[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-langchain-langsmith-trace":3,"mdc--ycnv4u-key":33,"related-org-langchain-langsmith-trace":1838,"related-repo-langchain-langsmith-trace":2019},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":31,"mdContent":32},"langsmith-trace","add tracing and query LangSmith traces","INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying\u002Fexporting trace data. Uses the langsmith CLI tool.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"langchain","LangChain","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Flangchain.png","langchain-ai",[13,17,20],{"name":14,"slug":15,"type":16},"Tracing","tracing","tag",{"name":18,"slug":19,"type":16},"Observability","observability",{"name":21,"slug":22,"type":16},"LangSmith","langsmith",139,"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangsmith-skills","2026-04-11T04:40:29.299419",null,17,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":26},[],"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangsmith-skills\u002Ftree\u002FHEAD\u002Fconfig\u002Fskills\u002Flangsmith-trace","---\nname: langsmith-trace\ndescription: \"INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying\u002Fexporting trace data. Uses the langsmith CLI tool.\"\n---\n\n\u003Coneliner>\nTwo main topics: **adding tracing** to your application, and **querying traces** for debugging and analysis. Python and Javascript implementations are both supported.\n\u003C\u002Foneliner>\n\n\u003Csetup>\nEnvironment Variables\n\n```bash\nLANGSMITH_API_KEY=lsv2_pt_your_api_key_here          # REQUIRED\nLANGSMITH_PROJECT=your-project-name                   # Optional: default project\nLANGSMITH_WORKSPACE_ID=your-workspace-id              # Optional: for org-scoped keys\n```\n\nAuthentication is REQUIRED: either set the `LANGSMITH_API_KEY` environment variable, or pass the `--api-key` flag to CLI commands (preferred):\n```bash\nlangsmith trace list --project my-project --api-key $LANGSMITH_API_KEY\n```\n\n**IMPORTANT:** Always check the environment variables or `.env` file for `LANGSMITH_PROJECT` before querying or interacting with LangSmith. This tells you which project contains the relevant traces and data. If the LangSmith project is not available, use your best judgement to identify the right one.\n\nCLI Tool\n```bash\ncurl -sSL https:\u002F\u002Fraw.githubusercontent.com\u002Flangchain-ai\u002Flangsmith-cli\u002Fmain\u002Fscripts\u002Finstall.sh | sh\n```\n\u003C\u002Fsetup>\n\n\u003Ctrace_langchain_oss>\nFor LangChain\u002FLangGraph apps, tracing is automatic. Just set environment variables:\n\n```bash\nexport LANGSMITH_TRACING=true\nexport LANGSMITH_API_KEY=\u003Cyour-api-key>\nexport OPENAI_API_KEY=\u003Cyour-openai-api-key>  # or your LLM provider's key\n```\n\nOptional variables:\n- `LANGSMITH_PROJECT` - specify project name (defaults to \"default\")\n- `LANGCHAIN_CALLBACKS_BACKGROUND=false` - use for serverless to ensure traces complete before function exit (Python)\n\u003C\u002Ftrace_langchain_oss>\n\n\u003Ctrace_other_frameworks>\nFor non-LangChain apps, if the framework has native OpenTelemetry support, use LangSmith's OpenTelemetry integration.\n\nIf the app is NOT using a framework, or using one without automatic OTel support, use the traceable decorator\u002Fwrapper and wrap your LLM client.\n\n\u003Cpython>\nUse @traceable decorator and wrap_openai() for automatic tracing.\n```python\nfrom langsmith import traceable\nfrom langsmith.wrappers import wrap_openai\nfrom openai import OpenAI\n\nclient = wrap_openai(OpenAI())\n\n@traceable\ndef my_llm_pipeline(question: str) -> str:\n    resp = client.chat.completions.create(\n        model=\"gpt-4o-mini\",\n        messages=[{\"role\": \"user\", \"content\": question}],\n    )\n    return resp.choices[0].message.content\n\n# Nested tracing example\n@traceable\ndef rag_pipeline(question: str) -> str:\n    docs = retrieve_docs(question)\n    return generate_answer(question, docs)\n\n@traceable(name=\"retrieve_docs\")\ndef retrieve_docs(query: str) -> list[str]:\n    return docs\n\n@traceable(name=\"generate_answer\")\ndef generate_answer(question: str, docs: list[str]) -> str:\n    return client.chat.completions.create(...)\n```\n\u003C\u002Fpython>\n\n\u003Ctypescript>\nUse traceable() wrapper and wrapOpenAI() for automatic tracing.\n```typescript\nimport { traceable } from \"langsmith\u002Ftraceable\";\nimport { wrapOpenAI } from \"langsmith\u002Fwrappers\";\nimport OpenAI from \"openai\";\n\nconst client = wrapOpenAI(new OpenAI());\n\nconst myLlmPipeline = traceable(async (question: string): Promise\u003Cstring> => {\n  const resp = await client.chat.completions.create({\n    model: \"gpt-4o-mini\",\n    messages: [{ role: \"user\", content: question }],\n  });\n  return resp.choices[0].message.content || \"\";\n}, { name: \"my_llm_pipeline\" });\n\n\u002F\u002F Nested tracing example\nconst retrieveDocs = traceable(async (query: string): Promise\u003Cstring[]> => {\n  return docs;\n}, { name: \"retrieve_docs\" });\n\nconst generateAnswer = traceable(async (question: string, docs: string[]): Promise\u003Cstring> => {\n  const resp = await client.chat.completions.create({\n    model: \"gpt-4o-mini\",\n    messages: [{ role: \"user\", content: `${question}\\nContext: ${docs.join(\"\\n\")}` }],\n  });\n  return resp.choices[0].message.content || \"\";\n}, { name: \"generate_answer\" });\n\nconst ragPipeline = traceable(async (question: string): Promise\u003Cstring> => {\n  const docs = await retrieveDocs(question);\n  return await generateAnswer(question, docs);\n}, { name: \"rag_pipeline\" });\n```\n\u003C\u002Ftypescript>\n\nBest Practices:\n- **Apply traceable to all nested functions** you want visible in LangSmith\n- **Wrapped clients auto-trace all calls** — `wrap_openai()`\u002F`wrapOpenAI()` records every LLM call\n- **Name your traces** for easier filtering\n- **Add metadata** for searchability\n\u003C\u002Ftrace_other_frameworks>\n\n\u003Ctraces_vs_runs>\nUse the `langsmith` CLI to query trace data.\n\n**Understanding the difference is critical:**\n\n- **Trace** = A complete execution tree (root run + all child runs). A trace represents one full agent invocation with all its LLM calls, tool calls, and nested operations.\n- **Run** = A single node in the tree (one LLM call, one tool call, etc.)\n\n**Generally, query traces first** — they provide complete context and preserve hierarchy needed for trajectory analysis and dataset generation.\n\u003C\u002Ftraces_vs_runs>\n\n\u003Ccommand_structure>\nTwo command groups with consistent behavior:\n\n```\nlangsmith\n├── trace (operations on trace trees - USE THIS FIRST)\n│   ├── list    - List traces (filters apply to root run)\n│   ├── get     - Get single trace with full hierarchy\n│   └── export  - Export traces to JSONL files (one file per trace)\n│\n├── run (operations on individual runs - for specific analysis)\n│   ├── list    - List runs (flat, filters apply to any run)\n│   ├── get     - Get single run\n│   └── export  - Export runs to single JSONL file (flat)\n│\n├── dataset (dataset operations)\n│   ├── list    - List datasets\n│   ├── get     - Get dataset details\n│   ├── create  - Create empty dataset\n│   ├── delete  - Delete dataset\n│   ├── export  - Export dataset to file\n│   └── upload  - Upload local JSON as dataset\n│\n├── example (example operations)\n│   ├── list    - List examples in a dataset\n│   ├── create  - Add example to a dataset\n│   └── delete  - Delete an example\n│\n├── evaluator (evaluator operations)\n│   ├── list    - List evaluators\n│   ├── upload  - Upload evaluator\n│   └── delete  - Delete evaluator\n│\n├── experiment (experiment operations)\n│   ├── list    - List experiments\n│   └── get     - Get experiment results\n│\n├── thread (thread operations)\n│   ├── list    - List conversation threads\n│   └── get     - Get thread details\n│\n└── project (project operations)\n    └── list    - List tracing projects\n```\n\n**Key differences:**\n\n| | `traces *` | `runs *` |\n|---|---|---|\n| Filters apply to | Root run only | Any matching run |\n| `--run-type` | Not available | Available |\n| Returns | Full hierarchy | Flat list |\n| Export output | Directory (one file\u002Ftrace) | Single file |\n\u003C\u002Fcommand_structure>\n\n\u003Cquerying_traces>\nQuery traces using the `langsmith` CLI. Commands are language-agnostic.