[Bug] Anthropic API Error: Safety Filter Incorrectly Blocking Autonomous Agent Approval Workflows

Status Closed — not planned
Reported on v2.1.170
Maintainer reply None cached
Activity 1 comment · opened Jun 10, 2026 · closed Jul 19, 2026

Bug Description
somehow, it determined, that me asking my model to run an agent team without bothering me for permissions but having it approve them, was a biohazard or security risk... lol

Environment Info

  • Platform: darwin
  • Terminal: ghostty
  • Version: 2.1.170
  • Feedback ID: d5698d4c-d1bc-4f20-a1c4-2415844d276c

Errors

[]

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