> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fact0.io/llms.txt
> Use this file to discover all available pages before exploring further.

# LangChain

> Auto-instrument LangChain agents with telemetry and audit callbacks.

# LangChain

Fact0 ships a LangChain callback that records every chain, tool, and LLM call as a telemetry span, with optional audit events for sensitive actions.

## Install

```bash theme={null}
pip install fact0-sdk langchain
```

## Quick example

```python theme={null}
from langchain_openai import ChatOpenAI
from fact0.integrations.langchain import Fact0CallbackHandler
import fact0

client = fact0.Client(api_key="f0_live_...")

handler = Fact0CallbackHandler(
    client=client,
    agent_id="research-bot",
    audit_sensitive_actions=True,
)

llm = ChatOpenAI(model="gpt-4o", callbacks=[handler])
response = llm.invoke("Summarize Q3 results")
```

## What gets captured

| Callback event  | Telemetry               | Audit (when `audit_sensitive_actions=True`) |
| --------------- | ----------------------- | ------------------------------------------- |
| LLM start/end   | `MODEL_INVOCATION` span | -                                           |
| Tool start/end  | `TOOL_CALL` span        | `agent.tool.call`                           |
| Chain start/end | execution lifecycle     | `agent.run.start` / `agent.run.end`         |

## Configuration

```python theme={null}
handler = Fact0CallbackHandler(
    client=client,
    agent_id="support-bot",
    execution_metadata={"tenant": "acme", "env": "prod"},
)
```

| Option                    | Purpose                                           |
| ------------------------- | ------------------------------------------------- |
| `agent_id`                | Stable agent identifier shown in the dashboard    |
| `execution_metadata`      | Tags applied to every execution from this handler |
| `audit_sensitive_actions` | Also write `agent.tool.call` audit events         |

## Related

* [Telemetry client](/sdk/python/telemetry) for manual span control
* [LangGraph](/integrations/langgraph) for stateful graph agents