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

Experimental advisor tool: the env override now bypasses less

You'll notice
Useful2 Signal3
Tools Notable not in their notes

The experimental advisor override no longer skips per-model eligibility checks, only the rank requirement.

CLAUDE_CODE_ENABLE_EXPERIMENTAL_ADVISOR_TOOL
What

Setting CLAUDE_CODE_ENABLE_EXPERIMENTAL_ADVISOR_TOOL still skips the advisor rank requirement, but no longer skips the other per-model eligibility guards. Those guards previously sat after an early return that the env var triggered.

Details
  • The env check now lives inside the rank predicate, ahead of the rank comparison, rather than at the top of each availability check.
  • Callers run their own conditions first and only then consult that predicate.
Evidence

CLAUDE_CODE_ENABLE_EXPERIMENTAL_ADVISOR_TOOL

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

See this entry in the whole of v2.1.232 →