8 lines
126 KiB
Plaintext
8 lines
126 KiB
Plaintext
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"b13ea466-b422-49db-b5b6-b37d089c13ec","source":"runtime","type":"session.started","ts":"2026-07-02T01:41:38.105Z","seq":1,"sourceSeq":1,"sessionId":"b13ea466-b422-49db-b5b6-b37d089c13ec","sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","runId":"1cb54571-bcb0-4479-8149-ee319df69c62","workspaceDir":"/home/yangxuan/.openclaw/workspace","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"trigger":"user","sessionFile":"/home/yangxuan/.openclaw/agents/main/sessions/b13ea466-b422-49db-b5b6-b37d089c13ec.jsonl","workspaceDir":"/home/yangxuan/.openclaw/workspace","agentId":"main","messageProvider":"openclaw-weixin","localModelLean":false,"toolCount":24,"clientToolCount":0}}
|
||
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"b13ea466-b422-49db-b5b6-b37d089c13ec","source":"runtime","type":"trace.metadata","ts":"2026-07-02T01:41:38.107Z","seq":2,"sourceSeq":2,"sessionId":"b13ea466-b422-49db-b5b6-b37d089c13ec","sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","runId":"1cb54571-bcb0-4479-8149-ee319df69c62","workspaceDir":"/home/yangxuan/.openclaw/workspace","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"capturedAt":"2026-07-02T01:41:38.105Z","harness":{"type":"openclaw","name":"OpenClaw","version":"2026.6.11","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":"$OPENCLAW_STATE_DIR/workspace","sessionFile":"$OPENCLAW_STATE_DIR/agents/main/sessions/b13ea466-b422-49db-b5b6-b37d089c13ec.jsonl"},"model":{"provider":"deepseek","name":"deepseek-v4-flash","api":"openai-completions","fastMode":false,"thinkLevel":"off","reasoningLevel":"off"},"config":{"redacted":{"meta":{"lastTouchedVersion":"2026.6.11","lastTouchedAt":"2026-07-02T01:14:04.045Z"},"wizard":{"lastRunAt":"2026-06-29T03:08:31.226Z","lastRunVersion":"2026.6.9","lastRunCommand":"doctor","lastRunMode":"local"},"auth":{"profiles":{"ollama:default":{"provider":"ollama","mode":"api_key"}}},"models":{"mode":"merge","providers":{"openai":{"baseUrl":"http://192.168.2.74:3000/v1","api":"openai-completions","models":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"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":"new-api/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","memorySearch":{"provider":"openai","model":"text-embedding-v4"},"compaction":{"mode":"safeguard"},"timeoutSeconds":3600,"maxConcurrent":2,"subagents":{"maxConcurrent":4,"archiveAfterMinutes":60},"sandbox":{"mode":"off"}},"list":[{"id":"main","name":"主智能体","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","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":"backend","name":"后端开发","workspace":"/home/yangxuan/.openclaw/workspace/backend","agentDir":"/home/yangxuan/.openclaw/agents/backend/agent","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"tools":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"front","name":"前端开发","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},"tools":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"resume","name":"简历管理","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":"旅行规划","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}},{"id":"planner","name":"方案规划","workspace":"/home/yangxuan/.openclaw/workspace/planner","agentDir":"/home/yangxuan/.openclaw/agents/planner/agent","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"identity":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}]},"tools":{"profile":"coding","alsoAllow":["ezviz_device","ezviz_capture","ezviz_message"],"deny":["group:web","browser"],"web":{"search":{"enabled":true,"provider":"searxng","openaiCodex":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"fetch":{"enabled":true}}},"bindings":[{"agentId":"main","match":{"channel":"openclaw-weixin","accountId":"4a0926e2cb5f-im-bot"}},{"type":"route","agentId":"resume","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,"allowFrom":["*"],"groupAllowFrom":["*"],"separateSessionByConversation":true,"sharedMemoryAcrossConversations":false,"groupSessionScope":"group"},"ezviz":{"enabled":true,"appId":"92aa2d25a04247afacb76b1f75f9cf80"}},"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":"password","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},"baidu-text-translate":{"enabled":true,"env":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}},"plugins":{"allow":["deepseek","dingtalk-connector","ezviz","memory-core","ollama","openclaw-weixin","searxng"],"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}},"ezviz":{"enabled":false},"memory-core":{"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"bundledDiscovery":"compat"},"cron":{"maxConcurrentRuns":8}},"runtime":{"timeoutMs":3600000,"trigger":"user","disableTools":false,"toolResultFormat":"plain"}},"plugins":{"source":"active-registry","importedRuntimePluginIds":["deepseek","dingtalk-connector","duckduckgo","google","memory-core","minimax","ollama","openclaw-weixin","searxng","xai"],"entries":[{"id":"dingtalk-connector","name":"DingTalk Channel","version":"0.8.23","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/projects/dingtalk-real-ai-dingtalk-connector-aa54111b45/node_modules/@dingtalk-real-ai/dingtalk-connector/dist/index.mjs","rootDir":"/home/yangxuan/.openclaw/npm/projects/dingtalk-real-ai-dingtalk-connector-aa54111b45/node_modules/@dingtalk-real-ai/dingtalk-connector","workspaceDir":"/home/yangxuan/.openclaw/workspace","channelIds":["dingtalk-connector"]},{"id":"memory-core","name":"Memory (Core)","version":"2026.6.11","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"]},{"id":"ollama","name":"Ollama Provider","version":"2026.6.11","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","ollama-cloud"],"mediaUnderstandingProviderIds":["ollama"],"webSearchProviderIds":["ollama"],"memoryEmbeddingProviderIds":["ollama"]},{"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/projects/tencent-weixin-openclaw-weixin-7783ac86ba/node_modules/@tencent-weixin/openclaw-weixin/dist/index.js","rootDir":"/home/yangxuan/.openclaw/npm/projects/tencent-weixin-openclaw-weixin-7783ac86ba/node_modules/@tencent-weixin/openclaw-weixin","workspaceDir":"/home/yangxuan/.openclaw/workspace","channelIds":["openclaw-weixin"]},{"id":"searxng","name":"SearXNG Plugin","version":"2026.6.11","description":"Bundled SearXNG web search plugin","origin":"global","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","source":"/home/yangxuan/.openclaw/npm/projects/openclaw-searxng-plugin-92d078bddc/node_modules/@openclaw/searxng-plugin/dist/index.js","rootDir":"/home/yangxuan/.openclaw/npm/projects/openclaw-searxng-plugin-92d078bddc/node_modules/@openclaw/searxng-plugin","workspaceDir":"/home/yangxuan/.openclaw/workspace","webSearchProviderIds":["searxng"]}]},"skills":{"snapshotVersion":1782956396530,"entries":[{"id":"baidu-text-translate","name":"baidu-text-translate","description":"Use this skill whenever you need to translate text with the trans-cli tool (Baidu Translation AI API). Covers JSON output contract, Baidu-specific language codes (jp/kor/fra/spa/ara — not ISO defaults), exit code semantics, error decision tree, first-time API key setup, QUOTA_EXCEEDED / AUTH_FAILED recovery, environment self-diagnosis via `trans doctor`, and listing supported languages via `trans languages`. Trigger on any of: running `trans text`, shell pipelines with translation, trans-cli errors, API key configuration, `trans doctor` checks, or looking up language codes.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/baidu-text-translate/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/baidu-text-translate","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/baidu-text-translate","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/baidu-text-translate/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"clawhub","name":"clawhub","description":"Search ClawHub for skills when a requested capability is not already available; install, verify, update, publish, or sync skills.","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":"Code","name":"Code","description":"Coding workflow with planning, implementation, verification, and testing for clean software development.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/openclaw-code/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/openclaw-code","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/openclaw-code","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/openclaw-code/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"database-admin","name":"database-admin","description":"Comprehensive database administration, schema management, data operations, and optimization. Use when Codex needs to: (1) Create or modify database tables with proper indexing, (2) Perform bulk data insertions with type safety and constraint handling, (3) Execute complex queries with JOINs, aggregations, and subqueries, (4) Optimize query performance through indexing and execution plan analysis, (5) Manage database backups, restores, and migrations, (6) Handle special data types (BIGINT, UUID, JSONB, enums), (7) Implement transactional safety with ACID compliance, or (8) Debug and resolve database errors including constraint violations, type mismatches, and foreign key issues","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/database-admin/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/database-admin","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/database-admin","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/database-admin/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"database-schema-designer","name":"database-schema-designer","description":"Database Schema Designer","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/database-schema-designer/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/database-schema-designer","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/database-schema-designer","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/database-schema-designer/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"db-query","name":"db-query","description":"Query project databases with automatic SSH tunnel management. Use when you need to execute SQL queries against configured databases, especially those accessible only via SSH tunnels. Automatically manages SSH connection lifecycle (establishes tunnel before query, closes after). Supports multiple databases distinguished by description/name from config file.