Follow Discord
Sweep 30 Oct 2026 · 01:02Z Build v2.1.314 532 read Stable v2.1.308 Latest v2.1.314 Next v2.1.314 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.314 ·

Resumed sessions that had already finished replying are no longer nudged to continue

When a resumed session had already finished replying, Claude Code no longer adds a prompt telling the model to continue

You'll notice Bug Fixes
JSON All of v2.1.314
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
SessionsArea: what it touches
Bug FixesKind: in v2.1.314,
Bug FixesSection of the release
What

Resuming a session means picking up an earlier conversation where it left off. If the conversation looks like it was cut off, Claude Code adds a prompt asking the model to continue.

Claude Code now skips that prompt in one case. The case is a conversation where all of these are true:

  • It ends with background context rather than a reply.
  • No action is still waiting for its result.
  • Its last rows show only a queued note with no real work after it.

This is controlled by a setting that is on unless it is switched off remotely.

Why

You should see fewer extra turns started on their own when you resume a session that had already finished replying.

Read from
Feature flag
tengu_partitioned_finch Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.314: on

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.314. It isn't a statement about your account. What a flag value here can and cannot tell you

How sure we are
One source agreesOne thing we can check says the same as this entry.
The name it cites is new in this buildNew in this build: tengu_partitioned_finch

See this entry in the whole of v2.1.314 →

Feedback