Skip to content

feat(deps): bump the ai-sdk group with 14 updates#52

Closed
dependabot[bot] wants to merge 1 commit into
mainfrom
dependabot/npm_and_yarn/ai-sdk-fa3f6ff32e
Closed

feat(deps): bump the ai-sdk group with 14 updates#52
dependabot[bot] wants to merge 1 commit into
mainfrom
dependabot/npm_and_yarn/ai-sdk-fa3f6ff32e

Conversation

@dependabot

@dependabot dependabot Bot commented on behalf of github Jul 1, 2026

Copy link
Copy Markdown
Contributor

Bumps the ai-sdk group with 14 updates:

Package From To
ai 6.0.207 7.0.9
@ai-sdk/amazon-bedrock 4.0.118 5.0.6
@ai-sdk/anthropic 3.0.85 4.0.4
@ai-sdk/cohere 3.0.39 4.0.2
@ai-sdk/deepseek 2.0.39 3.0.2
@ai-sdk/google 3.0.83 4.0.4
@ai-sdk/groq 3.0.42 4.0.2
@ai-sdk/mistral 3.0.40 4.0.2
@ai-sdk/openai 3.0.72 4.0.4
@ai-sdk/openai-compatible 2.0.51 3.0.2
@ai-sdk/xai 3.0.96 4.0.3
@ai-sdk/gateway 3.0.133 4.0.7
@ai-sdk/provider 3.0.10 4.0.1
@ai-sdk/provider-utils 4.0.30 5.0.2

Updates ai from 6.0.207 to 7.0.9

Release notes

Sourced from ai's releases.

ai@7.0.9

Patch Changes

  • Updated dependencies [2edc641]
  • Updated dependencies [c18018c]
    • @​ai-sdk/gateway@​4.0.7

ai@7.0.8

Patch Changes

  • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation
  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/gateway@​4.0.6
    • @​ai-sdk/provider-utils@​5.0.2

ai@6.0.217

Patch Changes

  • fa850e6: feat (video): add first-class frameImages and inputReferences call options for video generation
  • Updated dependencies [95bc6fd]
  • Updated dependencies [f6b2159]
  • Updated dependencies [fa850e6]
    • @​ai-sdk/gateway@​3.0.141
    • @​ai-sdk/provider@​3.0.13
    • @​ai-sdk/provider-utils@​4.0.34
Changelog

Sourced from ai's changelog.

7.0.9

Patch Changes

  • Updated dependencies [2edc641]
  • Updated dependencies [c18018c]
    • @​ai-sdk/gateway@​4.0.7

7.0.8

Patch Changes

  • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation
  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/gateway@​4.0.6
    • @​ai-sdk/provider-utils@​5.0.2

7.0.7

Patch Changes

  • d598481: Fix: convertToModelMessages no longer emits an empty assistant message when a block contains only unknown data parts (e.g. a data part before step-start with no convertDataPart provided)

7.0.6

Patch Changes

  • 989402d: Add ToolLoopAgent types for deprecated tool call callback aliases.
  • Updated dependencies [7e3c99e]
    • @​ai-sdk/gateway@​4.0.5

7.0.5

Patch Changes

  • a2750db: fix(ai): prune orphaned tool-approval responses in pruneMessages

    When pruning a specific tool by name (toolCalls: [{ type, tools: [...] }]), pruneMessages left the tool's tool-approval-response in place while removing its tool-approval-request and tool-call. The tool name of an approval response was resolved per-message, but approval responses live in a separate tool message from their approval request, so the name could never be resolved and the response was always kept. Tool name resolution is now done across all messages, so approval requests and responses are pruned together.

7.0.4

Patch Changes

  • Updated dependencies [6a436e3]
    • @​ai-sdk/provider-utils@​5.0.1
    • @​ai-sdk/gateway@​4.0.4

7.0.3

... (truncated)

Commits

Updates @ai-sdk/amazon-bedrock from 4.0.118 to 5.0.6

Release notes

Sourced from @​ai-sdk/amazon-bedrock's releases.

@​ai-sdk/google-vertex@​5.0.6

Patch Changes

  • 7ac79e7: feat(vertex): support tuned models
  • Updated dependencies [dc1eb8d]
    • @​ai-sdk/google@​4.0.4

@​ai-sdk/provider-utils@​5.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1

@​ai-sdk/svelte@​4.0.217

Patch Changes

  • Updated dependencies [fa850e6]
    • ai@6.0.217
    • @​ai-sdk/provider-utils@​4.0.34
Changelog

Sourced from @​ai-sdk/amazon-bedrock's changelog.