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/db-query/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/db-query","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/db-query","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/db-query/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"db-schema","name":"db-schema","description":"Generate database schemas, migrations, and ERD diagrams from plain English descriptions — supports PostgreSQL, MySQL, SQLite, and MongoDB with proper indexes and constraints.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/db-schema-gen/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/db-schema-gen","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/db-schema-gen","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/db-schema-gen/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"deep-research-pro","name":"deep-research-pro","description":"Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/deep-research-pro/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/deep-research-pro","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/deep-research-pro","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/deep-research-pro/SKILL.md","scope":"project","source":"openclaw-workspace"},"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":"dingtalk-channel-rules","name":"dingtalk-channel-rules","description":"钉钉会话输出规则。在钉钉会话中始终生效。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/dingtalk-channel-rules/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/dingtalk-channel-rules","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/dingtalk-channel-rules","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/dingtalk-channel-rules/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"dingtalk-troubleshoot","name":"dingtalk-troubleshoot","description":"钉钉连接器问题排查。包含 dws CLI 常见错误处理、授权问题排查和连接故障诊断。\n当 dws 命令执行失败、授权异常、连接中断时自动激活。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/dingtalk-troubleshoot/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/dingtalk-troubleshoot","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/dingtalk-troubleshoot","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/dingtalk-troubleshoot/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"docker-essentials","name":"docker-essentials","description":"Essential Docker commands and workflows for container management, image operations, and debugging.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/docker-essentials/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/docker-essentials","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/docker-essentials","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/docker-essentials/SKILL.md","scope":"project","source":"openclaw-workspace"},"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":"dws-cli","name":"dws-cli","description":"在钉钉会话中通过 dws CLI 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/工作台等）。\n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、提交日报周报时使用。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/dws-cli/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/dws-cli","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/dws-cli","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/dws-cli/SKILL.md","scope":"project","source":"openclaw-extra"},"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":"humanizer","name":"humanizer","description":"Remove signs of AI-generated writing from text. Use when editing or reviewing\ntext to make it sound more natural and human-written. Based on Wikipedia's\ncomprehensive \"Signs of AI writing\" guide. Detects and fixes patterns including:\ninflated symbolism, promotional language, superficial -ing analyses, vague\nattributions, em dash overuse, rule of three, AI vocabulary words, negative\nparallelisms, and excessive conjunctive phrases.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/humanizer/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/humanizer","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/humanizer","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/humanizer/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"imap-smtp-email","name":"imap-smtp-email","description":"Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Supports multiple accounts. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/imap-smtp-email/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/imap-smtp-email","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/imap-smtp-email","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/imap-smtp-email/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"mcporter","name":"mcporter","description":"Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/mcporter/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/mcporter","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/mcporter","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/mcporter/SKILL.md","scope":"project","source":"openclaw-workspace"},"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":"multi-search-engine","name":"multi-search-engine","description":"Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/multi-search-engine/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/multi-search-engine","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/multi-search-engine","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/multi-search-engine/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"MySQL","name":"MySQL","description":"Write correct MySQL queries with proper character sets, indexing, transactions, and production patterns.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/MySQL/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/MySQL","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/MySQL","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/MySQL/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"news-summary","name":"news-summary","description":"This skill should be used when the user asks for news updates, daily briefings, or what's happening in the world. Fetches news from trusted international RSS feeds and can create voice summaries.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/news-summary/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/news-summary","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/news-summary","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/news-summary/SKILL.md","scope":"project","source":"openclaw-workspace"},"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":"obsidian-official-cli","name":"obsidian-official-cli","description":"Work with Obsidian vaults using the official Obsidian CLI (v1.12+). Open, search, create, move, and manage notes from the terminal. Use when working with Obsidian vaults for note management, file operations, searching content, managing tasks, properties, links, plugins, themes, sync operations, or any command-line interaction with Obsidian.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/obsidian-official-cli/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/obsidian-official-cli","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/obsidian-official-cli","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/obsidian-official-cli/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"opencode-controller","name":"opencode-controller","description":"Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/opencode-controller/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/opencode-controller","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/opencode-controller","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/opencode-controller/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"openspec","name":"openspec","description":"Spec-driven development with OpenSpec CLI. Use when building features, migrations, refactors, or any structured development work. Manages proposal → specs → design → tasks → implementation workflows. Supports custom schemas (TDD, rapid, etc.). Trigger on requests involving feature planning, spec writing, change management, or when /opsx commands are mentioned.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/openspec/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/openspec","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/openspec","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/openspec/SKILL.md","scope":"project","source":"openclaw-workspace"},"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":"qiushi-openclaw-skills","name":"qiushi-openclaw-skills","description":"求是 OpenClaw Skills 是基于毛泽东思想方法论的 AI Agent 技能集合，按照 OpenClaw 技能格式进行改造，旨在为 AI 提供系统化的思考和行动框架。","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/qiushi-openclaw-skill/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/qiushi-openclaw-skill","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/qiushi-openclaw-skill","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/qiushi-openclaw-skill/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"requirements-analyst","name":"requirements-analyst","description":"将产品需求转化为前后端可执行的技术规范，输出离线性优先的结构化文档。