{"version":"2.1.267","anchor":"thinking-disabled-effort-cap-follows-the-same-gate-precedenc","canonical_anchor":"thinking-disabled-effort-cap-follows-the-same-gate-precedenc","heading":"thinking_disabled_effort_cap follows the same gate-precedence rework","tier":"internal","area":"Model Safety","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.267\/e\/thinking-disabled-effort-cap-follows-the-same-gate-precedenc","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.267","markdown":"### thinking_disabled_effort_cap follows the same gate-precedence rework\n\nThe thinking_disabled_effort_cap flag can now override the claude-opus-5 hardcoded default in either direction\n\n**What**\n\nA helper that decides whether an extra-high reasoning effort cap applies to a model previously required the `thinking_disabled_effort_cap` flag to be exactly true, or the model to literally be `claude-opus-5`. Now, any explicit value returned by the flag (true or false) is used first, and the `claude-opus-5` hardcoded default only applies when the flag has no value at all.\n\n**Why**\n\nThis mirrors a similar change to another flag in this release, letting the server control this cap explicitly instead of it always being forced on for `claude-opus-5`.\n\n- Area: Model Safety\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5"}