[Bug] Claude models returning safety rejections despite valid cyber verification
Status Closed — not planned
Reported on v2.1.289
Maintainer reply None cached
Activity 1 comment · opened Oct 4, 2026 · closed Oct 11, 2026
Bug Description
opus 5.5, sonnet 5.5 and even opus 5 are getting safeguarded. I have cyber verification and this is so annoying which makes me think about switching to kimi and glm
Environment Info
- Platform: linux
- Terminal: xterm-256color
- Version: 2.1.289
- Feedback ID: b3a21be6-617a-4f30-8f02-c37039b64754
This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