5.0.6

Patch Changes

  • c18018c: feat (provider/anthropic): add claude-sonnet-5 model id
  • Updated dependencies [c18018c]
    • @​ai-sdk/anthropic@​4.0.4

5.0.5

Patch Changes

  • 85a80fc: fix (amazon-bedrock): send the correct bedrockRerankingConfiguration request key for reranking

5.0.4

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/anthropic@​4.0.3
    • @​ai-sdk/openai@​4.0.4
    • @​ai-sdk/provider-utils@​5.0.2

5.0.3

Patch Changes

  • Updated dependencies [dfffb27]
  • Updated dependencies [1ead90c]
    • @​ai-sdk/anthropic@​4.0.2
    • @​ai-sdk/openai@​4.0.3

5.0.2

Patch Changes

  • Updated dependencies [6a436e3]
    • @​ai-sdk/provider-utils@​5.0.1
    • @​ai-sdk/anthropic@​4.0.1
    • @​ai-sdk/openai@​4.0.2

5.0.1

Patch Changes

  • Updated dependencies [9507724]
    • @​ai-sdk/openai@​4.0.1

5.0.0

... (truncated)

Commits

Updates @ai-sdk/anthropic from 3.0.85 to 4.0.4

Release notes

Sourced from @​ai-sdk/anthropic's releases.

@​ai-sdk/openai@​4.0.4

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/google@​4.0.4

Patch Changes

  • dc1eb8d: Support Gemini Interactions video output. Parse video output blocks from the Google Interactions API into file parts (buffered and streaming), and surface the per-modality output token breakdown via providerMetadata.google.outputTokensByModality.

@​ai-sdk/klingai@​4.0.3

Patch Changes

  • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation
  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/xai@​4.0.3

Patch Changes

  • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation
  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/openai-compatible@​3.0.2
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/mistral@​4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/perplexity@​4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/provider@​4.0.1

Patch Changes

  • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation

@​ai-sdk/react@​3.0.219

Patch Changes

... (truncated)

Changelog

Sourced from @​ai-sdk/anthropic's changelog.

4.0.4

Patch Changes

  • c18018c: feat (provider/anthropic): add claude-sonnet-5 model id

4.0.3

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

4.0.2

Patch Changes

  • dfffb27: fix(anthropic): correctly map delta type when code execution tools are used

4.0.1

Patch Changes

  • Updated dependencies [6a436e3]
    • @​ai-sdk/provider-utils@​5.0.1

4.0.0

Major Changes

  • 832f86f: fix(anthropic): remove cacheCreationInputTokens from providerMetadata

  • 34bd95d: feat(ai): add support for uploading provider skills using the provider references abstraction

  • 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

  • 3887c70: feat(provider): add new top-level reasoning parameter to spec and support it in generateText and streamText

  • 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

  • e02f041: feat(provider/anthropic): add support for claude-opus-4-8
  • 648705c: fix(provider/anthropic): fix remaining errors with Anthropic code_execution tool dynamic calls from latest web_fetch or web_search
  • 38fc777: Add AI Gateway hint to provider READMEs
  • ee798eb: chore(provider-utils): rename Experimental_Sandbox to Experimental_SandboxSession
  • e748b35: chore: update v3 specs to v4
  • 19c5ee2: fix(anthropic): reorder assistant content b/w client and provider tool use
  • 0ee8aec: feat (provider/anthropic): support passing metadata.user_id

... (truncated)

Commits

Updates @ai-sdk/cohere from 3.0.39 to 4.0.2

Release notes

Sourced from @​ai-sdk/cohere's releases.

@​ai-sdk/mistral@​4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/perplexity@​4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/provider@​4.0.1

Patch Changes

  • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation

@​ai-sdk/react@​3.0.219

Patch Changes

  • Updated dependencies [fa850e6]
    • ai@6.0.217
    • @​ai-sdk/provider-utils@​4.0.34

@​ai-sdk/vue@​3.0.217

Patch Changes

  • Updated dependencies [fa850e6]
    • ai@6.0.217
    • @​ai-sdk/provider-utils@​4.0.34

@​ai-sdk/svelte@​3.0.209

Patch Changes

  • ai@5.0.209

@​ai-sdk/google-vertex@​3.0.146

Patch Changes

  • Updated dependencies [8260f89]
    • @​ai-sdk/google@​2.0.78

@​ai-sdk/xai@​3.0.101

Patch Changes

  • fa850e6: feat (video): add first-class frameImages and inputReferences call options for video generation
  • Updated dependencies [fa850e6]
    • @​ai-sdk/provider@​3.0.13

... (truncated)

Changelog

Sourced from @​ai-sdk/cohere's changelog.

