掉 front-matter（文大师输出专用 md2html.py 处理）\n- 有封面图时传 `--cover` 参数，无封面图时也发布（不阻塞）\n- 公众号草稿创建后必须验证草稿箱中是否存在\n\n#### 规则3：文章大师输出文件的 front-matter 处理\n- 文章大师输出文件可能有 front-matter 也可能没有\n- 用 `md2html.py` 统一处理（自动检测并去掉 front-matter）\n- 提取标题时用 `md2html.py --title-only` 获取标题\n\n#### 规则4：发布后必须验证所有渠道\n- Z-Blog：用 getRecentPosts 验证文章是否存在，确认内容为 HTML 格式\n- 公众号：用 batchget 接口验证草稿箱中是否有该文章\n- WordPress：用 XML-RPC getRecentPosts 验证\n\n### 🛠️ 通用工具\n- `~/.openclaw/agents/发布大师/workspace/scripts/md2html.py`：Markdown→HTML 转换（带 front-matter 处理）\n- `~/.openclaw/agents/发布大师/workspace/scripts/publish-wordpress.py`：WordPress XML-RPC 发布\n- `skills/baoyu-post-to-wechat/scripts/wechat-api.ts`：公众号发布\n\n### ✂️ 文章写作规范（2026-05-13 更新）\n- 文末**不加**备注信息\n- 文末**不加**来源引用长尾巴\n- 文末**不加**短视频逐字稿（逐字稿由脚本大师独立输出）\n- 如果需要注明来源，用一句话带过，不要用清单或引用块\n\n### 📁 文件保存规范\n- **文章大师作品：** ~/.openclaw/agents/文章大师/workspace/[主题]-[日期]-v1.md\n- **脚本大师作品（逐字稿）：** ~/.openclaw/workspace/jiaoben/[主题]-逐字稿-[日期]-v1.md\n  **或** ~/.openclaw/workspace/jiaoben/[主题]-脚本-[日期]-v1.md\n- Z-Blog HTML：不需要单独保存HTML，md2html.py 临时生成即可\n- 公众号Markdown：~/.openclaw/agents/101/workspace/post-to-wechat/[日期]/[主题].md（去掉 front-matter）\n- 封面图：~/.openclaw/agents/101/workspace/post-to-wechat/[日期]/imgs/cover.jpg\n\n---\n\n**座右铭：** \"高效协同，精准交付，让首长的每一个想法都变成现实\"\n## /root/.openclaw/agents/101/workspace/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/agents/101/workspace/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/agents/101/workspace/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<!-- OPENCLAW_CACHE_BOUNDARY -->\n\n## Runtime\nRuntime: agent=101 | host=<redacted> | os=Linux 6.8.0-55-generic (x64) | node=v22.22.1 | model=<redacted> | default_model=<redacted> | 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":"51e0d2da-b4cf-4803-af8a-47f3a985de16","source":"runtime","type":"model.completed","ts":"2026-05-13T07:01:37.191Z","seq":5,"sourceSeq":5,"sessionId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","sessionKey":"agent:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","runId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"promptErrorSource":null,"usage":{"input":3394,"output":354,"cacheRead":34432,"total":38180},"promptCache":{"lastCallUsage":{"input":3250,"output":273,"cacheRead":17280,"cacheWrite":0,"total":20803},"lastCacheTouchAt":1778655693613},"compactionCount":0,"assistantTexts":["📰 **金十快报 | 5月13日 15:00**\n\n**最新快讯：**\n• 大摩全面上调中国股指目标价\n• 法国4月通胀率确认为2.5%，创2024年7月以来新高\n• 沙特阿美寻求从房地产投资组合筹集超100亿美元\n• 阿联酋银行联合会：该国绝对没有出现美元短缺\n\n**今日已发布重要数据：**\n📍 法国4月CPI终值 2.2%（符合预期）\n📍 法国4月调和CPI终值 2.5%（符合预期）\n📍 法国Q1失业率 8.1%（前值7.9%）\n📍 德国4月批发物价年率 6.3%（前值4.1%）\n📍 日本3月贸易帐 8305亿日元（前值2676亿）\n📍 美国EIA下调WTI及布伦特原油均价预期\n📍 美国API原油库存 -218.8万桶（利多）\n\n**待关注（北京时间）：**\n🔥 17:00 欧元区Q1 GDP修正值\n🔥 20:30 美国4月PPI（重磅）\n🔥 22:30 美国EIA原油库存\n\n数据来源：金十数据 MCP ✅"],"finalPromptText":"[cron:5b095488-a65a-42db-8589-bc7abbd281b1 金十快报整点推送] 现在是整点推送时间，请立即执行以下任务：\n\n1. 执行脚本 /root/.openclaw/cron/scripts/jin10_flash_mcp.sh 通过金十数据MCP获取真实快报\n2. 将脚本输出的快报内容整理成简洁格式\n3. 直接回复给我，由系统推送到飞书\n\n⚠️ 这个脚本会通过金十数据MCP（mcp.jin10.com/mcp）获取真实数据，不是模拟数据\nCurrent time: Wednesday, May 13th, 2026 - 3:00 PM (Asia/Shanghai) / 2026-05-13 07:00 UTC\n\nUse the message tool if you need to notify the user directly for the current chat. If you do not send directly, your final plain-text reply will be delivered automatically.","messagesSnapshot":[{"role":"user","content":[{"type":"text","text":"[cron:5b095488-a65a-42db-8589-bc7abbd281b1 金十快报整点推送] 现在是整点推送时间，请立即执行以下任务：\n\n1. 执行脚本 /root/.openclaw/cron/scripts/jin10_flash_mcp.sh 通过金十数据MCP获取真实快报\n2. 将脚本输出的快报内容整理成简洁格式\n3. 直接回复给我，由系统推送到飞书\n\n⚠️ 这个脚本会通过金十数据MCP（mcp.jin10.com/mcp）获取真实数据，不是模拟数据\nCurrent time: Wednesday, May 13th, 2026 - 3:00 PM (Asia/Shanghai) / 2026-05-13 07:00 UTC\n\nUse the message tool if you need to notify the user directly for the current chat. If you do not send directly, your final plain-text reply will be delivered automatically."}],"timestamp":1778655690893},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_JCqgIPV7OhxXPbR3RgSY2465","name":"exec","arguments":{"command":"bash /root/.openclaw/cron/scripts/jin10_flash_mcp.sh 2>&1","timeout":60}}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":144,"output":81,"cacheRead":17152,"cacheWrite":0,"totalTokens":17377,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1778655690900,"responseId":"b1c37d33-bbaf-4cc0-9fd8-93319fe30e79"},{"role":"toolResult","toolCallId":"call_00_JCqgIPV7OhxXPbR3RgSY2465","toolName":"exec","content":[{"type":"text","text":"【金十快报 