LangChain

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

pip install rebuno langchain langchain-openai

Model calls

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

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.

Tools

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

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.

The agent

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 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 is a support agent that investigates a customer issue, creates a ticket, and emails a summary after approval.

Get started

Writing agents

Frameworks

Reference

Install

Model calls

Tools

The agent

What Rebuno adds

Full example

​Install

​Model calls

​Tools

​The agent

​What Rebuno adds

​Full example

Install

Model calls

Tools

The agent

What Rebuno adds

Full example