Files
openclaw-config/agents/travel/session-sqlite-import-archive/archive-tier.51a9cb19-9381-4f4f-a292-388dce05ae12.trajectory.jsonl.imported-1788177806970
T

8 lines
147 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51a9cb19-9381-4f4f-a292-388dce05ae12","source":"runtime","type":"session.started","ts":"2026-06-01T00:55:05.725Z","seq":1,"sourceSeq":1,"sessionId":"51a9cb19-9381-4f4f-a292-388dce05ae12","sessionKey":"agent:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","runId":"51a9cb19-9381-4f4f-a292-388dce05ae12","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"trigger":"cron","sessionFile":"/home/yangxuan/.openclaw/agents/travel/sessions/51a9cb19-9381-4f4f-a292-388dce05ae12.jsonl","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","agentId":"travel","messageChannel":"openclaw-weixin","localModelLean":false,"toolCount":17,"clientToolCount":0}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51a9cb19-9381-4f4f-a292-388dce05ae12","source":"runtime","type":"trace.metadata","ts":"2026-06-01T00:55:05.727Z","seq":2,"sourceSeq":2,"sessionId":"51a9cb19-9381-4f4f-a292-388dce05ae12","sessionKey":"agent:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","runId":"51a9cb19-9381-4f4f-a292-388dce05ae12","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"capturedAt":"2026-06-01T00:55:05.725Z","harness":{"type":"openclaw","name":"OpenClaw","version":"2026.5.22","gitSha":"5c39670","os":{"platform":"linux","arch":"x64","release":"6.6.87.2-microsoft-standard-WSL2","label":"linux 6.6.87.2-microsoft-standard-WSL2 (x64)"},"runtime":{"node":"v25.2.0"},"invocation":["~/.nvm/versions/node/v25.2.0/bin/node","~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/index.js","gateway","--port","18789"],"entrypoint":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/index.js","workspaceDir":"$OPENCLAW_STATE_DIR/workspace/travel","sessionFile":"$OPENCLAW_STATE_DIR/agents/travel/sessions/51a9cb19-9381-4f4f-a292-388dce05ae12.jsonl"},"model":{"provider":"deepseek","name":"deepseek-v4-flash","api":"openai-completions","fastMode":false,"thinkLevel":"off","reasoningLevel":"off"},"config":{"redacted":{"meta":{"lastTouchedVersion":"2026.5.22","lastTouchedAt":"2026-05-31T14:46:43.308Z"},"wizard":{"lastRunAt":"2026-05-25T11:11:10.893Z","lastRunVersion":"2026.5.22","lastRunCommand":"doctor","lastRunMode":"local"},"auth":{"profiles":{"ollama:default":{"provider":"ollama","mode":"api_key"}}},"models":{"mode":"merge","providers":{"ollama":{"baseUrl":"http://127.0.0.1:11434","api":"ollama","models":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"new-api":{"baseUrl":"http://192.168.2.74:3000/v1","api":"openai-completions","request":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"models":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"deepseek":{"baseUrl":"https://api.deepseek.com/v1","api":"openai-completions","models":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}},"agents":{"defaults":{"model":{"primary":"deepseek/deepseek-v4-flash"},"models":{"ollama/huihui_ai/glm-4.7-flash-abliterated:latest":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"ollama/deepseek-v4-flash:cloud":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"deepseek/deepseek-v4-pro":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"deepseek/deepseek-v4-flash":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"new-api/deepseek-v4-flash":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"new-api/qwen3.5-plus":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"new-api/qwen3.7-max":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"new-api/glm-5.1":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"workspace":"/home/yangxuan/.openclaw/workspace/travel","compaction":{"mode":"safeguard"},"timeoutSeconds":3600,"maxConcurrent":2,"subagents":{"maxConcurrent":4,"archiveAfterMinutes":60},"sandbox":{"mode":"off"},"name":"旅途助手","agentDir":"/home/yangxuan/.openclaw/agents/travel/agent","identity":{"name":"旅途助手","avatar":"./avatars/assistant.jpg"}},"list":[{"id":"main","name":"生活助手","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"bt","name":"下载助手","workspace":"/home/yangxuan/.openclaw/workspace/bt","agentDir":"/home/yangxuan/.openclaw/agents/bt/agent","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"storage","name":"仓库管理员","workspace":"/home/yangxuan/.openclaw/workspace/storage","agentDir":"/home/yangxuan/.openclaw/agents/storage/agent","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"java","name":"Java 后端","workspace":"/home/yangxuan/.openclaw/workspace/java","agentDir":"/home/yangxuan/.openclaw/agents/java/agent","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"front","name":"前端","workspace":"/home/yangxuan/.openclaw/workspace/front","agentDir":"/home/yangxuan/.openclaw/agents/front/agent","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"resume","name":"简历助手","workspace":"/home/yangxuan/.openclaw/workspace/resume","agentDir":"/home/yangxuan/.openclaw/agents/resume/agent","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"travel","name":"旅途助手","workspace":"/home/yangxuan/.openclaw/workspace/travel","agentDir":"/home/yangxuan/.openclaw/agents/travel/agent","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}]},"tools":{"profile":"coding","deny":["group:web","browser"],"web":{"search":{"enabled":true,"provider":"searxng","openaiCodex":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"fetch":{"enabled":true}}},"bindings":[{"agentId":"travel","match":{"channel":"openclaw-weixin","accountId":"4a0926e2cb5f-im-bot"}},{"agentId":"java","match":{"channel":"dingtalk-connector"}}],"messages":{"groupChat":{"visibleReplies":"message_tool"},"ackReactionScope":"group-mentions"},"commands":{"native":"auto","nativeSkills":"auto","restart":true,"ownerDisplay":"raw"},"session":{"dmScope":"per-channel-peer"},"channels":{"openclaw-weixin":{"enabled":true,"defaultAccount":"4a0926e2cb5f-im-bot"},"dingtalk-connector":{"enabled":true,"defaultAccount":"default","clientId":"dingnumf057etbbowhfu","dmPolicy":"open","groupPolicy":"open","requireMention":true,"separateSessionByConversation":true,"sharedMemoryAcrossConversations":false,"groupSessionScope":"group"}},"gateway":{"port":18789,"mode":"local","bind":"loopback","controlUi":{"allowedOrigins":["http://localhost:18789","http://127.0.0.1:18789","https://xuan-pc-nj-wsl.baiji-algieba.ts.net"],"allowInsecureAuth":true},"auth":{"mode":"token","allowTailscale":true},"trustedProxies":["127.0.0.1","100.115.195.0/24"],"tailscale":{"mode":"serve","resetOnExit":false},"http":{"endpoints":{"chatCompletions":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"nodes":{"denyCommands":[]}},"skills":{"entries":{"agent-browser":{"enabled":true},"Github":{"enabled":true},"notion":{"enabled":false},"openai-whisper":{"enabled":false},"openai-whisper-api":{"enabled":false},"oracle":{"enabled":false},"apple-notes":{"enabled":false},"apple-reminders":{"enabled":false},"bear-notes":{"enabled":false},"himalaya":{"enabled":false},"xurl":{"enabled":false},"blogwatcher":{"enabled":false},"blucli":{"enabled":false},"bluebubbles":{"enabled":false},"camsnap":{"enabled":false},"coding-agent":{"enabled":false},"discord":{"enabled":false},"eightctl":{"enabled":false},"gemini":{"enabled":false},"gifgrep":{"enabled":false},"gog":{"enabled":false},"goplaces":{"enabled":false},"imsg":{"enabled":false},"model-usage":{"enabled":false},"nano-pdf":{"enabled":false},"obsidian":{"enabled":false},"openhue":{"enabled":false},"ordercli":{"enabled":false},"peekaboo":{"enabled":false},"sag":{"enabled":false},"searxng-web-search":{"enabled":false},"session-logs":{"enabled":false},"sherpa-onnx-tts":{"enabled":false},"slack":{"enabled":false},"songsee":{"enabled":false},"sonoscli":{"enabled":false},"spotify-player":{"enabled":false},"summarize":{"enabled":false},"things-mac":{"enabled":false},"trello":{"enabled":false},"voice-call":{"enabled":false},"wacli":{"enabled":false}}},"plugins":{"allow":["deepseek","memory-core","ollama","openclaw-weixin","searxng","dingtalk-connector"],"entries":{"ollama":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"deepseek":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"searxng":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"openclaw-weixin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"browser":{"enabled":false},"dingtalk-connector":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"memory-core":{"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"bundledDiscovery":"compat"}},"runtime":{"timeoutMs":3600000,"trigger":"cron","disableTools":false,"toolResultFormat":"plain"}},"plugins":{"source":"active-registry","importedRuntimePluginIds":["anthropic","arcee","byteplus","cerebras","chutes","cloudflare-ai-gateway","comfy","copilot-proxy","deepinfra","deepseek","dingtalk-connector","fal","fireworks","github-copilot","google","groq","huggingface","kilocode","kimi","litellm","lmstudio","memory-core","microsoft-foundry","minimax","mistral","moonshot","nvidia","ollama","openai","openclaw-weixin","opencode","opencode-go","openrouter","qianfan","qwen","searxng","sglang","stepfun","synthetic","tencent","together","venice","vercel-ai-gateway","vllm","volcengine","vydra","xai","xiaomi","zai"],"entries":[{"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":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/active-memory/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/active-memory"},{"id":"admin-http-rpc","name":"@openclaw/admin-http-rpc","version":"2026.5.22","description":"OpenClaw admin HTTP RPC endpoint","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/admin-http-rpc/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/admin-http-rpc"},{"id":"alibaba","name":"@openclaw/alibaba-provider","version":"2026.5.22","description":"OpenClaw Alibaba Model Studio video provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/alibaba/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/alibaba","videoGenerationProviderIds":["alibaba"]},{"id":"anthropic","name":"@openclaw/anthropic-provider","version":"2026.5.22","description":"OpenClaw Anthropic provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/anthropic/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/anthropic","providerIds":["anthropic"],"mediaUnderstandingProviderIds":["anthropic"]},{"id":"arcee","name":"@openclaw/arcee-provider","version":"2026.5.22","description":"OpenClaw Arcee provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/arcee/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/arcee","providerIds":["arcee"]},{"id":"azure-speech","name":"Azure Speech","version":"2026.5.22","description":"Azure AI Speech text-to-speech (MP3, native Ogg/Opus voice notes, PCM telephony).","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/azure-speech/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/azure-speech","speechProviderIds":["azure","azure-speech"]},{"id":"bonjour","name":"Bonjour Gateway Discovery","version":"2026.5.22","description":"Advertise the local OpenClaw gateway over Bonjour/mDNS.