Packages

@ai-sdk/google

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

Upgrading @ai-sdk/google From 0.0.28 to 4.0.122

468 releases in betweennotes for 466

Reading releases, release notes and advisories…

Other targets from 0.0.28Newest 0.x0.0.55
  1. 0.0.28yours
  2. 26 releases
  3. 1.0.0major
  4. 68 releases
  5. 2.0.0major
  6. 109 releases
  7. 3.0.0major
  8. 143 releases
  9. 4.0.0security
  10. 6 releases
  11. 4.0.7security
  12. 110 releases
  13. 4.0.122target
15+
changes to make
0
advisories fixed
124+
new
216+
fixes

Counted from 466 of 468 release notes. Advisories are counted from the advisory database, in full.

Before you upgrade

Tick each one off as you go
  • Breaking4.0.0
  • Breaking4.0.0
  • Breaking4.0.0
  • Breaking4.0.0
  • Breaking4.0.0
  • Breaking4.0.0
  • Breaking4.0.0
  • Breaking4.0.0
  • Breaking3.0.0
  • Breaking2.0.0

Security

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

    4.0.7
  • google: Prevent prototype pollution when streaming tool args

    4.0.0

Release by release

  1. 4.0.122

    17 Nov 20263 fixes
    • Fixed

      google: Reject structured output schemas in batch requests because inline Google batch requests ignore responseJsonSchema

    • Fixed

      provider/google: Redact MCP server credentials in telemetry

    • Fixed

      google: Include promptFeedback.blockReasonMessage in provider metadata

  2. 4.0.121

    13 Nov 20262 fixes
    • Fixed

      Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while preserving existing suggestions, endpoint-specific model lists, and support for custom model IDs.

    • Fixed

      Fix Google Interactions ignoring top-level reasoning in generation and streaming calls. Map reasoning to model-supported thinking levels, including Hydrogen's xhigh, preserve explicit thinkingLevel overrides and API defaults, and warn when reasoning is unsupported.

  3. 4.0.120

    13 Nov 20261 new
    • New

      Add experimental extraction models backed by structured language model output

  4. 4.0.119

    12 Nov 20261 new · 1 fix
    • New

      Add the gemini-4-hydrogen model ID and support Hydrogen's xhigh thinking level in Google Generate Content and Interactions provider options. Map portable reasoning: 'xhigh' to xhigh only for Hydrogen models.

    • Fixed

      Forward the provider's configured fetch transport when downloading file inputs. Add a fetch option to createDownload so core downloads can also use guarded-fetch for opt-in DNS validation on Node.js. The function returned by createDownload can now also be passed as experimental_download to generateText and streamText, and experimental_download now also handles generated file URLs returned by the model, so one hook covers all core downloads. Document that the default URL checks do not resolve DNS and recommend the guarded transport or network egress controls for untrusted URLs.

  5. 4.0.118

    11 Nov 20262 fixes
    • Fixed

      Use the native gemini decisions api for google decision models

    • Fixed

      Emit File Search and RAG document sources when streaming. Deduplicate by document URI or File Search store and title so distinct documents with matching titles and filenames are preserved.

  6. 4.0.117

    10 Nov 20261 new
    • New

      Add support for the gemini-4-carbon model with the same capabilities as gemini-4-argon.

  7. 4.0.116

    10 Nov 20262 fixes
    • Fixed

      Preserve the served service tier from the x-gemini-service-tier response header when usage metadata omits it, for generated and streamed responses.

    • Fixed

      Apply contiguous array-index validation to dotted numeric paths in streamed tool arguments, while preserving numeric object keys and valid contiguous array updates.

  8. 4.0.114

    7 Nov 20261 new · 3 fixes
    • New

      Add resolveProviderOptions to parse provider options that a model accepts under several providerOptions keys, either as aliases (first) or merged in order (merge), and use it for the existing multi-key lookups in the OpenAI, OpenAI-compatible, Anthropic, Google, and Amazon Bedrock models. Resolution behavior for these models is unchanged.

    • Fixed

      Pass providerOptions.google.labels through to Google and Vertex AI Interactions requests, including streaming, so callers can attach request metadata such as safety_identifier.

    • Fixed

      Omit Google provider-defined tools, including File Search and Vertex RAG Store, when toolChoice is none so disabled tools cannot retrieve data or execute server-side. Preserve function declarations needed by conversation history while disabling function calling. This also applies when structured output uses a synthetic JSON response tool.

    • Fixed

      Skip streamed tool-call array indexes that leave a gap so a small response can't build a huge sparse array

281 internal lines (docs, tests, tooling) left out.

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.