langsmith-fetch

LangSmith Fetch - Agent Debugging Skill

Debug LangChain and LangGraph agents by fetching execution traces directly from LangSmith Studio in your terminal.

When to Use This Skill

Automatically activate when user mentions:

🐛 "Debug my agent" or "What went wrong?"

🔍 "Show me recent traces" or "What happened?"

❌ "Check for errors" or "Why did it fail?"

💾 "Analyze memory operations" or "Check LTM"

📊 "Review agent performance" or "Check token usage"

🔧 "What tools were called?" or "Show execution flow"

Prerequisites

1. Install langsmith-fetch

pip install langsmith-fetch

2. Set Environment Variables

export LANGSMITH_API_KEY="your_langsmith_api_key"
export LANGSMITH_PROJECT="your_project_name"

Verify setup:

echo $LANGSMITH_API_KEY
echo $LANGSMITH_PROJECT

Core Workflows

Workflow 1: Quick Debug Recent Activity

When user asks: "What just happened?" or "Debug my agent"

Execute:

langsmith-fetch traces --last-n-minutes 5 --limit 5 --format pretty

Analyze and report:

✅ Number of traces found

⚠️ Any errors or failures

🛠️ Tools that were called

⏱️ Execution times

💰 Token usage

Example response format:

Found 3 traces in the last 5 minutes:
Trace 1: ✅ Success
Agent: memento

Tools: recall_memories, create_entities

Duration: 2.3s

Tokens: 1,245
Trace 2: ❌ Error
Agent: cypher

Error: "Neo4j connection timeout"

Duration: 15.1s

Failed at: search_nodes tool
Trace 3: ✅ Success
Agent: memento

Tools: store_memory

Duration: 1.8s

Tokens: 892
💡 Issue found: Trace 2 failed due to Neo4j timeout. Recommend checking database connection.

---

Workflow 2: Deep Dive Specific Trace

When user provides: Trace ID or says "investigate that error"

Execute:

langsmith-fetch trace <trace-id> --format json

Analyze JSON and report:

🎯 What the agent was trying to do

🛠️ Which tools were called (in order)

✅ Tool results (success/failure)

❌ Error messages (if any)

💡 Root cause analysis

🔧 Suggested fix

Example response format:

Deep Dive Analysis - Trace abc123
Goal: User asked "Find all projects in Neo4j"
Execution Flow:
✅ search_nodes(query: "projects")

   → Found 24 nodes
❌ get_node_details(node_id: "proj_123")

   → Error: "Node not found"
   → This is the failure point
⏹️ Execution stopped
Root Cause:
The search_nodes tool returned node IDs that no longer exist in the database,
possibly due to recent deletions.
Suggested Fix:
Add error handling in get_node_details tool

Filter deleted nodes in search results

Update cache invalidation strategy
Token Usage: 1,842 tokens ($0.0276)
Execution Time: 8.7 seconds

---

Workflow 3: Export Debug Session

When user says: "Save this session" or "Export traces"

Execute:

# Create session folder with timestamp
SESSION_DIR="langsmith-debug/session-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$SESSION_DIR"
Export traces

langsmith-fetch traces "$SESSION_DIR/traces" --last-n-minutes 30 --limit 50 --include-metadata
Export threads (conversations)

langsmith-fetch threads "$SESSION_DIR/threads" --limit 20

Report:

✅ Session exported successfully!
Location: langsmith-debug/session-20251224-143022/
Traces: 42 files

Threads: 8 files
You can now:
Review individual trace files

Share folder with team

Analyze with external tools

Archive for future reference
Session size: 2.3 MB

---

Workflow 4: Error Detection

When user asks: "Show me errors" or "What's failing?"

Execute:

# Fetch recent traces
langsmith-fetch traces --last-n-minutes 30 --limit 50 --format json > recent-traces.json
Search for errors

grep -i "error\|failed\|exception" recent-traces.json

Analyze and report:

📊 Total errors found

❌ Error types and frequency

🕐 When errors occurred

🎯 Which agents/tools failed

💡 Common patterns

Example response format:

Error Analysis - Last 30 Minutes
Total Traces: 50
Failed Traces: 7 (14% failure rate)
Error Breakdown:
Neo4j Connection Timeout (4 occurrences)

   - Agent: cypher
   - Tool: search_nodes
   - First occurred: 14:32
   - Last occurred: 14:45
   - Pattern: Happens during peak load
Memory Store Failed (2 occurrences)

   - Agent: memento
   - Tool: store_memory
   - Error: "Pinecone rate limit exceeded"
   - Occurred: 14:38, 14:41
Tool Not Found (1 occurrence)

   - Agent: sqlcrm
   - Attempted tool: "export_report" (doesn't exist)
   - Occurred: 14:35
💡 Recommendations:
Add retry logic for Neo4j timeouts

Implement rate limiting for Pinecone

Fix sqlcrm tool configuration

---

Common Use Cases

Use Case 1: "Agent Not Responding"

User says: "My agent isn't doing anything"

Steps:

Check if traces exist:

langsmith-fetch traces --last-n-minutes 5 --limit 5

If NO traces found:

- Tracing might be disabled
- Check: LANGCHAIN_TRACING_V2=true in environment
- Check: LANGCHAIN_API_KEY is set
- Verify agent actually ran

If traces found:

- Review for errors
- Check execution time (hanging?)
- Verify tool calls completed

---

Use Case 2: "Wrong Tool Called"

User says: "Why did it use the wrong tool?"

