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 integrations.

By Illumora Editorial

Source · Sep 15, 2026, 4:12 AM · On Illumora · Sep 15, 2026, 4:23 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/svelte@5.0.101 · vercel/ai
Save

Vercel has updated its AI SDK, with releases for @ai-sdk/svelte@5.0.101, @ai-sdk/vue@4.0.101, and @ai-sdk/tui@1.0.102. These updates include changes to the core ai package, now at ai@7.0.101, and specific fixes for the @ai-sdk/google@4.0.70 package.

Key Points

  • The core ai package, now at ai@7.0.101, 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 addresses an issue where Gemini expected functionResponse.response to be an object, but non-object tool results could lead to a socket closure with code 1007.
  • Non-object tool results are now wrapped under an output key to align with Gemini's expected google.protobuf.Struct type for the functionResponse.response field.
  • The @ai-sdk/angular@3.0.101 and @ai-sdk/code-mode@1.0.58 packages have updated dependencies to ai@7.0.101.

Context

According to Vercel, these updates were released via the Changesets release GitHub action. The changes address specific technical issues related to how tool outputs are handled and how schema definitions are managed, particularly for integrations with Google Gemini.

Why It Matters

These updates improve the reliability and compatibility of the Vercel AI SDK, especially for developers integrating with Google Gemini. Correct serialization of tool outputs and proper schema handling can prevent unexpected disconnections and ensure data integrity in AI applications.

What To Do

  • Developers using the Vercel AI SDK should update their @ai-sdk/svelte, @ai-sdk/vue, or @ai-sdk/tui packages to the latest versions.
  • Note the change in how non-object tool results are now wrapped under an output key when interacting with Gemini.
  • Review the updated dependency for @ai-sdk/angular and @ai-sdk/code-mode to ai@7.0.101.
  • Test existing Gemini integrations to ensure continued functionality with the schema preservation and tool output serialization fixes.

Keep Exploring

/atlas/**gemini**-family /techniques/output-schema /techniques/ptcf