@ai-sdk/typesafe-ai

This release record was completed by a GitHub Actions automated workflow and carries an official GitHub verified signature (Verified).

When using @ai-sdk/svelte, users should ensure that the versions of ai and @ai-sdk/svelte are aligned, avoiding mixing different major versions.

Within the AI SDK ecosystem, there exists an adapter package @ai-sdk/zod similar to @ai-sdk/valibot, with both providing the same public interface.

The release notes for this release do not list the specific change entries for @ai-sdk/harness 1.0.160 in detail.

For patch-level updates, if the changeset description is too brief or is not included in the release process, the Release page may show only the version number and build artifacts, lacking detailed user-facing explanations.

typesafe-ai is a package that provides a type-safe call wrapper on top of the AI SDK, and the matching dependency versions must be locked to ensure consistency between type definitions and runtime behavior.

v3.24.0 was released by GitHub with a verified signature.

The reasoning retention feature only takes effect on models that support reasoning output and does not affect regular conversational models.

The `@ai-sdk/typesafe-ai` package released version 3.0.27, which is a Patch Changes version and introduces no new features or breaking changes.

@ai-sdk/vue released version 4.0.149.

The @ai-sdk/zai package released version 3.0.8, which is a patch change.

@ai-sdk/svelte released version 5.0.93.

Version 3.0.40 contains documentation maintenance commit e729d58, which updates README.md to unify formatting and avoid duplicate content.

For projects using `@ai-sdk/typesafe-ai`, it is recommended to run the existing type checks and integration tests after upgrading to confirm that the compatibility of the provider interfaces has not drifted unexpectedly.

For projects locked to the 3.0.x series, following the 3.0.29 patch usually carries no additional cost.

3.0.29 is a patch version whose changes consist solely of two dependency updates, with no new features.

@ai-sdk/typesafe-ai is a type-safe wrapper layer for the AI SDK, providing stricter type constraints for scenarios such as model calls, tool definitions, and structured output.

The only change in version 3.0.28 is updating the dependency @ai-sdk/provider-utils to 5.0.69, with commit reference e64ed82.

The core commit of this update is 0c2a9de, which adds two parameters, maxOutputTokens and reasoning, to experimental decision calls.

For native decision providers, if the backend does not support either the maxOutputTokens or the reasoning setting, the system issues a warning rather than silently ignoring it.