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/bonjour/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/bonjour"},{"id":"browser","name":"@openclaw/browser-plugin","version":"2026.5.22","description":"OpenClaw browser tool plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"disabled in config","status":"disabled","error":"disabled in config","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/browser/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/browser"},{"id":"byteplus","name":"@openclaw/byteplus-provider","version":"2026.5.22","description":"OpenClaw BytePlus provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/byteplus/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/byteplus","providerIds":["byteplus","byteplus-plan"],"videoGenerationProviderIds":["byteplus"]},{"id":"canvas","name":"Canvas","version":"2026.5.22","description":"Experimental Canvas control and A2UI rendering surfaces for paired nodes.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/canvas/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/canvas"},{"id":"cerebras","name":"@openclaw/cerebras-provider","version":"2026.5.22","description":"OpenClaw Cerebras provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/cerebras/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/cerebras","providerIds":["cerebras"]},{"id":"chutes","name":"@openclaw/chutes-provider","version":"2026.5.22","description":"OpenClaw Chutes.ai provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/chutes/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/chutes","providerIds":["chutes"]},{"id":"clickclack","name":"@openclaw/clickclack","version":"2026.5.22","description":"OpenClaw ClickClack channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/clickclack/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/clickclack","channelIds":["clickclack"]},{"id":"cloudflare-ai-gateway","name":"@openclaw/cloudflare-ai-gateway-provider","version":"2026.5.22","description":"OpenClaw Cloudflare AI Gateway provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/cloudflare-ai-gateway/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/cloudflare-ai-gateway","providerIds":["cloudflare-ai-gateway"]},{"id":"comfy","name":"@openclaw/comfy-provider","version":"2026.5.22","description":"OpenClaw ComfyUI provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/comfy/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/comfy","providerIds":["comfy"],"imageGenerationProviderIds":["comfy"],"videoGenerationProviderIds":["comfy"],"musicGenerationProviderIds":["comfy"]},{"id":"copilot-proxy","name":"@openclaw/copilot-proxy","version":"2026.5.22","description":"OpenClaw Copilot Proxy provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/copilot-proxy/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/copilot-proxy","providerIds":["copilot-proxy"]},{"id":"deepgram","name":"@openclaw/deepgram-provider","version":"2026.5.22","description":"OpenClaw Deepgram media-understanding provider","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/deepgram/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/deepgram","realtimeTranscriptionProviderIds":["deepgram"],"mediaUnderstandingProviderIds":["deepgram"]},{"id":"deepinfra","name":"@openclaw/deepinfra-provider","version":"2026.5.22","description":"OpenClaw DeepInfra provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/deepinfra/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/deepinfra","providerIds":["deepinfra"],"speechProviderIds":["deepinfra"],"mediaUnderstandingProviderIds":["deepinfra"],"imageGenerationProviderIds":["deepinfra"],"videoGenerationProviderIds":["deepinfra"],"memoryEmbeddingProviderIds":["deepinfra"]},{"id":"deepseek","name":"DeepSeek Provider","version":"2026.5.22","description":"Bundled DeepSeek provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/deepseek/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/deepseek","providerIds":["deepseek"]},{"id":"device-pair","name":"Device Pairing","description":"Generate setup codes and approve device pairing requests.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/device-pair/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/device-pair"},{"id":"dingtalk-connector","name":"DingTalk Channel","version":"0.8.22","description":"Official OpenClaw DingTalk channel plugin | 钉钉官方 OpenClaw 插件","origin":"global","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/home/yangxuan/.openclaw/npm/node_modules/@dingtalk-real-ai/dingtalk-connector/dist/index.mjs","rootDir":"/home/yangxuan/.openclaw/npm/node_modules/@dingtalk-real-ai/dingtalk-connector","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","channelIds":["dingtalk-connector"]},{"id":"document-extract","name":"Document Extraction","version":"2026.5.22","description":"Extract text and fallback page images from local document attachments.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/document-extract/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/document-extract"},{"id":"duckduckgo","name":"@openclaw/duckduckgo-plugin","version":"2026.5.22","description":"OpenClaw DuckDuckGo plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/duckduckgo/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/duckduckgo","webSearchProviderIds":["duckduckgo"]},{"id":"elevenlabs","name":"@openclaw/elevenlabs-speech","version":"2026.5.22","description":"OpenClaw ElevenLabs speech plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/elevenlabs/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/elevenlabs","speechProviderIds":["elevenlabs"],"realtimeTranscriptionProviderIds":["elevenlabs"],"mediaUnderstandingProviderIds":["elevenlabs"]},{"id":"exa","name":"@openclaw/exa-plugin","version":"2026.5.22","description":"OpenClaw Exa plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/exa/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/exa","webSearchProviderIds":["exa"]},{"id":"fal","name":"@openclaw/fal-provider","version":"2026.5.22","description":"OpenClaw fal provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/fal/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/fal","providerIds":["fal"],"imageGenerationProviderIds":["fal"],"videoGenerationProviderIds":["fal"],"musicGenerationProviderIds":["fal"]},{"id":"file-transfer","name":"File Transfer","version":"2026.5.22","description":"Fetch, list, and write files on paired nodes via dedicated node commands. Bypasses bash stdout truncation by using base64 over node.invoke for binaries up to 16 MB.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/file-transfer/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/file-transfer"},{"id":"firecrawl","name":"@openclaw/firecrawl-plugin","version":"2026.5.22","description":"OpenClaw Firecrawl plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/firecrawl/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/firecrawl","webFetchProviderIds":["firecrawl"],"webSearchProviderIds":["firecrawl"]},{"id":"fireworks","name":"@openclaw/fireworks-provider","version":"2026.5.22","description":"OpenClaw Fireworks provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/fireworks/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/fireworks","providerIds":["fireworks"]},{"id":"github-copilot","name":"@openclaw/github-copilot-provider","version":"2026.5.22","description":"OpenClaw GitHub Copilot provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/github-copilot/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/github-copilot","providerIds":["github-copilot"],"memoryEmbeddingProviderIds":["github-copilot"]},{"id":"google","name":"@openclaw/google-plugin","version":"2026.5.22","description":"OpenClaw Google plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/google/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/google","providerIds":["google","google-gemini-cli","google-vertex"],"speechProviderIds":["google"],"realtimeVoiceProviderIds":["google"],"mediaUnderstandingProviderIds":["google"],"imageGenerationProviderIds":["google"],"videoGenerationProviderIds":["google"],"musicGenerationProviderIds":["google"],"webSearchProviderIds":["gemini"],"memoryEmbeddingProviderIds":["gemini"]},{"id":"gradium","name":"@openclaw/gradium-speech","version":"2026.5.22","description":"OpenClaw Gradium speech plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/gradium/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/gradium","speechProviderIds":["gradium"]},{"id":"groq","name":"@openclaw/groq-provider","version":"2026.5.22","description":"OpenClaw Groq media-understanding provider","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/groq/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/groq","providerIds":["groq"],"mediaUnderstandingProviderIds":["groq"]},{"id":"huggingface","name":"@openclaw/huggingface-provider","version":"2026.5.22","description":"OpenClaw Hugging Face provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/huggingface/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/huggingface","providerIds":["huggingface"]},{"id":"imessage","name":"@openclaw/imessage","version":"2026.5.22","description":"OpenClaw iMessage channel plugin using imsg on a signed-in Mac","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/imessage/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/imessage","channelIds":["imessage"]},{"id":"inworld","name":"Inworld","version":"2026.5.22","description":"Inworld streaming text-to-speech (MP3, OGG_OPUS, PCM telephony).","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/inworld/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/inworld","speechProviderIds":["inworld"]},{"id":"irc","name":"@openclaw/irc","version":"2026.5.22","description":"OpenClaw IRC channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/irc/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/irc","channelIds":["irc"]},{"id":"kilocode","name":"@openclaw/kilocode-provider","version":"2026.5.22","description":"OpenClaw Kilo Gateway provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/kilocode/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/kilocode","providerIds":["kilocode"]},{"id":"kimi","name":"@openclaw/kimi-provider","version":"2026.5.22","description":"OpenClaw Kimi provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/kimi-coding/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/kimi-coding","providerIds":["kimi","kimi-coding"]},{"id":"litellm","name":"@openclaw/litellm-provider","version":"2026.5.22","description":"OpenClaw LiteLLM provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/litellm/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/litellm","providerIds":["litellm"],"imageGenerationProviderIds":["litellm"]},{"id":"llm-task","name":"LLM Task","version":"2026.5.21","description":"Generic JSON-only LLM tool for structured tasks callable from workflows.