当用户提出产品需求、PRD、功能描述或模糊想法时自动触发。","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/requirements-analyst/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/requirements-analyst","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/requirements-analyst","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/requirements-analyst/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"rss-ai-reader","name":"rss-ai-reader","description":"📰 RSS AI 阅读器 — 自动抓取订阅、LLM生成摘要、多渠道推送！\n支持 Claude/OpenAI 生成中文摘要，推送到飞书/Telegram/Email。\n触发条件: 用户要求订阅RSS、监控博客、抓取新闻、生成摘要、设置定时抓取、\n\"帮我订阅\"、\"监控这个网站\"、\"每天推送新闻\"、RSS/Atom feed 相关。","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/rss-ai-reader/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/rss-ai-reader","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/rss-ai-reader","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/rss-ai-reader/SKILL.md","scope":"project","source":"openclaw-workspace"},"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":"sql-toolkit","name":"sql-toolkit","description":"Query, design, migrate, and optimize SQL databases. Use when working with SQLite, PostgreSQL, or MySQL — schema design, writing queries, creating migrations, indexing, backup/restore, and debugging slow queries. No ORMs required.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/sql-toolkit/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/sql-toolkit","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/sql-toolkit","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/sql-toolkit/SKILL.md","scope":"project","source":"openclaw-workspace"},"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":"using-superpowers","name":"using-superpowers","description":"Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/using-superpowers/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/using-superpowers","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/using-superpowers","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/using-superpowers/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"video-frames","name":"video-frames","description":"Extract frames or short clips from videos using ffmpeg.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/video-frames/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/video-frames","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/video-frames","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/video-frames/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"weather","name":"weather","description":"Get current weather and forecasts (no API key required).","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/weather/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/weather","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/weather","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/weather/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"web-search","name":"web-search","description":"This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses a self-hosted SearXNG instance to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.","filePath":"$OPENCLAW_STATE_DIR/workspace/skills/web-search/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/web-search","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/workspace/skills/web-search","origin":"top-level","path":"$OPENCLAW_STATE_DIR/workspace/skills/web-search/SKILL.md","scope":"project","source":"openclaw-workspace"},"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.\nIf a skill's <version> differs from a previous turn, re-read its SKILL.md before using it.\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>baidu-text-translate</name>\n <description>Use this skill whenever you need to translate text with the trans-cli tool (Baidu Translation AI API). Covers JSON output contract, Baidu-specific language codes (jp/kor/fra/spa/ara — not ISO defaults), exit code semantics, error decision tree, first-time API key setup, QUOTA_EXCEEDED / AUTH_FAILED recovery, environment self-diagnosis via `trans doctor`, and listing supported languages via `trans languages`. Trigger on any of: running `trans text`, shell pipelines with translation, trans-cli errors, API key configuration, `trans doctor` checks, or looking up language codes.</description>\n <location>~/.openclaw/workspace/skills/baidu-text-translate/SKILL.md</location>\n <version>sha256:4157f3a14f706f1e</version>\n </skill>\n <skill>\n <name>clawhub</name>\n <description>Search ClawHub for skills when a requested capability is not already available; install, verify, update, publish, or sync skills.</description>\n <location>~/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/skills/clawhub/SKILL.md</location>\n <version>sha256:6bb70d95cbd1a545</version>\n </skill>\n <skill>\n <name>Code</name>\n <description>Coding workflow with planning, implementation, verification, and testing for clean software development.</description>\n <location>~/.openclaw/workspace/skills/openclaw-code/SKILL.md</location>\n <version>sha256:f09694134cc55cc0</version>\n </skill>\n <skill>\n <name>database-admin</name>\n <description>Comprehensive database administration, schema management, data operations, and optimization. Use when Codex needs to: (1) Create or modify database tables with proper indexing, (2) Perform bulk data insertions with type safety and constraint handling, (3) Execute complex queries with JOINs, aggregations, and subqueries, (4) Optimize query performance through indexing and execution plan analysis, (5) Manage database backups, restores, and migrations, (6) Handle special data types (BIGINT, UUID, JSONB, enums), (7) Implement transactional safety with ACID compliance, or (8) Debug and resolve database errors including constraint violations, type mismatches, and foreign key issues</description>\n <location>~/.openclaw/workspace/skills/database-admin/SKILL.md</location>\n <version>sha256:7649e43727f2fb8b</version>\n </skill>\n <skill>\n <name>database-schema-designer</name>\n <description>Database Schema Designer</description>\n <location>~/.openclaw/workspace/skills/database-schema-designer/SKILL.md</location>\n <version>sha256:3f2282ec8135dfdf</version>\n </skill>\n <skill>\n <name>db-query</name>\n <description>Query project databases with automatic SSH tunnel management. Use when you need to execute SQL queries against configured databases, especially those accessible only via SSH tunnels. Automatically manages SSH connection lifecycle (establishes tunnel before query, closes after). Supports multiple databases distinguished by description/name from config file.</description>\n <location>~/.openclaw/workspace/skills/db-query/SKILL.md</location>\n <version>sha256:eaffe1e617f2b8f2</version>\n </skill>\n <skill>\n <name>db-schema</name>\n <description>Generate database schemas, migrations, and ERD diagrams from plain English descriptions — supports PostgreSQL, MySQL, SQLite, and MongoDB with proper indexes and constraints.</description>\n <location>~/.openclaw/workspace/skills/db-schema-gen/SKILL.md</location>\n <version>sha256:c511ce8bb306f227</version>\n </skill>\n <skill>\n <name>deep-research-pro</name>\n <description>Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.</description>\n <location>~/.openclaw/workspace/skills/deep-research-pro/SKILL.md</location>\n <version>sha256:a780f8bbec442198</version>\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 <version>sha256:6195e03fcb04a1a6</version>\n </skill>\n <skill>\n <name>dingtalk-channel-rules</name>\n <description>钉钉会话输出规则。在钉钉会话中始终生效。</description>\n <location>~/.openclaw/plugin-skills/dingtalk-channel-rules/SKILL.md</location>\n <version>sha256:4abd7ff39fd8ab23</version>\n </skill>\n <skill>\n <name>dingtalk-troubleshoot</name>\n <description>钉钉连接器问题排查。包含 dws CLI 常见错误处理、授权问题排查和连接故障诊断。\n当 dws 命令执行失败、授权异常、连接中断时自动激活。</description>\n <location>~/.openclaw/plugin-skills/dingtalk-troubleshoot/SKILL.md</location>\n <version>sha256:831e1260e77bcf9b</version>\n </skill>\n <skill>\n <name>docker-essentials</name>\n <description>Essential Docker commands and workflows for container management, image operations, and debugging.</description>\n <location>~/.openclaw/workspace/skills/docker-essentials/SKILL.md</location>\n <version>sha256:bf8120febd5275b0</version>\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 <version>sha256:25f131a2e41eeeca</version>\n </skill>\n <skill>\n <name>dws-cli</name>\n <description>在钉钉会话中通过 dws CLI 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/工作台等）。\n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、提交日报周报时使用。</description>\n <location>~/.openclaw/plugin-skills/dws-cli/SKILL.md</location>\n <version>sha256:e1e0cb89e56c9a8d</version>\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 <version>sha256:e7a64973e1862117</version>\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 <version>sha256:46f3610b1668c284</version>\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 <version>sha256:518ec6e0482cf1c7</version>\n </skill>\n <skill>\n <name>humanizer</name>\n <description>Remove signs of AI-generated writing from text. Use when editing or reviewing\ntext to make it sound more natural and human-written. Based on Wikipedia's\ncomprehensive "Signs of AI writing" guide. Detects and fixes patterns including:\ninflated symbolism, promotional language, superficial -ing analyses, vague\nattributions, em dash overuse, rule of three, AI vocabulary words, negative\nparallelisms, and excessive conjunctive phrases.