15:00】\n推送时间: 2026-05-13 15:01:32\n========================================\n\nSession: B234DRN6QVLT4ZXLRLIEEZSASD\n📰 最新快讯:\n   14:49 【法国4月通胀率确认为2.5%，创2024年7月以来新高】金十数据5月13日讯，法国国家统计局周三表示，4月份法国按欧盟...\n   14:48 【大摩全面上调中国股指目标价】金十数据5月13日讯，5月13日，摩根士丹利发布题为“锻造新前沿（Forging New ...\n   14:48 SK创新：预计尽管存在不确定性，即使第二季度冲突得到解决，生产和物流的恢复正常也需要时间。\n   14:47 法国4月调和CPI年率终值录得2.5%，为2024年7月以来最高。\n   14:46 金十数据整理：每日电动车行业动态汇总（2026-05-13）\n   14:46 沙特阿美公司寻求从其房地产投资组合中筹集超过100亿美元。\n   14:46 阿联酋银行联合会主席表示，该国绝对没有出现美元短缺。\n   14:45 法国4月CPI月率终值 1%，预期1%，前值1.00%。\n   14:45 法国4月CPI年率终值 2.2%，预期2.2%，前值2.20%。\n   14:45 法国4月调和CPI年率终值 2.5%，预期2.5%，前值2.50%。\n\n📅 今日财经日历:\n   ⭐⭐ 00:00 美国5月EIA当年WTI原油均价预期(美元/桶) (前值:87.41) 实际:85.68 利空\n   ⭐⭐ 00:00 美国5月EIA当年布伦特原油均价预期(美元/桶) (前值:96) 实际:94.85 利空\n   ⭐⭐ 00:00 美国5月EIA当年短期前景美国原油产量预期(万桶/日) (前值:1351) 实际:1365 利空\n   ⭐⭐ 00:00 美国5月EIA次年短期前景美国原油产量预期(万桶/日) (前值:1395) 实际:1410 利空\n   ⭐ 00:00 美国5月EIA当年天然气产量预期(亿立方英尺/日) (前值:1096) 实际:1106 利空\n   ⭐ 00:00 美国5月EIA次年天然气产量预期(亿立方英尺/日) (前值:1126) 实际:1150 利空\n   ⭐⭐⭐ 01:00 美国至5月12日10年期国债竞拍-得标利率 (前值:4.28) 实际:4.468 利空\n   ⭐⭐⭐ 01:00 美国至5月12日10年期国债竞拍-投标倍数 (前值:2.43) 实际:2.4 利空\n   ⭐⭐ 01:00 美国至5月12日10年期国债竞拍-得标利率配置百分比 (前值:38.89) 实际:22 利空\n   ⭐⭐ 02:00 美国4月政府预算(亿美元) (前值:-1640) 实际:2150 利多\n   ⭐⭐⭐ 04:30 美国至5月8日当周API原油库存(万桶) (前值:-814.1) 实际:-218.8 利多\n   ⭐⭐ 04:30 美国至5月8日当周API原油进口(万桶) (前值:-14.4) 实际:33.7 利空\n   ⭐⭐ 04:30 美国至5月8日当周API取暖油库存(万桶) (前值:-47.3) 实际:-11.6 利空\n   ⭐⭐ 04:30 美国至5月8日当周API库欣原油库存(万桶) (前值:-104.5) 实际:-175.5 利多\n   ⭐⭐ 04:30 美国至5月8日当周API成品油进口(万桶/日) (前值:26.5) 实际:-31.7 利多\n   ⭐⭐ 04:30 美国至5月8日当周API投产原油量(万桶/日) (前值:4.1) 实际:18.8 利空\n   ⭐ 04:30 美国至5月8日当周API汽油库存(万桶) (前值:-610.7) 实际:50.2 利空\n   ⭐ 04:30 美国至5月8日当周API精炼油库存(万桶) (前值:-464.2) 实际:-31.9 利空\n   ⭐⭐ 07:00 韩国4月失业率 (前值:2.70) 实际:2.8 利空\n   ⭐⭐⭐ 07:50 日本3月贸易帐(亿日元) (前值:2676) 实际:8305 利多\n   ⭐⭐ 07:50 日本3月季调后经常账(亿日元) (前值:27090) 实际:39006 利多\n   ⭐⭐ 07:50 日本4月季调后银行贷款年率 (前值:4.80) 实际:5.4 利多\n   ⭐⭐ 07:50 日本4月季调后除信托外银行贷款年率 (前值:5.20) 实际:6 利多\n   ⭐⭐ 07:50 日本3月未季调经常帐(亿日元) (前值:39327) 实际:46815 利多\n   ⭐ 09:30 澳大利亚第一季度季调后薪资价格指数季率 (前值:0.80) 实际:0.8 影响较小\n   ⭐ 09:30 澳大利亚第一季度季调后薪资价格指数年率 (前值:3.40) 实际:3.3 影响较小\n   ⭐ 11:00 韩国3月L货币供应年率 (前值:8) 实际:7.2 利空\n   ⭐ 11:00 韩国3月L货币供应月率 (前值:0.90) 实际:-0.4 利空\n   ⭐ 11:00 韩国3月货币供应M2月率 (前值:0.00) 实际:0.4 利多\n   ⭐⭐ 13:00 日本4月经济观察家前景指数 (前值:38.7) 实际:39.4 利空\n   ⭐⭐ 13:00 日本4月经济观察家现况指数 (前值:42.2) 实际:40.8 利空\n   ⭐⭐⭐ 13:30 法国第一季度ILO失业率 (前值:7.90) 实际:8.1 利空\n   ⭐⭐ 14:00 德国4月批发物价指数年率 (前值:4.1) 实际:6.3 利多\n   ⭐⭐ 14:00 德国4月批发物价指数月率 (前值:2.7) 实际:2 利空\n   ⭐⭐⭐ 14:45 法国4月CPI月率终值 (前值:1.00) 实际:1 影响较小\n   ⭐⭐ 14:45 法国4月CPI年率终值 (前值:2.20) 实际:2.2 影响较小\n   ⭐ 14:45 法国4月调和CPI年率终值 (前值:2.50) 实际:2.5 影响较小\n   ⭐ 14:45 法国4月调和CPI月率终值 (前值:1.20) 实际:1.2 影响较小\n   ⭐⭐⭐ 17:00 欧元区第一季度GDP年率修正值 (前值:0.80) 未公布\n   ⭐⭐⭐ 17:00 欧元区第一季度季调后就业人数季率初值 (前值:0.20) 未公布\n   ⭐⭐⭐ 17:00 欧元区3月工业产出月率 (前值:0.40) 未公布\n   ⭐⭐ 17:00 欧元区第一季度GDP季率修正值 (前值:0.10) 未公布\n   ⭐⭐ 17:00 欧元区第一季度季调后就业人数年率初值 (前值:0.70) 未公布\n   ⭐⭐ 17:00 欧元区3月工业产出年率 (前值:-0.60) 未公布\n   ⭐⭐ 19:00 美国至5月8日当周MBA30年期固定抵押贷款利率 (前值:6.45) 未公布\n   ⭐⭐ 19:00 美国至5月8日当周MBA抵押贷款申请活动指数 (前值:285.3) 未公布\n   ⭐ 19:00 美国至5月8日当周MBA抵押贷款再融资活动指数 (前值:928.6) 未公布\n   ⭐ 19:00 美国至5月8日当周MBA抵押贷款购买指数 (前值:171.1) 未公布\n   ⭐⭐⭐ 20:30 美国4月PPI年率 (前值:4.00) 未公布\n   ⭐⭐⭐ 20:30 美国4月PPI月率 (前值:0.50) 未公布\n   ⭐⭐ 20:30 美国4月核心PPI年率 (前值:3.80) 未公布\n   ⭐⭐ 20:30 美国4月核心PPI月率 (前值:0.10) 未公布\n   ⭐⭐⭐⭐ 22:30 美国至5月8日当周EIA原油库存(万桶) (前值:-231.3) 未公布\n   ⭐⭐⭐ 22:30 美国至5月8日当周EIA俄克拉荷马州库欣原油库存(万桶) (前值:-64.8) 未公布\n   ⭐⭐⭐ 22:30 美国至5月8日当周EIA战略石油储备库存(万桶) (前值:-522.4) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA原油产量引伸需求数据(万桶/日) (前值:1938) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA原油进口(万桶) (前值:141.5) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA取暖油库存(万桶) (前值:-3.8) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA成品油进口(万桶/日) (前值:-0.9) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA投产原油量(万桶/日) (前值:-4.2) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA汽油产量(万桶/日) (前值:-27.5) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA精炼厂设备利用率 (前值:90.1) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA精炼油产量(万桶/日) (前值:-2.4) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA新配方汽油库存(万桶) (前值:0.2) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA汽油库存(万桶) (前值:-250.4) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA精炼油库存(万桶) (前值:-129.4) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA蒸馏燃油产量引伸需求数据(万桶/日) (前值:522.39) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA车用汽油总产量引伸需求数据(万桶/日) (前值:966.89) 