Sign in
← AI PulseAug 28, 2026

Wire · news · Single-source brief

Vercel AI SDK Updates: Structured Output, ToolLoopAgent, and Amazon Bedrock Enhancements

Vercel has released updates to its AI SDK, including exposing parsed structured output in streamText end callbacks and fixes for ToolLoopAgent settings.

By Illumora Editorial

Source · Aug 28, 2026, 5:20 PM · On Illumora · Aug 28, 2026, 5:32 PM

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

Rewritten from one allowlisted primary — not independent enterprise reporting. 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/zai@3.0.2 · vercel/ai
Save

Vercel has released updates to its AI SDK, with version @ai-sdk/zai@3.0.2 being opened by the Changesets release GitHub action. This release includes enhancements to how structured output is handled and addresses specific functionalities within the SDK.

Key Points

  • The release exposes parsed structured output in streamText end callbacks.
  • A fix allows tool approval secrets in ToolLoopAgent settings and prepareCall.
  • The SDK now handles stateful and empty-match regular expressions in smoothStream.
  • For Amazon Bedrock, assistant messages are omitted when only cache points remain after unsigned reasoning is filtered.
  • Amazon Bedrock integration now includes a model family setting for embeddings to support ARN.
  • Amazon Bedrock streaming responses can now accept citation deltas.

Context

According to Vercel, this release was initiated by the Changesets release GitHub action. It consolidates various updates across different components of the AI SDK, including core functionalities and specific provider integrations like Amazon Bedrock.

Why It Matters

These updates enhance the robustness and flexibility of the Vercel AI SDK, offering developers improved control over structured output, better handling of tool-based agents, and more comprehensive integration with Amazon Bedrock services. The changes can streamline development workflows and improve the reliability of AI-powered applications.

What To Do

  • Developers should review the updated streamText end callbacks for structured output handling.
  • Check ToolLoopAgent settings to utilize tool approval secrets in prepareCall.
  • Note the improved handling of regular expressions in smoothStream.
  • For Amazon Bedrock users, explore the new model family setting for embeddings and support for citation deltas in streaming responses.