Unclear How these cases change what resume offers to continue is not shown.
When you resume a session, Claude Code looks at the end of the saved conversation to decide whether the last turn was cut off. It now handles a few cases differently:
- A prompt followed by extra context rows can be judged by looking at the part before those rows. Before, that case always counted as an interrupted prompt.
- A turn that ends in trailing context rows can count as interrupted for that reason.
- Results from agents started in the background that were kept when you stopped a turn now count as a deliberate stop rather than an interruption.
The first case sits behind a remote switch that falls back to on when Anthropic's servers send no value.
This affects whether resuming offers to continue a turn that was interrupted.
tengu_candid_heron Not enough to sayNothing 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 v2.1.318: 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 v2.1.318. It isn't a statement about your account. What a flag value here can and cannot tell you
How these cases change what resume offers to continue is not shown.
New in this build: tengu_candid_heron