Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.307 ·

Auto-compact window is remembered per model when a session is resumed

Each model's auto-compact window is now saved with the session and restored on resume, and the default window for a model has changed

You'll notice Improvements
JSON All of v2.1.307
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
CompactionArea: what it touches
ImprovementsKind: in v2.1.307,
ImprovementsSection of the release

Unclear The size limits and cap behind the new default window are not known, so it is unclear when compaction now starts for a given model.

What

Compaction is when Claude Code summarises older parts of a conversation to free up room in the context window, which is how much text the model can take in at once. The autoCompactWindow setting decides how full the context gets before that happens.

Claude Code now saves a value for each model with the session's own stored data. The value is either a number or "auto". When the session is loaded again, that saved value is applied as if you had set autoCompactWindow in your user settings. Changes to it are written back to the session.

The default window for a model also works differently now:

  • A model whose window is above a certain size is given a cap.
  • Other models default to a 1M window that you opt into.
Why

A compaction window chosen for a model carries over when you resume a session, instead of being lost.

Read from
Names in the bundleautoCompactWindow
How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtThe size limits and cap behind the new default window are not known, so it is unclear when compaction now starts for a given model.

See this entry in the whole of v2.1.307 →

Feedback