{"version":"2.1.280","anchor":"auto-mode-classifier-now-reports-whether-it-actually-ran","canonical_anchor":"auto-mode-classifier-now-reports-whether-it-actually-ran","heading":"Auto mode classifier now reports whether it actually ran","tier":"internal","area":"Auto Mode","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/auto-mode-classifier-now-reports-whether-it-actually-ran","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### Auto mode classifier now reports whether it actually ran\n\nAuto mode's tool classifier now reports whether it actually ran\n\n**What**\n\nIn Claude Code's auto mode, the internal classifier that decides how to handle a tool call now returns a `classifierRan` flag alongside its verdict, stating whether the classification step actually executed. The fallback logic used when the classifier refuses to answer or gives no verdict was reworked to use this new flag.\n\n**Why**\n\nThis lets the fallback logic distinguish between the classifier running and abstaining versus not running at all, which should make auto mode's fallback behavior more accurate in edge cases.\n\n- Area: Auto Mode\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}