langsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
Documentation
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:
- š "Debug my agent" or "What went wrong?"
- š "Show me recent traces" or "What happened?"
- ā "Check for errors" or "Why did it fail?"
- š¾ "Analyze memory operations" or "Check LTM"
- š "Review agent performance" or "Check token usage"
- š§ "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:
- ā Number of traces found
- ā ļø Any errors or failures
- š ļø Tools that were called
- ā±ļø Execution times
- š° Token usage
Example response format:
Found 3 traces in the last 5 minutes:
Trace 1: ā
Success
- Agent: memento
- Tools: recall_memories, create_entities
- Duration: 2.3s
- Tokens: 1,245
Trace 2: ā Error
- Agent: cypher
- Error: "Neo4j connection timeout"
- Duration: 15.1s
- Failed at: search_nodes tool
Trace 3: ā
Success
- Agent: memento
- Tools: store_memory
- Duration: 1.8s
- Tokens: 892
š” 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:
- šÆ What the agent was trying to do
- š ļø Which tools were called (in order)
- ā Tool results (success/failure)
- ā Error messages (if any)
- š” Root cause analysis
- š§ Suggested fix
Example response format:
Deep Dive Analysis - Trace abc123
Goal: User asked "Find all projects in Neo4j"
Execution Flow:
1. ā
search_nodes(query: "projects")
ā Found 24 nodes
2. ā get_node_details(node_id: "proj_123")
ā Error: "Node not found"
ā This is the failure point
3. ā¹ļø 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:
1. Add error handling in get_node_details tool
2. Filter deleted nodes in search results
3. 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:
ā
Session exported successfully!
Location: langsmith-debug/session-20251224-143022/
- Traces: 42 files
- Threads: 8 files
You can now:
1. Review individual trace files
2. Share folder with team
3. Analyze with external tools
4. 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:
- š Total errors found
- ā Error types and frequency
- š When errors occurred
- šÆ Which agents/tools failed
- š” Common patterns
Example response format:
Error Analysis - Last 30 Minutes
Total Traces: 50
Failed Traces: 7 (14% failure rate)
Error Breakdown:
1. Neo4j Connection Timeout (4 occurrences)
- Agent: cypher
- Tool: search_nodes
- First occurred: 14:32
- Last occurred: 14:45
- Pattern: Happens during peak load
2. Memory Store Failed (2 occurrences)
- Agent: memento
- Tool: store_memory
- Error: "Pinecone rate limit exceeded"
- Occurred: 14:38, 14:41
3. Tool Not Found (1 occurrence)
- Agent: sqlcrm
- Attempted tool: "export_report" (doesn't exist)
- Occurred: 14:35
š” Recommendations:
1. Add retry logic for Neo4j timeouts
2. Implement rate limiting for Pinecone
3. 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 migh
Use Cases
- š "Debug my agent" or "What went wrong?"
- š "Show me recent traces" or "What happened?"
- ā "Check for errors" or "Why did it fail?"
- š¾ "Analyze memory operations" or "Check LTM"
- š "Review agent performance" or "Check token usage"
Quick Info
- Source
- ComposioHQ
- Category
- Development & Code Tools
- Repository
- View Repo
- Scraped At
- Jan 26, 2026
Tags
Related Skills
2d-games
2D game development principles. Sprites, tilemaps, physics, camera.
add_repo_inst
Please browse the current repository under /workspace/{{ REPO_FOLDER_NAME }}, look at the documentation and relevant code, and understand the purpose of this repository.
address_pr_comments
First, check the branch {{ BRANCH_NAME }} and read the diff against the main branch to understand the purpose.