</description>\n <location>~/.openclaw/workspace/skills/humanizer/SKILL.md</location>\n <version>sha256:d7ce483d368e4301</version>\n </skill>\n <skill>\n <name>imap-smtp-email</name>\n <description>Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Supports multiple accounts. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.</description>\n <location>~/.openclaw/workspace/skills/imap-smtp-email/SKILL.md</location>\n <version>sha256:01345a894f2863a4</version>\n </skill>\n <skill>\n <name>mcporter</name>\n <description>Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.</description>\n <location>~/.openclaw/workspace/skills/mcporter/SKILL.md</location>\n <version>sha256:475253164a0cca24</version>\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 <version>sha256:8b8832f9f0f58b16</version>\n </skill>\n <skill>\n <name>multi-search-engine</name>\n <description>Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.</description>\n <location>~/.openclaw/workspace/skills/multi-search-engine/SKILL.md</location>\n <version>sha256:ef2d2706e82ad0fc</version>\n </skill>\n <skill>\n <name>MySQL</name>\n <description>Write correct MySQL queries with proper character sets, indexing, transactions, and production patterns.</description>\n <location>~/.openclaw/workspace/skills/MySQL/SKILL.md</location>\n <version>sha256:97003e1d9502f459</version>\n </skill>\n <skill>\n <name>news-summary</name>\n <description>This skill should be used when the user asks for news updates, daily briefings, or what's happening in the world. Fetches news from trusted international RSS feeds and can create voice summaries.</description>\n <location>~/.openclaw/workspace/skills/news-summary/SKILL.md</location>\n <version>sha256:1b4c45b56f567567</version>\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 <version>sha256:cc39026fd84e5cfa</version>\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 <version>sha256:50d2f6828eaf4bbf</version>\n </skill>\n <skill>\n <name>obsidian-official-cli</name>\n <description>Work with Obsidian vaults using the official Obsidian CLI (v1.12+). Open, search, create, move, and manage notes from the terminal. Use when working with Obsidian vaults for note management, file operations, searching content, managing tasks, properties, links, plugins, themes, sync operations, or any command-line interaction with Obsidian.</description>\n <location>~/.openclaw/workspace/skills/obsidian-official-cli/SKILL.md</location>\n <version>sha256:d9c66873957818a1</version>\n </skill>\n <skill>\n <name>opencode-controller</name>\n <description>Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.</description>\n <location>~/.openclaw/workspace/skills/opencode-controller/SKILL.md</location>\n <version>sha256:6535df08ba8b0bbc</version>\n </skill>\n <skill>\n <name>openspec</name>\n <description>Spec-driven development with OpenSpec CLI. Use when building features, migrations, refactors, or any structured development work. Manages proposal → specs → design → tasks → implementation workflows. Supports custom schemas (TDD, rapid, etc.). Trigger on requests involving feature planning, spec writing, change management, or when /opsx commands are mentioned.</description>\n <location>~/.openclaw/workspace/skills/openspec/SKILL.md</location>\n <version>sha256:720f832d1879e281</version>\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 <version>sha256:bfb1891204b67260</version>\n </skill>\n <skill>\n <name>qiushi-openclaw-skills</name>\n <description>求是 OpenClaw Skills 是基于毛泽东思想方法论的 AI Agent 技能集合，按照 OpenClaw 技能格式进行改造，旨在为 AI 提供系统化的思考和行动框架。</description>\n <location>~/.openclaw/workspace/skills/qiushi-openclaw-skill/SKILL.md</location>\n <version>sha256:b21d933b7f61584d</version>\n </skill>\n <skill>\n <name>requirements-analyst</name>\n <description>将产品需求转化为前后端可执行的技术规范，输出离线性优先的结构化文档。当用户提出产品需求、PRD、功能描述或模糊想法时自动触发。</description>\n <location>~/.openclaw/workspace/skills/requirements-analyst/SKILL.md</location>\n <version>sha256:f766e6b7b585e7e8</version>\n </skill>\n <skill>\n <name>rss-ai-reader</name>\n <description>📰 RSS AI 阅读器 — 自动抓取订阅、LLM生成摘要、多渠道推送！\n支持 Claude/OpenAI 生成中文摘要，推送到飞书/Telegram/Email。\n触发条件: 用户要求订阅RSS、监控博客、抓取新闻、生成摘要、设置定时抓取、\n"帮我订阅"、"监控这个网站"、"每天推送新闻"、RSS/Atom feed 相关。</description>\n <location>~/.openclaw/workspace/skills/rss-ai-reader/SKILL.md</location>\n <version>sha256:0abcc8438f644cdb</version>\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 <version>sha256:9e971bac63ad787f</version>\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 <version>sha256:1258cde2d0e53267</version>\n </skill>\n <skill>\n <name>sql-toolkit</name>\n <description>Query, design, migrate, and optimize SQL databases. Use when working with SQLite, PostgreSQL, or MySQL — schema design, writing queries, creating migrations, indexing, backup/restore, and debugging slow queries. No ORMs required.</description>\n <location>~/.openclaw/workspace/skills/sql-toolkit/SKILL.md</location>\n <version>sha256:515ecf904449a3cd</version>\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 <version>sha256:d8b6a48d329aef0a</version>\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 <version>sha256:1fe28cd924d8ae2d</version>\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 <version>sha256:98b6b8392ec57e11</version>\n </skill>\n <skill>\n <name>using-superpowers</name>\n <description>Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions</description>\n <location>~/.openclaw/workspace/skills/using-superpowers/SKILL.md</location>\n <version>sha256:81d921b16502091f</version>\n </skill>\n <skill>\n <name>video-frames</name>\n <description>Extract frames or short clips from videos using ffmpeg.</description>\n <location>~/.openclaw/workspace/skills/video-frames/SKILL.md</location>\n <version>sha256:7e24245498aca878</version>\n </skill>\n <skill>\n <name>weather</name>\n <description>Get current weather and forecasts (no API key required).</description>\n <location>~/.openclaw/workspace/skills/weather/SKILL.md</location>\n <version>sha256:1ca0c8d768ad603e</version>\n </skill>\n <skill>\n <name>web-search</name>\n <description>This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses a self-hosted SearXNG instance to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.</description>\n <location>~/.openclaw/workspace/skills/web-search/SKILL.md</location>\n <version>sha256:6f4c4e7b17dc89ae</version>\n </skill>\n</available_skills>","systemPromptReport":{"source":"run","generatedAt":1782956498091,"sessionId":"b13ea466-b422-49db-b5b6-b37d089c13ec","sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","provider":"deepseek","model":"deepseek-v4-flash","workspaceDir":"/home/yangxuan/.openclaw/workspace","bootstrapMaxChars":20000,"bootstrapTotalMaxChars":60000,"bootstrapTruncation":{"warningMode":"always","warningShown":false,"truncatedFiles":0,"nearLimitFiles":0,"totalNearLimit":false},"sandbox":{"mode":"off","sandboxed":false},"systemPrompt":{"chars":38066,"hash":"b0c805dd3e9d3a743ba8ebda4437eb1ae6c89d9c272243bdcb08564c7de0bc42","projectContextChars":7598,"nonProjectContextChars":30468},"injectedWorkspaceFiles":[{"name":"AGENTS.md","path":"/home/yangxuan/.openclaw/workspace/AGENTS.md","missing":false,"rawChars":3608,"injectedChars":3608,"truncated":false},{"name":"SOUL.md","path":"/home/yangxuan/.openclaw/workspace/SOUL.md","missing":false,"rawChars":1261,"injectedChars":1261,"truncated":false},{"name":"TOOLS.md","path":"/home/yangxuan/.openclaw/workspace/TOOLS.md","missing":false,"rawChars":160,"injectedChars":160,"truncated":false},{"name":"IDENTITY.md","path":"/home/yangxuan/.openclaw/workspace/IDENTITY.md","missing":false,"rawChars":1125,"injectedChars":1125,"truncated":false},{"name":"USER.md","path":"/home/yangxuan/.openclaw/workspace/USER.md","missing":false,"rawChars":281,"injectedChars":281,"truncated":false},{"name":"HEARTBEAT.md","path":"/home/yangxuan/.openclaw/workspace/HEARTBEAT.md","missing":false,"rawChars":55,"injectedChars":55,"truncated":false},{"name":"MEMORY.md","path":"/home/yangxuan/.openclaw/workspace/MEMORY.md","missing":false,"rawChars":575,"injectedChars":575,"truncated":false}],"skills":{"promptChars":17310,"hash":"bda8af5376e6829c8e83a1d68d8af61b5f30be4eeefb1bb0661c6db84f0d63ff","entries":[{"name":"baidu-text-translate","blockChars":799},{"name":"clawhub","blockChars":355},{"name":"Code","blockChars":300},{"name":"database-admin","blockChars":891},{"name":"database-schema-designer","blockChars":251},{"name":"db-query","blockChars":553},{"name":"db-schema","blockChars":375},{"name":"deep-research-pro","blockChars":336},{"name":"diagram-maker","blockChars":328},{"name":"dingtalk-channel-rules","blockChars":240},{"name":"dingtalk-troubleshoot","blockChars":289},{"name":"docker-essentials","blockChars":311},{"name":"dws","blockChars":379},{"name":"dws-cli","blockChars":323},{"name":"gh-issues","blockChars":351},{"name":"github","blockChars":322},{"name":"healthcheck","blockChars":340},{"name":"humanizer","blockChars":645},{"name":"imap-smtp-email","blockChars":518},{"name":"mcporter","blockChars":359},{"name":"meme-maker","blockChars":313},{"name":"multi-search-engine","blockChars":421},{"name":"MySQL","blockChars":293},{"name":"news-summary","blockChars":403},{"name":"node-connect","blockChars":343},{"name":"node-inspect-debugger","blockChars":339},{"name":"obsidian-official-cli","blockChars":563},{"name":"opencode-controller","blockChars":383},{"name":"openspec","blockChars":557},{"name":"python-debugpy","blockChars":327},{"name":"qiushi-openclaw-skills","blockChars":310},{"name":"requirements-analyst","blockChars":282},{"name":"rss-ai-reader","blockChars":400},{"name":"skill-creator","blockChars":321},{"name":"spike","blockChars":313},{"name":"sql-toolkit","blockChars