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 v2.1.111 Home All releases ←olderv2.1.110 v2.1.112newer→
Claude Code v2.1.111

New "xhigh" Effort Level

What

A new effort level called "xhigh" is added between "high" and "max", providing deeper reasoning capability exclusive to Opus 4.7.

Usage
# Set effort via CLI flag
claude --effort xhigh

# Set effort in-session
/effort xhigh
Details
  • The effort scale now has five levels: low, medium, high, xhigh, max
  • "xhigh" is described as "Deeper reasoning than high, just below maximum (Opus 4.7 only)"
  • "xhigh" is the automatic default effort level when using Opus 4.7
  • If "xhigh" is requested on a model that doesn't support it, it falls back to "high"
  • The effortLevel setting now accepts: low, medium, high, xhigh, max
  • The /effort command help text is updated accordingly
Evidence

"xhigh" effort level (search for "xhigh") — 0 occurrences in v2.1.110, 40 in v2.1.111. Default logic in bF1() at line ~237923 (search for "opus-4-7" returning "xhigh")

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 v2.1.111 →