\n\n```bash\n# List recent traces (most common operation)\nlangsmith trace list --limit 10 --project my-project --api-key $LANGSMITH_API_KEY\n\n# List traces with metadata (timing, tokens, costs)\nlangsmith trace list --limit 10 --include-metadata --api-key $LANGSMITH_API_KEY\n\n# Filter traces by time\nlangsmith trace list --last-n-minutes 60 --api-key $LANGSMITH_API_KEY\nlangsmith trace list --since 2025-01-20T10:00:00Z --api-key $LANGSMITH_API_KEY\n\n# Get specific trace with full hierarchy\nlangsmith trace get \u003Ctrace-id> --api-key $LANGSMITH_API_KEY\n\n# List traces and show hierarchy inline\nlangsmith trace list --limit 5 --show-hierarchy --api-key $LANGSMITH_API_KEY\n\n# Export traces to JSONL (one file per trace, includes all runs)\nlangsmith trace export .\u002Ftraces --limit 20 --full --api-key $LANGSMITH_API_KEY\n\n# Filter traces by performance\nlangsmith trace list --min-latency 5.0 --limit 10 --api-key $LANGSMITH_API_KEY    # Slow traces (>= 5s)\nlangsmith trace list --error --last-n-minutes 60 --api-key $LANGSMITH_API_KEY     # Failed traces\n\n# List specific run types (flat list)\nlangsmith run list --run-type llm --limit 20 --api-key $LANGSMITH_API_KEY\n```\n\u003C\u002Fquerying_traces>\n\n\u003Cfilters>\nAll commands support these filters (all AND together):\n\n**Basic filters:**\n- `--trace-ids abc,def` - Filter to specific traces\n- `--limit N` - Max results\n- `--project NAME` - Project name\n- `--last-n-minutes N` - Time filter\n- `--since TIMESTAMP` - Time filter (ISO format)\n- `--error \u002F --no-error` - Error status\n- `--name PATTERN` - Name contains (case-insensitive)\n\n**Performance filters:**\n- `--min-latency SECONDS` - Minimum latency (e.g., `5` for >= 5s)\n- `--max-latency SECONDS` - Maximum latency\n- `--min-tokens N` - Minimum total tokens\n- `--tags tag1,tag2` - Has any of these tags\n\n**Advanced filter:**\n- `--filter QUERY` - Raw LangSmith filter query for complex cases (feedback, metadata, etc.)\n\n```bash\n# Filter traces by feedback score using raw LangSmith query\nlangsmith trace list --filter 'and(eq(feedback_key, \"correctness\"), gte(feedback_score, 0.8))' --api-key $LANGSMITH_API_KEY\n```\n\u003C\u002Ffilters>\n\n\u003Cexport_format>\nExport creates `.jsonl` files (one run per line) with these fields:\n```json\n{\"run_id\": \"...\", \"trace_id\": \"...\", \"name\": \"...\", \"run_type\": \"...\", \"parent_run_id\": \"...\", \"inputs\": {...}, \"outputs\": {...}}\n```\n\nUse `--include-io` or `--full` to include inputs\u002Foutputs (required for dataset generation).\n\u003C\u002Fexport_format>\n\n\u003Ctips>\n- **Start with traces** — they provide complete context needed for trajectory and dataset generation\n- Use `traces export --full` for bulk data destined for datasets\n- Always specify `--project` to avoid mixing data from different projects\n- Use `\u002Ftmp` for temporary exports\n- Include `--include-metadata` for performance\u002Fcost analysis\n- Stitch files: `cat .\u002Ftraces\u002F*.jsonl > all.jsonl`\n\u003C\u002Ftips>\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,46,272,277,365,370,396,401,406,1832],{"type":39,"tag":40,"props":41,"children":42},"element","oneliner",{},[43],{"type":44,"value":45},"text","\nTwo main topics: **adding tracing** to your application, and **querying traces** for debugging and analysis. Python and Javascript implementations are both supported.\n",{"type":39,"tag":47,"props":48,"children":49},"setup",{},[50,52,140,161,206,232,237],{"type":44,"value":51},"\nEnvironment Variables\n",{"type":39,"tag":53,"props":54,"children":59},"pre",{"className":55,"code":56,"language":57,"meta":58,"style":58},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","LANGSMITH_API_KEY=lsv2_pt_your_api_key_here          # REQUIRED\nLANGSMITH_PROJECT=your-project-name                   # Optional: default project\nLANGSMITH_WORKSPACE_ID=your-workspace-id              # Optional: for org-scoped keys\n","bash","",[60],{"type":39,"tag":61,"props":62,"children":63},"code",{"__ignoreMap":58},[64,94,117],{"type":39,"tag":65,"props":66,"children":69},"span",{"class":67,"line":68},"line",1,[70,76,82,88],{"type":39,"tag":65,"props":71,"children":73},{"style":72},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[74],{"type":44,"value":75},"LANGSMITH_API_KEY",{"type":39,"tag":65,"props":77,"children":79},{"style":78},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[80],{"type":44,"value":81},"=",{"type":39,"tag":65,"props":83,"children":85},{"style":84},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[86],{"type":44,"value":87},"lsv2_pt_your_api_key_here",{"type":39,"tag":65,"props":89,"children":91},{"style":90},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[92],{"type":44,"value":93},"          # REQUIRED\n",{"type":39,"tag":65,"props":95,"children":97},{"class":67,"line":96},2,[98,103,107,112],{"type":39,"tag":65,"props":99,"children":100},{"style":72},[101],{"type":44,"value":102},"LANGSMITH_PROJECT",{"type":39,"tag":65,"props":104,"children":105},{"style":78},[106],{"type":44,"value":81},{"type":39,"tag":65,"props":108,"children":109},{"style":84},[110],{"type":44,"value":111},"your-project-name",{"type":39,"tag":65,"props":113,"children":114},{"style":90},[115],{"type":44,"value":116},"                   # Optional: default project\n",{"type":39,"tag":65,"props":118,"children":120},{"class":67,"line":119},3,[121,126,130,135],{"type":39,"tag":65,"props":122,"children":123},{"style":72},[124],{"type":44,"value":125},"LANGSMITH_WORKSPACE_ID",{"type":39,"tag":65,"props":127,"children":128},{"style":78},[129],{"type":44,"value":81},{"type":39,"tag":65,"props":131,"children":132},{"style":84},[133],{"type":44,"value":134},"your-workspace-id",{"type":39,"tag":65,"props":136,"children":137},{"style":90},[138],{"type":44,"value":139},"              # Optional: for org-scoped keys\n",{"type":39,"tag":141,"props":142,"children":143},"p",{},[144,146,151,153,159],{"type":44,"value":145},"Authentication is REQUIRED: either set the ",{"type":39,"tag":61,"props":147,"children":149},{"className":148},[],[150],{"type":44,"value":75},{"type":44,"value":152}," environment variable, or pass the ",{"type":39,"tag":61,"props":154,"children":156},{"className":155},[],[157],{"type":44,"value":158},"--api-key",{"type":44,"value":160}," flag to CLI commands (preferred):",{"type":39,"tag":53,"props":162,"children":164},{"className":55,"code":163,"language":57,"meta":58,"style":58},"langsmith trace list --project my-project --api-key $LANGSMITH_API_KEY\n",[165],{"type":39,"tag":61,"props":166,"children":167},{"__ignoreMap":58},[168],{"type":39,"tag":65,"props":169,"children":170},{"class":67,"line":68},[171,176,181,186,191,196,201],{"type":39,"tag":65,"props":172,"children":174},{"style":173},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[175],{"type":44,"value":22},{"type":39,"tag":65,"props":177,"children":178},{"style":84},[179],{"type":44,"value":180}," trace",{"type":39,"tag":65,"props":182,"children":183},{"style":84},[184],{"type":44,"value":185}," list",{"type":39,"tag":65,"props":187,"children":188},{"style":84},[189],{"type":44,"value":190}," --project",{"type":39,"tag":65,"props":192,"children":193},{"style":84},[194],{"type":44,"value":195}," my-project",{"type":39,"tag":65,"props":197,"children":198},{"style":84},[199],{"type":44,"value":200}," --api-key",{"type":39,"tag":65,"props":202,"children":203},{"style":72},[204],{"type":44,"value":205}," $LANGSMITH_API_KEY\n",{"type":39,"tag":141,"props":207,"children":208},{},[209,215,217,223,225,230],{"type":39,"tag":210,"props":211,"children":212},"strong",{},[213],{"type":44,"value":214},"IMPORTANT:",{"type":44,"value":216}," Always check the environment variables or ",{"type":39,"tag":61,"props":218,"children":220},{"className":219},[],[221],{"type":44,"value":222},".env",{"type":44,"value":224}," file for ",{"type":39,"tag":61,"props":226,"children":228},{"className":227},[],[229],{"type":44,"value":102},{"type":44,"value":231}," before querying or interacting with LangSmith. This tells you which project contains the relevant traces and data. If the LangSmith project is not available, use your best judgement to identify the right one.",{"type":39,"tag":141,"props":233,"children":234},{},[235],{"type":44,"value":236},"CLI Tool",{"type":39,"tag":53,"props":238,"children":240},{"className":55,"code":239,"language":57,"meta":58,"style":58},"curl -sSL https:\u002F\u002Fraw.githubusercontent.com\u002Flangchain-ai\u002Flangsmith-cli\u002Fmain\u002Fscripts\u002Finstall.sh | sh\n",[241],{"type":39,"tag":61,"props":242,"children":243},{"__ignoreMap":58},[244],{"type":39,"tag":65,"props":245,"children":246},{"class":67,"line":68},[247,252,257,262,267],{"type":39,"tag":65,"props":248,"children":249},{"style":173},[250],{"type":44,"value":251},"curl",{"type":39,"tag":65,"props":253,"children":254},{"style":84},[255],{"type":44,"value":256}," -sSL",{"type":39,"tag":65,"props":258,"children":259},{"style":84},[260],{"type":44,"value":261}," https:\u002F\u002Fraw.githubusercontent.com\u002Flangchain-ai\u002Flangsmith-cli\u002Fmain\u002Fscripts\u002Finstall.sh",{"type":39,"tag":65,"props":263,"children":264},{"style":78},[265],{"type":44,"value":266}," |",{"type":39,"tag":65,"props":268,"children":269},{"style":173},[270],{"type":44,"value":271}," sh\n",{"type":39,"tag":141,"props":273,"children":274},{},[275],{"type":44,"value":276},"\u003Ctrace_langchain_oss>\nFor LangChain\u002FLangGraph apps, tracing is automatic. Just set environment variables:",{"type":39,"tag":53,"props":278,"children":280},{"className":55,"code":279,"language":57,"meta":58,"style":58},"export LANGSMITH_TRACING=true\nexport LANGSMITH_API_KEY=\u003Cyour-api-key>\nexport OPENAI_API_KEY=\u003Cyour-openai-api-key>  # or your LLM provider's key\n",[281],{"type":39,"tag":61,"props":282,"children":283},{"__ignoreMap":58},[284,307,334],{"type":39,"tag":65,"props":285,"children":286},{"class":67,"line":68},[287,293,298,302],{"type":39,"tag":65,"props":288,"children":290},{"style":289},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[291],{"type":44,"value":292},"export",{"type":39,"tag":65,"props":294,"children":295},{"style":72},[296],{"type":44,"value":297}," LANGSMITH_TRACING",{"type":39,"tag":65,"props":299,"children":300},{"style":78},[301],{"type":44,"value":81},{"type":39,"tag":65,"props":303,"children":304},{"style":72},[305],{"type":44,"value":306},"true\n",{"type":39,"tag":65,"props":308,"children":309},{"class":67,"line":96},[310,314,319,324,329],{"type":39,"tag":65,"props":311,"children":312},{"style":289},[313],{"type":44,"value":292},{"type":39,"tag":65,"props":315,"children":316},{"style":72},[317],{"type":44,"value":318}," LANGSMITH_API_KEY",{"type":39,"tag":65,"props":320,"children":321},{"style":78},[322],{"type":44,"value":323},"=\u003C",{"type":39,"tag":65,"props":325,"children":326},{"style":72},[327],{"type":44,"value":328},"your-api-key",{"type":39,"tag":65,"props":330,"children":331},{"style":78},[332],{"type":44,"value":333},">\n",{"type":39,"tag":65,"props":335,"children":336},{"class":67,"line":119},[337,341,346,350,355,360],{"type":39,"tag":65,"props":338,"children":339},{"style":289},[340],{"type":44,"value":292},{"type":39,"tag":65,"props":342,"children":343},{"style":72},[344],{"type":44,"value":345}," OPENAI_API_KEY",{"type":39,"tag":65,"props":347,"children":348},{"style":78},[349],{"type":44,"value":323},{"type":39,"tag":65,"props":351,"children":352},{"style":72},[353],{"type":44,"value":354},"your-openai-api-key",{"type":39,"tag":65,"props":356,"children":357},{"style":78},[358],{"type":44,"value":359},">",{"type":39,"tag":65,"props":361,"children":362},{"style":90},[363],{"type":44,"value":364},"  # or your LLM provider's key\n",{"type":39,"tag":141,"props":366,"children":367},{},[368],{"type":44,"value":369},"Optional variables:",{"type":39,"tag":371,"props":372,"children":373},"ul",{},[374,385],{"type":39,"tag":375,"props":376,"children":377},"li",{},[378,383],{"type":39,"tag":61,"props":379,"children":381},{"className":380},[],[382],{"type":44,"value":102},{"type":44,"value":384}," - specify project name (defaults to \"default\")",{"type":39,"tag":375,"props":386,"children":387},{},[388,394],{"type":39,"tag":61,"props":389,"children":391},{"className":390},[],[392],{"type":44,"value":393},"LANGCHAIN_CALLBACKS_BACKGROUND=false",{"type":44,"value":395}," - use for serverless to ensure traces complete before function exit (Python)\n\u003C\u002Ftrace_langchain_oss>",{"type":39,"tag":141,"props":397,"children":398},{},[399],{"type":44,"value":400},"\u003Ctrace_other_frameworks>\nFor non-LangChain apps, if the framework has native OpenTelemetry support, use LangSmith's OpenTelemetry integration.",{"type":39,"tag":141,"props":402,"children":403},{},[404],{"type":44,"value":405},"If the app is NOT using a framework, or using one without automatic OTel support, use the traceable decorator\u002Fwrapper and wrap your LLM client.",{"type":39,"tag":407,"props":408,"children":409},"python",{},[410,412,417,436,443,448,460,471,481,486,545,557,565,588,598,603,612,620,749,761,1302,1307,1544,1557,1805,1826],{"type":44,"value":411},"\nUse @traceable decorator and wrap_openai() for automatic tracing.\n```python\nfrom langsmith import traceable\nfrom langsmith.wrappers import wrap_openai\nfrom openai import OpenAI\n",{"type":39,"tag":141,"props":413,"children":414},{},[415],{"type":44,"value":416},"client = wrap_openai(OpenAI())",{"type":39,"tag":141,"props":418,"children":419},{},[420,422,427,429,434],{"type":44,"value":421},"@traceable\ndef my_llm_pipeline(question: str) -> str:\nresp = client.chat.completions.create(\nmodel=\"gpt-4o-mini\",\nmessages=",{"type":39,"tag":65,"props":423,"children":424},{},[425],{"type":44,"value":426},"{\"role\": \"user\", \"content\": question}",{"type":44,"value":428},",\n)\nreturn resp.choices",{"type":39,"tag":65,"props":430,"children":431},{},[432],{"type":44,"value":433},"0",{"type":44,"value":435},".message.content",{"type":39,"tag":437,"props":438,"children":440},"h1",{"id":439},"nested-tracing-example",[441],{"type":44,"value":442},"Nested tracing example",{"type":39,"tag":141,"props":444,"children":445},{},[446],{"type":44,"value":447},"@traceable\ndef rag_pipeline(question: str) -> str:\ndocs = retrieve_docs(question)\nreturn generate_answer(question, docs)",{"type":39,"tag":141,"props":449,"children":450},{},[451,453,458],{"type":44,"value":452},"@traceable(name=\"retrieve_docs\")\ndef retrieve_docs(query: str) -> list",{"type":39,"tag":65,"props":454,"children":455},{},[456],{"type":44,"value":457},"str",{"type":44,"value":459},":\nreturn docs",{"type":39,"tag":141,"props":461,"children":462},{},[463,465,469],{"type":44,"value":464},"@traceable(name=\"generate_answer\")\ndef generate_answer(question: str, docs: list",{"type":39,"tag":65,"props":466,"children":467},{},[468],{"type":44,"value":457},{"type":44,"value":470},") -> str:\nreturn client.chat.completions.create(...)",{"type":39,"tag":53,"props":472,"children":476},{"className":473,"code":475,"language":44},[474],"language-text","\u003C\u002Fpython>\n\n\u003Ctypescript>\nUse traceable() wrapper and wrapOpenAI() for automatic tracing.\n```typescript\nimport { traceable } from \"langsmith\u002Ftraceable\";\nimport { wrapOpenAI } from \"langsmith\u002Fwrappers\";\nimport OpenAI from \"openai\";\n\nconst client = wrapOpenAI(new OpenAI());\n\nconst myLlmPipeline = traceable(async (question: string): Promise\u003Cstring> => {\n  const resp = await client.chat.completions.create({\n    model: \"gpt-4o-mini\",\n    messages: [{ role: \"user\", content: question }],\n  });\n  return resp.choices[0].message.content || \"\";\n}, { name: \"my_llm_pipeline\" });\n\n\u002F\u002F Nested tracing example\nconst retrieveDocs = traceable(async (query: string): Promise\u003Cstring[]> => {\n  return docs;\n}, { name: \"retrieve_docs\" });\n\nconst generateAnswer = traceable(async (question: string, docs: string[]): Promise\u003Cstring> => {\n  const resp = await client.chat.completions.create({\n    model: \"gpt-4o-mini\",\n    messages: [{ role: \"user\", content: `${question}\\nContext: ${docs.join(\"\\n\")}` }],\n  });\n  return resp.choices[0].message.content || \"\";\n}, { name: \"generate_answer\" });\n\nconst ragPipeline = traceable(async (question: string): Promise\u003Cstring> => {\n  const docs = await retrieveDocs(question);\n  return await generateAnswer(question, docs);\n}, { name: \"rag_pipeline\" });\n",[477],{"type":39,"tag":61,"props":478,"children":479},{"__ignoreMap":58},[480],{"type":44,"value":475},{"type":39,"tag":141,"props":482,"children":483},{},[484],{"type":44,"value":485},"Best Practices:",{"type":39,"tag":371,"props":487,"children":488},{},[489,499,525,535],{"type":39,"tag":375,"props":490,"children":491},{},[492,497],{"type":39,"tag":210,"props":493,"children":494},{},[495],{"type":44,"value":496},"Apply traceable to all nested functions",{"type":44,"value":498}," you want visible in LangSmith",{"type":39,"tag":375,"props":500,"children":501},{},[502,507,509,515,517,523],{"type":39,"tag":210,"props":503,"children":504},{},[505],{"type":44,"value":506},"Wrapped