[Bug] Anthropic API: Safeguards triggering false positives and downgrading model to Opus 4.8

Related Claude Code issues

Matched on shared title terms, labels, topic and reported release — ranked so issues with real discussion come first.

• [Bug] Safeguard false-positives downgrading models during legitimate security audits
  Resolved 💬 1 v2.1.221 #83864
• [Bug] Fable 5 safeguards triggering false positives on literary criticism terms
  Resolved 💬 1 v2.1.212 #78947
• Fable 5.1 is downgrading to Opus 4.8
  Open 💬 0 v2.1.260 #92184
• [Bug] Model switching to Opus 4.8 triggering false positive security safeguards
  Resolved 💬 1 v2.1.216 #80181
• [Bug] Classifier over-triggering false positives in tool execution validation
  Open 💬 1 v2.1.269 #95479
• [Bug] Session unexpectedly downgrading to Claude Opus 4.8 from requested model Fable 5
  Resolved 💬 2 v2.1.224 #85415
• [Bug] Biology classifier false-positives on benign theory queries, incorrectly downgrading Fable to Opus
  Resolved 💬 3 v2.1.173 #68018
• [Bug] Opus 5 safety filter triggering false positives on consecutive requests
  Resolved 💬 1 v2.1.226 #87541

Browse by topic

Same class of failure, ranked by community engagement — this issue is one of many, so it may not appear in the visible list: IDE & terminal integration

Browse all Claude Code issue topics →