Packages

@ai-sdk/google

4.0.122 · 17 Nov 2026Apache-2.014.6M / weekRepositoryHomepagenpmAtom feed

Your version

497 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.

  1. 3.0.114

    26 Aug 2026
    • Preserve recursive tool input schemas without aborting Google model calls.

  2. 3.0.112 – 3.0.1132 releases that only update dependencies@ai-sdk/provider-utils 4.0.48Show each
  3. 3.0.111

    20 Aug 2026
    • Inline local JSON Schema references in Google tool and structured-output schemas.

  4. 3.0.110

    14 Aug 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.46

  5. 3.0.109

    14 Aug 2026
    • google: Add gemini-3.7-flash model

  6. 3.0.108

    12 Aug 2026
    • Preserve forced tool calls when strict function tools are configured.

  7. 3.0.107

    11 Aug 2026
    • Preserve Google API error details in APICallError.data.

  8. 3.0.103 – 3.0.1064 releases that only update dependencies@ai-sdk/provider 3.0.15@ai-sdk/provider-utils 4.0.44Show each
  9. 3.0.102

    28 Jul 2026
    • Forward topK through Google Interactions requests and warn when unsupported frequency or presence penalties are provided.

  10. 3.0.101

    24 Jul 2026
    • google: Omit unsupported function call IDs

  11. 3.0.100

    23 Jul 2026
    • provider/google: Default unknown Gemini model IDs to the newest supported capabilities

  12. 3.0.99

    22 Jul 2026
    • Avoid missing thought-signature warnings and skip-validator injection for valid unsigned Gemini 3 parallel function calls in the same model response.

  13. 3.0.98

    21 Jul 2026
    • google: Add gemini-3.6-flash and gemini-3.5-flash-lite models

  14. 3.0.97

    21 Jul 2026
    • provider/google: Surface Gemini responseId as response-metadata (stream) and response.id (generate)

  15. 3.0.96

    20 Jul 2026
    • provider/google: Associate multiple code execution results with their tool call

  16. 3.0.95

    17 Jul 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.40

  17. 3.0.94

    15 Jul 2026
    • provider/google: Forward Vertex-only imageConfig options (personGeneration, prominentPeople, imageOutputOptions)

  18. 3.0.93

    14 Jul 2026
    • Allow google.interactions agent requests to include supported tools, including file_search.

  19. 3.0.92

    14 Jul 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.39

  20. 3.0.91

    9 Jul 2026
    • Fix Google tool result conversion to send file data as inline data instead of JSON text on the legacy tool-result path.

    • Expand standalone Google threshold provider options into safety settings.

    • Feat (video): support video (not just image) reference inputs in inputReferences for reference-to-video generation

  21. 3.0.90

    7 Jul 2026
    • Backport Gemini Interactions video output parsing and per-modality output token breakdown for AI SDK v6.

    • Backport vertex.interactions() for the Gemini Interactions API on Vertex AI for AI SDK v6.

    • Pass documented Gemini external HTTPS file URLs through without downloading them.

  22. 3.0.89

    6 Jul 2026
    • Security

      Prevent prototype pollution when synchronously parsing provider JSON inputs and expose secureJsonParse from provider-utils.

    • Fix Google embedding batch size to respect the Gemini API limit of 100 requests per batch.

  23. 3.0.88

    1 Jul 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.35

  24. 3.0.87

    30 Jun 2026
    • Feat (video): add first-class frameImages and inputReferences call options for video generation

  25. 3.0.85 – 3.0.862 releases that only update dependencies@ai-sdk/provider-utils 4.0.33@ai-sdk/provider 3.0.12Show each
  26. 3.0.84

    25 Jun 2026
    • Publish all packages under the @ai-v6 dist tag.

  27. 3.0.83

    16 Jun 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.30

  28. 3.0.82

    12 Jun 2026
    • Security

      google: Prevent prototype pollution when streaming tool args

    • Only send provider credentials to same-origin response-supplied URLs

      Several provider clients followed a URL taken from the provider's API response (a polling/status URL or a final media URL such as polling_url, urls.get, result_url, result.sample, or video.uri) and reused the authenticated headers — or appended ?key=<API_KEY> — on that request. Because the host of the response-supplied URL was never validated, the long-lived API key was sent to whatever host the response named (a CDN in the benign case, or an attacker-chosen host if the provider response was tampered with), allowing credential exfiltration.

      A new isSameOrigin helper is added to @ai-sdk/provider-utils, and the affected fetches in @ai-sdk/black-forest-labs, @ai-sdk/fireworks, @ai-sdk/replicate, @ai-sdk/gladia, @ai-sdk/fal, and @ai-sdk/google now attach credentials only when the followed URL is same-origin with the provider's configured API origin. Requests to a foreign origin are made without the credential.

  29. 3.0.81

    11 Jun 2026
  30. 3.0.80

    27 May 2026
    • google: auto-inject skip_thought_signature_validator for Gemini 3 tool-call replays without a signature

      Gemini 3 models reject requests when an assistant functionCall part lacks a thoughtSignature with HTTP 400 "Function call is missing a thought_signature in functionCall parts." This is easy to hit when application code persists/serializes messages and drops providerOptions.google.thoughtSignature (custom DB schemas, useChat server routes that rebuild messages, synthetic tool-call injection).

      The provider now detects this case (Gemini 3 model + missing signature under google, googleVertex, and vertex namespaces) and injects the documented skip_thought_signature_validator sentinel into the outbound functionCall, plus surfaces a one-shot warning per request listing the affected tool names so the developer can find and fix the upstream serialization. Non-Gemini-3 models are unaffected, and real signatures take precedence when present.

  31. 3.0.79

    21 May 2026
    • provider/google: Support Google search grounding when using generateImage with Gemini

  32. 3.0.78

    21 May 2026
    • 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.

  33. 3.0.77

    20 May 2026
    • google: Read serviceTier from x-gemini-service-tier response header in Gemini API and use PayGo for Vertex

  34. 3.0.75

    16 May 2026
    • google: Update Interactions API implementation to cater for upstream breaking changes coming May 26

  35. 3.0.74

    15 May 2026
    • provider/google: Support functionCall.id when returned by Gemini API and provide matching functionResponse.id

  36. 3.0.73

    12 May 2026
    • google: Add fileData support to embedding model

  37. 3.0.72

    11 May 2026
    • provider/google: Support cancelling long-running Interactions API agents via AbortSignal, and process their intermittent stream

  38. 3.0.71

    8 May 2026
    • 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.

  39. 3.0.70

    7 May 2026
    • provider/google: Fix lack of image consistency when using Interactions API in stateless mode

  40. 3.0.68

    6 May 2026
    • provider/google: Add support for the Gemini Interactions API

  41. 3.0.66 – 3.0.672 releases that only update dependencies@ai-sdk/provider-utils 4.0.26@ai-sdk/provider 3.0.10Show each
  42. 3.0.65

    29 Apr 2026
    • Trigger release for all packages after provenance setup

  43. 3.0.64

    16 Apr 2026

    Maintenance only: docs, tests, build or refactoring. Nothing changes in how you use it.

  44. 3.0.63

    13 Apr 2026
    • google: Fix serviceTier to be correctly formatted for Vertex API

A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.