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]: swe_bench/eval_infer.py type checking issues #6336

Open
1 task done
neubig opened this issue Jan 17, 2025 · 2 comments
Open
1 task done

[Bug]: swe_bench/eval_infer.py type checking issues #6336

neubig opened this issue Jan 17, 2025 · 2 comments
Labels
bug Something isn't working evaluation Related to running evaluations with OpenHands fix-me Attempt to fix this issue with OpenHands

Comments

@neubig
Copy link
Contributor

neubig commented Jan 17, 2025

Is there an existing issue for the same bug?

  • I have checked the existing issues.

Describe the bug and reproduction steps

There are a number of issues in eval_infer.py for swe_bench that would not pass mypy checks.

For instance in this line:
https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation/benchmarks/swe_bench/eval_infer.py#L94

The type of metadata is EvalMetadata | None, but the None type is not accounted for. We should run basic linting and type safety checks to tighten up the code and reduce unexpected errors.

OpenHands Installation

Docker command in README

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 17, 2025
@openhands-agent
Copy link
Contributor

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

@openhands-agent
Copy link
Contributor

An attempt was made to automatically fix this issue, but it was unsuccessful. A branch named 'openhands-fix-issue-6336' has been created with the attempted changes. You can view the branch here. Manual intervention may be required.

Additional details about the failure:
The issue has not been successfully resolved based on the evidence provided. The AI agent attempted to run mypy type checking on the specified files (eval_infer.py and mapping.py), but the command failed with exit code 1, indicating type checking errors are still present.

The original issue pointed out type safety problems in eval_infer.py, specifically that the metadata variable's potential None value was not being properly handled. The mypy failure suggests these type safety issues have not been fixed yet, as the type checker is still detecting problems. No actual code changes were shown in the provided thread that would address the identified typing issues.

To resolve this issue, code changes would need to be made to properly handle the None case for the metadata variable and any other type safety issues detected by mypy. Since no such changes are evident and the type checker is still failing, the bug remains unresolved.

@mamoodi mamoodi added the evaluation Related to running evaluations with OpenHands label Jan 18, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working evaluation Related to running evaluations with OpenHands fix-me Attempt to fix this issue with OpenHands
Projects
None yet
Development

No branches or pull requests

3 participants