Under the hood
Conversation compaction now preserves trailing thinking blocks before computing what to strip
What
When converting the transcript into API messages, Claude Code now first applies trailing-thinking preservation (keeping the model's most recent reasoning, or 'thinking', blocks) and only then computes the plan for which thinking blocks to strip, based on that already-preserved result. Previously the strip plan was computed directly from the raw messages.
Why
Ordering it this way means the strip plan takes the preserved trailing thinking into account, rather than being computed before that preservation happens.
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
The evidence doesn't say what practical difference in compacted output this reordering produces.