Installation
Setup
We recommend using UUIDs for session_id and user_id so traces can be grouped reliably across runs.
Usage
Pass the handler via LangChain’s config["callbacks"]:
Unlike other integrations, LangGraph does not use the instrument() pattern. You must pass the handler in config for each invocation.
What gets traced
Token usage
Token usage is extracted from LangChain’s usage_metadata (primary) or legacy llm_output.token_usage (fallback). The mapping is: input_tokens → prompt_tokens, output_tokens → completion_tokens. Reasoning tokens are subtracted from output_tokens when present.
This example builds a ReAct agent using LangGraph with two tools. We trace the agent via LangGraphCallbackHandler:
This produces a trace with: CHAIN (root) → LLM (model call) → TOOL (get_weather) → TOOL (get_population) → LLM (final response).