{"version":"2.1.269","anchor":"context-compaction-pipeline-reorders-trailing-thinking-prese","canonical_anchor":"context-compaction-pipeline-reorders-trailing-thinking-prese","heading":"Context-compaction pipeline reorders trailing-thinking preservation ahead of the strip plan","tier":"internal","area":"Compaction","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/context-compaction-pipeline-reorders-trailing-thinking-prese","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### Context-compaction pipeline reorders trailing-thinking preservation ahead of the strip plan\n\nConversation compaction now preserves trailing thinking blocks before computing what to strip\n\n**Unclear.** The evidence doesn't say what practical difference in compacted output this reordering produces.\n\n**What**\n\nWhen 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.\n\n**Why**\n\nOrdering it this way means the strip plan takes the preserved trailing thinking into account, rather than being computed before that preservation happens.\n\n- Area: Compaction\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5"}