{"version":"2.1.271","anchor":"new-model-capability-quirk-id-lucky-cerf","canonical_anchor":"new-model-capability-quirk-id-lucky-cerf","heading":"New model-capability quirk id: lucky_cerf","tier":"internal","area":"Model Config","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271\/e\/new-model-capability-quirk-id-lucky-cerf","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271","markdown":"### New model-capability quirk id: lucky_cerf\n\nNew per-model capability flag lucky_cerf added to the internal model quirks list\n\n**Unclear.** What `lucky_cerf` controls or which models it applies to is not stated.\n\n**What**\n\nA 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`.\n\n**Why**\n\nThis is an internal flag whose purpose is not described; it likely lets Claude Code adjust behavior for models that have this particular quirk.\n\n- Area: Model Config\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}