langchain-ai / langchain-ai/langgraph-fullstack-python

Handling Interrupts.

Open
#4 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
155
Forks
40
PR merge metrics
No merged PRs in 30d

Description

I just can't find a way to change your code to handle interrupts. Could you please help?

I have a react agent, created with create_react_agent, which has the following tool:

def get_customer_name() -> str:
    """Get customer name.

    Returns:
        str: The customer name.
    """
    options: List[str] = ...

    selected_customer = interrupt(
        {   
            "text": "Select the customer name: ",
            "options": options,
        }
    )

    return selected_customer

What I expect to happen is to somehow read text and options in the frontend. I know this is possible because I managed to do this using CopilotKit.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the interrupt created inside the get_customer_name tool and the create_react_agent entry point to see how its text and options could reach the frontend. Done means the frontend can read those values and provide a response that resumes the agent; the issue does not name files or tests to run.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
full-stack
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.