未公布\n   ⭐ 23:30 美国至5月13日4个月国债竞拍-得标利率 (前值:3.61) 未公布\n   ⭐ 23:30 美国至5月13日4个月国债竞拍-得标利率配置百分比 (前值:70.08) 未公布\n   ⭐ 23:30 美国至5月13日4个月国债竞拍-投标倍数 (前值:3.13) 未公布\n   ⭐⭐⭐ 00:00 中国4月M2货币供应年率 (前值:8.5)\n   ⭐⭐ 00:00 中国4月今年迄今新增人民币贷款(亿元) (前值:86000)\n   ⭐ 00:00 中国4月M0货币供应年率 (前值:12.5)\n   ⭐ 00:00 中国4月M1货币供应年率 (前值:5.1)\n   ⭐ 00:00 中国4月今年迄今社会融资规模增量(亿元) (前值:148300)\n   ⭐⭐ 19:00 德国3月未季调经常帐(亿欧元) (前值:220) 未公布\n\n========================================\n数据来源: 金十数据 MCP（真实数据）✅"}],"details":{"status":"completed","exitCode":0,"durationMs":1075,"aggregated":"【金十快报 15:00】\n推送时间: 2026-05-13 15:01:32\n========================================\n\nSession: B234DRN6QVLT4ZXLRLIEEZSASD\n📰 最新快讯:\n   14:49 【法国4月通胀率确认为2.5%，创2024年7月以来新高】金十数据5月13日讯，法国国家统计局周三表示，4月份法国按欧盟...\n   14:48 【大摩全面上调中国股指目标价】金十数据5月13日讯，5月13日，摩根士丹利发布题为“锻造新前沿（Forging New ...\n   14:48 SK创新：预计尽管存在不确定性，即使第二季度冲突得到解决，生产和物流的恢复正常也需要时间。\n   14:47 法国4月调和CPI年率终值录得2.5%，为2024年7月以来最高。\n   14:46 金十数据整理：每日电动车行业动态汇总（2026-05-13）\n   14:46 沙特阿美公司寻求从其房地产投资组合中筹集超过100亿美元。\n   14:46 阿联酋银行联合会主席表示，该国绝对没有出现美元短缺。\n   14:45 法国4月CPI月率终值 1%，预期1%，前值1.00%。\n   14:45 法国4月CPI年率终值 2.2%，预期2.2%，前值2.20%。\n   14:45 法国4月调和CPI年率终值 2.5%，预期2.5%，前值2.50%。\n\n📅 今日财经日历:\n   ⭐⭐ 00:00 美国5月EIA当年WTI原油均价预期(美元/桶) (前值:87.41) 实际:85.68 利空\n   ⭐⭐ 00:00 美国5月EIA当年布伦特原油均价预期(美元/桶) (前值:96) 实际:94.85 利空\n   ⭐⭐ 00:00 美国5月EIA当年短期前景美国原油产量预期(万桶/日) (前值:1351) 实际:1365 利空\n   ⭐⭐ 00:00 美国5月EIA次年短期前景美国原油产量预期(万桶/日) (前值:1395) 实际:1410 利空\n   ⭐ 00:00 美国5月EIA当年天然气产量预期(亿立方英尺/日) (前值:1096) 实际:1106 利空\n   ⭐ 00:00 美国5月EIA次年天然气产量预期(亿立方英尺/日) (前值:1126) 实际:1150 利空\n   ⭐⭐⭐ 01:00 美国至5月12日10年期国债竞拍-得标利率 (前值:4.28) 实际:4.468 利空\n   ⭐⭐⭐ 01:00 美国至5月12日10年期国债竞拍-投标倍数 (前值:2.43) 实际:2.4 利空\n   ⭐⭐ 01:00 美国至5月12日10年期国债竞拍-得标利率配置百分比 (前值:38.89) 实际:22 利空\n   ⭐⭐ 02:00 美国4月政府预算(亿美元) (前值:-1640) 实际:2150 利多\n   ⭐⭐⭐ 04:30 美国至5月8日当周API原油库存(万桶) (前值:-814.1) 实际:-218.8 利多\n   ⭐⭐ 04:30 美国至5月8日当周API原油进口(万桶) (前值:-14.4) 实际:33.7 利空\n   ⭐⭐ 04:30 美国至5月8日当周API取暖油库存(万桶) (前值:-47.3) 实际:-11.6 利空\n   ⭐⭐ 04:30 美国至5月8日当周API库欣原油库存(万桶) (前值:-104.5) 实际:-175.5 利多\n   ⭐⭐ 04:30 