Sign in
← AI PulseSep 15, 2026

Wire · news · Multi-source brief

Vercel AI SDK Updates Tool Output Serialization and Google Gemini Schema Handling

Vercel has released updates to its AI SDK, including fixes for serializing tool output JSON values and preserving JSON Schema for Google Gemini models.

By Illumora Editorial

Source · Sep 15, 2026, 4:12 AM · On Illumora · Sep 15, 2026, 4:24 AM

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/workflow@2.0.32 · vercel/ai
Save

Vercel has issued updates across several AI SDK packages, including @ai-sdk/workflow@2.0.32, @ai-sdk/sandbox-vercel@1.0.111, @ai-sdk/tui@1.0.102, and @ai-sdk/svelte@5.0.101. These releases address issues related to tool output serialization and schema handling for Google Gemini models.

Key Points

  • The ai@7.0.101 package includes a fix to serialize tool output JSON values.
  • The @ai-sdk/google@4.0.70 package now preserves JSON Schema instead of converting it to OpenAPI schema.
  • A fix in @ai-sdk/google@4.0.70 ensures functionResponse.response remains an object for Gemini models.
  • Gemini expects google.protobuf.Struct for functionResponse.response, which only accepts objects.
  • Previously, non-object tool results (string, number, array, null) could cause Gemini to close the socket with code 1007.
  • Non-object tool results are now wrapped under an output key as prescribed by the field's documentation.

Context

According to the Vercel AI SDK changelog, these updates aim to improve the reliability of tool calls and responses, particularly when interacting with Google Gemini models. The changes ensure that data types align with the expectations of the Gemini API, preventing connection issues that previously occurred with non-object tool outputs.

Why It Matters

These updates are significant for developers using the Vercel AI SDK with Google Gemini, as they resolve critical issues that could lead to unexpected disconnections and incorrect schema interpretations. The fixes enhance the stability and predictability of tool use within AI applications.

What To Do

  • Update your Vercel AI SDK packages to the latest versions, specifically ai@7.0.101 and @ai-sdk/google@4.0.70.
  • Review your tool implementations to ensure compatibility with the updated serialization of JSON values.
  • Test tool calls with Google Gemini models to confirm that non-object results are now correctly handled.

Keep Exploring

/atlas/**gemini**-family