Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计提醒

langsmith-traces朗史密斯痕迹

Agent Skill

langsmith-traces 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,943

周安装

105

GitHub Stars

638

下载量

1,130
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:langsmith-traces(朗史密斯痕迹)
来源仓库:https://github.com/langchain-ai/langchain-skills
仓库路径:skills/langsmith-traces
安装命令:
npx skills add https://github.com/langchain-ai/langchain-skills --skill 'Langsmith Traces'
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/langchain-ai/langchain-skills --skill 'Langsmith Traces'

简介

用于查找、检索和筛选相关信息。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

  • 适合根据关键词快速定位候选结果。
  • 通过 GitHub 安装并使用 npx 命令激活。
  • 需确认权限范围和维护状态,注意是否触发联网或命令执行。
  • langsmith-traces 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

LANGSMITH_API_KEY=lsv2_pt_your_api_key_here          # Required
LANGSMITH_PROJECT=your-project-name                   # Optional: default project
LANGSMITH_WORKSPACE_ID=your-workspace-id              # Optional: for org-scoped keys

Python Dependencies

pip install langsmith click rich python-dotenv

TypeScript Dependencies

npm install langsmith commander chalk cli-table3 ora dotenv
npm install -D tsx typescript @types/node

<trace_langchain_oss> For LangChain/LangGraph apps, tracing is automatic. Just set environment variables:

export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=<your-api-key>
export OPENAI_API_KEY=<your-openai-api-key>  # or your LLM provider's key

Optional variables:

  • LANGSMITH_PROJECT - specify project name (defaults to "default")
  • LANGCHAIN_CALLBACKS_BACKGROUND=false - use for serverless to ensure traces complete before function exit (Python) </trace_langchain_oss>

<trace_other_frameworks> For non-LangChain apps, if the framework has native OpenTelemetry support, use LangSmith's OpenTelemetry integration.

If the app is NOT using a framework, or using one without automatic OTel support, use the traceable decorator/wrapper and wrap your LLM client.

client = wrap_openai(OpenAI())

@traceable def my_llm_pipeline(question: str) -> str: resp = client.chat.completions.create(model="gpt-4o-mini", messages=[{"role": "user", "content": question}],) return resp.choices[0].message.content

Nested tracing example

@traceable def rag_pipeline(question: str) -> str: docs = retrieve_docs(question) return generate_answer(question, docs)

@traceable(name="retrieve_docs") def retrieve_docs(query: str) -> list[str]: return docs

@traceable(name="generate_answer") def generate_answer(question: str, docs: list[str]) -> str: return client.chat.completions.create(...)

</python>

<typescript>
Use traceable() wrapper and wrapOpenAI() for automatic tracing.

import { traceable } from "langsmith/traceable"; import { wrapOpenAI } from "langsmith/wrappers"; import OpenAI from "openai";

const client = wrapOpenAI(new OpenAI());

const myLlmPipeline = traceable(async (question: string): Promise<string> => { const resp = await client.chat.completions.create({ model: "gpt-4o-mini", messages: [{ role: "user", content: question }], }); return resp.choices[0].message.content || ""; }, { name: "my_llm_pipeline" });

// Nested tracing example const retrieveDocs = traceable(async (query: string): Promise<string[]> => { return docs; }, { name: "retrieve_docs" });

const generateAnswer = traceable(async (question: string, docs: string[]): Promise<string> => { const resp = await client.chat.completions.create({ model: "gpt-4o-mini", messages: [{ role: "user", content: ${question}\nContext: ${docs.join("\n")} }], }); return resp.choices[0].message.content || ""; }, { name: "generate_answer" });

const ragPipeline = traceable(async (question: string): Promise<string> => { const docs = await retrieveDocs(question); return await generateAnswer(question, docs); }, { name: "rag_pipeline" });


Best Practices:

- **Apply traceable to all nested functions** you want visible in LangSmith
- **Wrapped clients auto-trace all calls** — `wrap_openai()`/`wrapOpenAI()` records every LLM call
- **Name your traces** for easier filtering
- **Add metadata** for searchability </trace_other_frameworks>

<traces_vs_runs> Use the included scripts to query trace data.

**Understanding the difference is critical:**

- **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.
- **Run** = A single node in the tree (one LLM call, one tool call, etc.)

