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

Publish warnings no longer flood the tool result

You'll notice
Useful2 Signal1
Artifacts

Long publish warning lists get truncated so they don't crowd out the actual result.

What

Warnings returned when publishing an artifact are joined and cut off at half the result budget, with a marker where the text stops, so a long warning list cannot crowd out the rest of the result.

Details
  • Truncated output ends with (warnings truncated)
  • A separate helper sanitizes and caps each individual server warning before joining
Evidence

(warnings truncated)

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

See this entry in the whole of v2.1.229 →