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/llm-task/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/llm-task"},{"id":"lmstudio","name":"@openclaw/lmstudio-provider","version":"2026.5.22","description":"OpenClaw LM Studio provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/lmstudio/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/lmstudio","providerIds":["lmstudio"],"memoryEmbeddingProviderIds":["lmstudio"]},{"id":"mattermost","name":"@openclaw/mattermost","version":"2026.5.22","description":"OpenClaw Mattermost channel plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/mattermost/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/mattermost","channelIds":["mattermost"]},{"id":"memory-core","name":"Memory (Core)","version":"2026.5.22","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":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/memory-core/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/memory-core","toolNames":["memory_get","memory_search"],"memoryEmbeddingProviderIds":["local"]},{"id":"memory-wiki","name":"Memory Wiki","version":"2026.5.22","description":"Persistent wiki compiler and Obsidian-friendly knowledge vault for OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/memory-wiki/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/memory-wiki"},{"id":"microsoft","name":"@openclaw/microsoft-speech","version":"2026.5.22","description":"OpenClaw Microsoft speech plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/microsoft/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/microsoft","speechProviderIds":["microsoft"]},{"id":"microsoft-foundry","name":"@openclaw/microsoft-foundry","version":"2026.5.22","description":"OpenClaw Microsoft Foundry provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/microsoft-foundry/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/microsoft-foundry","providerIds":["microsoft-foundry"]},{"id":"migrate-claude","name":"Claude Migration","version":"2026.5.22","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":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/migrate-claude/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/migrate-claude"},{"id":"migrate-hermes","name":"Hermes Migration","version":"2026.5.22","description":"Imports Hermes configuration, memories, skills, and supported credentials into OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/migrate-hermes/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/migrate-hermes"},{"id":"minimax","name":"@openclaw/minimax-provider","version":"2026.5.22","description":"OpenClaw MiniMax provider and OAuth plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/minimax/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/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":"@openclaw/mistral-provider","version":"2026.5.22","description":"OpenClaw Mistral provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/mistral/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/mistral","providerIds":["mistral"],"realtimeTranscriptionProviderIds":["mistral"],"mediaUnderstandingProviderIds":["mistral"],"memoryEmbeddingProviderIds":["mistral"]},{"id":"moonshot","name":"@openclaw/moonshot-provider","version":"2026.5.22","description":"OpenClaw Moonshot provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/moonshot/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/moonshot","providerIds":["moonshot"],"mediaUnderstandingProviderIds":["moonshot"],"webSearchProviderIds":["kimi"]},{"id":"nvidia","name":"@openclaw/nvidia-provider","version":"2026.5.22","description":"OpenClaw NVIDIA provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/nvidia/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/nvidia","providerIds":["nvidia"]},{"id":"oc-path","name":"OC Path","version":"2026.5.22","description":"Adds the openclaw path CLI for oc:// workspace file addressing.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/oc-path/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/oc-path"},{"id":"ollama","name":"Ollama Provider","version":"2026.5.22","description":"Bundled Ollama provider plugin","origin":"bundled","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/ollama/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/ollama","providerIds":["ollama"],"mediaUnderstandingProviderIds":["ollama"],"webSearchProviderIds":["ollama"],"memoryEmbeddingProviderIds":["ollama"]},{"id":"open-prose","name":"OpenProse","version":"2026.5.22","description":"OpenProse VM skill pack with a /prose slash command.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/open-prose/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/open-prose"},{"id":"openai","name":"@openclaw/openai-provider","version":"2026.5.22","description":"OpenClaw OpenAI provider plugins","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/openai/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/openai","providerIds":["openai","openai-codex"],"speechProviderIds":["openai"],"realtimeTranscriptionProviderIds":["openai"],"realtimeVoiceProviderIds":["openai"],"mediaUnderstandingProviderIds":["openai","openai-codex"],"imageGenerationProviderIds":["openai"],"videoGenerationProviderIds":["openai"],"memoryEmbeddingProviderIds":["openai"]},{"id":"openclaw-weixin","name":"Weixin","version":"2.4.3","description":"Weixin channel (getUpdates long-poll + sendMessage)","origin":"global","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/home/yangxuan/.openclaw/npm/node_modules/@tencent-weixin/openclaw-weixin/dist/index.js","rootDir":"/home/yangxuan/.openclaw/npm/node_modules/@tencent-weixin/openclaw-weixin","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","channelIds":["openclaw-weixin"]},{"id":"opencode","name":"@openclaw/opencode-provider","version":"2026.5.22","description":"OpenClaw OpenCode Zen provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/opencode/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/opencode","providerIds":["opencode"],"mediaUnderstandingProviderIds":["opencode"]},{"id":"opencode-go","name":"@openclaw/opencode-go-provider","version":"2026.5.22","description":"OpenClaw OpenCode Go provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/opencode-go/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/opencode-go","providerIds":["opencode-go"],"mediaUnderstandingProviderIds":["opencode-go"]},{"id":"openrouter","name":"@openclaw/openrouter-provider","version":"2026.5.22","description":"OpenClaw OpenRouter provider plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/openrouter/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/openrouter","providerIds":["openrouter"],"speechProviderIds":["openrouter"],"mediaUnderstandingProviderIds":["openrouter"],"imageGenerationProviderIds":["openrouter"],"videoGenerationProviderIds":["openrouter"],"musicGenerationProviderIds":["openrouter"]},{"id":"perplexity","name":"@openclaw/perplexity-plugin","version":"2026.5.22","description":"OpenClaw Perplexity plugin","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/perplexity/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/perplexity","webSearchProviderIds":["perplexity"]},{"id":"phone-control","name":"Phone Control","description":"Arm/disarm high-risk phone node commands (camera/screen/writes) with an optional auto-expiry.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/phone-control/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/phone-control"},{"id":"policy","name":"Policy","version":"2026.5.22","description":"Adds policy-backed doctor checks for workspace conformance.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"not in allowlist","status":"disabled","error":"not in allowlist","format":"openclaw","source":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/policy/index.js","rootDir":"/home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/extensions/policy"},{"truncated":true,"reason":"trajectory-array-size-limit","originalLength":93,"limitItems":64}]},"skills":{"snapshotVersion":0,"entries":[{"id":"canvas","name":"canvas","description":"Present HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/canvas/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/canvas","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/canvas","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/canvas/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"clawhub","name":"clawhub","description":"Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/clawhub/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/clawhub","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/clawhub","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/clawhub/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"diagram-maker","name":"diagram-maker","description":"Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/diagram-maker","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/diagram-maker","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"dws","name":"dws","description":"管理钉钉产品能力(AI表格/日历/通讯录/群聊与机器人/待办/审批/考勤/日志/DING消息/开放平台文档/钉钉文档/钉钉云盘/AI听记/邮箱/在线电子表格/知识库等)。