clients auto-trace all calls",{"type":44,"value":508}," — ",{"type":39,"tag":61,"props":510,"children":512},{"className":511},[],[513],{"type":44,"value":514},"wrap_openai()",{"type":44,"value":516},"\u002F",{"type":39,"tag":61,"props":518,"children":520},{"className":519},[],[521],{"type":44,"value":522},"wrapOpenAI()",{"type":44,"value":524}," records every LLM call",{"type":39,"tag":375,"props":526,"children":527},{},[528,533],{"type":39,"tag":210,"props":529,"children":530},{},[531],{"type":44,"value":532},"Name your traces",{"type":44,"value":534}," for easier filtering",{"type":39,"tag":375,"props":536,"children":537},{},[538,543],{"type":39,"tag":210,"props":539,"children":540},{},[541],{"type":44,"value":542},"Add metadata",{"type":44,"value":544}," for searchability\n\u003C\u002Ftrace_other_frameworks>",{"type":39,"tag":141,"props":546,"children":547},{},[548,550,555],{"type":44,"value":549},"\u003Ctraces_vs_runs>\nUse the ",{"type":39,"tag":61,"props":551,"children":553},{"className":552},[],[554],{"type":44,"value":22},{"type":44,"value":556}," CLI to query trace data.",{"type":39,"tag":141,"props":558,"children":559},{},[560],{"type":39,"tag":210,"props":561,"children":562},{},[563],{"type":44,"value":564},"Understanding the difference is critical:",{"type":39,"tag":371,"props":566,"children":567},{},[568,578],{"type":39,"tag":375,"props":569,"children":570},{},[571,576],{"type":39,"tag":210,"props":572,"children":573},{},[574],{"type":44,"value":575},"Trace",{"type":44,"value":577}," = A complete execution tree (root run + all child runs). A trace represents one full agent invocation with all its LLM calls, tool calls, and nested operations.",{"type":39,"tag":375,"props":579,"children":580},{},[581,586],{"type":39,"tag":210,"props":582,"children":583},{},[584],{"type":44,"value":585},"Run",{"type":44,"value":587}," = A single node in the tree (one LLM call, one tool call, etc.)",{"type":39,"tag":141,"props":589,"children":590},{},[591,596],{"type":39,"tag":210,"props":592,"children":593},{},[594],{"type":44,"value":595},"Generally, query traces first",{"type":44,"value":597}," — they provide complete context and preserve hierarchy needed for trajectory analysis and dataset generation.\n\u003C\u002Ftraces_vs_runs>",{"type":39,"tag":141,"props":599,"children":600},{},[601],{"type":44,"value":602},"\u003Ccommand_structure>\nTwo command groups with consistent behavior:",{"type":39,"tag":53,"props":604,"children":607},{"className":605,"code":606,"language":44},[474],"langsmith\n├── trace (operations on trace trees - USE THIS FIRST)\n│   ├── list    - List traces (filters apply to root run)\n│   ├── get     - Get single trace with full hierarchy\n│   └── export  - Export traces to JSONL files (one file per trace)\n│\n├── run (operations on individual runs - for specific analysis)\n│   ├── list    - List runs (flat, filters apply to any run)\n│   ├── get     - Get single run\n│   └── export  - Export runs to single JSONL file (flat)\n│\n├── dataset (dataset operations)\n│   ├── list    - List datasets\n│   ├── get     - Get dataset details\n│   ├── create  - Create empty dataset\n│   ├── delete  - Delete dataset\n│   ├── export  - Export dataset to file\n│   └── upload  - Upload local JSON as dataset\n│\n├── example (example operations)\n│   ├── list    - List examples in a dataset\n│   ├── create  - Add example to a dataset\n│   └── delete  - Delete an example\n│\n├── evaluator (evaluator operations)\n│   ├── list    - List evaluators\n│   ├── upload  - Upload evaluator\n│   └── delete  - Delete evaluator\n│\n├── experiment (experiment operations)\n│   ├── list    - List experiments\n│   └── get     - Get experiment results\n│\n├── thread (thread operations)\n│   ├── list    - List conversation threads\n│   └── get     - Get thread details\n│\n└── project (project operations)\n    └── list    - List tracing projects\n",[608],{"type":39,"tag":61,"props":609,"children":610},{"__ignoreMap":58},[611],{"type":44,"value":606},{"type":39,"tag":141,"props":613,"children":614},{},[615],{"type":39,"tag":210,"props":616,"children":617},{},[618],{"type":44,"value":619},"Key differences:",{"type":39,"tag":621,"props":622,"children":623},"table",{},[624,654],{"type":39,"tag":625,"props":626,"children":627},"thead",{},[628],{"type":39,"tag":629,"props":630,"children":631},"tr",{},[632,636,645],{"type":39,"tag":633,"props":634,"children":635},"th",{},[],{"type":39,"tag":633,"props":637,"children":638},{},[639],{"type":39,"tag":61,"props":640,"children":642},{"className":641},[],[643],{"type":44,"value":644},"traces *",{"type":39,"tag":633,"props":646,"children":647},{},[648],{"type":39,"tag":61,"props":649,"children":651},{"className":650},[],[652],{"type":44,"value":653},"runs *",{"type":39,"tag":655,"props":656,"children":657},"tbody",{},[658,677,699,717,735],{"type":39,"tag":629,"props":659,"children":660},{},[661,667,672],{"type":39,"tag":662,"props":663,"children":664},"td",{},[665],{"type":44,"value":666},"Filters apply to",{"type":39,"tag":662,"props":668,"children":669},{},[670],{"type":44,"value":671},"Root run only",{"type":39,"tag":662,"props":673,"children":674},{},[675],{"type":44,"value":676},"Any matching run",{"type":39,"tag":629,"props":678,"children":679},{},[680,689,694],{"type":39,"tag":662,"props":681,"children":682},{},[683],{"type":39,"tag":61,"props":684,"children":686},{"className":685},[],[687],{"type":44,"value":688},"--run-type",{"type":39,"tag":662,"props":690,"children":691},{},[692],{"type":44,"value":693},"Not available",{"type":39,"tag":662,"props":695,"children":696},{},[697],{"type":44,"value":698},"Available",{"type":39,"tag":629,"props":700,"children":701},{},[702,707,712],{"type":39,"tag":662,"props":703,"children":704},{},[705],{"type":44,"value":706},"Returns",{"type":39,"tag":662,"props":708,"children":709},{},[710],{"type":44,"value":711},"Full hierarchy",{"type":39,"tag":662,"props":713,"children":714},{},[715],{"type":44,"value":716},"Flat list",{"type":39,"tag":629,"props":718,"children":719},{},[720,725,730],{"type":39,"tag":662,"props":721,"children":722},{},[723],{"type":44,"value":724},"Export output",{"type":39,"tag":662,"props":726,"children":727},{},[728],{"type":44,"value":729},"Directory (one file\u002Ftrace)",{"type":39,"tag":662,"props":731,"children":732},{},[733],{"type":44,"value":734},"Single file",{"type":39,"tag":629,"props":736,"children":737},{},[738,743,746],{"type":39,"tag":662,"props":739,"children":740},{},[741],{"type":44,"value":742},"\u003C\u002Fcommand_structure>",{"type":39,"tag":662,"props":744,"children":745},{},[],{"type":39,"tag":662,"props":747,"children":748},{},[],{"type":39,"tag":141,"props":750,"children":751},{},[752,754,759],{"type":44,"value":753},"\u003Cquerying_traces>\nQuery traces using the ",{"type":39,"tag":61,"props":755,"children":757},{"className":756},[],[758],{"type":44,"value":22},{"type":44,"value":760}," CLI. Commands are language-agnostic.",{"type":39,"tag":53,"props":762,"children":764},{"className":55,"code":763,"language":57,"meta":58,"style":58},"# List recent traces (most common operation)\nlangsmith trace list --limit 10 --project my-project --api-key $LANGSMITH_API_KEY\n\n# List traces with metadata (timing, tokens, costs)\nlangsmith trace list --limit 10 --include-metadata --api-key $LANGSMITH_API_KEY\n\n# Filter traces by time\nlangsmith trace list --last-n-minutes 60 --api-key $LANGSMITH_API_KEY\nlangsmith trace list --since 2025-01-20T10:00:00Z --api-key $LANGSMITH_API_KEY\n\n# Get specific trace with full hierarchy\nlangsmith trace get \u003Ctrace-id> --api-key $LANGSMITH_API_KEY\n\n# List traces and show hierarchy inline\nlangsmith trace list --limit 5 --show-hierarchy --api-key $LANGSMITH_API_KEY\n\n# Export traces to JSONL (one file per trace, includes all runs)\nlangsmith trace export .