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

Doc: Update usage_faq.md to include the claude-sonnet-3.5 shortcut #606

Closed samefarrar closed 1 week ago

samefarrar commented 1 week ago

[!NOTE] IF YOU SEE A LOT OF FORMATTING RELATED MERGE CONFLICTS PLEASE MAKE SURE THAT YOU ARE USING OUR CODE FORMATTER. Please see our development guide.

Reference Issues/PRs

What does this implement/fix? Explain your changes.

In sweagent/agent/models.py, claude-3.5-sonnet is implemented, but the documentation for usage doesn't yet reflect that.

klieret commented 1 week ago

Thanks!