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

Fixed #571 - show message that model arg is ignored in case of using Azure OpenAI #592

Closed jank closed 1 week ago

jank commented 1 week ago

…AzureOpenAI

Reference Issues/PRs

Fixes #571

What does this implement/fix? Explain your changes.

Log warning message that model command line arg is ignored in case of using AzureOpenAI.

codecov[bot] commented 1 week ago

Codecov Report

Attention: Patch coverage is 0% with 2 lines in your changes missing coverage. Please review.

Project coverage is 76.29%. Comparing base (5a473be) to head (3c4258f).

Files Patch % Lines
sweagent/agent/models.py 0.00% 2 Missing :warning:
Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #592 +/- ## ========================================== + Coverage 76.25% 76.29% +0.04% ========================================== Files 21 21 Lines 3318 3320 +2 ========================================== + Hits 2530 2533 +3 + Misses 788 787 -1 ```

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

jank commented 1 week ago

Just for the record. I created the original diff for this fix using SWE-Agent. A few manual changes were necessary as GPT-4 introduced an import of logging instead of using the available logger. Overall quite impressive work from the SWE-Agent team.

ofirpress commented 1 week ago

Cool! Thank you so much!