langsmith-tracing

name	langsmith-tracing
description	LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
allowed-tools	Read, Grep, Write, Edit, Bash, Glob, WebFetch
graph	{"domains":["domain:software-engineering"],"specializations":["specialization:ai-agents-conversational"],"skillAreas":["skill-area:agent-debugging-logging","skill-area:agent-simulation-testing"],"roles":["role:ml-engineer","role:backend-engineer"],"workflows":["workflow:ml-model-lifecycle","workflow:feature-development"]}

langsmith-tracing

Configure LangSmith observability and tracing for LLM applications built with LangChain and LangGraph frameworks.

Overview

LangSmith is the managed observability suite by LangChain that provides:

• Dashboards and alerting for LLM applications
• Human-in-the-loop evaluation capabilities
• Deep LangChain/LangGraph integration
• Run Tree model for nested traces
• MCP connectivity to Claude, VSCode

Capabilities

Core Tracing Setup

• Initialize LangSmith client and API configuration
• Configure project/workspace settings
• Set up trace collection and sampling
• Enable debug logging for agent execution

Integration Patterns

• LangChain chain tracing with automatic instrumentation
• LangGraph workflow state tracking
• Custom span creation for non-LangChain code
• Parent-child trace relationships

Debugging Features

• Fetch execution traces for analysis
• Query run history and metadata
• Export traces for offline analysis
• Compare runs across different versions

Usage

Environment Setup

# Set required environment variables
export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<project-name>

Python Integration

from langsmith import Client, traceable
from langchain.callbacks.tracers import LangChainTracer

# Initialize client
client = Client()

# Use @traceable decorator for custom functions
@traceable(name="custom_operation")
def my_function(input_data):
    # Your logic here
    return result

# Initialize tracer for LangChain
tracer = LangChainTracer(project_name="my-project")

# Use with LangChain chains
chain.invoke(input, config={"callbacks": [tracer]})

Trace Retrieval

# Fetch traces from LangSmith
runs = client.list_runs(
    project_name="my-project",
    start_time=datetime.now() - timedelta(hours=24),
    execution_order=1,  # Root runs only
    error=False,  # Successful runs only
)

for run in runs:
    print(f"Run ID: {run.id}")
    print(f"Latency: {run.latency_p99}")
    print(f"Tokens: {run.total_tokens}")

Task Definition

When used in a babysitter process, this skill produces:

const langsmithTracingTask = defineTask({
  name: 'langsmith-tracing-setup',
  description: 'Configure LangSmith tracing for the application',

  inputs: {
    projectName: { type: 'string', required: true },
    apiKeyEnvVar: { type: 'string', default: 'LANGCHAIN_API_KEY' },
    samplingRate: { type: 'number', default: 1.0 },
    enableDebug: { type: 'boolean', default: false }
  },

  outputs: {
    configured: { type: 'boolean' },
    projectUrl: { type: 'string' },
    artifacts: { type: 'array' }
  },

  async run(inputs, taskCtx) {
    return {
      kind: 'skill',
      title: `Configure LangSmith tracing for ${inputs.projectName}`,
      skill: {
        name: 'langsmith-tracing',
        context: {
          projectName: inputs.projectName,
          : inputs.,
          : inputs.,
          : inputs.,
          : [
            ,
            ,
            ,
            ,
            
          ]
        }
      },
      : {
        : ,
        : 
      }
    };
  }
});

Applicable Processes

• llm-observability-monitoring
• agent-evaluation-framework
• react-agent-implementation
• conversation-quality-testing
• regression-testing-agent

External Dependencies

• LangSmith account and API key
• LangChain Python library
• langsmith Python package

References

• LangSmith Documentation
• LangSmith Fetch Skill
• Langfuse Integration
• Comet Opik MCP

Related Skills

• SK-OBS-002 langfuse-integration
• SK-OBS-003 phoenix-arize-setup
• SK-OBS-004 opentelemetry-llm

Related Agents

• AG-OPS-004 observability-engineer
• AG-SAF-004 agent-evaluator