":430},{"name":"taskflow","blockChars":343},{"name":"taskflow-inbox-triage","blockChars":353},{"name":"tmux","blockChars":331},{"name":"using-superpowers","blockChars":372},{"name":"video-frames","blockChars":258},{"name":"weather","blockChars":249},{"name":"web-search","blockChars":555}]},"tools":{"listChars":0,"schemaChars":22998,"entries":[{"name":"read","summaryChars":298,"summaryHash":"f8a1d7cf1ecfe02b1b5865c93387e6a5891e5079117b4fe18614b6f912521727","schemaChars":304,"schemaHash":"134f19bcabe3e29d63c5cebb38f1d2556759fd08adad6bc90a4b4d3cd1fb8441","propertiesCount":3},{"name":"edit","summaryChars":326,"summaryHash":"c498a85576e187d069e8e8ea4f70f81bddd57829600d385ef61c4359fd634c9e","schemaChars":834,"schemaHash":"457e8bb9f800b21be76c4fd8c0e3078bf07ee9bf93ac82f39944c171bd8f6d84","propertiesCount":2},{"name":"write","summaryChars":127,"summaryHash":"cdb1c46027b22d1f1b923b47bfe297821d9fe589a9f9d92994961948060a4d89","schemaChars":225,"schemaHash":"e98a2484f667cf7c22d76ca103bf2022bf9113dc63fe38b899e71c328cb1e833","propertiesCount":2},{"name":"apply_patch","summaryChars":132,"summaryHash":"432bf38688a4f011d2b765a441ac07e1fdfa9faf2051679adee04abcd9332d93","schemaChars":153,"schemaHash":"05521268363ff4f191472c90d69ef08a503ba9acf1d2febc50b3ee68db32ab65","propertiesCount":1},{"name":"exec","summaryChars":539,"summaryHash":"4825198988fbfa8ebf5c2a8fbe3946da0be639b1e3b737ceaa4364195bba3f04","schemaChars":1283,"schemaHash":"2608ea36cf51376859b7204cda1bf1a2507134eb542097b9e8dbc8af617f216b","propertiesCount":12},{"name":"process","summaryChars":456,"summaryHash":"55297e65d460e0e1e06e7fad4cedb75ffda8fac9fa8b10aa06d6cead3c5a76ea","schemaChars":1074,"schemaHash":"a2d30a25569f409d7e8539844c89a088044535388b24031d014577b96ed27c5c","propertiesCount":12},{"name":"cron","summaryChars":3820,"summaryHash":"d3bc0032e9c0ba71e5983ee4d06bd4b70ea5170dcb5d85fbff1bd71f01b070f4","schemaChars":8415,"schemaHash":"cf77c4202e964d7a3602d9de2cf1f1cd20b4b1c322c40be87bc3eb0328c7cfb8","propertiesCount":15},{"name":"image_generate","summaryChars":468,"summaryHash":"d093313d17509b72795516c6ad7c92a9f1e8c7943239d570fd81347dc2557424","schemaChars":2264,"schemaHash":"1ff0d91a2a16769e27d71721f3307059944254c0567f9db718fe90e1665b088d","propertiesCount":16},{"name":"video_generate","summaryChars":307,"summaryHash":"59fd08c3f2947e0394c7d1aae5219763bf201537bef536228c6c4fd63724e415","schemaChars":2042,"schemaHash":"ec3a2b299579c1c85d5cb3d5b18e1185c6bb62ca128aa508692098174393cb35","propertiesCount":18},{"name":"get_goal","summaryChars":71,"summaryHash":"58dea7906d9e17e5f89a75fea24597ee068d8a56af824370dc27f8501374d6e3","schemaChars":33,"schemaHash":"8243f0af367f188a376f2c17b5eabe872a2f7a979813e0d4e2be6d594c2aa259","propertiesCount":0},{"name":"create_goal","summaryChars":155,"summaryHash":"f01e3a63d673a410ba55213ce6bd3fa2b0d2279e8e780c18aa0cb5aa991b29b3","schemaChars":267,"schemaHash":"27ee794432736471bd76390e236cc7d7e98f8469a02656e7a27109041eea0f8c","propertiesCount":2},{"name":"update_goal","summaryChars":212,"summaryHash":"285201690e5f2456b4cdcd252ff391709b84d69538df61bad694d3c0cfc19958","schemaChars":207,"schemaHash":"c37894492eedfad02f1e7fe1488900765bfe547f3b3f34cefbab4f7f57441c2c","propertiesCount":2},{"name":"skill_workshop","summaryChars":171,"summaryHash":"577c1d2b8f56bf3e9dd5e00463bbce8b8bf4cf201da9b21b588dcaa3bc6ed8cf","schemaChars":2273,"schemaHash":"15481d6889a320a46728ee32304f0a2b510c0bcf77d445052c1ef2fa5dd5368b","propertiesCount":13},{"name":"update_plan","summaryChars":163,"summaryHash":"ea18cc44224e849c68cdf0a4839c295c1b20daf2699e2fc2be4c4e1552327455","schemaChars":489,"schemaHash":"50cb08b8a29e72637eb6720e6f5f3786783824537574f05ee9ae7a5f4ecacc4b","propertiesCount":2},{"name":"sessions_list","summaryChars":135,"summaryHash":"c7e411ae02e3adff5504aaee48f02d262a8abb9152558a3172aae289e3b05faf","schemaChars":435,"schemaHash":"c29c6b82c36a2d95a88c8944f129929b2621ee2af6d17b2ab101d4d7e9633d89","propertiesCount":9},{"name":"sessions_history","summaryChars":117,"summaryHash":"f5d45b76f11a8ac63cc45d456fb6f675f0b1a2e191feb9671924cb5830058f03","schemaChars":162,"schemaHash":"ac33b8af2252262afe479236046f5a04bc018f1fcf24d1a8bf32743f0e867598","propertiesCount":3},{"name":"sessions_send","summaryChars":282,"summaryHash":"061e9ef3487676bb2a4fd4c0336bd973aaab5eea0725e7443c4cb17518cd1e78","schemaChars":275,"schemaHash":"f1fbaa412fe6b6aee102234c87c5aa140f39c9086f9bae6e1e9691309a602ffb","propertiesCount":5},{"name":"sessions_spawn","summaryChars":578,"summaryHash":"c75061234ba01a4eb29ca223c1c63a44935e9e555ef2ca280722ba9e844db86d","schemaChars":1151,"schemaHash":"9a91c7668463da8a66386260ce2ae97e7efe3bb93b9b6f03ac85102c354457e1","propertiesCount":15},{"name":"sessions_yield","summaryChars":79,"summaryHash":"f3782fc41c1522657e1d3494f486a2df998fed38a6b89dcf7f6934fb41424320","schemaChars":60,"schemaHash":"b1c4c753820bc3096d85ef7a266a14c9fbe12450536db58076b75bb61d14dbbb","propertiesCount":1},{"name":"subagents","summaryChars":132,"summaryHash":"1c2ffd38549c0444b118d43736fc4b875ea1aaabc446bbf8bc1fc4ee9180cca4","schemaChars":122,"schemaHash":"c4a241d2c3d46ba7985abfce4d3fcd63298ce81f89d49183c8f3d584c48d0c33","propertiesCount":2},{"name":"session_status","summaryChars":278,"summaryHash":"71177e543dc6235bad4b1a26761995681dcec27ab58dcb4f4f8a7fc9a7b2b5aa","schemaChars":89,"schemaHash":"d2995f3d69d126e98ac93eec3c2a9fe5556925bd7979a8e4b6b5a2bf62d329dd","propertiesCount":2},{"name":"image","summaryChars":119,"summaryHash":"0eae16e4e16f86cc74ea64bdd48812b0a1d86577fee36dc4cf2c6e7974c83ef6","schemaChars":350,"schemaHash":"49bb766071c935edca8c2d0df47fc2109bbffe3d4ba32d0b19fe90ec873736ce","propertiesCount":6},{"name":"memory_search","summaryChars":605,"summaryHash":"0f918d28864d3682ae77731f149273997c84773592a466b18c7cd0121b599a05","schemaChars":250,"schemaHash":"088cd2a3d3a47b251429ff7c56844cdedd1c45c3af0fa8bfaf7aa795766976bf","propertiesCount":4},{"name":"memory_get","summaryChars":239,"summaryHash":"bff1141a3da31a345c550337417efc9ace4da2909004606c727c59ca1a294495","schemaChars":241,"schemaHash":"78f5d58460a82f9104deebad2f1873a8cde05d1ce7328b3ba4da6e994653e70a","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:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","agentId":"main","messageProvider":"openclaw-weixin"}}}
|
||
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"b13ea466-b422-49db-b5b6-b37d089c13ec","source":"runtime","type":"context.compiled","ts":"2026-07-02T01:41:38.123Z","seq":3,"sourceSeq":3,"sessionId":"b13ea466-b422-49db-b5b6-b37d089c13ec","sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","runId":"1cb54571-bcb0-4479-8149-ee319df69c62","workspaceDir":"/home/yangxuan/.openclaw/workspace","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"systemPrompt":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":38066,"limitChars":32768},"prompt":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"message_id\": \"openclaw-weixin:1782956497922-4c934716\",\n \"timestamp\": \"Thu 2026-07-02 09:41:37 GMT+8\"\n}\n```\n\nError: reply session initialization conflicted for agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45\n\n为什么总是冲突","messages":[],"tools":[{"name":"apply_patch","description":"Apply a patch to one or more files using the apply_patch format. The input should include *** Begin Patch and *** End Patch markers.","parameters":{"type":"object","required":["input"],"properties":{"input":{"type":"string","description":"Patch content using the *** Begin Patch/End Patch format."}}}},{"name":"create_goal","description":"Create a goal only when explicitly requested by the user or system instructions. Fails if a goal already exists; use user-facing goal controls to clear it.","parameters":{"type":"object","required":["objective"],"properties":{"objective":{"type":"string","description":"Concrete objective to pursue. Create only when explicitly requested."},"token_budget":{"type":"number","description":"Optional positive token budget for this goal."}}}},{"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: compact job summaries; includeDisabled true includes disabled; use get for full job details; 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: run only if due by default; needs jobId; pass runMode=\"force\" to trigger now\n- runs: run history; needs jobId\n- wake: send wake event; needs text, optional mode; defaults the target to the calling session/agent. Pass top-level sessionKey/agentId to wake a different lane.\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":"integer","minimum":1},"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},"description":"Run mode for action=\"run\": omitted defaults to \"due\"; use \"force\" to trigger now."},"contextMessages":{"type":"integer","minimum":0,"maximum":10},"agentId":{"type":"string","description":"List filter for `action: \"list\"`; wake target override for `action: \"wake\"` (defaults to the calling agent when omitted on wake)"},"sessionKey":{"type":"string","description":"Wake target override for `action: \"wake\"`: route the event to the named session rather than the calling agent's current session. Defaults to the resolved calling-session key when omitted."}},"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":"Baseline ask comes from tools.exec.ask and host approvals; channel-origin calls ignore per-call ask when effective host ask is off."},"node":{"type":"string","description":"Node id/name for host=node."}}}},{"name":"get_goal","description":"Get the current goal for this thread, including status and token usage.","parameters":{"type":"object","properties":{}}},{"name":"image","description":"Analyze images with available vision model. Use image for one path/URL, images for max 20. Prompt says what to inspect.","parameters":{"type":"object","properties":{"prompt":{"type":"string"},"image":{"type":"string","description":"One image path/URL."