{"version":"2.1.174","anchor":"advisor-model-capability-enforcement","canonical_anchor":"advisor-model-capability-enforcement","heading":"Advisor Model Capability Enforcement","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.174\/e\/advisor-model-capability-enforcement","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.174","markdown":"### Advisor Model Capability Enforcement\n\nThe advisor feature now enforces that the configured advisor model must be at least as capable as the main model, using a new numeric capability ranking table:\n\n| Model | Rank | |---|---| | claude-haiku-4-5 | 1 | | claude-sonnet-4-6 | 2 | | claude-opus-4-6 | 3 | | claude-opus-4-7 \/ 4-8 | 4 | | claude-fable-5 \/ claude-mythos-5 | 5 |\n\nIf the advisor ranks below the main model, the session emits a warning and the advisor is not activated for the main model (subagents may still use it). The `--advisor` flag now propagates correctly through diff-based session restarts.\n\n**Evidence**\n\nCapability rank table (search for `\"claude-haiku-4-5\"` near `\"claude-fable-5\"` in the same object), warning message (search for `\"Advisor will not activate on the main model (advisor is less capable)\"`)"}