Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug]: "Success/failure" behavior is not consistent for file reading and editing #6262

Open
1 task done
neubig opened this issue Jan 14, 2025 · 3 comments · May be fixed by #6263
Open
1 task done

[Bug]: "Success/failure" behavior is not consistent for file reading and editing #6262

neubig opened this issue Jan 14, 2025 · 3 comments · May be fixed by #6263
Labels
bug Something isn't working fix-me Attempt to fix this issue with OpenHands

Comments

@neubig
Copy link
Contributor

neubig commented Jan 14, 2025

Is there an existing issue for the same bug?

  • I have checked the existing issues.

Describe the bug and reproduction steps

In "ran a python command" and "ran a bash command", we have success/failure indicators about whether the command worked well, in the form of green checks or red xs when the command worked or didn't work.

Screenshot 2025-01-14 at 3 59 23 AM

However, when using tools for file reading/editing, currently we get results that are not consistent. If it succeeds we get "Read the contents of a file" or "edited the contents of a file" with no success indicator, and if it fails we get "Ran a python command" with no success indicator.

Screenshot 2025-01-14 at 4 00 14 AM

The expected behavior is:

  • Success: "Read the contents of a file" or "Edited the contents of a file" with a success indicator
  • Failure: "Read the contents of a file" or "Edited the contents of a file" with a failure indicator

We should:

  1. Write tests demonstrating the desired behavior
  2. Run these new tests by following the standard workflow in fe-unit-tests.yml to make sure that they fail (demonstrating that the current behavior is undesired)
  3. Fix the behavior and make sure that the tests pass

OpenHands Installation

app.all-hands.dev

OpenHands Version

No response

Operating System

None

Logs, Errors, Screenshots, and Additional Context

No response

@neubig neubig added bug Something isn't working fix-me Attempt to fix this issue with OpenHands labels Jan 14, 2025
@openhands-agent
Copy link
Contributor

OpenHands started fixing the issue! You can monitor the progress here.

@openhands-agent
Copy link
Contributor

A potential fix has been generated and a draft PR #6263 has been created. Please review the changes.

@mamoodi
Copy link
Collaborator

mamoodi commented Jan 14, 2025

Related: #5725

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working fix-me Attempt to fix this issue with OpenHands
Projects
None yet
3 participants