Source Intelligence
Follow Discord

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 v2.1.232 Home All releases ←olderv2.1.231 v2.1.233newer→
Claude Code v2.1.232

Advisor results validate their stop reason

Under the hood
Useful2 Signal2
Advisor Models

Advisor results now normalise unknown stop reasons and route refusals into refusal handling.

What

Results coming back from an advisor tool now map their stop reason through a known list, including compaction, refusal and context-window-exceeded, and anything unrecognised becomes unknown instead of being passed through. A refusal reason triggers the refusal handling path.

Evidence

model_context_window_exceeded: !0

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.232 →