{"version":"2.1.269","anchor":"assistant-thinking-blocks-get-per-message-memoized-summary-c","canonical_anchor":"assistant-thinking-blocks-get-per-message-memoized-summary-c","heading":"Assistant thinking blocks get per-message memoized summary caching","tier":"internal","area":"Transcript","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/assistant-thinking-blocks-get-per-message-memoized-summary-c","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### Assistant thinking blocks get per-message memoized summary caching\n\nAssistant 'thinking' text is now cached per message along with a reserved slot for a future summary\n\n**Unclear.** The `summary` slot is reserved but the finding doesn't say what will populate it or when.\n\n**What**\n\nThe internal helper that pulls out an assistant message's thinking block (Claude's internal reasoning text, shown separately from its main reply) now caches the result per message instead of recomputing it every time. The cached record includes the thinking text, whether it's blank, and a reserved `summary` slot that isn't used yet.\n\n**Why**\n\nThis is a performance and groundwork change: caching avoids redundant recomputation, and the reserved `summary` field suggests a future feature to show a condensed version of a thinking block, though that isn't active yet.\n\n- Area: Transcript\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}