Under the hood
New per-model capability flag lucky_cerf added to the internal model quirks list
What
A new entry, lucky_cerf, has been added to the list of per-model capability or behavior flags Claude Code tracks, alongside existing entries like refusal_fallback, thinking_display_updates, and quizzical_shore.
Why
This is an internal flag whose purpose is not described; it likely lets Claude Code adjust behavior for models that have this particular quirk.
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
What `lucky_cerf` controls or which models it applies to is not stated.