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 v2.1.239 Home All releases olderv2.1.238 v2.1.240newer
Claude Code v2.1.239

Malformed artifact results are reported instead of rendered

You'll notice
Useful3 Signal2
Artifacts

Artifact tool results are checked before display, so corrupt records are flagged instead of shown.

What

Every artifact tool result is now validated before display. When a record fails validation, Claude is told the record is unreadable and to re-run the action rather than being shown fields that cannot be trusted. This applies to all artifact results, with no flag.

Details
  • Listings are truncated with a count of rows that could not be salvaged.
  • Paths and content types are checked against patterns, and entry and field counts are capped.
Evidence

This record of the artifact listing is unreadable

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

See this entry in the whole of v2.1.239 →