Source Intelligence
Follow Discord
Reading a new release v2.1.251 Analysing changes · 2/5 Sorting the findings · 1/4 steps 470 findings $18.91 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 v2.0.10 Home All releases ←olderv2.0.9 v2.0.11newer→
Claude Code v2.0.10

Model Descriptions for Claude

What changed: Model options now include descriptions specifically tailored for Claude's decision-making

Details:

  • Added descriptionForModel field to model configurations
  • Sonnet 4.5: "the most powerful model. Generally best for most coding tasks"
  • Sonnet (1M context): "with 1M context window - for long sessions with large codebases"
  • Opus 4.1: "slower and more expensive than Sonnet, generally not recommended over Sonnet 4.5"
  • Helps Claude make better model switching decisions when exiting plan mode
  • Evidence: kB4.descriptionForModel at line 364157, fL1.descriptionForModel at line 364164, wtA.descriptionForModel at line 364173 in v2.0.10 (did not exist in v2.0.9)

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 v2.0.10 →