search

princeton-nlp / SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.
https://princeton-nlp.github.io/SWE-agent/
MIT License
11.86k stars 1.18k forks source link

Cap swebench version dependency #621

Closed carlosejimenez closed 4 days ago

carlosejimenez commented 5 days ago

What does this implement/fix? Explain your changes.

Caps the swebench package dependency <2.0.0 to avoid breaking changes in the major version update.

We should update SWE-agent to use the new swebench package in the near future, but this should avoid issues with new users of SWE-agent.

codecov[bot] commented 5 days ago

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Project coverage is 76.33%. Comparing base (3ae505c) to head (dfda189).

Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #621 +/- ## ======================================= Coverage 76.33% 76.33% ======================================= Files 23 23 Lines 3402 3402 ======================================= Hits 2597 2597 Misses 805 805 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.