{"version":"2.1.273","anchor":"prompt-suggestion-generation-now-tries-multiple-candidate-re","canonical_anchor":"prompt-suggestion-generation-now-tries-multiple-candidate-re","heading":"Prompt-suggestion generation now tries multiple candidate replies","tier":"notice","area":"UI","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.273\/e\/prompt-suggestion-generation-now-tries-multiple-candidate-re","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.273","markdown":"### Prompt-suggestion generation now tries multiple candidate replies\n\nPrompt-suggestion generation now tries several candidate replies instead of just the first one\n\n**What**\n\nWhen Claude Code asks the model to suggest a follow-up prompt, it used to stop at the very first assistant text reply it found and clean it up with a set of regex rules. Now it first collects all of the assistant's candidate text replies, then runs the same cleanup rules over each candidate in order, stopping only once a candidate actually produces a usable, non-empty suggestion.\n\n**Why**\n\nThis makes prompt suggestions more reliable: if the first candidate reply turns out empty or unusable after cleanup, Claude Code now falls through to try the next one instead of giving up.\n\n- Area: UI\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}