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

# LangChain

> Durable execution, policy, and approvals for LangChain agents in Python

A LangChain agent runs on Rebuno unchanged apart from two seams. The chat model
takes a Rebuno HTTP client, so every model call is recorded as an `llm_call`
step, and tools are declared with `@tool`, so every tool call is recorded as a
`tool_call` step. On a re-dispatch the agent runs from the top and recorded
steps replay instead of calling the model or the tool again.

## Install

```bash theme={"theme":{"light":"min-light","dark":"material-theme-ocean"}}
pip install rebuno langchain langchain-openai
```

## Model calls

`ChatOpenAI` accepts an async HTTP client through `http_async_client`. Pass
`http_client()`:

```python theme={"theme":{"light":"min-light","dark":"material-theme-ocean"}}
from langchain_openai import ChatOpenAI
from rebuno import http_client

llm = ChatOpenAI(model="gpt-5.5", http_async_client=http_client())
```

Streaming works the same way. A streamed call is recorded as the assembled
response and replays as a stream. See [LLM calls](/sdk/python/llm-calls).

## Tools

`@tool` keeps the function's signature and docstring, so LangChain binds it as
a plain function:

```python theme={"theme":{"light":"min-light","dark":"material-theme-ocean"}}
from rebuno import tool


@tool("lookup_orders", idempotency="safe_to_retry")
async def lookup_orders(customer_id: str) -> dict:
    """Look up a customer's recent orders."""
    ...


@tool("send_email", idempotency="at_most_once")
async def send_email(body: str) -> dict:
    """Email the support summary."""
    ...
```

Mark anything with a side effect, such as sending an email or creating a
ticket, `at_most_once`. See [idempotency](/sdk/python/tools#idempotency).

## The agent

```python theme={"theme":{"light":"min-light","dark":"material-theme-ocean"}}
from langchain.agents import create_agent
from rebuno import Agent


async def process(query: str) -> dict:
    llm = ChatOpenAI(model="gpt-5.5", http_async_client=http_client())
    graph = create_agent(model=llm, tools=[lookup_orders, send_email])
    result = await graph.ainvoke({"messages": [{"role": "user", "content": query}]})
    return {"answer": result["messages"][-1].content}


agent = Agent("support")

if __name__ == "__main__":
    agent.run(process)
```

## What Rebuno adds

* **Policy.** Every model and tool call is checked against [policy](/policy)
  before it runs. A denied tool returns the rule's reason to the model as the
  tool result, so the agent can take a different path.
* **Approvals.** A tool that requires approval parks the execution. Once it's
  approved, the agent is dispatched again, the earlier steps replay, and the
  approved call runs.
* **Recovery.** If the worker dies partway through, the next dispatch replays
  every completed step and continues from the first one that didn't finish.
  Model calls that already ran are not paid for twice.

## Full example

[`examples/frameworks/python/langchain_agent.py`](https://github.com/rebuno/rebuno/blob/main/examples/frameworks/python/langchain_agent.py)
is a support agent that investigates a customer issue, creates a ticket, and
emails a summary after approval.