Steps:

Get the specific trace

Review available tools at execution time

Check agent's reasoning for tool selection

Examine tool descriptions/instructions

Suggest prompt or tool config improvements

---

Use Case 3: "Memory Not Working"

User says: "Agent doesn't remember things"

Steps:

Search for memory operations:

langsmith-fetch traces --last-n-minutes 10 --limit 20 --format raw | grep -i "memory\|recall\|store"

Check:

- Were memory tools called?
- Did recall return results?
- Were memories actually stored?
- Are retrieved memories being used?

---

Use Case 4: "Performance Issues"

User says: "Agent is too slow"

Steps:

Export with metadata:

langsmith-fetch traces ./perf-analysis --last-n-minutes 30 --limit 50 --include-metadata

Analyze:

- Execution time per trace
- Tool call latencies
- Token usage (context size)
- Number of iterations
- Slowest operations

Identify bottlenecks and suggest optimizations

---

Output Format Guide

Pretty Format (Default)

langsmith-fetch traces --limit 5 --format pretty

Use for: Quick visual inspection, showing to users

JSON Format

langsmith-fetch traces --limit 5 --format json

Use for: Detailed analysis, syntax-highlighted review

Raw Format

langsmith-fetch traces --limit 5 --format raw

Use for: Piping to other commands, automation

---

Advanced Features

Time-Based Filtering

# After specific timestamp
langsmith-fetch traces --after "2025-12-24T13:00:00Z" --limit 20
Last N minutes (most common)

langsmith-fetch traces --last-n-minutes 60 --limit 100

Include Metadata

# Get extra context
langsmith-fetch traces --limit 10 --include-metadata
Metadata includes: agent type, model, tags, environment

Concurrent Fetching (Faster)

# Speed up large exports
langsmith-fetch traces ./output --limit 100 --concurrent 10

---

Troubleshooting

"No traces found matching criteria"

Possible causes:

No agent activity in the timeframe

Tracing is disabled

Wrong project name

API key issues

Solutions:

# 1. Try longer timeframe
langsmith-fetch traces --last-n-minutes 1440 --limit 50
2. Check environment

echo $LANGSMITH_API_KEY
echo $LANGSMITH_PROJECT
3. Try fetching threads instead

langsmith-fetch threads --limit 10
4. Verify tracing is enabled in your code

Check for: LANGCHAIN_TRACING_V2=true

"Project not found"

Solution:

# View current config
langsmith-fetch config show
Set correct project

export LANGSMITH_PROJECT="correct-project-name"
Or configure permanently

langsmith-fetch config set project "your-project-name"

Environment variables not persisting

Solution:

# Add to shell config file (~/.bashrc or ~/.zshrc)
echo 'export LANGSMITH_API_KEY="your_key"' >> ~/.bashrc
echo 'export LANGSMITH_PROJECT="your_project"' >> ~/.bashrc
Reload shell config

source ~/.bashrc

---

Best Practices

1. Regular Health Checks

# Quick check after making changes
langsmith-fetch traces --last-n-minutes 5 --limit 5

2. Organized Storage

langsmith-debug/
├── sessions/
│   ├── 2025-12-24/
│   └── 2025-12-25/
├── error-cases/
└── performance-tests/

3. Document Findings

When you find bugs:

Export the problematic trace

Save to error-cases/ folder

Note what went wrong in a README

Share trace ID with team

4. Integration with Development

# Before committing code
langsmith-fetch traces --last-n-minutes 10 --limit 5
If errors found

langsmith-fetch trace <error-id> --format json > pre-commit-error.json

---

Quick Reference

# Most common commands
Quick debug

langsmith-fetch traces --last-n-minutes 5 --limit 5 --format pretty
Specific trace

langsmith-fetch trace <trace-id> --format pretty
Export session

langsmith-fetch traces ./debug-session --last-n-minutes 30 --limit 50
Find errors

langsmith-fetch traces --last-n-minutes 30 --limit 50 --format raw | grep -i error
With metadata

langsmith-fetch traces --limit 10 --include-metadata

---

Resources

LangSmith Fetch CLI: https://github.com/langchain-ai/langsmith-fetch

LangSmith Studio: https://smith.langchain.com/

LangChain Docs: https://docs.langchain.com/

This Skill Repo: https://github.com/OthmanAdi/langsmith-fetch-skill

---

Notes for Claude

Always check if langsmith-fetch is installed before running commands

Verify environment variables are set

Use --format pretty for human-readable output

Use --format json when you need to parse and analyze data

When exporting sessions, create organized folder structures

Always provide clear analysis and actionable insights

If commands fail, help troubleshoot configuration issues

---

Version: 0.1.0
Author: Ahmad Othman Ammar Adi
License: MIT
Repository: https://github.com/OthmanAdi/langsmith-fetch-skill