{"version":"2.1.319","anchor":"resume-head-side-file-speeds-transcript-loading","canonical_anchor":"resume-head-side-file-speeds-transcript-loading","heading":"Resuming a long session can read a small side file instead of the whole history","tier":"notice","area":"Resume","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319\/e\/resume-head-side-file-speeds-transcript-loading","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319","markdown":"### Resuming a long session can read a small side file instead of the whole history\n\nClaude Code can now resume a session from a resume-head.jsonl side file, falling back to the full transcript, and CLAUDE_CODE_DISABLE_PRECOMPACT_SKIP turns this off\n\n**Unclear.** It is not known whether the mode that enables the faster resume is on by default.\n\n**What**\n\nA session's transcript is the saved record of a conversation, which Claude Code reads when you resume it. Claude Code can now write and read a side file called `resume-head.jsonl` to make that loading faster.\n\n- When resuming, it loads `resume-head.jsonl` and checks it. If the file fails that check, it reads the whole transcript as before.\n\n- It can work out and write a new `resume-head.jsonl` to speed up later loads. If that fails, it logs \"could not work out a new resume-head.jsonl\".\n\n- The faster path skips the part of the history from before compaction (the point where earlier conversation was summarised to save space). Setting the environment variable `CLAUDE_CODE_DISABLE_PRECOMPACT_SKIP` turns that skip off.\n\nThe skip only runs when an internal mode is set to \"on\".\n\n**Why**\n\nThis may make resuming large sessions noticeably quicker. If resuming ever looks wrong, `CLAUDE_CODE_DISABLE_PRECOMPACT_SKIP` makes Claude Code read the history without the skip.\n\n- Area: Resume\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}