Hacker News new | ask | show | jobs
by jdthedisciple 296 days ago
uhh... .gitignore solves that right?
1 comments

These agents often generate randomly named files and dump them anywhere. You can end up with dozens of files added if you let it run on any problem it tries to create one-off "test / reproduction" cases. It hasn't always cleaned them up so a "git add all" approach can bring in junk, and the patterns for names aren't consistent. In fact they're often called stuff like *-test.js which looks like it could be a source OR test file.
That's why I wouldn't recommend "git add all", but rather use something like gitextensions [0] and visually add files or delete them, so you know what's happening in git world.

[0] https://gitextensions.github.io/