{"version":"2.1.277","anchor":"prompt-suggestion-generation-for-sdk-turns-drops-the-cached","canonical_anchor":"prompt-suggestion-generation-for-sdk-turns-drops-the-cached","heading":"Prompt-suggestion generation for SDK turns drops the cached 'turnBriefNext' shortcut","tier":"internal","area":"SDK","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.277\/e\/prompt-suggestion-generation-for-sdk-turns-drops-the-cached","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.277","markdown":"### Prompt-suggestion generation for SDK turns drops the cached 'turnBriefNext' shortcut\n\nSDK prompt suggestions no longer reuse a cached shortcut and now always generate fresh\n\n**What**\n\nWhen the SDK generates a suggested next prompt for a turn, it used to first check a cached value (`promptSuggestion.turnBriefNext`) tied to the last assistant message, and only generate a fresh suggestion if nothing was cached. That caching shortcut has been removed, so prompt suggestions are now always generated in full each time.\n\n**Why**\n\nThis means SDK-generated prompt suggestions are computed fresh rather than potentially reused from a stale cached value.\n\n- Area: SDK\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}