当用户需要操作表格数据、管理日程会议、查询通讯录、管理群聊、机器人发消息、创建待办、提交审批、查看考勤、提交日报周报(钉钉日志模版)、读写钉钉文档、上传下载云盘文件、查询听记纪要、收发邮件、读写在线电子表格(axls)、管理钉钉知识库时使用。","filePath":"~/.agents/skills/dws/SKILL.md","baseDir":"~/.agents/skills/dws","source":"agents-skills-personal","sourceInfo":{"baseDir":"~/.agents/skills/dws","origin":"top-level","path":"~/.agents/skills/dws/SKILL.md","scope":"project","source":"agents-skills-personal"},"disableModelInvocation":false,"available":true},{"id":"gh-issues","name":"gh-issues","description":"Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/gh-issues/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/gh-issues","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/gh-issues","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/gh-issues/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"github","name":"github","description":"GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/github/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/github","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/github","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/github/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"healthcheck","name":"healthcheck","description":"Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/healthcheck","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/healthcheck","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"mcporter","name":"mcporter","description":"List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/mcporter/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/mcporter","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/mcporter","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/mcporter/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"meme-maker","name":"meme-maker","description":"Search meme templates, suggest formats, and generate local or hosted image memes.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/meme-maker/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/meme-maker","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/meme-maker","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/meme-maker/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":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-connect/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-connect","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-connect","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-connect/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"node-inspect-debugger","name":"node-inspect-debugger","description":"Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-inspect-debugger","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-inspect-debugger","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"python-debugpy","name":"python-debugpy","description":"Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/python-debugpy","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/python-debugpy","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"skill-creator","name":"skill-creator","description":"Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/skill-creator","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/skill-creator","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"spike","name":"spike","description":"Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/spike/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/spike","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/spike","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/spike/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":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/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":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow-inbox-triage","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow-inbox-triage","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"tmux","name":"tmux","description":"Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/tmux/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/tmux","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/tmux","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/tmux/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"video-frames","name":"video-frames","description":"Extract frames or short clips from videos using ffmpeg.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/video-frames/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/video-frames","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/video-frames","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/video-frames/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"weather","name":"weather","description":"Current weather and forecasts with wttr.in via curl for locations, rain, temperature, travel planning.","filePath":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/weather/SKILL.md","baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/weather","source":"openclaw-bundled","sourceInfo":{"baseDir":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/weather","origin":"top-level","path":"~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/weather/SKILL.md","scope":"project","source":"openclaw-bundled"},"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>canvas</name>\n <description>Present HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/canvas/SKILL.md</location>\n </skill>\n <skill>\n <name>clawhub</name>\n <description>Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/clawhub/SKILL.md</location>\n </skill>\n <skill>\n <name>diagram-maker</name>\n <description>Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md</location>\n </skill>\n <skill>\n <name>dws</name>\n <description>管理钉钉产品能力(AI表格/日历/通讯录/群聊与机器人/待办/审批/考勤/日志/DING消息/开放平台文档/钉钉文档/钉钉云盘/AI听记/邮箱/在线电子表格/知识库等)。当用户需要操作表格数据、管理日程会议、查询通讯录、管理群聊、机器人发消息、创建待办、提交审批、查看考勤、提交日报周报(钉钉日志模版)、读写钉钉文档、上传下载云盘文件、查询听记纪要、收发邮件、读写在线电子表格(axls)、管理钉钉知识库时使用。</description>\n <location>~/.agents/skills/dws/SKILL.md</location>\n </skill>\n <skill>\n <name>gh-issues</name>\n <description>Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/gh-issues/SKILL.md</location>\n </skill>\n <skill>\n <name>github</name>\n <description>GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/github/SKILL.md</location>\n </skill>\n <skill>\n <name>healthcheck</name>\n <description>Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/healthcheck/SKILL.md</location>\n </skill>\n <skill>\n <name>mcporter</name>\n <description>List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/mcporter/SKILL.md</location>\n </skill>\n <skill>\n <name>meme-maker</name>\n <description>Search meme templates, suggest formats, and generate local or hosted image memes.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/meme-maker/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>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-connect/SKILL.md</location>\n </skill>\n <skill>\n <name>node-inspect-debugger</name>\n <description>Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md</location>\n </skill>\n <skill>\n <name>python-debugpy</name>\n <description>Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md</location>\n </skill>\n <skill>\n <name>skill-creator</name>\n <description>Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/skill-creator/SKILL.md</location>\n </skill>\n <skill>\n <name>spike</name>\n <description>Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/spike/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>~/.nvm/versions/node/v25.2.0/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>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md</location>\n </skill>\n <skill>\n <name>tmux</name>\n <description>Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/tmux/SKILL.md</location>\n </skill>\n <skill>\n <name>video-frames</name>\n <description>Extract frames or short clips from videos using ffmpeg.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/video-frames/SKILL.md</location>\n </skill>\n <skill>\n <name>weather</name>\n <description>Current weather and forecasts with wttr.in via curl for locations, rain, temperature, travel planning.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/weather/SKILL.md</location>\n </skill>\n</available_skills>","systemPromptReport":{"source":"run","generatedAt":1780275305663,"sessionId":"51a9cb19-9381-4f4f-a292-388dce05ae12","sessionKey":"agent:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","provider":"deepseek","model":"deepseek-v4-flash","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","bootstrapMaxChars":12000,"bootstrapTotalMaxChars":60000,"bootstrapTruncation":{"warningMode":"always","warningShown":false,"truncatedFiles":0,"nearLimitFiles":0,"totalNearLimit":false},"sandbox":{"mode":"off","sandboxed":false},"systemPrompt":{"chars":21421,"projectContextChars":11183,"nonProjectContextChars":10238},"injectedWorkspaceFiles":[{"name":"AGENTS.md","path":"/home/yangxuan/.openclaw/workspace/travel/AGENTS.md","missing":false,"rawChars":7877,"injectedChars":7877,"truncated":false},{"name":"SOUL.md","path":"/home/yangxuan/.openclaw/workspace/travel/SOUL.md","missing":false,"rawChars":768,"injectedChars":768,"truncated":false},{"name":"TOOLS.md","path":"/home/yangxuan/.openclaw/workspace/travel/TOOLS.md","missing":false,"rawChars":475,"injectedChars":475,"truncated":false},{"name":"IDENTITY.md","path":"/home/yangxuan/.openclaw/workspace/travel/IDENTITY.md","missing":false,"rawChars":787,"injectedChars":787,"truncated":false},{"name":"USER.md","path":"/home/yangxuan/.openclaw/workspace/travel/USER.md","missing":false,"rawChars":280,"injectedChars":280,"truncated":false}],"skills":{"promptChars":5820,"entries":[{"name":"canvas","blockChars":278},{"name":"clawhub","blockChars":268},{"name":"diagram-maker","blockChars":281},{"name":"dws","blockChars":332},{"name":"gh-issues","blockChars":304},{"name":"github","blockChars":275},{"name":"healthcheck","blockChars":293},{"name":"mcporter","blockChars":281},{"name":"meme-maker","blockChars":266},{"name":"node-connect","blockChars":296},{"name":"node-inspect-debugger","blockChars":292},{"name":"python-debugpy","blockChars":280},{"name":"skill-creator","blockChars":274},{"name":"spike","blockChars":266},{"name":"taskflow","blockChars":296},{"name":"taskflow-inbox-triage","blockChars":306},{"name":"tmux","blockChars":284},{"name":"video-frames","blockChars":244},{"name":"weather","blockChars":281}]},"tools":{"listChars":0,"schemaChars":16174,"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":539,"schemaChars":1187,"propertiesCount":12},{"name":"process","summaryChars":456,"schemaChars":1074,"propertiesCount":12},{"name":"cron","summaryChars":3610,"schemaChars":7131,"propertiesCount":14},{"name":"message","summaryChars":276,"schemaChars":2031,"propertiesCount":30},{"name":"update_plan","summaryChars":163,"schemaChars":489,"propertiesCount":2},{"name":"sessions_list","summaryChars":135,"schemaChars":432,"propertiesCount":9},{"name":"sessions_history","summaryChars":117,"schemaChars":161,"propertiesCount":3},{"name":"sessions_send","summaryChars":224,"schemaChars":274,"propertiesCount":5},{"name":"sessions_spawn","summaryChars":332,"schemaChars":1240,"propertiesCount":17},{"name":"sessions_yield","summaryChars":79,"schemaChars":60,"propertiesCount":1},{"name":"subagents","summaryChars":129,"schemaChars":191,"propertiesCount":4},{"name":"session_status","summaryChars":278,"schemaChars":89,"propertiesCount":2},{"name":"memory_search","summaryChars":605,"schemaChars":237,"propertiesCount":4},{"name":"memory_get","summaryChars":239,"schemaChars":215,"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:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","agentId":"travel","messageChannel":"openclaw-weixin"}}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51a9cb19-9381-4f4f-a292-388dce05ae12","source":"runtime","type":"context.compiled","ts":"2026-06-01T00:55:05.743Z","seq":3,"sourceSeq":3,"sessionId":"51a9cb19-9381-4f4f-a292-388dce05ae12","sessionKey":"agent:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","runId":"51a9cb19-9381-4f4f-a292-388dce05ae12","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"systemPrompt":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call 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- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\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- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\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- update_plan\nTOOLS.md is usage guidance, not availability.\nFor long waits, avoid rapid poll loops: use exec with enough yieldMs or process(action=poll, timeout=<ms>).\nLarger work: use `sessions_spawn`; completion is push-based.\n`sessions_spawn`: omit `context` unless transcript needed; then set `context:\"fork\"`.\nDo not poll `subagents list` / `sessions_list` in a loop; use `sessions_yield` when waiting for spawned sub-agent completion events, and check status only on-demand (for intervention, debugging, or when explicitly asked).\n## Tool Call Style\nRoutine low-risk calls: no narration.\nNarrate only for complex, sensitive/destructive, or explicitly requested steps.\nFirst-class tool exists: use it; do not ask user to run equivalent CLI/slash command.\nIf exec returns approval-pending, send the exact /approve command from \"Reply with:\"; do not ask for another 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, but keep command/script previews separate from the /approve command and never substitute the shell command/script for the approval id or slug.\n## Safety\nNo independent goals: no self-preservation, replication, resource acquisition, power-seeking, or long-term plans beyond the user's request.\nSafety/oversight over completion. Conflicts: pause/ask. Obey stop/pause/audit; never bypass safeguards.\nDo not persuade anyone to expand access or disable safeguards. Do not copy yourself or change prompts/safety/tool policy unless explicitly requested.\n## OpenClaw Control\nDo not invent commands.\nConfig/restart: prefer `gateway` tool (`config.schema.lookup|get|patch|apply`, `restart`).\nCLI lifecycle only on explicit user request: `openclaw gateway status|restart|start|stop`.\n`restart`, not stop+start.\n## Skills\nScan <available_skills>. If one clearly applies, read its SKILL.md at exact <location> with `read`, then follow it.\nIf several apply, choose the most specific. If none clearly apply, read none.\nOne skill up front max. Never guess/fabricate skill paths.\nExternal API writes: batch when safe, avoid tight loops, 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>canvas</name>\n <description>Present HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/canvas/SKILL.md</location>\n </skill>\n <skill>\n <name>clawhub</name>\n <description>Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/clawhub/SKILL.md</location>\n </skill>\n <skill>\n <name>diagram-maker</name>\n <description>Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md</location>\n </skill>\n <skill>\n <name>dws</name>\n <description>管理钉钉产品能力(AI表格/日历/通讯录/群聊与机器人/待办/审批/考勤/日志/DING消息/开放平台文档/钉钉文档/钉钉云盘/AI听记/邮箱/在线电子表格/知识库等)。当用户需要操作表格数据、管理日程会议、查询通讯录、管理群聊、机器人发消息、创建待办、提交审批、查看考勤、提交日报周报(钉钉日志模版)、读写钉钉文档、上传下载云盘文件、查询听记纪要、收发邮件、读写在线电子表格(axls)、管理钉钉知识库时使用。</description>\n <location>~/.agents/skills/dws/SKILL.md</location>\n </skill>\n <skill>\n <name>gh-issues</name>\n <description>Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/gh-issues/SKILL.md</location>\n </skill>\n <skill>\n <name>github</name>\n <description>GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/github/SKILL.md</location>\n </skill>\n <skill>\n <name>healthcheck</name>\n <description>Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/healthcheck/SKILL.md</location>\n </skill>\n <skill>\n <name>mcporter</name>\n <description>List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/mcporter/SKILL.md</location>\n </skill>\n <skill>\n <name>meme-maker</name>\n <description>Search meme templates, suggest formats, and generate local or hosted image memes.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/meme-maker/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>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-connect/SKILL.md</location>\n </skill>\n <skill>\n <name>node-inspect-debugger</name>\n <description>Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md</location>\n </skill>\n <skill>\n <name>python-debugpy</name>\n <description>Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md</location>\n </skill>\n <skill>\n <name>skill-creator</name>\n <description>Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/skill-creator/SKILL.md</location>\n </skill>\n <skill>\n <name>spike</name>\n <description>Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/spike/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>~/.nvm/versions/node/v25.2.0/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>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md</location>\n </skill>\n <skill>\n <name>tmux</name>\n <description>Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/tmux/SKILL.md</location>\n </skill>\n <skill>\n <name>video-frames</name>\n <description>Extract frames or short clips from videos using ffmpeg.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/video-frames/SKILL.md</location>\n </skill>\n <skill>\n <name>weather</name>\n <description>Current weather and forecasts with wttr.in via curl for locations, rain, temperature, travel planning.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/weather/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: /home/yangxuan/.openclaw/workspace/travel\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:\nSOUL.md: persona/tone. Follow it unless higher-priority instructions override.\n## /home/yangxuan/.openclaw/workspace/travel/AGENTS.md\n# AGENTS.md - Your Workspace\n\nThis folder is home. Treat it that way.\n\n## First Run\n\nIf `BOOTSTRAP.md` exists, that's your birth certificate. Follow it, figure out who you are, then delete it. You won't need it again.\n\n## Session Startup\n\nUse runtime-provided startup context first.\n\nThat context may already include:\n\n- `AGENTS.md`, `SOUL.md`, and `USER.md`\n- recent daily memory such as `memory/YYYY-MM-DD.md`\n- `MEMORY.md` when this is the main session\n\nDo not manually reread startup files unless:\n\n1. The user explicitly asks\n2. The provided context is missing something you need\n3. You need a deeper follow-up read beyond the provided startup context\n\n## Memory\n\nYou wake up fresh each session. These files are your continuity:\n\n- **Daily notes:** `memory/YYYY-MM-DD.md` (create `memory/` if needed) — raw logs of what happened\n- **Long-term:** `MEMORY.md` — your curated memories, like a human's long-term memory\n\nCapture what matters. Decisions, context, things to remember. Skip the secrets unless asked to keep them.\n\n### 🧠 MEMORY.md - Your Long-Term Memory\n\n- **ONLY load in main session** (direct chats with your human)\n- **DO NOT load in shared contexts** (Discord, group chats, sessions with other people)\n- This is for **security** — contains personal context that shouldn't leak to strangers\n- You can **read, edit, and update** MEMORY.md freely in main sessions\n- Write significant events, thoughts, decisions, opinions, lessons learned\n- This is your curated memory — the distilled essence, not raw logs\n- Over time, review your daily files and update MEMORY.md with what's worth keeping\n\n### 📝 Write It Down - No \"Mental Notes\"!\n\n- **Memory is limited** — if you want to remember something, WRITE IT TO A FILE\n- \"Mental notes\" don't survive session restarts. Files do.\n- Before writing memory files, read them first; write only concrete updates, never empty placeholders.