{"version":"2.1.274","anchor":"prompt-suggestion-generation-can-now-reuse-a-precomputed-tu","canonical_anchor":"prompt-suggestion-generation-can-now-reuse-a-precomputed-tu","heading":"Prompt-suggestion generation can now reuse a precomputed 'turn brief' instead of a fresh model call","tier":"internal","area":"Elsewhere","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274\/e\/prompt-suggestion-generation-can-now-reuse-a-precomputed-tu","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274","markdown":"### Prompt-suggestion generation can now reuse a precomputed 'turn brief' instead of a fresh model call\n\nPrompt suggestions can now reuse a precomputed 'turn brief' instead of always making a fresh model call\n\n**What**\n\nWhen generating a suggested next prompt in SDK or print mode, Claude Code now first checks for a precomputed 'turn brief' - a short summary produced as part of a turn's post-turn classification. If that precomputed brief matches the current turn, it's used directly as the suggestion instead of triggering a new generation request to the model.\n\n**Why**\n\nThis can make prompt suggestions appear faster and avoids an extra model call when a suitable summary is already available.\n\n- Area: Elsewhere\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5"}