[Bug] Safeguard false-positives downgrading models during legitimate security audits

Status Open
Reported on v2.1.221
Maintainer reply None cached
Activity 0 comments · opened Aug 4, 2026

Bug Description

This is pretty straightforward - if I have a verifiable work history of deploying code to the live project, you can stop assuming I am a bad actor and treating me that way.

Environment Info

  • Platform: darwin
  • Terminal: iTerm.app
  • Version: 2.1.221
  • Feedback ID: 6ffe4d9a-061f-45dd-8758-93ae31406a23

Errors

[]

View original on GitHub ↗