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 v2.1.234 Home All releases olderv2.1.233 v2.1.235newer
Claude Code v2.1.234

Artifact tool logs why it exposed the actions it did

Under the hood
Useful1 Signal2
Artifacts

A debug line now records why the artifact tool offered the actions it did.

What

Building the artifact tool's input schema now writes one debug line recording every input to that decision, so a log alone explains which artifact actions a session offered.

Details
  • The line covers capabilities, comments, db, assets, read_page_data, where the flag value came from, and a freshness indicator.
  • Whether remote watch is unsupported is recorded into session state at the same time.
  • Diagnostic only, and it runs on every schema build.
Evidence

Artifact input schema built: capabilities=

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

See this entry in the whole of v2.1.234 →