@ai-sdk/provider-utils
5.0.83 · 20 Nov 2026Apache-2.076.4M / weekRepositoryHomepagenpmAtom feed
Upgrading @ai-sdk/provider-utils From 5.0.42 to 5.0.43
1 release in betweenevery note read
Release by release
- New
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. - New
ai: Support tool search with direct tool calling
- New
ai: Add native tool search tool
- Fixed
Default language-model evaluation adapters to
reasoning: 'none', using each provider's existing reasoning mapping. Explicit reasoning settings inproviderOptionscontinue to override the default.
- New
1 internal line (docs, tests, tooling) left out.
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 Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to.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.