\u002Ftraces --limit 20 --full --api-key $LANGSMITH_API_KEY\n\n# Filter traces by performance\nlangsmith trace list --min-latency 5.0 --limit 10 --api-key $LANGSMITH_API_KEY    # Slow traces (>= 5s)\nlangsmith trace list --error --last-n-minutes 60 --api-key $LANGSMITH_API_KEY     # Failed traces\n\n# List specific run types (flat list)\nlangsmith run list --run-type llm --limit 20 --api-key $LANGSMITH_API_KEY\n",[765],{"type":39,"tag":61,"props":766,"children":767},{"__ignoreMap":58},[768,776,818,827,836,873,881,890,924,958,966,975,1019,1027,1036,1074,1082,1090,1134,1142,1151,1199,1242,1250,1259],{"type":39,"tag":65,"props":769,"children":770},{"class":67,"line":68},[771],{"type":39,"tag":65,"props":772,"children":773},{"style":90},[774],{"type":44,"value":775},"# List recent traces (most common operation)\n",{"type":39,"tag":65,"props":777,"children":778},{"class":67,"line":96},[779,783,787,791,796,802,806,810,814],{"type":39,"tag":65,"props":780,"children":781},{"style":173},[782],{"type":44,"value":22},{"type":39,"tag":65,"props":784,"children":785},{"style":84},[786],{"type":44,"value":180},{"type":39,"tag":65,"props":788,"children":789},{"style":84},[790],{"type":44,"value":185},{"type":39,"tag":65,"props":792,"children":793},{"style":84},[794],{"type":44,"value":795}," --limit",{"type":39,"tag":65,"props":797,"children":799},{"style":798},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[800],{"type":44,"value":801}," 10",{"type":39,"tag":65,"props":803,"children":804},{"style":84},[805],{"type":44,"value":190},{"type":39,"tag":65,"props":807,"children":808},{"style":84},[809],{"type":44,"value":195},{"type":39,"tag":65,"props":811,"children":812},{"style":84},[813],{"type":44,"value":200},{"type":39,"tag":65,"props":815,"children":816},{"style":72},[817],{"type":44,"value":205},{"type":39,"tag":65,"props":819,"children":820},{"class":67,"line":119},[821],{"type":39,"tag":65,"props":822,"children":824},{"emptyLinePlaceholder":823},true,[825],{"type":44,"value":826},"\n",{"type":39,"tag":65,"props":828,"children":830},{"class":67,"line":829},4,[831],{"type":39,"tag":65,"props":832,"children":833},{"style":90},[834],{"type":44,"value":835},"# List traces with metadata (timing, tokens, costs)\n",{"type":39,"tag":65,"props":837,"children":839},{"class":67,"line":838},5,[840,844,848,852,856,860,865,869],{"type":39,"tag":65,"props":841,"children":842},{"style":173},[843],{"type":44,"value":22},{"type":39,"tag":65,"props":845,"children":846},{"style":84},[847],{"type":44,"value":180},{"type":39,"tag":65,"props":849,"children":850},{"style":84},[851],{"type":44,"value":185},{"type":39,"tag":65,"props":853,"children":854},{"style":84},[855],{"type":44,"value":795},{"type":39,"tag":65,"props":857,"children":858},{"style":798},[859],{"type":44,"value":801},{"type":39,"tag":65,"props":861,"children":862},{"style":84},[863],{"type":44,"value":864}," --include-metadata",{"type":39,"tag":65,"props":866,"children":867},{"style":84},[868],{"type":44,"value":200},{"type":39,"tag":65,"props":870,"children":871},{"style":72},[872],{"type":44,"value":205},{"type":39,"tag":65,"props":874,"children":876},{"class":67,"line":875},6,[877],{"type":39,"tag":65,"props":878,"children":879},{"emptyLinePlaceholder":823},[880],{"type":44,"value":826},{"type":39,"tag":65,"props":882,"children":884},{"class":67,"line":883},7,[885],{"type":39,"tag":65,"props":886,"children":887},{"style":90},[888],{"type":44,"value":889},"# Filter traces by time\n",{"type":39,"tag":65,"props":891,"children":893},{"class":67,"line":892},8,[894,898,902,906,911,916,920],{"type":39,"tag":65,"props":895,"children":896},{"style":173},[897],{"type":44,"value":22},{"type":39,"tag":65,"props":899,"children":900},{"style":84},[901],{"type":44,"value":180},{"type":39,"tag":65,"props":903,"children":904},{"style":84},[905],{"type":44,"value":185},{"type":39,"tag":65,"props":907,"children":908},{"style":84},[909],{"type":44,"value":910}," --last-n-minutes",{"type":39,"tag":65,"props":912,"children":913},{"style":798},[914],{"type":44,"value":915}," 60",{"type":39,"tag":65,"props":917,"children":918},{"style":84},[919],{"type":44,"value":200},{"type":39,"tag":65,"props":921,"children":922},{"style":72},[923],{"type":44,"value":205},{"type":39,"tag":65,"props":925,"children":927},{"class":67,"line":926},9,[928,932,936,940,945,950,954],{"type":39,"tag":65,"props":929,"children":930},{"style":173},[931],{"type":44,"value":22},{"type":39,"tag":65,"props":933,"children":934},{"style":84},[935],{"type":44,"value":180},{"type":39,"tag":65,"props":937,"children":938},{"style":84},[939],{"type":44,"value":185},{"type":39,"tag":65,"props":941,"children":942},{"style":84},[943],{"type":44,"value":944}," --since",{"type":39,"tag":65,"props":946,"children":947},{"style":84},[948],{"type":44,"value":949}," 2025-01-20T10:00:00Z",{"type":39,"tag":65,"props":951,"children":952},{"style":84},[953],{"type":44,"value":200},{"type":39,"tag":65,"props":955,"children":956},{"style":72},[957],{"type":44,"value":205},{"type":39,"tag":65,"props":959,"children":961},{"class":67,"line":960},10,[962],{"type":39,"tag":65,"props":963,"children":964},{"emptyLinePlaceholder":823},[965],{"type":44,"value":826},{"type":39,"tag":65,"props":967,"children":969},{"class":67,"line":968},11,[970],{"type":39,"tag":65,"props":971,"children":972},{"style":90},[973],{"type":44,"value":974},"# Get specific trace with full hierarchy\n",{"type":39,"tag":65,"props":976,"children":978},{"class":67,"line":977},12,[979,983,987,992,997,1002,1007,1011,1015],{"type":39,"tag":65,"props":980,"children":981},{"style":173},[982],{"type":44,"value":22},{"type":39,"tag":65,"props":984,"children":985},{"style":84},[986],{"type":44,"value":180},{"type":39,"tag":65,"props":988,"children":989},{"style":84},[990],{"type":44,"value":991}," get",{"type":39,"tag":65,"props":993,"children":994},{"style":78},[995],{"type":44,"value":996}," \u003C",{"type":39,"tag":65,"props":998,"children":999},{"style":84},[1000],{"type":44,"value":1001},"trace-i",{"type":39,"tag":65,"props":1003,"children":1004},{"style":72},[1005],{"type":44,"value":1006},"d",{"type":39,"tag":65,"props":1008,"children":1009},{"style":78},[1010],{"type":44,"value":359},{"type":39,"tag":65,"props":1012,"children":1013},{"style":84},[1014],{"type":44,"value":200},{"type":39,"tag":65,"props":1016,"children":1017},{"style":72},[1018],{"type":44,"value":205},{"type":39,"tag":65,"props":1020,"children":1022},{"class":67,"line":1021},13,[1023],{"type":39,"tag":65,"props":1024,"children":1025},{"emptyLinePlaceholder":823},[1026],{"type":44,"value":826},{"type":39,"tag":65,"props":1028,"children":1030},{"class":67,"line":1029},14,[1031],{"type":39,"tag":65,"props":1032,"children":1033},{"style":90},[1034],{"type":44,"value":1035},"# List traces and show hierarchy inline\n",{"type":39,"tag":65,"props":1037,"children":1039},{"class":67,"line":1038},15,[1040,1044,1048,1052,1056,1061,1066,1070],{"type":39,"tag":65,"props":1041,"children":1042},{"style":173},[1043],{"type":44,"value":22},{"type":39,"tag":65,"props":1045,"children":1046},{"style":84},[1047],{"type":44,"value":180},{"type":39,"tag":65,"props":1049,"children":1050},{"style":84},[1051],{"type":44,"value":185},{"type":39,"tag":65,"props":1053,"children":1054},{"style":84},[1055],{"type":44,"value":795},{"type":39,"tag":65,"props":1057,"children":1058},{"style":798},[1059],{"type":44,"value":1060}," 5",{"type":39,"tag":65,"props":1062,"children":1063},{"style":84},[1064],{"type":44,"value":1065}," --show-hierarchy",{"type":39,"tag":65,"props":1067,"children":1068},{"style":84},[1069],{"type":44,"value":200},{"type":39,"tag":65,"props":1071,"children":1072},{"style":72},[1073],{"type":44,"value":205},{"type":39,"tag":65,"props":1075,"children":1077},{"class":67,"line":1076},16,[1078],{"type":39,"tag":65,"props":1079,"children":1080},{"emptyLinePlaceholder":823},[1081],{"type":44,"value":826},{"type":39,"tag":65,"props":1083,"children":1084},{"class":67,"line":27},[1085],{"type":39,"tag":65,"props":1086,"children":1087},{"style":90},[1088],{"type":44,"value":1089},"# Export traces to JSONL (one file per trace, includes all runs)\n",{"type":39,"tag":65,"props":1091,"children":1093},{"class":67,"line":1092},18,[1094,1098,1102,1107,1112,1116,1121,1126,1130],{"type":39,"tag":65,"props":1095,"children":1096},{"style":173},[1097],{"type":44,"value":22},{"type":39,"tag":65,"props":1099,"children":1100},{"style":84},[1101],{"type":44,"value":180},{"type":39,"tag":65,"props":1103,"children":1104},{"style":84},[1105],{"type":44,"value":1106}," export",{"type":39,"tag":65,"props":1108,"children":1109},{"style":84},[1110],{"type":44,"value":1111}," .