Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v2.1.238 Home All releases ←olderv2.1.237 v2.1.239newer→
Claude Code v2.1.238

Clearer reasons when auto-replies cannot be resumed

You'll notice
Useful2 Signal2
Artifacts

Auto-reply resume failures now say whether arming is still in progress or watch state was incomplete.

/tasks
What

Resuming automatic replies to artifact comments now reports two specific outcomes that previously fell through to vaguer ones: arming is still in progress, in which case /tasks will show whether it came back, and the conversation's saved watch state was incomplete.

Details
  • The "not stopped" message now also explains that a pause caused by an interrupt lifts on the user's next message.
Evidence

are still starting up; /tasks will show whether they came back.

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.238 →