Packages

@ai-sdk/provider-utils

5.0.83 · 20 Nov 2026Apache-2.076.4M / weekRepositoryHomepagenpmAtom feed

Your version

5.0.43

16 Sep 2026Where it was published

5.0.83 is the newest release of 5.x.

In short

3 new1 fixed1 internal

Release note

The section about @ai-sdk/provider-utils of a note shared by several packages.

Patch Changes

  • Default language-model evaluation adapters to reasoning: 'none', using each provider's existing reasoning mapping. Explicit reasoning settings in providerOptions continue to override the default.

  • Add experimental Choice, Score, and Boolean evaluations through openai.evaluationModel() and a shared structured language-model evaluation adapter in @ai-sdk/provider-utils/experimental-evaluation. Preserve exact labels and metadata, validate score bounds, and return prompted Boolean P(true) estimates validated to be in [0, 1]. Boolean estimates are not guaranteed to be calibrated; application code chooses thresholds.

  • ai: Support tool search with direct tool calling

  • ai: Add native tool search tool

A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.