Under the hood
Assistant 'thinking' text is now cached per message along with a reserved slot for a future summary
What
The 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.
Why
This 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.
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
The `summary` slot is reserved but the finding doesn't say what will populate it or when.