美国至5月8日当周API成品油进口(万桶/日) (前值:26.5) 实际:-31.7 利多\n   ⭐⭐ 04:30 美国至5月8日当周API投产原油量(万桶/日) (前值:4.1) 实际:18.8 利空\n   ⭐ 04:30 美国至5月8日当周API汽油库存(万桶) (前值:-610.7) 实际:50.2 利空\n   ⭐ 04:30 美国至5月8日当周API精炼油库存(万桶) (前值:-464.2) 实际:-31.9 利空\n   ⭐⭐ 07:00 韩国4月失业率 (前值:2.70) 实际:2.8 利空\n   ⭐⭐⭐ 07:50 日本3月贸易帐(亿日元) (前值:2676) 实际:8305 利多\n   ⭐⭐ 07:50 日本3月季调后经常账(亿日元) (前值:27090) 实际:39006 利多\n   ⭐⭐ 07:50 日本4月季调后银行贷款年率 (前值:4.80) 实际:5.4 利多\n   ⭐⭐ 07:50 日本4月季调后除信托外银行贷款年率 (前值:5.20) 实际:6 利多\n   ⭐⭐ 07:50 日本3月未季调经常帐(亿日元) (前值:39327) 实际:46815 利多\n   ⭐ 09:30 澳大利亚第一季度季调后薪资价格指数季率 (前值:0.80) 实际:0.8 影响较小\n   ⭐ 09:30 澳大利亚第一季度季调后薪资价格指数年率 (前值:3.40) 实际:3.3 影响较小\n   ⭐ 11:00 韩国3月L货币供应年率 (前值:8) 实际:7.2 利空\n   ⭐ 11:00 韩国3月L货币供应月率 (前值:0.90) 实际:-0.4 利空\n   ⭐ 11:00 韩国3月货币供应M2月率 (前值:0.00) 实际:0.4 利多\n   ⭐⭐ 13:00 日本4月经济观察家前景指数 (前值:38.7) 实际:39.4 利空\n   ⭐⭐ 13:00 日本4月经济观察家现况指数 (前值:42.2) 实际:40.8 利空\n   ⭐⭐⭐ 13:30 法国第一季度ILO失业率 (前值:7.90) 实际:8.1 利空\n   ⭐⭐ 14:00 德国4月批发物价指数年率 (前值:4.1) 实际:6.3 利多\n   ⭐⭐ 14:00 德国4月批发物价指数月率 (前值:2.7) 实际:2 利空\n   ⭐⭐⭐ 14:45 法国4月CPI月率终值 (前值:1.00) 实际:1 影响较小\n   ⭐⭐ 14:45 法国4月CPI年率终值 (前值:2.20) 实际:2.2 影响较小\n   ⭐ 14:45 法国4月调和CPI年率终值 (前值:2.50) 实际:2.5 影响较小\n   ⭐ 14:45 法国4月调和CPI月率终值 (前值:1.20) 实际:1.2 影响较小\n   ⭐⭐⭐ 17:00 欧元区第一季度GDP年率修正值 (前值:0.80) 未公布\n   ⭐⭐⭐ 17:00 欧元区第一季度季调后就业人数季率初值 (前值:0.20) 未公布\n   ⭐⭐⭐ 17:00 欧元区3月工业产出月率 (前值:0.40) 未公布\n   ⭐⭐ 17:00 欧元区第一季度GDP季率修正值 (前值:0.10) 未公布\n   ⭐⭐ 17:00 欧元区第一季度季调后就业人数年率初值 (前值:0.70) 未公布\n   ⭐⭐ 17:00 欧元区3月工业产出年率 (前值:-0.60) 未公布\n   ⭐⭐ 19:00 美国至5月8日当周MBA30年期固定抵押贷款利率 (前值:6.45) 未公布\n   ⭐⭐ 19:00 美国至5月8日当周MBA抵押贷款申请活动指数 (前值:285.3) 未公布\n   ⭐ 19:00 美国至5月8日当周MBA抵押贷款再融资活动指数 (前值:928.6) 未公布\n   ⭐ 19:00 美国至5月8日当周MBA抵押贷款购买指数 (前值:171.1) 未公布\n   ⭐⭐⭐ 20:30 美国4月PPI年率 (前值:4.00) 未公布\n   ⭐⭐⭐ 20:30 美国4月PPI月率 (前值:0.50) 未公布\n   ⭐⭐ 20:30 美国4月核心PPI年率 (前值:3.80) 未公布\n   ⭐⭐ 20:30 美国4月核心PPI月率 (前值:0.10) 未公布\n   ⭐⭐⭐⭐ 22:30 美国至5月8日当周EIA原油库存(万桶) (前值:-231.3) 未公布\n   ⭐⭐⭐ 22:30 美国至5月8日当周EIA俄克拉荷马州库欣原油库存(万桶) (前值:-64.8) 未公布\n   ⭐⭐⭐ 22:30 美国至5月8日当周EIA战略石油储备库存(万桶) (前值:-522.4) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA原油产量引伸需求数据(万桶/日) (前值:1938) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA原油进口(万桶) (前值:141.5) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA取暖油库存(万桶) (前值:-3.8) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA成品油进口(万桶/日) (前值:-0.9) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA投产原油量(万桶/日) (前值:-4.2) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA汽油产量(万桶/日) (前值:-27.5) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA精炼厂设备利用率 (前值:90.1) 未公布\n   ⭐⭐ 22:30 美国至5月8日当周EIA精炼油产量(万桶/日) (前值:-2.4) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA新配方汽油库存(万桶) (前值:0.2) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA汽油库存(万桶) (前值:-250.4) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA精炼油库存(万桶) (前值:-129.4) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA蒸馏燃油产量引伸需求数据(万桶/日) (前值:522.39) 未公布\n   ⭐ 22:30 美国至5月8日当周EIA车用汽油总产量引伸需求数据(万桶/日) (前值:966.89) 未公布\n   ⭐ 23:30 美国至5月13日4个月国债竞拍-得标利率 (前值:3.61) 未公布\n   ⭐ 23:30 美国至5月13日4个月国债竞拍-得标利率配置百分比 (前值:70.08) 未公布\n   ⭐ 23:30 美国至5月13日4个月国债竞拍-投标倍数 (前值:3.13) 未公布\n   ⭐⭐⭐ 00:00 中国4月M2货币供应年率 (前值:8.5)\n   ⭐⭐ 00:00 中国4月今年迄今新增人民币贷款(亿元) (前值:86000)\n   ⭐ 00:00 中国4月M0货币供应年率 (前值:12.5)\n   ⭐ 00:00 中国4月M1货币供应年率 (前值:5.1)\n   ⭐ 00:00 中国4月今年迄今社会融资规模增量(亿元) (前值:148300)\n   ⭐⭐ 19:00 德国3月未季调经常帐(亿欧元) (前值:220) 未公布\n\n========================================\n数据来源: 金十数据 MCP（真实数据）✅","cwd":"/root/.openclaw/agents/101/workspace"},"isError":false,"timestamp":1778655693611},{"role":"assistant","content":[{"type":"text","text":"📰 **金十快报 | 5月13日 15:00**\n\n**最新快讯：**\n• 大摩全面上调中国股指目标价\n• 法国4月通胀率确认为2.5%，创2024年7月以来新高\n• 沙特阿美寻求从房地产投资组合筹集超100亿美元\n• 阿联酋银行联合会：该国绝对没有出现美元短缺\n\n**今日已发布重要数据：**\n📍 法国4月CPI终值 2.2%（符合预期）\n📍 法国4月调和CPI终值 2.5%（符合预期）\n📍 法国Q1失业率 8.1%（前值7.9%）\n📍 德国4月批发物价年率 6.3%（前值4.1%）\n📍 日本3月贸易帐 8305亿日元（前值2676亿）\n📍 美国EIA下调WTI及布伦特原油均价预期\n📍 美国API原油库存 -218.8万桶（利多）\n\n**待关注（北京时间）：**\n🔥 17:00 欧元区Q1 GDP修正值\n🔥 20:30 美国4月PPI（重磅）\n🔥 22:30 美国EIA原油库存\n\n数据来源：金十数据 MCP ✅"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":3250,"output":273,"cacheRead":17280,"cacheWrite":0,"totalTokens":20803,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1778655693613,"responseId":"e3c4aa5b-a239-409d-9794-c7f50bc8e608"}]}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","source":"runtime","type":"trace.artifacts","ts":"2026-05-13T07:01:37.191Z","seq":6,"sourceSeq":6,"sessionId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