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

Enh: Always write log to traj directory #588

Closed klieret closed 2 weeks ago

klieret commented 2 weeks ago

Closes #581

codecov[bot] commented 2 weeks ago

Codecov Report

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

Project coverage is 76.29%. Comparing base (b72abc7) to head (1e8b017). Report is 1 commits behind head on main.

Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #588 +/- ## ========================================== + Coverage 76.16% 76.29% +0.12% ========================================== Files 21 21 Lines 3293 3311 +18 ========================================== + Hits 2508 2526 +18 Misses 785 785 ```

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