Sign in
← AI PulseSep 16, 2026

Wire · news · Multi-source brief

Vercel AI SDK Updates TypeSafe Provider and Core AI Features

Vercel has released updates across several AI SDK packages, including the addition of a TypeSafe provider for experimental evaluation and enhancements to core AI functionalities such as mid-conversation tool discovery.

By Illumora Editorial

Source · Sep 16, 2026, 6:26 PM · On Illumora · Sep 16, 2026, 6:38 PM

Media from the primary source — shown here so you can stay on Illumora.

Synthesized from multiple allowlisted primaries on the same event. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →Vercel AI SDK Changelog — Release @ai-sdk/minimax@3.0.32 · vercel/ai
Save

Vercel has updated its AI SDK, introducing new capabilities in the @ai-sdk/typesafe-ai@3.0.0 package and refining core AI features. These updates are noted across releases for @ai-sdk/minimax@3.0.32, @ai-sdk/huggingface@2.0.50, @ai-sdk/klingai@4.0.44, and @ai-sdk/hume@3.0.42.

The TypeSafe provider now supports experimental_evaluate, enabling native handling of Choice, Score, and Boolean questions within a single request. This enhancement also includes structured JSON rubrics, probability distributions, confidence metadata, and workflow serialization.

Key Points

  • The @ai-sdk/typesafe-ai@3.0.0 package introduces a TypeSafe provider for experimental_evaluate.
  • This provider supports native Choice, Score, and Boolean questions in one request.
  • Structured JSON rubrics are now included for evaluation.
  • Probability distributions and confidence metadata are supported.
  • Workflow serialization is a new feature of the TypeSafe provider.
  • Mid-conversation tool discovery and updates for code-mode have been added to the ai package.
  • The rawInput in output-error UI message parts has been deprecated.

Context

According to the Vercel AI SDK Changelog, these updates were managed through the Changesets release GitHub action. The @ai-sdk/provider-utils@5.0.42, @ai-sdk/provider@4.0.16, and ai@7.0.103 packages also received dependency updates. Additionally, default Node.js downloads are now protected by DNS validation and connection pinning, even when frameworks or instrumentation wrap global fetch before or after the SDK loads.

Why It Matters

These updates provide developers with more robust tools for evaluating AI model outputs and integrating dynamic tool use within conversational AI applications. The enhanced evaluation capabilities can lead to more precise and structured assessments of model performance, while improved tool discovery can enable more flexible and responsive AI interactions.

What To Do

  • Review the @ai-sdk/typesafe-ai@3.0.0 documentation for details on experimental_evaluate.
  • Explore the new mid-conversation tool discovery features in the ai package for code-mode applications.
  • Note the deprecation of rawInput in output-error UI message parts and adjust existing implementations.
  • Verify that Node.js downloads in your environment maintain DNS validation and connection pinning with the updated SDK.