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Image paths/URLs; maxImages default 20."},"model":{"type":"string"},"maxBytesMb":{"type":"number","exclusiveMinimum":0},"maxImages":{"type":"integer","minimum":1}}}},{"name":"image_generate","description":"Create/edit images. Session chats: background task; do not call image_generate again for same request; wait completion, then report through the current visible-reply contract with generated media attached using structured media fields. Transparent: outputFormat=\"png\" or \"webp\" + background=\"transparent\"; OpenAI also supports openai.background and routes default model to gpt-image-1.5. Use action=\"list\" for providers/models/readiness/auth, \"status\" for active task.","parameters":{"type":"object","properties":{"action":{"type":"string","description":"\"generate\" default, \"status\" active task, \"list\" providers/models."},"prompt":{"type":"string","description":"Image prompt."},"image":{"type":"string","description":"Reference image path/URL for edit."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference images for edit or style reference; max 10."},"model":{"type":"string","description":"Provider/model override, e.g. openai/gpt-image-2; transparent OpenAI: openai/gpt-image-1.5."},"filename":{"type":"string","description":"Output filename hint; basename preserved in managed media dir."},"size":{"type":"string","description":"Size hint: 1024x1024, 1536x1024, 1024x1536, 2048x2048, 3840x2160."},"aspectRatio":{"type":"string","description":"Aspect ratio: 1:1, 2:3, 3:2, 2.35:1, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 4:1, 1:4, 8:1, 1:8."},"resolution":{"type":"string","description":"Resolution: 1K, 2K, 4K; useful for Google."},"quality":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Quality: low, medium, high, auto."},"outputFormat":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Output format: png, jpeg, webp."},"background":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Background: transparent, opaque, auto. Transparent needs png/webp output."},"openai":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"fal":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"count":{"type":"integer","description":"Image count 1-4.","minimum":1,"maximum":4},"timeoutMs":{"type":"integer","description":"Provider timeout ms (300000 tends to be a safe amount).","minimum":1}}}},{"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":"integer","minimum":1},"lines":{"type":"integer","minimum":1},"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":"integer","minimum":1},"minScore":{"type":"number"},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["query"],"additionalProperties":false}},{"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":"integer","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":"integer","minimum":1},"activeMinutes":{"type":"integer","minimum":1},"messageLimit":{"type":"integer","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; sessionKey wins when redundant label metadata is present. 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":"integer","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. Delegate sidecar/parallel tasks: batch file reads, multi-step searches, data collection. Avoid delegating quick lookups or single-file reads unless policy prefers delegation. After spawning, do non-overlapping work while run-mode results return.","parameters":{"type":"object","required":["task"],"properties":{"task":{"type":"string"},"taskName":{"type":"string","description":"Stable alias for later targeting; lowercase letters/digits/underscores/hyphens, 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"},"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":"skill_workshop","description":"Create, update, revise, list, inspect, apply, reject, or quarantine Skill Workshop proposals when reusable procedures should be captured, improved, or explicitly approved.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"create for a new skill proposal, update for an existing skill, revise for a pending proposal, list or inspect proposals for proposal discovery, apply/reject/quarantine for explicit proposal lifecycle actions."},"proposal_id":{"type":"string","description":"Existing proposal id for action=inspect, action=revise, action=apply, action=reject, or action=quarantine."},"name":{"type":"string","description":"Skill/proposal name. Required for action=create; optional resolver for action=inspect or action=revise when proposal_id is unknown."},"query":{"type":"string","description":"Optional query for action=list."},"status":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Optional proposal status filter for action=list."},"limit":{"type":"integer","minimum":1,"maximum":50,"description":"Maximum proposals to return for action=list. Defaults to 20."},"description":{"type":"string","maxLength":160,"description":"Skill description for action=create, action=update, or action=revise. Keep it concise; max 160 bytes."},"skill_name":{"type":"string","description":"Existing skill name or key for action=update."},"proposal_content":{"type":"string","description":"Full proposed procedure markdown for action=create, action=update, or action=revise. It will be stored as PROPOSAL.md. Keep under configured skills.workshop.maxSkillBytes; default max is 40000 bytes."},"support_files":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Optional support files to store with the proposal."},"goal":{"type":"string","description":"Proposal or improvement goal."},"evidence":{"type":"string","description":"Short evidence or notes."},"reason":{"type":"string","description":"Optional reason for action=apply, action=reject, or action=quarantine."}},"additionalProperties":false}},{"name":"subagents","description":"List active and recent subagents for the 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}},"recentMinutes":{"type":"integer","minimum":1}}}},{"name":"update_goal","description":"Mark the current goal complete only when achieved, or blocked only after the same blocking condition recurs for at least three consecutive goal turns. Do not use blocked for ordinary difficulty or missing polish.","parameters":{"type":"object","required":["status"],"properties":{"status":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"complete | blocked."},"note":{"type":"string","description":"Short status note."}}}},{"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":"video_generate","description":"Create videos. Session chats: background task; do not call video_generate again for same request; wait completion, then report through the current visible-reply contract with generated media attached using structured media fields. \"status\" checks active task. Duration may round to provider-supported value.","parameters":{"type":"object","properties":{"action":{"type":"string","description":"\"generate\" default, \"status\" active task, \"list\" providers/models."},"prompt":{"type":"string","description":"Video prompt."},"image":{"type":"string","description":"One reference image path/URL."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference images; max 9."},"imageRoles":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"`image` + `images` roles by index after de-dupe. Values: first_frame, last_frame, reference_image; empty string leaves unset."},"video":{"type":"string","description":"One reference video path/URL."},"videos":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference videos; max 4."},"videoRoles":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"`video` + `videos` roles by index after de-dupe. Value: reference_video; empty string leaves unset."},"model":{"type":"string","description":"Provider/model override, e.g. qwen/wan2.6-t2v."},"filename":{"type":"string","description":"Output filename hint; basename preserved in managed media dir."},"size":{"type":"string","description":"Size hint, e.g. 1280x720, 1920x1080."},"aspectRatio":{"type":"string","description":"Aspect ratio: 1:1, 16:9, 9:16, \"adaptive\", or provider value; unsupported normalized/ignored."},"resolution":{"type":"string","description":"Resolution: 360P, 480P, 540P, 720P, 768P, 1080P, 4K, or provider value; unsupported normalized/ignored."},"durationSeconds":{"type":"integer","description":"Target seconds; may round to nearest supported duration.","minimum":1},"audio":{"type":"boolean","description":"Generated-audio toggle."},"watermark":{"type":"boolean","description":"Watermark toggle."},"providerOptions":{"type":"object","patternProperties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Provider JSON options, e.g. {\"seed\":42}. Keys/types must match provider capabilities; mismatch skips candidate. Use action=list for accepted keys."},"timeoutMs":{"type":"integer","description":"Provider timeout ms.","minimum":1}}}},{"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":"b5b11c85"}}
|
||
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"b13ea466-b422-49db-b5b6-b37d089c13ec","source":"runtime","type":"prompt.submitted","ts":"2026-07-02T01:41:38.127Z","seq":4,"sourceSeq":4,"sessionId":"b13ea466-b422-49db-b5b6-b37d089c13ec","sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","runId":"1cb54571-bcb0-4479-8149-ee319df69c62","workspaceDir":"/home/yangxuan/.openclaw/workspace","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"prompt":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"message_id\": \"openclaw-weixin:1782956497922-4c934716\",\n \"timestamp\": \"Thu 2026-07-02 09:41:37 GMT+8\"\n}\n```\n\nError: reply session initialization conflicted for agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45\n\n为什么总是冲突","systemPrompt":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":38066,"limitChars":32768},"messages":[],"imagesCount":0}}