**Generally, query traces first** — they provide complete context and preserve hierarchy needed for trajectory analysis and dataset generation. </traces_vs_runs>

<command_structure> Two command groups with consistent behavior:

query_traces.py / query_traces.ts ├── traces (operations on trace trees - USE THIS FIRST) │ ├── list - List traces (filters apply to root run) │ ├── get - Get single trace with full hierarchy │ └── export - Export traces to JSONL files (one file per trace) │ └── runs (operations on individual runs - for specific analysis) ├── list - List runs (flat, filters apply to any run) ├── get - Get single run └── export - Export runs to single JSONL file (flat)


**Key differences:**

|  | `traces *` | `runs *` |
| --- | --- | --- |
| Filters apply to | Root run only | Any matching run |
| `--run-type` | Not available | Available |
| Returns | Full hierarchy | Flat list |
| Export output | Directory (one file/trace) | Single file |
| </command_structure> |  |  |

<querying_traces> Python and Typescript scripts are both provided, and identical in usage. You should use whichever script matches your current project context.

# List traces with metadata (timing, tokens, costs)

python query_traces.py traces list --limit 10 --include-metadata

# Filter traces by time

python query_traces.py traces list --last-n-minutes 60 python query_traces.py traces list --since 2025-01-20T10:00:00Z

# Get specific trace with full hierarchy

python query_traces.py traces get

# List traces and show hierarchy inline

python query_traces.py traces list --limit 5 --show-hierarchy

# Export traces to JSONL (one file per trace, includes all runs)

python query_traces.py traces export./traces --limit 20 --full

# Filter traces by performance

python query_traces.py traces list --min-latency 5.0 --limit 10 # Slow traces (>= 5s) python query_traces.py traces list --error --last-n-minutes 60 # Failed traces

# List specific run types (flat list)

python query_traces.py runs list --run-type llm --limit 20

</python>

<typescript> Query traces using the TypeScript CLI script.

# List recent traces (most common operation)
npx tsx query_traces.ts traces list --limit 10 --project my-project

# List traces with metadata (timing, tokens, costs)
npx tsx query_traces.ts traces list --limit 10 --include-metadata

# Filter traces by time
npx tsx query_traces.ts traces list --last-n-minutes 60
npx tsx query_traces.ts traces list --since 2025-01-20T10:00:00Z

# Get specific trace with full hierarchy
npx tsx query_traces.ts traces get <trace-id>

# List traces and show hierarchy inline
npx tsx query_traces.ts traces list --limit 5 --show-hierarchy

# Export traces to JSONL (one file per trace, includes all runs)
npx tsx query_traces.ts traces export ./traces --limit 20 --full

# Filter traces by performance
npx tsx query_traces.ts traces list --min-latency 5.0 --limit 10    # Slow traces (>= 5s)
npx tsx query_traces.ts traces list --error --last-n-minutes 60     # Failed traces

# List specific run types (flat list)
npx tsx query_traces.ts runs list --run-type llm --limit 20

Basic filters:

  • --trace-ids abc,def - Filter to specific traces
  • --limit N - Max results
  • --project NAME - Project name
  • --last-n-minutes N - Time filter
  • --since TIMESTAMP - Time filter (ISO format)
  • --error / --no-error - Error status
  • --name PATTERN - Name contains (case-insensitive)

Performance filters:

  • --min-latency SECONDS - Minimum latency (e.g., 5 for >= 5s)
  • --max-latency SECONDS - Maximum latency
  • --min-tokens N - Minimum total tokens
  • --tags tag1,tag2 - Has any of these tags

Advanced filter:

  • --filter QUERY - Raw LangSmith filter query for complex cases (feedback, metadata, etc.)

<export_format> Export creates .jsonl files (one run per line) with these fields:

{"run_id": "...", "trace_id": "...", "name": "...", "run_type": "...", "parent_run_id": "...", "inputs": {...}, "outputs": {...}}

Use --include-io or --full to include inputs/outputs (required for dataset generation). </export_format>

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.26%
按下载量换算387

Claude

31.59%
按下载量换算357

Cursor

20.33%
按下载量换算230

Gemini CLI

10.77%
按下载量换算122

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills