Source Intelligence
Reading a new release v2.1.251 Analysing changes · 2/5 Deeper second pass · 4/5 agents 427 findings $12.75 so far

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 v2.1.45 Home All releases olderv2.1.44 v2.1.47newer
Claude Code v2.1.45

Effort Setting Description Updated

What

The Opus 4.6 effort setting description has been expanded to better explain the trade-offs.

Before: "Effort lets you control thinking intensity in Opus 4.6." After: "Effort lets you control the trade off between response thoroughness and token efficiency for Opus 4.6. Higher effort levels offer higher capability, and lower levels tend to use fewer tokens to optimize..."

Evidence

Updated effort description (search for "Effort lets you control the trade off between response thoroughness")

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

See this entry in the whole of v2.1.45 →