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 v2.1.113 Home All releases olderv2.1.112 v2.1.114newer
Claude Code v2.1.113

Improved Effort Level Messaging

The effort level notification changed from "Effort level set to auto" to "Effort level set to max", providing clearer feedback when effort is maximized. The "ultrathink" keyword now triggers a system prompt explaining that deeper reasoning is being applied.

Evidence

Effort messaging (search for "Effort level set to max")

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 v2.1.113 →