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
11.88k stars 1.19k forks source link

Enh: Start from clone of python conda environment for speedup #548

Closed klieret closed 1 month ago

klieret commented 1 month ago

Saves about 20s (out of 30s for setting up the conda env to begin with).

Currently only enabled for what's like the single issues (as opposed to the SWE-bench ones).

Todo:

Closes #491

codecov[bot] commented 1 month ago

Codecov Report

Attention: Patch coverage is 68.75000% with 5 lines in your changes missing coverage. Please review.

Project coverage is 76.17%. Comparing base (d9d9a9b) to head (d96c0d6). Report is 3 commits behind head on main.

Files Patch % Lines
sweagent/environment/swe_env.py 37.50% 5 Missing :warning:
Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #548 +/- ## ======================================= Coverage 76.16% 76.17% ======================================= Files 20 20 Lines 3239 3261 +22 ======================================= + Hits 2467 2484 +17 - Misses 772 777 +5 ```

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