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.
More internal model calls marked as machine-driven
Under the hood
Useful1Signal2
Artifacts
Behind-the-scenes classifier calls for artifact reactions are now tagged as machine calls, not your turns.
What's wrong with this entry?
Anonymous. No account, no email.
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.