Unclear Not settled whether anything runs this quick check in this release.
What
Claude Code can extract memories (notes saved for later sessions) from recent exchanges in the background.
- A cheap first pass now asks a small model whether the recent exchanges are likely to produce a memory write, answering
{"write_likely": true|false}. - If it fails, the full pass still runs.
- Its verdicts (yes, no, empty or error) are recorded in usage reporting, alongside a new entry about subagent work in remote sessions.
- A new route skips its work when
memorySaveis set.
Why
Background memory extraction can skip model calls when nothing is likely to be saved, which can change when memories get written.
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
Not settled whether anything runs this quick check in this release.