Precomputed compaction summaries are checked for coverage and fit before reuse
Before reusing a summary prepared in advance, auto-compact now checks it still covers the conversation and fits, and refuses it with a named reason if not
Nothing to try yetTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
CompactionArea: what it touches
Internal ChangesKind: in v2.1.288,
In DevelopmentSection of the release
What
Compaction is when Claude Code shrinks a long conversation into a summary so it fits the model's context window. Sometimes that summary is prepared in advance. Before reusing it, Claude Code now checks that it still covers the conversation and still fits:
Reuse can now be refused with named reasons, including rows_unreadable and would_not_fit.
Loading a prepared summary back from disk no longer rejects it for grew_too_much. It now checks modelMatch, preservedUuidCount and rows_unreadable instead.
The discard log now includes token sizes, and saved summaries record preservedMessageCount and preservedUuidCount.
The related gate tengu_sepia_moth was off for this site's account and for the anonymous baseline in earlier readings, but no reading has been taken under this release.
Why
Auto-compact should be less likely to swap in a prepared summary that is out of date or that would push the conversation over its size limit.
