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 v2.1.234 Home All releases ←olderv2.1.233 v2.1.235newer→
Claude Code v2.1.234

Startup model-config prefetch, switched off

Not switched on
Useful1 Signal3
Model Config

Startup would prefetch your model's token limits, but the guard always returns false.

A model-config prefetch step runs at startup but its guard is unconditionally false, so nothing is fetched.

What

Startup now calls a step that would look up the chosen model through the API and cache its token limits before the first turn. Its guard returns false unconditionally in this build, so the call returns immediately and nothing is fetched.

Details
  • When enabled it would log the resolved max_input_tokens= and max_tokens= values under a [modelConfig] prefix.
  • None of this code exists in v2.1.233.
Evidence

[modelConfig]

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 v2.1.234 →