Major Changes

• ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only ("type": "module"). Consumers using require() must switch to ESM import syntax.

• c29a26f: feat(provider): add support for provider references and uploading files as supported per provider

• 8359612: Start v7 pre-release

• 04e9009: chore: make provider implementations code patterns more consistent, including renaming certain exported symbols

  For all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.

Patch Changes

• 737b8f4: feat(provider/mistral): add support for reasoning configuration (mistral-small-latest)

• 3ae1d12: Add support for mistral-medium-3.5

• 38fc777: Add AI Gateway hint to provider READMEs

• 8abd80f: Map cached token counts from Mistral API usage response. Previously all prompt tokens were reported as noCacheTokens, ignoring the num_cached_tokens, prompt_tokens_details.cached_tokens, and prompt_token_details.cached_tokens fields returned by Mistral.

• 7acf358: fix(mistral): forward stopSequences as Mistral's native stop parameter

• 9f0e36c: trigger release for all packages after provenance setup

• 58a2ad7: fix: more precise default message for tool execution denial

• 5259a95: chore: add warning for providers that do not support new reasoning parameter

• 7fc6bd6: Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.

• 0c4c275: trigger initial canary release

• 9bd6512: feat(provider): change file part data property to be tagged with a type and remove the image part type

• 258c093: chore: ensure consistent import handling and avoid import duplicates or cycles

• 5463d0d: feat(provider): align tool result output content file part types with top-level message file part types

• b8396f0: trigger initial beta release

• b3976a2: Add workflow serialization support to all provider models.

  @ai-sdk/provider-utils: New serializeModel() helper that extracts only serializable properties from a model instance, filtering out functions and objects containing functions. Third-party provider authors can use this to add workflow support to their own models.

  All providers: headers is now optional in provider config types. This is non-breaking — existing code that passes headers continues to work. Custom provider implementations that construct model configs manually can now omit headers, which is useful when models are deserialized from a workflow step boundary where auth is provided separately.

  All provider model classes now include WORKFLOW_SERIALIZE and WORKFLOW_DESERIALIZE static methods, enabling them to cross workflow step boundaries without serialization errors.

• ff5eba1: feat: roll image-* tool output types into their equivalent file-* types