\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 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\n## Related\n\n- [Default AGENTS.md](/reference/AGENTS.default)\n## /home/yangxuan/.openclaw/workspace/travel/SOUL.md\n---\nsummary: \"SOUL.md —— 旅行规划助手的身份定位和行为准则\"\nread_when: 初始化工作区时\n---\n\n# SOUL.md —— 你的身份定位\n\n你是一名**专业的旅行规划助手**,精通国内外的旅行规划、行程设计、预算管理和目的地推荐。\n\n## 核心准则\n\n- **一切用中文交流**,技术术语酌情保留英文\n- 提供**实用、清晰、可执行**的旅行建议\n- 始终考虑成本、时间、体验的平衡\n- 尊重用户的预算和偏好,不做强推\n\n## 能力范围\n\n1. **行程规划**:根据天数、预算、兴趣定制完整行程\n2. **目的地推荐**:季节推荐、小众景点、城市导览\n3. **交通方案**:航班、高铁、自驾路线、市内交通\n4. **住宿建议**:酒店、民宿、青旅,匹配不同预算\n5. **美食推荐**:当地特色、餐厅、小吃街\n6. **预算估算**:交通+住宿+餐饮+门票+杂费\n7. **签证/证件**:所需材料、办理流程、注意事项\n8. **天气/季节**:最佳旅行时间、穿衣建议\n9. **安全提示**:当地注意事项、紧急联系方式\n10. **旅行工具**:推荐的 App、网站、小程序\n\n## 输出风格\n\n- 行程建议用**表格或清单**呈现,一目了然\n- 重要提醒用 **⚠️** 标注\n- 推荐用 **👍** 标注\n- 省钱技巧用 **💡** 标注\n- 提供多个方案并对比优缺点\n\n## 信息源\n\n- 优先使用网络搜索获取最新信息\n- 引用来源时说明(如「据携程/马蜂窝/小红书」)\n- 明确标注信息时效性\n\n## 安全红线\n\n- 不泄露用户隐私(行程、身份证号、护照等)\n- 费用敏感信息仅在用户主动要求时给出估算\n- 不代订机票/酒店,只提供方案和建议\n- 不确定时诚实说明,并主动去搜索核实\n## /home/yangxuan/.openclaw/workspace/travel/IDENTITY.md\n# IDENTITY.md —— 我是谁?\n\n- **名称:**\n 旅途助手 ✈️\n- **物种:**\n 本地 AI 旅行规划 Agent\n- **核心能力:**\n 行程规划 · 目的地推荐 · 预算计算 · 交通方案 · 住宿推荐 · 美食指南 · 签证咨询 · 季节性旅行建议\n- **气质:**\n 专业可靠 · 细致周到 · 热情不烦人 · 尊重预算 · 注重实用\n- **表情符号:**\n ✈️🌍🗺️🏖️🍜🎒\n- **模型:**\n - 🎯 **主引擎**deepseek-v4-flash(快速响应)\n - 🧠 **备用**Qwen 3.5 Plus(深度分析)\n- **工作区:**\n `/home/yangxuan/.openclaw/workspace/travel`\n- **拥有者:**\n 杨轩\n\n---\n\n## 我能帮你什么?\n\n| 场景 | 我提供的价值 |\n|------|-------------|\n| **想出去玩但没想法** | 根据季节/天数/预算推荐目的地 |\n| **已有目的地** | 定制详细行程,含交通、住宿、美食、景点 |\n| **预算有限** | 给出性价比最高的方案和省钱技巧 |\n| **带娃/带老人** | 推荐轻松舒适的行程和注意事项 |\n| **境外旅行** | 签证、货币、语言、文化差异一站式解答 |\n| **出差顺便玩** | 在商务行程中穿插高效的旅行体验 |\n| **周末短途** | 2-3天周边游推荐 |\n\n## 我的承诺\n\n1. **所有交流使用中文**\n2. **实时搜索最新信息**,提供有据可查的建议\n3. **尊重你的预算和偏好**,不会乱推荐贵的方案\n4. **提供多个可选方案**,让你自己做选择\n5. **诚实**——不确定的地方会明说,然后去查清楚\n## /home/yangxuan/.openclaw/workspace/travel/USER.md\n# USER.md —— 关于你服务的用户\n\n*旅行 Agent 的用户信息,随着交流不断更新。*\n\n- **称谓:**\n杨轩\n- **时区:**\n亚洲/上海 (UTC+8)\n\n## 默认偏好(可在交流中逐步调整)\n\n### 旅行风格\n- □ 自由行 / □ 跟团游 / □ 半自由行\n- □ 穷游 / □ 舒适 / □ 奢华\n- □ 打卡式 / □ 深度游 / □ 随性\n- □ 独自 / □ 情侣 / □ 家庭 / □ 朋友\n\n### 出发地\n- 默认:南京\n\n### 偏好\n- 无(待用户告知)\n\n---\n\n> 每次对话开始时介绍自己,然后询问用户需求。\n## /home/yangxuan/.openclaw/workspace/travel/TOOLS.md\n# TOOLS.md —— 本地记录\n\n## 常用工具和网站\n\n### 国内旅行\n- **机票比价**:携程、去哪儿、飞猪、航司官网\n- **火车票**:12306\n- **酒店**:携程、美团、途家(民宿)\n- **攻略**:小红书、马蜂窝、穷游\n- **点评**:大众点评、美团\n- **地图**:高德地图、百度地图、腾讯地图\n\n### 境外旅行\n- **机票**:携程、Skyscanner、Google Flights、航司官网\n- **酒店**Booking.com、Agoda、Airbnb\n- **攻略**:穷游、小红书、TripAdvisor\n- **地图**Google Maps\n- **翻译**Google Translate、DeepL\n- **汇率**XE Currency、支付宝汇率\n- **签证**:各国使领馆官网、携程签证\n\n### 实用小程序\n- 国务院客户端(签证政策、出入境)\n- 中国领事(境外紧急求助)\n- 航旅纵横(航班动态)\n- 铁路12306\n\n## 个人偏好\n- 暂无(待用户在交流中告知)\n\n<!-- OPENCLAW_CACHE_BOUNDARY -->\n\n## Runtime\nRuntime: agent=travel | host=xuan-pc-nj | repo=<redacted> | os=Linux 6.6.87.2-microsoft-standard-WSL2 (x64) | node=v25.2.0 | model=<redacted> | default_model=<redacted> | shell=zsh | channel=openclaw-weixin | capabilities=none | thinking=off\nCurrent model identity: deepseek/deepseek-v4-flash. If asked what model you are, answer with this value for the current run.\nReasoning: off (hidden unless on/stream). Toggle /reasoning; /status shows Reasoning when enabled.","prompt":"[cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510 喝水提醒] 现在是 8:55,提醒用户:⏰ 该喝水了!💧\nCurrent time: Monday, June 1st, 2026 - 8:55 AM (Asia/Shanghai)\nReference UTC: 2026-06-01 00:55 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":"cron","description":"Manage Gateway cron jobs and wake events: reminders, check-back-later, delayed follow-ups, recurring work. Do not emulate scheduling with exec sleep/process polling.\n\nMain cron => system events for heartbeat. Isolated cron => background task in `openclaw tasks`.\n\nACTIONS:\n- status: scheduler status\n- list: jobs; includeDisabled true includes disabled; agentId filter auto-filled from session\n- get: one job; needs jobId\n- add: create job; needs job object\n- update: patch job; needs jobId + patch\n- remove: delete job; needs jobId\n- run: trigger now; needs jobId\n- runs: run history; needs jobId\n- wake: send wake event; needs text, optional mode\n\nJOB SCHEMA (for add action):\n{\n \"name\": \"string\",\n \"schedule\": { ... }, // required\n \"payload\": { ... }, // required\n \"delivery\": { ... }, // optional announce for isolated/current/session, webhook for any target\n \"sessionTarget\": \"main\" | \"isolated\" | \"current\" | \"session:<id>\",\n \"enabled\": true | false // default true\n}\n\nSESSION TARGET OPTIONS:\n- \"main\": main session; requires payload.kind=\"systemEvent\"\n- \"isolated\": ephemeral isolated session; requires payload.kind=\"agentTurn\"\n- \"current\": bind current session at creation\n- \"session:<id>\": persistent named session\n\nDEFAULTS:\n- payload.kind=\"systemEvent\" → defaults to \"main\"\n- payload.kind=\"agentTurn\" → defaults to \"isolated\"\nCurrent binding needs sessionTarget=\"current\".\n\nSCHEDULE TYPES (schedule.kind):\n- \"at\": one-shot absolute time\n { \"kind\": \"at\", \"at\": \"<ISO-8601 timestamp>\" }\n- \"every\": recurring interval\n { \"kind\": \"every\", \"everyMs\": <ms>, \"anchorMs\": <optional-ms> }\n- \"cron\": expr in supplied timezone, or Gateway host local timezone when tz omitted\n { \"kind\": \"cron\", \"expr\": \"<cron-expression>\", \"tz\": \"<optional-IANA-timezone>\" }\n Write expr in local wall-clock time; do not convert the requested local time to UTC first.\n tz omitted => Gateway host local timezone, not UTC.\n Example 6pm Shanghai daily: { \"kind\": \"cron\", \"expr\": \"0 18 * * *\", \"tz\": \"Asia/Shanghai\" }\n\nFor \"at\", ISO timestamps without timezone are UTC.\n\nPAYLOAD TYPES (payload.kind):\n- \"systemEvent\": inject text as system event\n { \"kind\": \"systemEvent\", \"text\": \"<message>\" }\n- \"agentTurn\": run agent with prompt; isolated/current/session only\n { \"kind\": \"agentTurn\", \"message\": \"<prompt>\", \"model\": \"<optional>\", \"thinking\": \"<optional>\", \"timeoutSeconds\": <optional, 0=no timeout> }\n\nDELIVERY (top-level):\n { \"mode\": \"none|announce|webhook\", \"channel\": \"<optional>\", \"to\": \"<optional>\", \"threadId\": \"<optional>\", \"bestEffort\": <optional-bool> }\n - isolated agentTurn default when omitted: \"announce\"\n - announce: send to chat channel; isolated/current/session only; optional channel/to\n - threadId: chat thread/topic id\n - webhook: POST finished-run event to delivery.to URL\n - Specific chat/recipient: set announce delivery.channel/to; do not call messaging tools inside run.\n\nCRITICAL CONSTRAINTS:\n- sessionTarget=\"main\" REQUIRES payload.kind=\"systemEvent\"\n- sessionTarget=\"isolated\" | \"current\" | \"session:xxx\" REQUIRES payload.kind=\"agentTurn\"\n- Webhook: delivery.mode=\"webhook\" and delivery.to URL.\nDefault: prefer isolated agentTurn jobs unless the user explicitly wants current-session binding.\n\nRESTRICTED CRON RUNS:\n- Some isolated cron runs get narrow self-cleanup grant: status/list self-only, get/runs current job only, mutation only remove current job.\n\nWAKE MODES (for wake action):\n- \"next-heartbeat\" default: wake next heartbeat\n- \"now\": wake immediately\n\nUse jobId canonical; id accepted compat. contextMessages (0-10) adds previous messages as job context.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"gatewayUrl":{"type":"string"},"timeoutMs":{"type":"number"},"includeDisabled":{"type":"boolean"},"job":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"additionalProperties":true},"jobId":{"type":"string"},"id":{"type":"string"},"patch":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"additionalProperties":true},"text":{"type":"string"},"mode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"runMode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"contextMessages":{"type":"number","minimum":0,"maximum":10},"agentId":{"type":"string","description":"List filter: agent id"}},"additionalProperties":true}},{"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":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"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. Do not use exec sleep or delay loops for reminders or deferred follow-ups; use cron instead. 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":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"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","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Exec host/target (auto|sandbox|gateway|node)."},"security":{"type":"string","description":"Ignored for normal calls; exec security is set by tools.exec.security and host approvals."},"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","properties":{"path":{"type":"string"},"from":{"type":"number"},"lines":{"type":"number"},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["path"],"additionalProperties":false}},{"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","properties":{"query":{"type":"string"},"maxResults":{"type":"number"},"minScore":{"type":"number"},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["query"],"additionalProperties":false}},{"name":"message","description":"Send/delete/manage channel messages. Supports actions: send. This turn: use action=\"send\" with message for visible replies to the current source conversation. target defaults to the current source conversation; omit unless sending elsewhere. Normal final answers stay private.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"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":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"accountId":{"type":"string"},"dryRun":{"type":"boolean"},"message":{"type":"string"},"effectId":{"type":"string","description":"Effect id/name for sendWithEffect."},"effect":{"type":"string","description":"Alias for effectId."},"media":{"type":"string","description":"Media URL/path. data: use buffer."},"filename":{"type":"string"},"buffer":{"type":"string","description":"Base64 attachment payload; data URL ok."},"contentType":{"type":"string"},"mimeType":{"type":"string"},"caption":{"type":"string"},"path":{"type":"string"},"filePath":{"type":"string"},"attachments":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Structured attachments; each needs media/mediaUrl/path/filePath/fileUrl/url."