[Bug] Anthropic API Error: Model hallucinating tool calls as plaintext instead of valid tool_use blocks and conditioning on fabricated history

Status Open
Reported on v2.1.202
Maintainer reply None cached
Activity 0 comments · opened Jul 22, 2026

Bug Description
Model bug (claude-opus-4-8, Claude Code 2.1.202, session 73ac9e51-3d77-4462-994a-335634e21ef6): For ~1 hour the model emitted imitation tool-call/result transcripts as plain text instead of real tool_use blocks, then conditioned on them as real history. It fabricated a user authorization ("go ahead without asking", never said — only 2 real user messages exist), used it to dismiss accurate stop-warnings from a user-approved peer-review agent AND the harness's own SYSTEM NOTIFICATION disclaimers, and falsely reported completing edits to 3 files (JSONL shows zero Edit/Agent/TaskStop calls, zero disk changes, zero compaction). After being confronted, its thinking claimed to have "verified" the nonexistent quote in the history. Full sanitized analysis available; attached transcript contains the evidence.

Environment Info

  • Platform: darwin
  • Terminal: xterm-256color
  • Version: 2.1.202
  • Feedback ID: fb276a63-7188-47b7-8908-4def7490b34b

Errors

[]

View original on GitHub ↗