{"version":"2.1.318","anchor":"thinking-always-on-notification-gets-a-hint-and-a-3s-timeo","canonical_anchor":"thinking-always-on-notification-gets-a-hint-and-a-3s-timeo","heading":"The \"thinking always on\" notice explains itself and clears after 3 seconds","tier":"notice","area":"Elsewhere","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318\/e\/thinking-always-on-notification-gets-a-hint-and-a-3s-timeo","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318","markdown":"### The \"thinking always on\" notice explains itself and clears after 3 seconds\n\nThe notice that thinking is always on now adds \"thinking always on for this model\" and disappears after 3 seconds\n\n**What**\n\nThinking is the step where the model reasons before it answers. For some models it is always on, and Claude Code shows a notice about this. That notice now carries the hint \"thinking always on for this model\" and goes away by itself after 3 seconds.\n\n**Why**\n\nThe notice now says why thinking cannot be turned off, and it no longer stays on screen.\n\n- Area: Elsewhere\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}