\u002Ftraces",{"type":39,"tag":65,"props":1113,"children":1114},{"style":84},[1115],{"type":44,"value":795},{"type":39,"tag":65,"props":1117,"children":1118},{"style":798},[1119],{"type":44,"value":1120}," 20",{"type":39,"tag":65,"props":1122,"children":1123},{"style":84},[1124],{"type":44,"value":1125}," --full",{"type":39,"tag":65,"props":1127,"children":1128},{"style":84},[1129],{"type":44,"value":200},{"type":39,"tag":65,"props":1131,"children":1132},{"style":72},[1133],{"type":44,"value":205},{"type":39,"tag":65,"props":1135,"children":1137},{"class":67,"line":1136},19,[1138],{"type":39,"tag":65,"props":1139,"children":1140},{"emptyLinePlaceholder":823},[1141],{"type":44,"value":826},{"type":39,"tag":65,"props":1143,"children":1145},{"class":67,"line":1144},20,[1146],{"type":39,"tag":65,"props":1147,"children":1148},{"style":90},[1149],{"type":44,"value":1150},"# Filter traces by performance\n",{"type":39,"tag":65,"props":1152,"children":1154},{"class":67,"line":1153},21,[1155,1159,1163,1167,1172,1177,1181,1185,1189,1194],{"type":39,"tag":65,"props":1156,"children":1157},{"style":173},[1158],{"type":44,"value":22},{"type":39,"tag":65,"props":1160,"children":1161},{"style":84},[1162],{"type":44,"value":180},{"type":39,"tag":65,"props":1164,"children":1165},{"style":84},[1166],{"type":44,"value":185},{"type":39,"tag":65,"props":1168,"children":1169},{"style":84},[1170],{"type":44,"value":1171}," --min-latency",{"type":39,"tag":65,"props":1173,"children":1174},{"style":798},[1175],{"type":44,"value":1176}," 5.0",{"type":39,"tag":65,"props":1178,"children":1179},{"style":84},[1180],{"type":44,"value":795},{"type":39,"tag":65,"props":1182,"children":1183},{"style":798},[1184],{"type":44,"value":801},{"type":39,"tag":65,"props":1186,"children":1187},{"style":84},[1188],{"type":44,"value":200},{"type":39,"tag":65,"props":1190,"children":1191},{"style":72},[1192],{"type":44,"value":1193}," $LANGSMITH_API_KEY    ",{"type":39,"tag":65,"props":1195,"children":1196},{"style":90},[1197],{"type":44,"value":1198},"# Slow traces (>= 5s)\n",{"type":39,"tag":65,"props":1200,"children":1202},{"class":67,"line":1201},22,[1203,1207,1211,1215,1220,1224,1228,1232,1237],{"type":39,"tag":65,"props":1204,"children":1205},{"style":173},[1206],{"type":44,"value":22},{"type":39,"tag":65,"props":1208,"children":1209},{"style":84},[1210],{"type":44,"value":180},{"type":39,"tag":65,"props":1212,"children":1213},{"style":84},[1214],{"type":44,"value":185},{"type":39,"tag":65,"props":1216,"children":1217},{"style":84},[1218],{"type":44,"value":1219}," --error",{"type":39,"tag":65,"props":1221,"children":1222},{"style":84},[1223],{"type":44,"value":910},{"type":39,"tag":65,"props":1225,"children":1226},{"style":798},[1227],{"type":44,"value":915},{"type":39,"tag":65,"props":1229,"children":1230},{"style":84},[1231],{"type":44,"value":200},{"type":39,"tag":65,"props":1233,"children":1234},{"style":72},[1235],{"type":44,"value":1236}," $LANGSMITH_API_KEY     ",{"type":39,"tag":65,"props":1238,"children":1239},{"style":90},[1240],{"type":44,"value":1241},"# Failed traces\n",{"type":39,"tag":65,"props":1243,"children":1245},{"class":67,"line":1244},23,[1246],{"type":39,"tag":65,"props":1247,"children":1248},{"emptyLinePlaceholder":823},[1249],{"type":44,"value":826},{"type":39,"tag":65,"props":1251,"children":1253},{"class":67,"line":1252},24,[1254],{"type":39,"tag":65,"props":1255,"children":1256},{"style":90},[1257],{"type":44,"value":1258},"# List specific run types (flat list)\n",{"type":39,"tag":65,"props":1260,"children":1262},{"class":67,"line":1261},25,[1263,1267,1272,1276,1281,1286,1290,1294,1298],{"type":39,"tag":65,"props":1264,"children":1265},{"style":173},[1266],{"type":44,"value":22},{"type":39,"tag":65,"props":1268,"children":1269},{"style":84},[1270],{"type":44,"value":1271}," run",{"type":39,"tag":65,"props":1273,"children":1274},{"style":84},[1275],{"type":44,"value":185},{"type":39,"tag":65,"props":1277,"children":1278},{"style":84},[1279],{"type":44,"value":1280}," --run-type",{"type":39,"tag":65,"props":1282,"children":1283},{"style":84},[1284],{"type":44,"value":1285}," llm",{"type":39,"tag":65,"props":1287,"children":1288},{"style":84},[1289],{"type":44,"value":795},{"type":39,"tag":65,"props":1291,"children":1292},{"style":798},[1293],{"type":44,"value":1120},{"type":39,"tag":65,"props":1295,"children":1296},{"style":84},[1297],{"type":44,"value":200},{"type":39,"tag":65,"props":1299,"children":1300},{"style":72},[1301],{"type":44,"value":205},{"type":39,"tag":141,"props":1303,"children":1304},{},[1305],{"type":44,"value":1306},"\u003C\u002Fquerying_traces>",{"type":39,"tag":1308,"props":1309,"children":1310},"filters",{},[1311,1313,1321,1401,1409,1464,1472,1486],{"type":44,"value":1312},"\nAll commands support these filters (all AND together):\n",{"type":39,"tag":141,"props":1314,"children":1315},{},[1316],{"type":39,"tag":210,"props":1317,"children":1318},{},[1319],{"type":44,"value":1320},"Basic filters:",{"type":39,"tag":371,"props":1322,"children":1323},{},[1324,1335,1346,1357,1368,1379,1390],{"type":39,"tag":375,"props":1325,"children":1326},{},[1327,1333],{"type":39,"tag":61,"props":1328,"children":1330},{"className":1329},[],[1331],{"type":44,"value":1332},"--trace-ids abc,def",{"type":44,"value":1334}," - Filter to specific traces",{"type":39,"tag":375,"props":1336,"children":1337},{},[1338,1344],{"type":39,"tag":61,"props":1339,"children":1341},{"className":1340},[],[1342],{"type":44,"value":1343},"--limit N",{"type":44,"value":1345}," - Max results",{"type":39,"tag":375,"props":1347,"children":1348},{},[1349,1355],{"type":39,"tag":61,"props":1350,"children":1352},{"className":1351},[],[1353],{"type":44,"value":1354},"--project NAME",{"type":44,"value":1356}," - Project name",{"type":39,"tag":375,"props":1358,"children":1359},{},[1360,1366],{"type":39,"tag":61,"props":1361,"children":1363},{"className":1362},[],[1364],{"type":44,"value":1365},"--last-n-minutes N",{"type":44,"value":1367}," - Time filter",{"type":39,"tag":375,"props":1369,"children":1370},{},[1371,1377],{"type":39,"tag":61,"props":1372,"children":1374},{"className":1373},[],[1375],{"type":44,"value":1376},"--since TIMESTAMP",{"type":44,"value":1378}," - Time filter (ISO format)",{"type":39,"tag":375,"props":1380,"children":1381},{},[1382,1388],{"type":39,"tag":61,"props":1383,"children":1385},{"className":1384},[],[1386],{"type":44,"value":1387},"--error \u002F --no-error",{"type":44,"value":1389}," - Error status",{"type":39,"tag":375,"props":1391,"children":1392},{},[1393,1399],{"type":39,"tag":61,"props":1394,"children":1396},{"className":1395},[],[1397],{"type":44,"value":1398},"--name PATTERN",{"type":44,"value":1400}," - Name contains (case-insensitive)",{"type":39,"tag":141,"props":1402,"children":1403},{},[1404],{"type":39,"tag":210,"props":1405,"children":1406},{},[1407],{"type":44,"value":1408},"Performance filters:",{"type":39,"tag":371,"props":1410,"children":1411},{},[1412,1431,1442,1453],{"type":39,"tag":375,"props":1413,"children":1414},{},[1415,1421,1423,1429],{"type":39,"tag":61,"props":1416,"children":1418},{"className":1417},[],[1419],{"type":44,"value":1420},"--min-latency SECONDS",{"type":44,"value":1422}," - Minimum latency (e.g., ",{"type":39,"tag":61,"props":1424,"children":1426},{"className":1425},[],[1427],{"type":44,"value":1428},"5",{"type":44,"value":1430}," for >= 5s)",{"type":39,"tag":375,"props":1432,"children":1433},{},[1434,1440],{"type":39,"tag":61,"props":1435,"children":1437},{"className":1436},[],[1438],{"type":44,"value":1439},"--max-latency SECONDS",{"type":44,"value":1441}," - Maximum latency",{"type":39,"tag":375,"props":1443,"children":1444},{},[1445,1451],{"type":39,"tag":61,"props":1446,"children":1448},{"className":1447},[],[1449],{"type":44,"value":1450},"--min-tokens N",{"type":44,"value":1452}," - Minimum total tokens",{"type":39,"tag":375,"props":1454,"children":1455},{},[1456,1462],{"type":39,"tag":61,"props":1457,"children":1459},{"className":1458},[],[1460],{"type":44,"value":1461},"--tags tag1,tag2",{"type":44,"value":1463}," - Has any of these tags",{"type":39,"tag":141,"props":1465,"children":1466},{},[1467],{"type":39,"tag":210,"props":1468,"children":1469},{},[1470],{"type":44,"value":1471},"Advanced filter:",{"type":39,"tag":371,"props":1473,"children":1474},{},[1475],{"type":39,"tag":375,"props":1476,"children":1477},{},[1478,1484],{"type":39,"tag":61,"props":1479,"children":1481},{"className":1480},[],[1482],{"type":44,"value":1483},"--filter QUERY",{"type":44,"value":1485}," - Raw LangSmith filter query for complex cases (feedback, metadata, etc.)",{"type":39,"tag":53,"props":1487,"children":1489},{"className":55,"code":1488,"language":57,"meta":58,"style":58},"# Filter traces by feedback score using raw LangSmith query\nlangsmith trace list --filter 'and(eq(feedback_key, \"correctness\"), gte(feedback_score, 0.8))' --api-key $LANGSMITH_API_KEY\n",[1490],{"type":39,"tag":61,"props":1491,"children":1492},{"__ignoreMap":58},[1493,1501],{"type":39,"tag":65,"props":1494,"children":1495},{"class":67,"line":68},[1496],{"type":39,"tag":65,"props":1497,"children":1498},{"style":90},[1499],{"type":44,"value":1500},"# Filter traces by feedback score using raw LangSmith query\n",{"type":39,"tag":65,"props":1502,"children":1503},{"class":67,"line":96},[1504,1508,1512,1516,1521,1526,1531,1536,1540],{"type":39,"tag":65,"props":1505,"children":1506},{"style":173},[1507],{"type":44,"value":22},{"type":39,"tag":65,"props":1509,"children":1510},{"style":84},[1511],{"type":44,"value":180},{"type":39,"tag":65,"props":1513,"children":1514},{"style":84},[1515],{"type":44,"value":185},{"type":39,"tag":65,"props":1517,"children":1518},{"style":84},[1519],{"type":44,"value":1520}," --filter",{"type":39,"tag":65,"props":1522,"children":1523},{"style":78},[1524],{"type":44,"value":1525}," '",{"type":39,"tag":65,"props":1527,"children":1528},{"style":84},[1529],{"type":44,"value":1530},"and(eq(feedback_key, \"correctness\"), gte(feedback_score, 0.8))",{"type":39,"tag":65,"props":1532,"children":1533},{"style":78},[1534],{"type":44,"value":1535},"'",{"type":39,"tag":65,"props":1537,"children":1538},{"style":84},[1539],{"type":44,"value":200},{"type":39,"tag":65,"props":1541,"children":1542},{"style":72},[1543],{"type":44,"value":205},{"type":39,"tag":141,"props":1545,"children":1546},{},[1547,1549,1555],{"type":44,"value":1548},"\u003Cexport_format>\nExport creates ",{"type":39,"tag":61,"props":1550,"children":1552},{"className":1551},[],[1553],{"type":44,"value":1554},".jsonl",{"type":44,"value":1556}," files (one run per line) with these fields:",{"type":39,"tag":53,"props":1558,"children":1562},{"className":1559,"code":1560,"language":1561,"meta":58,"style":58},"language-json shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","{\"run_id\": \"...\", \"trace_id\": \"...\", \"name\": \"...\", \"run_type\": \"...\", \"parent_run_id\": \"...\", \"inputs\": {...}, \"outputs\": {...}}\n","json",[1563],{"type":39,"tag":61,"props":1564,"children":1565},{"__ignoreMap":58},[1566],{"type":39,"tag":65,"props":1567,"children":1568},{"class":67,"line":68},[1569,1574,1579,1584,1588,1593,1598,1603,1607,1612,1616,1621,1625,1629,1633,1637,1641,1645,1649,1654,1658,1662,1666,1670,1674,1678,1682,1687,1691,1695,1699,1703,1707,1711,1715,1720,1724,1728,1732,1736,1740,1744,1748,1753,1757,1761,1766,1770,1775,1779,1784,1788,1792,1796,1800],{"type":39,"tag":65,"props":1570,"children":1571},{"style":78},[1572],{"type":44,"value":1573},"{",{"type":39,"tag":65,"props":1575,"children":1576},{"style":78},[1577],{"type":44,"value":1578},"\"",{"type":39,"tag":65,"props":1580,"children":1581},{"style":289},[1582],{"type":44,"value":1583},"run_id",{"type":39,"tag":65,"props":1585,"children":1586},{"style":78},[1587],{"type":44,"value":1578},{"type":39,"tag":65,"props":1589,"children":1590},{"style":78},[1591],{"type":44,"value":1592},":",{"type":39,"tag":65,"props":1594,"children":1595},{"style":78},[1596],{"type":44,"value":1597}," \"",{"type":39,"tag":65,"props":1599,"children":1600},{"style":84},[1601],{"type":44,"value":1602},"...",{"type":39,"tag":65,"props":1604,"children":1605},{"style":78},[1606],{"type":44,"value":1578},{"type":39,"tag":65,"props":1608,"children":1609},{"style":78},[1610],{"type":44,"value":1611},",",{"type":39,"tag":65,"props":1613,"children":1614},{"style":78},[1615],{"type":44,"value":1597},{"type":39,"tag":65,"props":1617,"children":1618},{"style":289},[1619],{"type":44,"value":1620},"trace_id",{"type":39,"tag":65,"props":1622,"children":1623},{"style":78},[1624],{"type":44,"value":1578},{"type":39,"tag":65,"props":1626,"children":1627},{"style":78},[1628],{"type":44,"value":1592},{"type":39,"tag":65,"props":1630,"children":1631},{"style":78},[1632],{"type":44,"value":1597},{"type":39,"tag":65,"props":1634,"children":1635},{"style":84},[1636],{"type":44,"value":1602},{"type":39,"tag":65,"props":1638,"children":1639},{"style":78},[1640],{"type":44,"value":1578},{"type":39,"tag":65,"props":1642,"children":1643},{"style":78},[1644],{"type":44,"value":1611},{"type":39,"tag":65,"props":1646,"children":1647},{"style":78},[1648],{"type":44,"value":1597},{"type":39,"tag":65,"props":1650,"children":1651},{"style":289},[1652],{"type":44,"value":1653},"name",{"type":39,"tag":65,"props":1655,"children":1656},{"style":78},[1657],{"type":44,"value":1578},{"type":39,"tag":65,"props":1659,"children":1660},{"style":78},[1661],{"type":44,"value":1592},{"type":39,"tag":65,"props":1663,"children":1664},{"style":78},[1665],{"type":44,"value":1597},{"type":39,"tag":65,"props":1667,"children":1668},{"style":84},[1669],{"type":44,"value":1602},{"type":39,"tag":65,"props":1671,"children":1672},{"style":78},[1673],{"type":44,"value":1578},{"type":39,"tag":65,"props":1675,"children":1676},{"style":78},[1677],{"type":44,"value":1611},{"type":39,"tag":65,"props":1679,"children":1680},{"style":78},[1681],{"type":44,"value":1597},{"type":39,"tag":65,"props":1683,"children":1684},{"style":289},[1685],{"type":44,"value":1686},"run_type",{"type":39,"tag":65,"props":1688,"children":1689},{"style":78},[1690],{"type":44,"value":1578},{"type":39,"tag":65,"props":1692,"children":1693},{"style":78},[1694],{"type":44,"value":1592},{"type":39,"tag":65,"props":1696,"children":1697},{"style":78},[1698],{"type":44,"value":1597},{"type":39,"tag":65,"props":1700,"children":1701},{"style":84},[1702],{"type":44,"value":1602},{"type":39,"tag":65,"props":1704,"children":1705},{"style":78},[1706],{"type":44,"value":1578},{"type":39,"tag":65,"props":1708,"children":1709},{"style":78},[1710],{"type":44,"value":1611},{"type":39,"tag":65,"props":1712,"children":1713},{"style":78},[1714],{"type":44,"value":1597},{"type":39,"tag":65,"props":1716,"children":1717},{"style":289},[1718],{"type":44,"value":1719},"parent_run_id",{"type":39,"tag":65,"props":1721,"children":1722},{"style":78},[1723],{"type":44,"value":1578},{"type":39,"tag":65,"props":1725,"children":1726},{"style":78},[1727],{"type":44,"value":1592},{"type":39,"tag":65,"props":1729,"children":1730},{"style":78},[1731],{"type":44,"value":1597},{"type":39,"tag":65,"props":1733,"children":1734},{"style":84},[1735],{"type":44,"value":1602},{"type":39,"tag":65,"props":1737,"children":1738},{"style":78},[1739],{"type":44,"value":1578},{"type":39,"tag":65,"props":1741,"children":1742},{"style":78},[1743],{"type":44,"value":1611},{"type":39,"tag":65,"props":1745,"children":1746},{"style":78},[1747],{"type":44,"value":1597},{"type":39,"tag":65,"props":1749,"children":1750},{"style":289},[1751],{"type":44,"value":1752},"inputs",{"type":39,"tag":65,"props":1754,"children":1755},{"style":78},[1756],{"type":44,"value":1578},{"type":39,"tag":65,"props":1758,"children":1759},{"style":78},[1760],{"type":44,"value":1592},{"type":39,"tag":65,"props":1762,"children":1763},{"style":78},[1764],{"type":44,"value":1765}," {",{"type":39,"tag":65,"props":1767,"children":1768},{"style":72},[1769],{"type":44,"value":1602},{"type":39,"tag":65,"props":1771,"children":1772},{"style":78},[1773],{"type":44,"value":1774},"},",{"type":39,"tag":65,"props":1776,"children":1777},{"style":78},[1778],{"type":44,"value":1597},{"type":39,"tag":65,"props":1780,"children":1781},{"style":289},[1782],{"type":44,"value":1783},"outputs",{"type":39,"tag":65,"props":1785,"children":1786},{"style":78},[1787],{"type":44,"value":1578},{"type":39,"tag":65,"props":1789,"children":1790},{"style":78},[1791],{"type":44,"value":1592},{"type":39,"tag":65,"props":1793,"children":1794},{"style":78},[1795],{"type":44,"value":1765},{"type":39,"tag":65,"props":1797,"children":1798},{"style":72},[1799],{"type":44,"value":1602},{"type":39,"tag":65,"props":1801,"children":1802},{"style":78},[1803],{"type":44,"value":1804},"}}\n",{"type":39,"tag":141,"props":1806,"children":1807},{},[1808,1810,1816,1818,1824],{"type":44,"value":1809},"Use ",{"type":39,"tag":61,"props":1811,"children":1813},{"className":1812},[],[1814],{"type":44,"value":1815},"--include-io",{"type":44,"value":1817}," or ",{"type":39,"tag":61,"props":1819,"children":1821},{"className":1820},[],[1822],{"type":44,"value":1823},"--full",{"type":44,"value":1825}," to include inputs\u002Foutputs (required for dataset generation).