{"version":"2.1.280","anchor":"new-per-model-effort-override-table-gated-by-tengu-witty-wan","canonical_anchor":"new-per-model-effort-override-table-gated-by-tengu-witty-wan","heading":"New per-model effort override table gated by tengu_witty_wand","tier":"soon","area":"Effort","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/new-per-model-effort-override-table-gated-by-tengu-witty-wan","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### New per-model effort override table gated by tengu_witty_wand\n\nModel effort level can now be set per-model via a gated remote-configured table\n\n**What**\n\nA new function determines a model's default \"effort\" level (how much reasoning effort it applies) by checking, in order: an explicit override, a table of per-model values read from a remote gate called `tengu_witty_wand`, an entry in the settings file, the model catalog's built-in `default_effort`, and finally falling back to \"high\" if nothing else applies.\n\n**Why**\n\nThis adds another layer of control for tuning default effort levels per model, sitting above the model catalog's built-in defaults but below any explicit override or settings-file entry.\n\n- Area: Effort\n- Names: `tengu_witty_wand`\n- Tier: Nothing to try yet\n- Useful: 2\/5\n- Signal: 3\/5\n- Present in the build but not switched on"}