{"version":"2.1.232","anchor":"advisor-results-validate-their-stop-reason","canonical_anchor":"advisor-results-validate-their-stop-reason","heading":"Advisor results validate their stop reason","tier":"internal","area":"Advisor Models","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232\/e\/advisor-results-validate-their-stop-reason","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232","markdown":"### Advisor results validate their stop reason\n\nAdvisor results now normalise unknown stop reasons and route refusals into refusal handling.\n\n**What**\n\nResults coming back from an advisor tool now map their stop reason through a known list, including compaction, refusal and context-window-exceeded, and anything unrecognised becomes `unknown` instead of being passed through. A refusal reason triggers the refusal handling path.\n\n**Evidence**\n\n`model_context_window_exceeded: !0`\n\n- Area: Advisor Models\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5"}