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

More internal model calls marked as machine-driven

Under the hood
Useful1 Signal2
Artifacts

Behind-the-scenes classifier calls for artifact reactions are now tagged as machine calls, not your turns.

What

The marker that tags a model call as mechanical rather than a user turn now also covers the classifier and triage calls behind artifact auto-reactions and replies. All of these already ran with thinking disabled; the marker only separates them from real user turns.

Evidence

thinkingConfig: { type: "disabled", mechanical: !0 },

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

See this entry in the whole of v2.1.238 →