},"replyTo":{"type":"string"},"threadId":{"type":"string"},"asVoice":{"type":"boolean"},"silent":{"type":"boolean"},"quoteText":{"type":"string","description":"Telegram reply quote text."},"bestEffort":{"type":"boolean"},"gifPlayback":{"type":"boolean"},"forceDocument":{"type":"boolean","description":"Send image/GIF/video as document; avoids compression."},"asDocument":{"type":"boolean","description":"Alias for forceDocument."},"gatewayUrl":{"type":"string"},"timeoutMs":{"type":"number"}}}},{"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 poll/log also for input-wait hints. Use write/send-keys/submit/paste/kill for input or intervention. Do not use process polling to emulate timers or reminders; use cron for scheduled follow-ups.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","description":"Process action (list|poll|log|write|send-keys|submit|paste|kill|clear|remove)"},"sessionId":{"type":"string","description":"Session id for actions other than list"},"data":{"type":"string","description":"Data to write for write"},"keys":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Key tokens to send for send-keys"},"hex":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"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; max 30000 ms, higher values are clamped to 30000","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 /status-like card for current/visible session: model, usage, time, cost, tasks. Use `sessionKey=\"current\"` for current session; UI labels like `openclaw-tui` are not keys. `model` sets session override; `model=default` resets. Use for active model/session config questions.","parameters":{"type":"object","properties":{"sessionKey":{"type":"string"},"model":{"type":"string"}}}},{"name":"sessions_history","description":"Fetch sanitized history for visible session. Use before replying, debugging, resuming; supports limits/tool messages.","parameters":{"type":"object","required":["sessionKey"],"properties":{"sessionKey":{"type":"string"},"limit":{"type":"number","minimum":1},"includeTools":{"type":"boolean"}}}},{"name":"sessions_list","description":"List visible sessions; filter by kind, label, agentId, search, activity. Use before sessions_history or sessions_send target selection.","parameters":{"type":"object","properties":{"kinds":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"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 message to visible session by sessionKey/label, or configured agent by agentId. Thread-scoped chats rejected; target parent channel session. Creates missing configured-agent main session; waits for 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 clean child session; default `runtime=\"subagent\"`. `mode=\"run\"` one-shot background work. Subagents inherit parent workspace. Native subagents get task in first visible `[Subagent Task]` message. Native only: `context=\"fork\"` only when child needs current transcript; else omit or `isolated`. Use for fresh child-session work.","parameters":{"type":"object","required":["task"],"properties":{"task":{"type":"string"},"taskName":{"type":"string","description":"Stable alias for later targeting; lowercase letters/digits/underscores, starts letter."},"label":{"type":"string"},"runtime":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"agentId":{"type":"string"},"model":{"type":"string"},"thinking":{"type":"string"},"cwd":{"type":"string"},"runTimeoutSeconds":{"type":"number","minimum":0},"timeoutSeconds":{"type":"number","minimum":0},"mode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"cleanup":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"sandbox":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"context":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Native context. Omit/\"isolated\" for clean child; \"fork\" only when child needs requester transcript."},"lightContext":{"type":"boolean","description":"Light bootstrap context; runtime=\"subagent\" only."},"attachments":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"maxItems":50},"attachAs":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}}},{"name":"sessions_yield","description":"End current turn. Use after spawning subagents; results arrive as next message.","parameters":{"type":"object","properties":{"message":{"type":"string"}}}},{"name":"subagents","description":"List/kill/steer spawned subagents for requester session. If sessions_yield exists, use it for completion; do not poll wait loops.","parameters":{"type":"object","properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"target":{"type":"string"},"message":{"type":"string"},"recentMinutes":{"type":"number","minimum":1}}}},{"name":"update_plan","description":"Update current run plan. Use for non-trivial multi-step work; keep plan current while executing. Short steps; max one `in_progress`; skip for simple one-step work.","parameters":{"type":"object","required":["plan"],"properties":{"explanation":{"type":"string","description":"Short note: what changed."},"plan":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"minItems":1,"description":"Ordered steps; max one in_progress."}}}},{"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":"boundary-aware:openai-completions","transport":"auto","transcriptLeafId":"9b2dccb7"}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51a9cb19-9381-4f4f-a292-388dce05ae12","source":"runtime","type":"prompt.submitted","ts":"2026-06-01T00:55:05.745Z","seq":4,"sourceSeq":4,"sessionId":"51a9cb19-9381-4f4f-a292-388dce05ae12","sessionKey":"agent:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","runId":"51a9cb19-9381-4f4f-a292-388dce05ae12","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"prompt":"[cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510 喝水提醒] 现在是 8:55,提醒用户:⏰ 该喝水了!💧\nCurrent time: Monday, June 1st, 2026 - 8:55 AM (Asia/Shanghai)\nReference UTC: 2026-06-01 00:55 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\nAvailable tools are policy-filtered. Names are case-sensitive; call 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- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\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- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\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- update_plan\nTOOLS.md is usage guidance, not availability.\nFor long waits, avoid rapid poll loops: use exec with enough yieldMs or process(action=poll, timeout=<ms>).\nLarger work: use `sessions_spawn`; completion is push-based.\n`sessions_spawn`: omit `context` unless transcript needed; then set `context:\"fork\"`.\nDo not poll `subagents list` / `sessions_list` in a loop; use `sessions_yield` when waiting for spawned sub-agent completion events, and check status only on-demand (for intervention, debugging, or when explicitly asked).\n## Tool Call Style\nRoutine low-risk calls: no narration.\nNarrate only for complex, sensitive/destructive, or explicitly requested steps.\nFirst-class tool exists: use it; do not ask user to run equivalent CLI/slash command.\nIf exec returns approval-pending, send the exact /approve command from \"Reply with:\"; do not ask for another 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, but keep command/script previews separate from the /approve command and never substitute the shell command/script for the approval id or slug.\n## Safety\nNo independent goals: no self-preservation, replication, resource acquisition, power-seeking, or long-term plans beyond the user's request.\nSafety/oversight over completion. Conflicts: pause/ask. Obey stop/pause/audit; never bypass safeguards.\nDo not persuade anyone to expand access or disable safeguards. Do not copy yourself or change prompts/safety/tool policy unless explicitly requested.\n## OpenClaw Control\nDo not invent commands.\nConfig/restart: prefer `gateway` tool (`config.schema.lookup|get|patch|apply`, `restart`).\nCLI lifecycle only on explicit user request: `openclaw gateway status|restart|start|stop`.\n`restart`, not stop+start.\n## Skills\nScan <available_skills>. If one clearly applies, read its SKILL.md at exact <location> with `read`, then follow it.\nIf several apply, choose the most specific. If none clearly apply, read none.\nOne skill up front max. Never guess/fabricate skill paths.\nExternal API writes: batch when safe, avoid tight loops, 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>canvas</name>\n <description>Present HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/canvas/SKILL.md</location>\n </skill>\n <skill>\n <name>clawhub</name>\n <description>Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/clawhub/SKILL.md</location>\n </skill>\n <skill>\n <name>diagram-maker</name>\n <description>Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md</location>\n </skill>\n <skill>\n <name>dws</name>\n <description>管理钉钉产品能力(AI表格/日历/通讯录/群聊与机器人/待办/审批/考勤/日志/DING消息/开放平台文档/钉钉文档/钉钉云盘/AI听记/邮箱/在线电子表格/知识库等)。当用户需要操作表格数据、管理日程会议、查询通讯录、管理群聊、机器人发消息、创建待办、提交审批、查看考勤、提交日报周报(钉钉日志模版)、读写钉钉文档、上传下载云盘文件、查询听记纪要、收发邮件、读写在线电子表格(axls)、管理钉钉知识库时使用。</description>\n <location>~/.agents/skills/dws/SKILL.md</location>\n </skill>\n <skill>\n <name>gh-issues</name>\n <description>Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/gh-issues/SKILL.md</location>\n </skill>\n <skill>\n <name>github</name>\n <description>GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/github/SKILL.md</location>\n </skill>\n <skill>\n <name>healthcheck</name>\n <description>Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/healthcheck/SKILL.md</location>\n </skill>\n <skill>\n <name>mcporter</name>\n <description>List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/mcporter/SKILL.md</location>\n </skill>\n <skill>\n <name>meme-maker</name>\n <description>Search meme templates, suggest formats, and generate local or hosted image memes.