\n\u003C\u002Fexport_format>",{"type":39,"tag":1827,"props":1828,"children":1829},"tips",{},[1830],{"type":44,"value":1831},"\n- **Start with traces** — they provide complete context needed for trajectory and dataset generation\n- Use `traces export --full` for bulk data destined for datasets\n- Always specify `--project` to avoid mixing data from different projects\n- Use `\u002Ftmp` for temporary exports\n- Include `--include-metadata` for performance\u002Fcost analysis\n- Stitch files: `cat .\u002Ftraces\u002F*.jsonl > all.jsonl`\n",{"type":39,"tag":1833,"props":1834,"children":1835},"style",{},[1836],{"type":44,"value":1837},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1839,"total":2018},[1840,1861,1872,1889,1902,1919,1936,1951,1965,1975,1986,2005],{"slug":1841,"name":1841,"fn":1842,"description":1843,"org":1844,"tags":1845,"stars":1858,"repoUrl":1859,"updatedAt":1860},"analyze-market","perform market analysis and size estimation","Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1846,1849,1852,1855],{"name":1847,"slug":1848,"type":16},"Marketing","marketing",{"name":1850,"slug":1851,"type":16},"Research","research",{"name":1853,"slug":1854,"type":16},"Sales","sales",{"name":1856,"slug":1857,"type":16},"Strategy","strategy",26592,"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Fdeepagents","2026-04-18T04:46:54.557115",{"slug":1862,"name":1862,"fn":1863,"description":1864,"org":1865,"tags":1866,"stars":1858,"repoUrl":1859,"updatedAt":1871},"arxiv-search","search arXiv for academic research papers","Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1867,1868],{"name":1850,"slug":1851,"type":16},{"name":1869,"slug":1870,"type":16},"Search","search","2026-05-13T06:11:01.203061",{"slug":1873,"name":1873,"fn":1874,"description":1875,"org":1876,"tags":1877,"stars":1858,"repoUrl":1859,"updatedAt":1888},"blog-post","write SEO-optimized blog posts","Write long-form blog posts with SEO optimization and clear structure.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1878,1881,1882,1885],{"name":1879,"slug":1880,"type":16},"Content Creation","content-creation",{"name":1847,"slug":1848,"type":16},{"name":1883,"slug":1884,"type":16},"SEO","seo",{"name":1886,"slug":1887,"type":16},"Writing","writing","2026-04-15T05:00:54.149813",{"slug":1890,"name":1890,"fn":1891,"description":1892,"org":1893,"tags":1894,"stars":1858,"repoUrl":1859,"updatedAt":1901},"competitor-analysis","analyze competitors and market positioning","Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1895,1898,1899,1900],{"name":1896,"slug":1897,"type":16},"Competitive Intelligence","competitive-intelligence",{"name":1847,"slug":1848,"type":16},{"name":1850,"slug":1851,"type":16},{"name":1856,"slug":1857,"type":16},"2026-04-18T04:46:55.79306",{"slug":1903,"name":1903,"fn":1904,"description":1905,"org":1906,"tags":1907,"stars":1858,"repoUrl":1859,"updatedAt":1918},"deepagents-thread-inspector","inspect local Deep Agents conversation threads","Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse ~\u002F.deepagents\u002F.state\u002Fsessions.db and a thread UUID or prefix.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1908,1911,1914,1915],{"name":1909,"slug":1910,"type":16},"Agents","agents",{"name":1912,"slug":1913,"type":16},"Debugging","debugging",{"name":9,"slug":8,"type":16},{"name":1916,"slug":1917,"type":16},"SQLite","sqlite","2026-07-24T06:08:57.102689",{"slug":1920,"name":1920,"fn":1921,"description":1922,"org":1923,"tags":1924,"stars":1858,"repoUrl":1859,"updatedAt":1935},"langgraph-docs","build stateful agents with LangGraph","Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1925,1926,1929,1932],{"name":1909,"slug":1910,"type":16},{"name":1927,"slug":1928,"type":16},"Documentation","documentation",{"name":1930,"slug":1931,"type":16},"LangGraph","langgraph",{"name":1933,"slug":1934,"type":16},"Multi-Agent","multi-agent","2026-05-13T06:11:03.650877",{"slug":1937,"name":1937,"fn":1938,"description":1939,"org":1940,"tags":1941,"stars":1858,"repoUrl":1859,"updatedAt":1950},"remember","capture knowledge into persistent memory","Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1942,1943,1944,1947],{"name":1909,"slug":1910,"type":16},{"name":1927,"slug":1928,"type":16},{"name":1945,"slug":1946,"type":16},"Knowledge Management","knowledge-management",{"name":1948,"slug":1949,"type":16},"Memory","memory","2026-05-13T06:10:58.510037",{"slug":1952,"name":1952,"fn":1953,"description":1954,"org":1955,"tags":1956,"stars":1858,"repoUrl":1859,"updatedAt":1964},"skill-creator","create agent skills and tool integrations","Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like \"create a skill\", \"new skill\", \"make a skill\", \"skill for X\", \"how do I create a skill\", or \"help me build a skill\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1957,1958,1961],{"name":1909,"slug":1910,"type":16},{"name":1959,"slug":1960,"type":16},"Engineering","engineering",{"name":1962,"slug":1963,"type":16},"Plugin Development","plugin-development","2026-05-13T06:10:59.88449",{"slug":1966,"name":1966,"fn":1967,"description":1968,"org":1969,"tags":1970,"stars":1858,"repoUrl":1859,"updatedAt":1974},"social-media","create optimized social media posts","Create social media posts optimized for engagement across platforms.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1971,1972,1973],{"name":1879,"slug":1880,"type":16},{"name":1847,"slug":1848,"type":16},{"name":1886,"slug":1887,"type":16},"2026-04-15T05:00:55.37452",{"slug":1976,"name":1976,"fn":1977,"description":1978,"org":1979,"tags":1980,"stars":1858,"repoUrl":1859,"updatedAt":1985},"web-research","conduct and synthesize web research","Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1981,1982,1983,1984],{"name":1909,"slug":1910,"type":16},{"name":1933,"slug":1934,"type":16},{"name":1850,"slug":1851,"type":16},{"name":1869,"slug":1870,"type":16},"2026-05-13T06:11:04.930044",{"slug":1987,"name":1987,"fn":1988,"description":1989,"org":1990,"tags":1991,"stars":2002,"repoUrl":2003,"updatedAt":2004},"mermaid-diagrams","embed Mermaid diagrams in documentation","Embed Mermaid diagrams in generated wiki pages. Use whenever documenting a runtime or request flow, a call sequence, a state machine or lifecycle, a data model or entity relationships, or non-trivial control flow, since these are clearer as a diagram than as prose. Also use when an update run touches a page that already contains a mermaid fence, or a page that contains a text fence a previous run degraded.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1992,1995,1996,1999],{"name":1993,"slug":1994,"type":16},"Diagrams","diagrams",{"name":1927,"slug":1928,"type":16},{"name":1997,"slug":1998,"type":16},"Markdown","markdown",{"name":2000,"slug":2001,"type":16},"Technical Writing","technical-writing",12181,"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Fopenwiki","2026-07-24T06:09:01.089597",{"slug":2006,"name":2006,"fn":2007,"description":2008,"org":2009,"tags":2010,"stars":2002,"repoUrl":2003,"updatedAt":2017},"write-connector","implement OpenWiki source connectors","Add a new built-in OpenWiki source connector. Use when a user asks to create or implement an OpenWiki connector.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2011,2014],{"name":2012,"slug":2013,"type":16},"API Development","api-development",{"name":2015,"slug":2016,"type":16},"Integrations","integrations","2026-07-18T05:48:23.961804",41,{"items":2020,"total":119},[2021,2038,2048],{"slug":2022,"name":2022,"fn":2023,"description":2024,"org":2025,"tags":2026,"stars":23,"repoUrl":24,"updatedAt":2037},"langsmith-dataset","create and manage LangSmith eval datasets","INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response, single_step, trajectory, RAG), CLI management commands, SDK-based creation, and example management. Uses the langsmith CLI tool.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2027,2030,2033,2034],{"name":2028,"slug":2029,"type":16},"Datasets","datasets",{"name":2031,"slug":2032,"type":16},"Evals","evals",{"name":21,"slug":22,"type":16},{"name":2035,"slug":2036,"type":16},"LLM","llm","2026-04-11T04:40:26.848233",{"slug":2039,"name":2039,"fn":2040,"description":2041,"org":2042,"tags":2043,"stars":23,"repoUrl":24,"updatedAt":2047},"langsmith-evaluator","build LangSmith evaluation pipelines","INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2044,2045,2046],{"name":2031,"slug":2032,"type":16},{"name":21,"slug":22,"type":16},{"name":2035,"slug":2036,"type":16},"2026-04-11T04:40:28.078348",{"slug":4,"name":4,"fn":5,"description":6,"org":2049,"tags":2050,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[2051,2052,2053],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16}]