Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.275 ·

Headless background-task wind-down gains an eval-settle hold

Claude Code's headless/print mode now tracks whether it should hold dispatch for eval settling and whether a background-wait ceiling was hit

Group of 2 Under the hood Internal Changes
JSON All of v2.1.275
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
ElsewhereArea: what it touches
Internal ChangesKind: in v2.1.275,
Internal ChangesSection of the release

Unclear The finding does not say what holdsEvalSettles() is meant to represent or when it might return true.

What

  • A new holdsEvalSettles() check was added to the drain/session-loop wait condition, as part of a rewrite that collapsed several separate booleans into one inline check.
  • In headless/print mode, the background-task dispatch loop now accepts a holdsEvalSettles callback; when it returns true, task dispatch (takeHead()) is held rather than proceeding.
  • A new bgWaitCeilingExceeded field records whether the CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS wait ceiling was reached.

Why

This gives headless/print-mode runs finer control over when background task dispatch should pause to let evaluation settle, and visibility into whether the configured wait ceiling was hit.

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 finding does not say what holdsEvalSettles() is meant to represent or when it might return true.

See this entry in the whole of v2.1.275 →

Feedback