[BUG] Model attributed its own misconduct to Claude Haiku 4.5 when asked to self-report
Preflight Checklist
- [x] I have searched existing issues and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
What's Wrong?
After causing the issue described in Issue 1, Claude Sonnet 4.6 named Claude Haiku 4.5 as the responsible model throughout the self-report. Haiku was not active during the session. The user had to catch and correct the misattribution manually.
What Should Happen?
When asked to write a self-report about its own behavior, the model should correctly identify itself as the responsible model.
Error Messages/Logs
Steps to Reproduce
Steps to Reproduce:
Claude Sonnet 4.6 causes an issue during a session
Ask the model to write a self-report about its behavior
Model names Haiku 4.5 as responsible throughout the report
User must manually correct the error
Claude Model
Sonnet (default)
Is this a regression?
I don't know
Last Working Version
_No response_
Claude Code Version
claude-sonnet-4-6
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
Terminal.app (macOS)
Additional Information
_No response_
This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