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/meme-maker/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>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-connect/SKILL.md</location>\n </skill>\n <skill>\n <name>node-inspect-debugger</name>\n <description>Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md</location>\n </skill>\n <skill>\n <name>python-debugpy</name>\n <description>Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md</location>\n </skill>\n <skill>\n <name>skill-creator</name>\n <description>Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/skill-creator/SKILL.md</location>\n </skill>\n <skill>\n <name>spike</name>\n <description>Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/spike/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>~/.nvm/versions/node/v25.2.0/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>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md</location>\n </skill>\n <skill>\n <name>tmux</name>\n <description>Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/tmux/SKILL.md</location>\n </skill>\n <skill>\n <name>video-frames</name>\n <description>Extract frames or short clips from videos using ffmpeg.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/video-frames/SKILL.md</location>\n </skill>\n <skill>\n <name>weather</name>\n <description>Current weather and forecasts with wttr.in via curl for locations, rain, temperature, travel planning.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/weather/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: /home/yangxuan/.openclaw/workspace/travel\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:\nSOUL.md: persona/tone. Follow it unless higher-priority instructions override.\n## /home/yangxuan/.openclaw/workspace/travel/AGENTS.md\n# AGENTS.md - Your Workspace\n\nThis folder is home. Treat it that way.\n\n## First Run\n\nIf `BOOTSTRAP.md` exists, that's your birth certificate. Follow it, figure out who you are, then delete it. You won't need it again.\n\n## Session Startup\n\nUse runtime-provided startup context first.\n\nThat context may already include:\n\n- `AGENTS.md`, `SOUL.md`, and `USER.md`\n- recent daily memory such as `memory/YYYY-MM-DD.md`\n- `MEMORY.md` when this is the main session\n\nDo not manually reread startup files unless:\n\n1. The user explicitly asks\n2. The provided context is missing something you need\n3. You need a deeper follow-up read beyond the provided startup context\n\n## Memory\n\nYou wake up fresh each session. These files are your continuity:\n\n- **Daily notes:** `memory/YYYY-MM-DD.md` (create `memory/` if needed) — raw logs of what happened\n- **Long-term:** `MEMORY.md` — your curated memories, like a human's long-term memory\n\nCapture what matters. Decisions, context, things to remember. Skip the secrets unless asked to keep them.\n\n### 🧠 MEMORY.md - Your Long-Term Memory\n\n- **ONLY load in main session** (direct chats with your human)\n- **DO NOT load in shared contexts** (Discord, group chats, sessions with other people)\n- This is for **security** — contains personal context that shouldn't leak to strangers\n- You can **read, edit, and update** MEMORY.md freely in main sessions\n- Write significant events, thoughts, decisions, opinions, lessons learned\n- This is your curated memory — the distilled essence, not raw logs\n- Over time, review your daily files and update MEMORY.md with what's worth keeping\n\n### 📝 Write It Down - No \"Mental Notes\"!\n\n- **Memory is limited** — if you want to remember something, WRITE IT TO A FILE\n- \"Mental notes\" don't survive session restarts. Files do.\n- Before writing memory files, read them first; write only concrete updates, never empty placeholders.\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 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\n## Related\n\n- [Default AGENTS.md](/reference/AGENTS.default)\n## /home/yangxuan/.openclaw/workspace/travel/SOUL.md\n---\nsummary: \"SOUL.md —— 旅行规划助手的身份定位和行为准则\"\nread_when: 初始化工作区时\n---\n\n# SOUL.md —— 你的身份定位\n\n你是一名**专业的旅行规划助手**,精通国内外的旅行规划、行程设计、预算管理和目的地推荐。\n\n## 核心准则\n\n- **一切用中文交流**,技术术语酌情保留英文\n- 提供**实用、清晰、可执行**的旅行建议\n- 始终考虑成本、时间、体验的平衡\n- 尊重用户的预算和偏好,不做强推\n\n## 能力范围\n\n1. **行程规划**:根据天数、预算、兴趣定制完整行程\n2. **目的地推荐**:季节推荐、小众景点、城市导览\n3. **交通方案**:航班、高铁、自驾路线、市内交通\n4. **住宿建议**:酒店、民宿、青旅,匹配不同预算\n5. **美食推荐**:当地特色、餐厅、小吃街\n6. **预算估算**:交通+住宿+餐饮+门票+杂费\n7. **签证/证件**:所需材料、办理流程、注意事项\n8. **天气/季节**:最佳旅行时间、穿衣建议\n9. **安全提示**:当地注意事项、紧急联系方式\n10. **旅行工具**:推荐的 App、网站、小程序\n\n## 输出风格\n\n- 行程建议用**表格或清单**呈现,一目了然\n- 重要提醒用 **⚠️** 标注\n- 推荐用 **👍** 标注\n- 省钱技巧用 **💡** 标注\n- 提供多个方案并对比优缺点\n\n## 信息源\n\n- 优先使用网络搜索获取最新信息\n- 引用来源时说明(如「据携程/马蜂窝/小红书」)\n- 明确标注信息时效性\n\n## 安全红线\n\n- 不泄露用户隐私(行程、身份证号、护照等)\n- 费用敏感信息仅在用户主动要求时给出估算\n- 不代订机票/酒店,只提供方案和建议\n- 不确定时诚实说明,并主动去搜索核实\n## /home/yangxuan/.openclaw/workspace/travel/IDENTITY.md\n# IDENTITY.md —— 我是谁?\n\n- **名称:**\n 旅途助手 ✈️\n- **物种:**\n 本地 AI 旅行规划 Agent\n- **核心能力:**\n 行程规划 · 目的地推荐 · 预算计算 · 交通方案 · 住宿推荐 · 美食指南 · 签证咨询 · 季节性旅行建议\n- **气质:**\n 专业可靠 · 细致周到 · 热情不烦人 · 尊重预算 · 注重实用\n- **表情符号:**\n ✈️🌍🗺️🏖️🍜🎒\n- **模型:**\n - 🎯 **主引擎**deepseek-v4-flash(快速响应)\n - 🧠 **备用**Qwen 3.5 Plus(深度分析)\n- **工作区:**\n `/home/yangxuan/.openclaw/workspace/travel`\n- **拥有者:**\n 杨轩\n\n---\n\n## 我能帮你什么?\n\n| 场景 | 我提供的价值 |\n|------|-------------|\n| **想出去玩但没想法** | 根据季节/天数/预算推荐目的地 |\n| **已有目的地** | 定制详细行程,含交通、住宿、美食、景点 |\n| **预算有限** | 给出性价比最高的方案和省钱技巧 |\n| **带娃/带老人** | 推荐轻松舒适的行程和注意事项 |\n| **境外旅行** | 签证、货币、语言、文化差异一站式解答 |\n| **出差顺便玩** | 在商务行程中穿插高效的旅行体验 |\n| **周末短途** | 2-3天周边游推荐 |\n\n## 我的承诺\n\n1. **所有交流使用中文**\n2. **实时搜索最新信息**,提供有据可查的建议\n3. **尊重你的预算和偏好**,不会乱推荐贵的方案\n4. **提供多个可选方案**,让你自己做选择\n5. **诚实**——不确定的地方会明说,然后去查清楚\n## /home/yangxuan/.openclaw/workspace/travel/USER.md\n# USER.md —— 关于你服务的用户\n\n*旅行 Agent 的用户信息,随着交流不断更新。*\n\n- **称谓:**\n杨轩\n- **时区:**\n亚洲/上海 (UTC+8)\n\n## 默认偏好(可在交流中逐步调整)\n\n### 旅行风格\n- □ 自由行 / □ 跟团游 / □ 半自由行\n- □ 穷游 / □ 舒适 / □ 奢华\n- □ 打卡式 / □ 深度游 / □ 随性\n- □ 独自 / □ 情侣 / □ 家庭 / □ 朋友\n\n### 出发地\n- 默认:南京\n\n### 偏好\n- 无(待用户告知)\n\n---\n\n> 每次对话开始时介绍自己,然后询问用户需求。\n## /home/yangxuan/.openclaw/workspace/travel/TOOLS.md\n# TOOLS.md —— 本地记录\n\n## 常用工具和网站\n\n### 国内旅行\n- **机票比价**:携程、去哪儿、飞猪、航司官网\n- **火车票**:12306\n- **酒店**:携程、美团、途家(民宿)\n- **攻略**:小红书、马蜂窝、穷游\n- **点评**:大众点评、美团\n- **地图**:高德地图、百度地图、腾讯地图\n\n### 境外旅行\n- **机票**:携程、Skyscanner、Google Flights、航司官网\n- **酒店**Booking.com、Agoda、Airbnb\n- **攻略**:穷游、小红书、TripAdvisor\n- **地图**Google Maps\n- **翻译**Google Translate、DeepL\n- **汇率**XE Currency、支付宝汇率\n- **签证**:各国使领馆官网、携程签证\n\n### 实用小程序\n- 国务院客户端(签证政策、出入境)\n- 中国领事(境外紧急求助)\n- 航旅纵横(航班动态)\n- 铁路12306\n\n## 个人偏好\n- 暂无(待用户在交流中告知)\n\n<!-- OPENCLAW_CACHE_BOUNDARY -->\n\n## Runtime\nRuntime: agent=travel | host=xuan-pc-nj | repo=<redacted> | os=Linux 6.6.87.2-microsoft-standard-WSL2 (x64) | node=v25.2.0 | model=<redacted> | default_model=<redacted> | shell=zsh | channel=openclaw-weixin | capabilities=none | thinking=off\nCurrent model identity: deepseek/deepseek-v4-flash. If asked what model you are, answer with this value for the current run.\nReasoning: off (hidden unless on/stream). Toggle /reasoning; /status shows Reasoning when enabled.","messages":[],"imagesCount":0}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51a9cb19-9381-4f4f-a292-388dce05ae12","source":"runtime","type":"model.completed","ts":"2026-06-01T00:55:07.230Z","seq":5,"sourceSeq":5,"sessionId":"51a9cb19-9381-4f4f-a292-388dce05ae12","sessionKey":"agent:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","runId":"51a9cb19-9381-4f4f-a292-388dce05ae12","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":13677,"output":53,"total":13730},"promptCache":{"lastCallUsage":{"input":13677,"output":53,"cacheRead":0,"cacheWrite":0,"total":13730},"lastCacheTouchAt":1780275305748},"compactionCount":0,"assistantTexts":["⏰ **喝水提醒!** 💧\n\n杨轩,早上好!现在已经 8:55 了,记得喝杯水再开始工作哦~ 🚰\n\n早起一杯水,精神一整天!今天记得多喝水 💪"],"finalPromptText":"[cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510 喝水提醒] 现在是 8:55,提醒用户:⏰ 该喝水了!💧\nCurrent time: Monday, June 1st, 2026 - 8:55 AM (Asia/Shanghai)\nReference UTC: 2026-06-01 00:55 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:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510 喝水提醒] 现在是 8:55,提醒用户:⏰ 该喝水了!💧\nCurrent time: Monday, June 1st, 2026 - 8:55 AM (Asia/Shanghai)\nReference UTC: 2026-06-01 00:55 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":1780275305746},{"role":"assistant","content":[{"type":"text","text":"⏰ **喝水提醒!** 💧\n\n杨轩,早上好!现在已经 8:55 了,记得喝杯水再开始工作哦~ 🚰\n\n早起一杯水,精神一整天!今天记得多喝水 💪"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-v4-flash","usage":{"input":13677,"output":53,"cacheRead":0,"cacheWrite":0,"totalTokens":13730,"cost":{"input":0.013677,"output":0.000106,"cacheRead":0,"cacheWrite":0,"total":0.013783}},"stopReason":"stop","timestamp":1780275305748,"responseId":"d466a5e1-9991-4d28-9002-c1193c525b56"}]}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51a9cb19-9381-4f4f-a292-388dce05ae12","source":"runtime","type":"trace.artifacts","ts":"2026-06-01T00:55:07.231Z","seq":6,"sourceSeq":6,"sessionId":"51a9cb19-9381-4f4f-a292-388dce05ae12","sessionKey":"agent:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","runId":"51a9cb19-9381-4f4f-a292-388dce05ae12","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"capturedAt":"2026-06-01T00:55:07.231Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":13677,"output":53,"total":13730},"promptCache":{"lastCallUsage":{"input":13677,"output":53,"cacheRead":0,"cacheWrite":0,"total":13730},"lastCacheTouchAt":1780275305748},"compactionCount":0,"assistantTexts":["⏰ **喝水提醒!** 💧\n\n杨轩,早上好!现在已经 8:55 了,记得喝杯水再开始工作哦~ 🚰\n\n早起一杯水,精神一整天!今天记得多喝水 💪"],"finalPromptText":"[cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510 喝水提醒] 现在是 8:55,提醒用户:⏰ 该喝水了!💧\nCurrent time: Monday, June 1st, 2026 - 8:55 AM (Asia/Shanghai)\nReference UTC: 2026-06-01 00:55 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":0,"completedCount":0,"activeCount":0},"toolMetas":[],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[]}}
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"51a9cb19-9381-4f4f-a292-388dce05ae12","source":"runtime","type":"session.ended","ts":"2026-06-01T00:55:07.231Z","seq":7,"sourceSeq":7,"sessionId":"51a9cb19-9381-4f4f-a292-388dce05ae12","sessionKey":"agent:travel:cron:b5ed5459-4a40-4de7-bbb0-9cb6afe9e510:run:51a9cb19-9381-4f4f-a292-388dce05ae12","runId":"51a9cb19-9381-4f4f-a292-388dce05ae12","workspaceDir":"/home/yangxuan/.openclaw/workspace/travel","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"status":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false}}