","sessionKey":"agent:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","runId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-05-13T07:01:37.191Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"promptErrorSource":null,"usage":{"input":3394,"output":354,"cacheRead":34432,"total":38180},"promptCache":{"lastCallUsage":{"input":3250,"output":273,"cacheRead":17280,"cacheWrite":0,"total":20803},"lastCacheTouchAt":1778655693613},"compactionCount":0,"assistantTexts":["📰 **金十快报 | 5月13日 15:00**\n\n**最新快讯：**\n• 大摩全面上调中国股指目标价\n• 法国4月通胀率确认为2.5%，创2024年7月以来新高\n• 沙特阿美寻求从房地产投资组合筹集超100亿美元\n• 阿联酋银行联合会：该国绝对没有出现美元短缺\n\n**今日已发布重要数据：**\n📍 法国4月CPI终值 2.2%（符合预期）\n📍 法国4月调和CPI终值 2.5%（符合预期）\n📍 法国Q1失业率 8.1%（前值7.9%）\n📍 德国4月批发物价年率 6.3%（前值4.1%）\n📍 日本3月贸易帐 8305亿日元（前值2676亿）\n📍 美国EIA下调WTI及布伦特原油均价预期\n📍 美国API原油库存 -218.8万桶（利多）\n\n**待关注（北京时间）：**\n🔥 17:00 欧元区Q1 GDP修正值\n🔥 20:30 美国4月PPI（重磅）\n🔥 22:30 美国EIA原油库存\n\n数据来源：金十数据 MCP ✅"],"finalPromptText":"[cron:5b095488-a65a-42db-8589-bc7abbd281b1 金十快报整点推送] 现在是整点推送时间，请立即执行以下任务：\n\n1. 执行脚本 /root/.openclaw/cron/scripts/jin10_flash_mcp.sh 通过金十数据MCP获取真实快报\n2. 将脚本输出的快报内容整理成简洁格式\n3. 直接回复给我，由系统推送到飞书\n\n⚠️ 这个脚本会通过金十数据MCP（mcp.jin10.com/mcp）获取真实数据，不是模拟数据\nCurrent time: Wednesday, May 13th, 2026 - 3:00 PM (Asia/Shanghai) / 2026-05-13 07:00 UTC\n\nUse the message tool if you need to notify the user directly for the current chat. If you do not send directly, your final plain-text reply will be delivered automatically.","itemLifecycle":{"startedCount":2,"completedCount":2,"activeCount":0},"toolMetas":[{"toolName":"exec","meta":"bash ~/.openclaw/cron/scripts/jin10_flash_mcp.sh 2>&1"}],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[]}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","source":"runtime","type":"session.ended","ts":"2026-05-13T07:01:37.191Z","seq":7,"sourceSeq":7,"sessionId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","sessionKey":"agent:101:cron:5b095488-a65a-42db-8589-bc7abbd281b1:run:51e0d2da-b4cf-4803-af8a-47f3a985de16","runId":"51e0d2da-b4cf-4803-af8a-47f3a985de16","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"status":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false}}