|
||
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"b13ea466-b422-49db-b5b6-b37d089c13ec","source":"runtime","type":"model.completed","ts":"2026-07-02T01:41:57.562Z","seq":5,"sourceSeq":5,"sessionId":"b13ea466-b422-49db-b5b6-b37d089c13ec","sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","runId":"1cb54571-bcb0-4479-8149-ee319df69c62","workspaceDir":"/home/yangxuan/.openclaw/workspace","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":38946,"output":637,"cacheRead":75520,"total":115103},"promptCache":{"lastCallUsage":{"input":20901,"output":440,"cacheRead":23936,"cacheWrite":0,"total":45277},"lastCacheTouchAt":1782956510153},"compactionCount":0,"assistantTexts":["这个问题我来看看。先查一下相关文档和状态。","看到了。问题的根源很清楚了。\n\n从日志可以看到：\n\n```\nmessage dispatch completed: channel=webchat sessionId=unknown sessionKey=agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45 source=replyResolver outcome=error duration=7ms error=\"Error: reply session initialization conflicted for agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45\"\n```\n\n**核心原因：Dashboard 的回复会话初始化冲突。**\n\n具体来说：\n\n1. **事件顺序**：Gateway 刚启动（1m40s 前），在准备过程中，Dashboard（webchat）向一个会话 `agent:main:dashboard:ef25d1b2...` 发送了消息，但这个会话 ID 已经被另一个初始化过程占用了。\n2. **典型场景**：Gateway 重启时，Dashboard 连接上来，它尝试恢复/初始化一个之前存在的会话，但该会话的初始化锁已经被其他请求（可能是 Tailscale 或其他后台请求）抢先持有，导致冲突。\n3. **跟你的微信消息无关**：这个 `agent:main:dashboard` 是 Dashboard 控制台的会话，不是微信这个会话。你的微信消息正常被处理了（可以看到后面有 `weixin inbound message` 和 `[model-fetch] response` 的处理日志）。\n\n**简单说**：Gateway 刚重启，Dashboard 那边抢会话 ID 冲突了。不影响你这边的使用。\n\n**几种解决方案：**\n\n1️⃣ **马上重启 Gateway**（最直接）：\n```bash\nopenclaw gateway restart\n```\n\n2️⃣ **如果反复出现**，可能是 Dashboard 的持久会话锁没清理干净，可以执行：\n```bash\nopenclaw sessions clear\n# 然后重启\nopenclaw gateway restart\n```\n\n3️⃣ **检查是否有多个 Dashboard 实例**在同时连接（比如浏览器开了多个标签页），这也会导致会话冲突。\n\n你现在正常用就好，这个不影响微信消息收发。如果频繁出现，我再帮你深入排查。"],"finalPromptText":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"message_id\": \"openclaw-weixin:1782956497922-4c934716\",\n \"timestamp\": \"Thu 2026-07-02 09:41:37 GMT+8\"\n}\n```\n\nError: reply session initialization conflicted for agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45\n\n为什么总是冲突","messagesSnapshot":[{"role":"user","content":[{"type":"text","text":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"message_id\": \"openclaw-weixin:1782956497922-4c934716\",\n \"timestamp\": \"Thu 2026-07-02 09:41:37 GMT+8\"\n}\n```\n\nError: reply session initialization conflicted for agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45\n\n为什么总是冲突"}],"timestamp":1782956498127},{"role":"assistant","content":[{"type":"text","text":"这个问题我来看看。先查一下相关文档和状态。"},{"type":"toolCall","id":"call_00_0PTY8eMPEeu9YmDyrqve2139","name":"session_status","arguments":{},"partialArgs":"{}"},{"type":"toolCall","id":"call_01_sRJM326b3THIxUjphvKj9106","name":"exec","arguments":{"command":"openclaw gateway status 2>&1 | head -80"},"partialArgs":"{\"command\": \"openclaw gateway status 2>&1 | head -80\"}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-v4-flash","usage":{"input":16302,"output":80,"cacheRead":6016,"cacheWrite":0,"totalTokens":22398,"cost":{"input":0.016302,"output":0.00015999999999999999,"cacheRead":0,"cacheWrite":0,"total":0.016462}},"stopReason":"toolUse","timestamp":1782956498173,"responseId":"97938c68-7b07-4a91-ab18-05d8eec42170"},{"role":"toolResult","toolCallId":"call_00_0PTY8eMPEeu9YmDyrqve2139","toolName":"session_status","content":[{"type":"text","text":"🦞 OpenClaw 2026.6.11 (e085fa1)\n⏱️ Uptime: gateway 1m 40s · system 23h 2m\n🧠 Model: deepseek/deepseek-v4-flash · 🔑 api-key (models.json)\n🧮 Tokens: 16k in / 80 out · 💵 Cost: $0.02\n🗄️ Cache: 27% hit · 6.0k cached, 0 new\n📚 Context: 22k/1.0m (2%) · 🧹 Compactions: 0\n📊 Usage: Balance ¥78.65\n🧵 Session: agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat • duration 2s • updated just now\n⚙️ Execution: direct · Runtime: OpenClaw Default · Think: off · Fast: off · elevated\n🔌 Plugins: OK\n🪢 Queue: steer (depth 0)\n\nRoute context:\n```json\n{\n \"origin\": {\n \"provider\": \"openclaw-weixin\",\n \"accountId\": \"4a0926e2cb5f-im-bot\"\n },\n \"active\": {\n \"channel\": \"openclaw-weixin\",\n \"to\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"accountId\": \"4a0926e2cb5f-im-bot\"\n },\n \"deliveryContext\": {\n \"channel\": \"openclaw-weixin\",\n \"to\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"accountId\": \"4a0926e2cb5f-im-bot\"\n }\n}\n```"}],"details":{"ok":true,"sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","changedModel":false,"statusText":"🦞 OpenClaw 2026.6.11 (e085fa1)\n⏱️ Uptime: gateway 1m 40s · system 23h 2m\n🧠 Model: deepseek/deepseek-v4-flash · 🔑 api-key (models.json)\n🧮 Tokens: 16k in / 80 out · 💵 Cost: $0.02\n🗄️ Cache: 27% hit · 6.0k cached, 0 new\n📚 Context: 22k/1.0m (2%) · 🧹 Compactions: 0\n📊 Usage: Balance ¥78.65\n🧵 Session: agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat • duration 2s • updated just now\n⚙️ Execution: direct · Runtime: OpenClaw Default · Think: off · Fast: off · elevated\n🔌 Plugins: OK\n🪢 Queue: steer (depth 0)\n\nRoute context:\n```json\n{\n \"origin\": {\n \"provider\": \"openclaw-weixin\",\n \"accountId\": \"4a0926e2cb5f-im-bot\"\n },\n \"active\": {\n \"channel\": \"openclaw-weixin\",\n \"to\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"accountId\": \"4a0926e2cb5f-im-bot\"\n },\n \"deliveryContext\": {\n \"channel\": \"openclaw-weixin\",\n \"to\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"accountId\": \"4a0926e2cb5f-im-bot\"\n }\n}\n```","origin":{"provider":"openclaw-weixin","accountId":"4a0926e2cb5f-im-bot"},"active":{"channel":"openclaw-weixin","to":"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat","accountId":"4a0926e2cb5f-im-bot"},"deliveryContext":{"channel":"openclaw-weixin","to":"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat","accountId":"4a0926e2cb5f-im-bot"}},"isError":false,"timestamp":1782956500791},{"role":"toolResult","toolCallId":"call_01_sRJM326b3THIxUjphvKj9106","toolName":"exec","content":[{"type":"text","text":"Service: systemd user (enabled)\nFile logs: /tmp/openclaw/openclaw-2026-07-02.log\nCommand: /home/yangxuan/.nvm/versions/node/v25.2.0/bin/node /home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/index.js gateway --port 18789\nService file: ~/.config/systemd/user/openclaw-gateway.service\nService env: OPENCLAW_GATEWAY_PORT=18789\n\nService config looks out of date or non-standard.\nService config issue: Gateway service PATH includes version managers or package managers; recommend a minimal PATH. (/home/yangxuan/.nvm/versions/node/v25.2.0/bin, /home/yangxuan/.nvm/current/bin)\nService config issue: Gateway service uses Node from a version manager; it can break after upgrades. (/home/yangxuan/.nvm/versions/node/v25.2.0/bin/node)\nService config issue: System Node 22 LTS (22.19+) or Node 24 not found; install it before migrating away from version managers.\nRecommendation: run \"openclaw doctor\" (or \"openclaw doctor --repair\").\nConfig (cli): ~/.openclaw/openclaw.json\nConfig (service): ~/.openclaw/openclaw.json\n\nGateway: bind=loopback (127.0.0.1), port=18789 (service args)\nProbe target: ws://127.0.0.1:18789\nDashboard: http://127.0.0.1:18789/\nProbe note: Loopback-only gateway; only local clients can connect.\n\nCLI version: 2026.6.11 (~/.nvm/versions/node/v25.2.0/bin/openclaw)\nGateway version: 2026.6.11\n\nRuntime: running (pid 425392, state active, sub running, last exit 0, reason 0)\nConnectivity probe: ok\nCapability: admin-capable\n\nListening: 127.0.0.1:18789, [::1]:18789\nPlugin version drift: 1 active official plugin not on gateway 2026.6.11\nRun openclaw gateway status --deep for affected plugin ids and fix commands.\n\nTroubles: run openclaw status\nTroubleshooting: https://docs.openclaw.ai/troubleshooting"}],"details":{"status":"completed","exitCode":0,"durationMs":622,"aggregated":"Service: systemd user (enabled)\nFile logs: /tmp/openclaw/openclaw-2026-07-02.log\nCommand: /home/yangxuan/.nvm/versions/node/v25.2.0/bin/node /home/yangxuan/.nvm/versions/node/v25.2.0/lib/node_modules/openclaw/dist/index.js gateway --port 18789\nService file: ~/.config/systemd/user/openclaw-gateway.service\nService env: OPENCLAW_GATEWAY_PORT=18789\n\nService config looks out of date or non-standard.\nService config issue: Gateway service PATH includes version managers or package managers; recommend a minimal PATH. (/home/yangxuan/.nvm/versions/node/v25.2.0/bin, /home/yangxuan/.nvm/current/bin)\nService config issue: Gateway service uses Node from a version manager; it can break after upgrades. (/home/yangxuan/.nvm/versions/node/v25.2.0/bin/node)\nService config issue: System Node 22 LTS (22.19+) or Node 24 not found; install it before migrating away from version managers.\nRecommendation: run \"openclaw doctor\" (or \"openclaw doctor --repair\").\nConfig (cli): ~/.openclaw/openclaw.json\nConfig (service): ~/.openclaw/openclaw.json\n\nGateway: bind=loopback (127.0.0.1), port=18789 (service args)\nProbe target: ws://127.0.0.1:18789\nDashboard: http://127.0.0.1:18789/\nProbe note: Loopback-only gateway; only local clients can connect.\n\nCLI version: 2026.6.11 (~/.nvm/versions/node/v25.2.0/bin/openclaw)\nGateway version: 2026.6.11\n\nRuntime: running (pid 425392, state active, sub running, last exit 0, reason 0)\nConnectivity probe: ok\nCapability: admin-capable\n\nListening: 127.0.0.1:18789, [::1]:18789\nPlugin version drift: 1 active official plugin not on gateway 2026.6.11\nRun openclaw gateway status --deep for affected plugin ids and fix commands.