Source Intelligence

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 v2.1.229 Home All releases olderv2.1.228 v2.1.231newer
Claude Code v2.1.229

Artifact watch prompt now spells out remote wake-ups and comments

You'll notice
Useful3 Signal3
Artifacts

The artifact watch prompt now explains remote wake-ups and comment forwarding before you allow it.

What

The confirmation shown the first time Claude watches an artifact was rewritten. It now says a remote session is woken with a new turn when the artifact is republished and, where you grant it, when a comment on the artifact is sent to Claude, and states that notifications carry no content. The Artifact tool description gained a matching sentence about durable wake subscriptions, emitted only when an internal flag is on.

Evidence

in a remote session, also when a comment on it is sent to Claude

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 v2.1.229 →