Daniel Rice

Terrible, confusing behavior. I cannot tell what has been undone, more times than not it's too much. Please make it VIM-like Thanks @Chillee for the fix. This is better than...

vim.enableNeovim is set to false for me

Could be related to https://bugs.kde.org/show_bug.cgi?id=395725

@Cretezy forked this repo here https://github.com/Cretezy/pymessenger2 It may be more up to date.

Are you asking if this module is thread-safe?

Easy workaround, add setuptools to additional_dependencies ```yaml - repo: https://github.com/landscapeio/prospector rev: v1.10.3 hooks: - id: prospector additional_dependencies: ["setuptools"] ```

Easy workaround, add setuptools to additional_dependencies ```yaml - repo: https://github.com/landscapeio/prospector rev: v1.10.3 hooks: - id: prospector additional_dependencies: ["setuptools"] ```

Gemini 2.5 Pro Experimental claims a 63.8% success rate on SWE-bench Verified with a custom agent setup ([See blog post](https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025/?_bhlid=e5b81688cdae64f414e4acb57a31fc46e19c83a7#advanced-coding)). Is OpenHands able to replicate that with the same model?

@enyst Thanks! I'm using it through Vertex AI and there are no rate limits I've encountered while still being free.

@srikanthccv Does anything need to be addressed in this PR before it can be merged?