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 v2.1.48 Home All releases ←olderv2.1.47 v2.1.49newer→
Claude Code v2.1.48

Model Capability Descriptions

What

Added explicit descriptions for model thinking capabilities in the schema.

Details
  • New effortLevels field describes available effort levels for models
  • New supportsAdaptiveThinking field indicates whether a model supports adaptive thinking (Claude decides when and how much to think)
Evidence

New schema descriptions (search for "Whether this model supports adaptive thinking")

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

See this entry in the whole of v2.1.48 →