NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm, #4234 most downloaded on npm
Latest stable
4.0.117
Last release 7 days ago
10 Nov 2026
Ships on a steady schedule
a new release about every 8 days
Most releases are documented
notes for 42 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
743 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
00a0f36: feat(google, google-vertex): added gemini-embedding-2, deep-research-max-preview-04-2026 and deep-research-preview-04-2026
gemini-embedding-2, deep-research-max-preview-04-2026 and deep-research-preview-04-2026a8d70b6: fix(google): auto-inject skip_thought_signature_validator for Gemini 3 tool-call replays without a signature
skip_thought_signature_validator for Gemini 3 tool-call replays without a signatureYour coding agent can read these notes before it upgrades. Set up the MCP server →
@ai-sdk/provider-utils@5.0.0-canary.44
b71c0d7: feat(provider/google): support Google search grounding when using generateImage with Gemini
generateImage with Gemini045d2e8: fix(google): read serviceTier from usageMetadata.serviceTier in both generate and stream paths
045d2e8: fix(google): read serviceTier from usageMetadata.serviceTier in both generate and stream paths
The previous implementation read serviceTier from the x-gemini-service-tier
response header, which is only populated on non-streaming responses. Gemini
streaming includes the value in usageMetadata.serviceTier on every chunk, so
providerMetadata.google.serviceTier was always null for streams. Read from
usageMetadata for both paths instead.
aeea161: feat(google): read serviceTier from x-gemini-service-tier response header in Gemini API and use PayGo for Vertex
serviceTier from x-gemini-service-tier response header in Gemini API and use PayGo for Vertex7f04802: feat(provider/google): add support for managed agents in the Interactions API
a2609df: fix(google): fix streaming tool call args
gemini-3.5-flash7fc6bd6: Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.
4e825f3: feat(google): update Interactions API implementation to cater for upstream breaking changes coming May 26
41da50c: fix(provider/google): support functionCall.id when returned by Gemini API and provide matching functionResponse.id
functionCall.id when returned by Gemini API and provide matching functionResponse.id@ai-sdk/provider-utils@5.0.0-canary.41
@ai-sdk/provider-utils@5.0.0-canary.40
@ai-sdk/provider-utils@5.0.0-canary.39
6a26901: feat(google): add fileData support to embedding model
fileData support to embedding modeldb394ab: feat(provider/google): support cancelling long-running Interactions API agents via AbortSignal, and process their intermittent stream
@ai-sdk/provider-utils@5.0.0-canary.37
@ai-sdk/provider-utils@5.0.0-canary.36
@ai-sdk/provider-utils@5.0.0-canary.35
ebbb0f2: fix(provider/google): fix lack of image consistency when using Interactions API in stateless mode
b04e23e: feat(provider/google): add support for the Gemini Interactions API
@ai-sdk/provider-utils@5.0.0-canary.33
cfca634: fix(google): emit Vertex no-args streaming tool calls and preserve thoughtSignature
cfca634: fix(google): emit Vertex no-args streaming tool calls and preserve thoughtSignature
Vertex emits a no-args function call as a single chunk shaped { functionCall: { name: 'X' } } with no args, no partialArgs, and no willContinue. The streaming parser had no branch for this shape, so the call was dropped along with any thoughtSignature it carried. For Gemini 3 thinking models this caused the next multi-turn step to 400 with missing thought_signature. The unary (doGenerate) path had the same drop.
Both paths now emit the call as a complete tool call with '{}' input and propagate thoughtSignature provider metadata.
Fixes #14847.
5463d0d: feat(provider): align tool result output content file part types with top-level message file part types
0c4c275: trigger initial canary release
@ai-sdk/provider-utils@5.0.0-beta.50
947cdab: Add Google realtime Live Translation provider options for gemini-3.5-live-translate-preview.
gemini-3.5-live-translate-preview.bdb9ea1: chore(google): remove now obsolete Interactions API Api-Revision header
Api-Revision headerb8396f0: trigger initial beta release
For all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.
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.
9bd6512: feat(provider): change file part data property to be tagged with a type and remove the image part type
9f0e36c: trigger release for all packages after provenance setup
58a2ad7: fix: more precise default message for tool execution denial
a3757d7: chore(provider/google): remove useless GenerativeAI affix from types and classes for consistency
@ai-sdk/provider-utils@5.0.0-beta.25
@ai-sdk/provider-utils@5.0.0-beta.24
@ai-sdk/provider-utils@5.0.0-beta.23
@ai-sdk/provider-utils@5.0.0-beta.22
55f0938: chore(provider/google): update available models
@ai-sdk/provider-utils@5.0.0-beta.21
b3976a2: Add workflow serialization support to all provider models.
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
Updated dependencies [b3976a2]
Updated dependencies [ff5eba1]
ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only ("type": "module"). Consumers using require() must switch to ESM imp
"type": "module"). Consumers using require() must switch to ESM import syntax.9a0a618: fix(google): fix serviceTier to be correctly formatted for Vertex API
serviceTier to be correctly formatted for Vertex API90e2d8a: chore: fix unused vars not being flagged by our lint tooling
5b7e7c2: fix(google-vertex): don't send streamFunctionCallArguments for unary API calls and change default to false
@ai-sdk/provider-utils@5.0.0-beta.17
5036db8: feat(google-vertex): add support for streaming tool arguments input
@ai-sdk/provider-utils@5.0.0-beta.16
@ai-sdk/provider-utils@5.0.0-beta.15
@ai-sdk/provider-utils@5.0.0-beta.14
46d1149: chore(provider-utils,google): fix grammar errors in error and warning messages
a05109d: feat(provider/google): preserve per-modality token details in usage data
@ai-sdk/provider-utils@5.0.0-beta.11
55db546: fix(provider/google): fix Gemini service tier enum after upstream update
c29a26f: feat(provider): add support for provider references and uploading files as supported per provider
38fc777: Add AI Gateway hint to provider READMEs
@ai-sdk/provider-utils@5.0.0-beta.9
@ai-sdk/provider-utils@5.0.0-beta.8
01fa606: feat(provider/google): support combining built-in tools with function calling on Gemini 3
9715ec7: feat(provider/google): add support for service tier parameter
One column per month.