\n\nTroubles: run openclaw status\nTroubleshooting: https://docs.openclaw.ai/troubleshooting","cwd":"/home/yangxuan/.openclaw/workspace"},"isError":false,"timestamp":1782956500793},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_65NzIi16h9LJogjbWOCb4617","name":"exec","arguments":{"command":"openclaw doctor 2>&1 | tail -40"},"partialArgs":"{\"command\": \"openclaw doctor 2>&1 | tail -40\"}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-v4-flash","usage":{"input":1090,"output":53,"cacheRead":22272,"cacheWrite":0,"totalTokens":23415,"cost":{"input":0.00109,"output":0.000106,"cacheRead":0,"cacheWrite":0,"total":0.001196}},"stopReason":"toolUse","timestamp":1782956500796,"responseId":"242875a6-ffed-49ec-8c3f-5e5352cd87ed"},{"role":"toolResult","toolCallId":"call_00_65NzIi16h9LJogjbWOCb4617","toolName":"exec","content":[{"type":"text","text":"│ │\n├───────────────────────────╯\n│\n◇ Plugins ──────╮\n│ │\n│ Loaded: 6 │\n│ Imported: 0 │\n│ Disabled: 63 │\n│ Errors: 0 │\n│ │\n├────────────────╯\n│\n◇ Plugin version drift ──────────────────────────────────────────────────╮\n│ │\n│ 1 active official plugin not on OpenClaw 2026.6.11 │\n│ - deepseek: 2026.6.9 (npm) -> expected 2026.6.11 │\n│ Fix: openclaw plugins update @openclaw/deepseek-provider@2026.6.11 && │\n│ openclaw gateway restart. │\n│ │\n├─────────────────────────────────────────────────────────────────────────╯\n│\n◇ TaskFlow recovery ─────────────────────────────────────────────────╮\n│ │\n│ 58d5a856-3a9c-4e15-8b95-12dca881409b: blocked TaskFlow points at │\n│ missing task 19d57711-39e3-43b2-91d8-3827b9b15f30; inspect before │\n│ retrying. │\n│ 92573f27-33f0-4360-be35-19b656065eb7: blocked TaskFlow points at │\n│ missing task 4077f526-b2dd-4ca5-ac55-1e92ebb8ad54; inspect before │\n│ retrying. │\n│ 8ccbe38d-68d0-424a-8efd-7320b4f995fe: blocked TaskFlow points at │\n│ missing task c9063a77-9e20-4320-826e-c31c05d7df27; inspect before │\n│ retrying. │\n│ Inspect: openclaw tasks flow show <flow-id> │\n│ Cancel: openclaw tasks flow cancel <flow-id> │\n│ │\n├─────────────────────────────────────────────────────────────────────╯\nRun \"openclaw doctor --fix\" to apply changes.\n│\n└ Doctor complete."}],"details":{"status":"completed","exitCode":0,"durationMs":6945,"aggregated":"│ │\n├───────────────────────────╯\n│\n◇ Plugins ──────╮\n│ │\n│ Loaded: 6 │\n│ Imported: 0 │\n│ Disabled: 63 │\n│ Errors: 0 │\n│ │\n├────────────────╯\n│\n◇ Plugin version drift ──────────────────────────────────────────────────╮\n│ │\n│ 1 active official plugin not on OpenClaw 2026.6.11 │\n│ - deepseek: 2026.6.9 (npm) -> expected 2026.6.11 │\n│ Fix: openclaw plugins update @openclaw/deepseek-provider@2026.6.11 && │\n│ openclaw gateway restart. │\n│ │\n├─────────────────────────────────────────────────────────────────────────╯\n│\n◇ TaskFlow recovery ─────────────────────────────────────────────────╮\n│ │\n│ 58d5a856-3a9c-4e15-8b95-12dca881409b: blocked TaskFlow points at │\n│ missing task 19d57711-39e3-43b2-91d8-3827b9b15f30; inspect before │\n│ retrying. │\n│ 92573f27-33f0-4360-be35-19b656065eb7: blocked TaskFlow points at │\n│ missing task 4077f526-b2dd-4ca5-ac55-1e92ebb8ad54; inspect before │\n│ retrying. │\n│ 8ccbe38d-68d0-424a-8efd-7320b4f995fe: blocked TaskFlow points at │\n│ missing task c9063a77-9e20-4320-826e-c31c05d7df27; inspect before │\n│ retrying. │\n│ Inspect: openclaw tasks flow show <flow-id> │\n│ Cancel: openclaw tasks flow cancel <flow-id> │\n│ │\n├─────────────────────────────────────────────────────────────────────╯\nRun \"openclaw doctor --fix\" to apply changes.\n│\n└ Doctor complete.","cwd":"/home/yangxuan/.openclaw/workspace"},"isError":false,"timestamp":1782956508795},{"role":"assistant","content":[{"type":"toolCall","id":"call_00_Sp0V4e6pl1sDsdI6GjRx1341","name":"exec","arguments":{"command":"tail -50 /tmp/openclaw/openclaw-2026-07-02.log 2>&1"},"partialArgs":"{\"command\": \"tail -50 /tmp/openclaw/openclaw-2026-07-02.log 2>&1\"}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-v4-flash","usage":{"input":653,"output":64,"cacheRead":23296,"cacheWrite":0,"totalTokens":24013,"cost":{"input":0.0006529999999999999,"output":0.000128,"cacheRead":0,"cacheWrite":0,"total":0.0007809999999999999}},"stopReason":"toolUse","timestamp":1782956508800,"responseId":"c64654c7-72f3-4152-b34f-df55c1d34b19"},{"role":"toolResult","toolCallId":"call_00_Sp0V4e6pl1sDsdI6GjRx1341","toolName":"exec","content":[{"type":"text","text":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":55995,"limitChars":32768}}],"details":{"status":"completed","exitCode":0,"durationMs":30,"aggregated":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":55995,"limitChars":32768},"cwd":"/home/yangxuan/.openclaw/workspace"},"isError":false,"timestamp":1782956510145},{"role":"assistant","content":[{"type":"text","text":"看到了。问题的根源很清楚了。\n\n从日志可以看到：\n\n```\nmessage dispatch completed: channel=webchat sessionId=unknown sessionKey=agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45 source=replyResolver outcome=error duration=7ms error=\"Error: reply session initialization conflicted for agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45\"\n```\n\n**核心原因：Dashboard 的回复会话初始化冲突。**\n\n具体来说：\n\n1. **事件顺序**：Gateway 刚启动（1m40s 前），在准备过程中，Dashboard（webchat）向一个会话 `agent:main:dashboard:ef25d1b2...` 发送了消息，但这个会话 ID 已经被另一个初始化过程占用了。\n2. **典型场景**：Gateway 重启时，Dashboard 连接上来，它尝试恢复/初始化一个之前存在的会话，但该会话的初始化锁已经被其他请求（可能是 Tailscale 或其他后台请求）抢先持有，导致冲突。\n3. **跟你的微信消息无关**：这个 `agent:main:dashboard` 是 Dashboard 控制台的会话，不是微信这个会话。你的微信消息正常被处理了（可以看到后面有 `weixin inbound message` 和 `[model-fetch] response` 的处理日志）。\n\n**简单说**：Gateway 刚重启，Dashboard 那边抢会话 ID 冲突了。不影响你这边的使用。\n\n**几种解决方案：**\n\n1️⃣ **马上重启 Gateway**（最直接）：\n```bash\nopenclaw gateway restart\n```\n\n2️⃣ **如果反复出现**，可能是 Dashboard 的持久会话锁没清理干净，可以执行：\n```bash\nopenclaw sessions clear\n# 然后重启\nopenclaw gateway restart\n```\n\n3️⃣ **检查是否有多个 Dashboard 实例**在同时连接（比如浏览器开了多个标签页），这也会导致会话冲突。\n\n你现在正常用就好，这个不影响微信消息收发。如果频繁出现，我再帮你深入排查。"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-v4-flash","usage":{"input":20901,"output":440,"cacheRead":23936,"cacheWrite":0,"totalTokens":45277,"cost":{"input":0.020901,"output":0.0008799999999999999,"cacheRead":0,"cacheWrite":0,"total":0.021781}},"stopReason":"stop","timestamp":1782956510153,"responseId":"b1d0bb83-da20-450f-979d-fc283adf0403"}]}}
|
||
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"b13ea466-b422-49db-b5b6-b37d089c13ec","source":"runtime","type":"trace.artifacts","ts":"2026-07-02T01:41:57.564Z","seq":6,"sourceSeq":6,"sessionId":"b13ea466-b422-49db-b5b6-b37d089c13ec","sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","runId":"1cb54571-bcb0-4479-8149-ee319df69c62","workspaceDir":"/home/yangxuan/.openclaw/workspace","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"capturedAt":"2026-07-02T01:41:57.564Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":38946,"output":637,"cacheRead":75520,"total":115103},"promptCache":{"lastCallUsage":{"input":20901,"output":440,"cacheRead":23936,"cacheWrite":0,"total":45277},"lastCacheTouchAt":1782956510153},"compactionCount":0,"assistantTexts":["这个问题我来看看。先查一下相关文档和状态。","看到了。问题的根源很清楚了。\n\n从日志可以看到：\n\n```\nmessage dispatch completed: channel=webchat sessionId=unknown sessionKey=agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45 source=replyResolver outcome=error duration=7ms error=\"Error: reply session initialization conflicted for agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45\"\n```\n\n**核心原因：Dashboard 的回复会话初始化冲突。**\n\n具体来说：\n\n1. **事件顺序**：Gateway 刚启动（1m40s 前），在准备过程中，Dashboard（webchat）向一个会话 `agent:main:dashboard:ef25d1b2...` 发送了消息，但这个会话 ID 已经被另一个初始化过程占用了。\n2. **典型场景**：Gateway 重启时，Dashboard 连接上来，它尝试恢复/初始化一个之前存在的会话，但该会话的初始化锁已经被其他请求（可能是 Tailscale 或其他后台请求）抢先持有，导致冲突。\n3. **跟你的微信消息无关**：这个 `agent:main:dashboard` 是 Dashboard 控制台的会话，不是微信这个会话。你的微信消息正常被处理了（可以看到后面有 `weixin inbound message` 和 `[model-fetch] response` 的处理日志）。\n\n**简单说**：Gateway 刚重启，Dashboard 那边抢会话 ID 冲突了。不影响你这边的使用。\n\n**几种解决方案：**\n\n1️⃣ **马上重启 Gateway**（最直接）：\n```bash\nopenclaw gateway restart\n```\n\n2️⃣ **如果反复出现**，可能是 Dashboard 的持久会话锁没清理干净，可以执行：\n```bash\nopenclaw sessions clear\n# 然后重启\nopenclaw gateway restart\n```\n\n3️⃣ **检查是否有多个 Dashboard 实例**在同时连接（比如浏览器开了多个标签页），这也会导致会话冲突。\n\n你现在正常用就好，这个不影响微信消息收发。如果频繁出现，我再帮你深入排查。"],"finalPromptText":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"o9cq80w6ZnnPGItW-GGACkwd69bA@im.wechat\",\n \"message_id\": \"openclaw-weixin:1782956497922-4c934716\",\n \"timestamp\": \"Thu 2026-07-02 09:41:37 GMT+8\"\n}\n```\n\nError: reply session initialization conflicted for agent:main:dashboard:ef25d1b2-d890-4151-bcd1-a9410a3f5c45\n\n为什么总是冲突","itemLifecycle":{"startedCount":7,"completedCount":7,"activeCount":0},"toolMetas":[{"toolName":"session_status","replaySafe":true},{"toolName":"exec","meta":"run openclaw gateway -> show first 80 lines","replaySafe":false},{"toolName":"exec","meta":"run openclaw doctor -> show last 40 lines","replaySafe":false},{"toolName":"exec","meta":"show last 50 lines of 2>&1","replaySafe":false}],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[]}}
|
||
{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"b13ea466-b422-49db-b5b6-b37d089c13ec","source":"runtime","type":"session.ended","ts":"2026-07-02T01:41:57.564Z","seq":7,"sourceSeq":7,"sessionId":"b13ea466-b422-49db-b5b6-b37d089c13ec","sessionKey":"agent:main:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","runId":"1cb54571-bcb0-4479-8149-ee319df69c62","workspaceDir":"/home/yangxuan/.openclaw/workspace","provider":"deepseek","modelId":"deepseek-v4-flash","modelApi":"openai-completions","data":{"status":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false}}
|