4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

4.0.1

Patch Changes

  • Updated dependencies [6a436e3]
    • @​ai-sdk/provider-utils@​5.0.1

4.0.0

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

  • 38fc777: Add AI Gateway hint to provider READMEs

  • 74d520f: feat: migrate providers to support new top-level reasoning parameter

  • 3cfb762: Harden streamed tool call argument parsing against prototype keys.

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

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

  • f2919d5: feat(provider/cohere): add support for passing images to Cohere models

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

  • 0c4c275: trigger initial canary release

  • 6fd51c0: fix(provider): preserve error type prefix in getErrorMessage

  • 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

  • b8396f0: trigger initial beta release

  • 90e2d8a: chore: fix unused vars not being flagged by our lint tooling

  • 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.

4.0.0-beta.54

... (truncated)

Commits

Updates @ai-sdk/deepseek from 2.0.39 to 3.0.2

Release notes

Sourced from @​ai-sdk/deepseek's releases.

@​ai-sdk/hume@​3.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/lmnt@​3.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/openai-compatible@​3.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/revai@​3.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/valibot@​3.0.2

Patch Changes

  • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/vercel@​3.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/openai-compatible@​3.0.2
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/langchain@​2.0.225

Patch Changes

  • Updated dependencies [fa850e6]
    • ai@6.0.217

@​ai-sdk/llamaindex@​2.0.217

Patch Changes

... (truncated)

Changelog

Sourced from @​ai-sdk/deepseek's changelog.

3.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

3.0.1

Patch Changes

  • Updated dependencies [6a436e3]
    • @​ai-sdk/provider-utils@​5.0.1

3.0.0

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.

  • 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

  • 38fc777: Add AI Gateway hint to provider READMEs

  • 0498012: fix(provider/deepseek): preserve reasoning_content for deepseek-v4 in multi-turn requests

  • 74d520f: feat: migrate providers to support new top-level reasoning parameter

  • 87280a6: Accept thinking.type: 'adaptive' and the full reasoningEffort enum (low, medium, high, xhigh, max) for the DeepSeek provider.

  • 45b3d76: fix(security): prevent streaming tool calls from finalizing on parsable partial JSON

    Streaming tool call arguments were finalized using isParsableJson() as a heuristic for completion. If partial accumulated JSON happened to be valid JSON before all chunks arrived, the tool call would be executed with incomplete arguments. Tool call finalization now only occurs in flush() after the stream is fully consumed.

  • b23b042: feat(azure): add deepseek model support to azure

  • eda4373: feat(provider/deepseek): add DeepSeek V4 reasoning effort support

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

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

  • f7295cb: revert incorrect fix vercel/ai#13172

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

  • f807e45: Extract shared StreamingToolCallTracker class into @ai-sdk/provider-utils to deduplicate streaming tool call handling across OpenAI-compatible providers. Also adds missing generateId() fallback for toolCallId in Alibaba's doGenerate path and ensures all providers finalize unfinished tool calls during stream flush.

  • 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

  • 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.

... (truncated)

Commits

Updates @ai-sdk/google from 3.0.83 to 4.0.4

Release notes

Sourced from @​ai-sdk/google's releases.

@​ai-sdk/google@​4.0.4

Patch Changes

  • dc1eb8d: Support Gemini Interactions video output. Parse video output blocks from the Google Interactions API into file parts (buffered and streaming), and surface the per-modality output token breakdown via providerMetadata.google.outputTokensByModality.

@​ai-sdk/google-vertex@​3.0.146

Patch Changes

  • Updated dependencies [8260f89]
    • @​ai-sdk/google@​2.0.78
Changelog

Sourced from @​ai-sdk/google's changelog.

4.0.4

Patch Changes

  • dc1eb8d: Support Gemini Interactions video output. Parse video output blocks from the Google Interactions API into file parts (buffered and streaming), and surface the per-modality output token breakdown via providerMetadata.google.outputTokensByModality.

4.0.3

Patch Changes

  • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation
  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

4.0.2

Patch Changes

  • Updated dependencies [6a436e3]
    • @​ai-sdk/provider-utils@​5.0.1

4.0.1

Patch Changes

  • ba6d510: chore: fix deprecated use of zod .passthrough()

4.0.0

Major Changes

  • a3757d7: chore(provider/google): remove useless GenerativeAI affix from types and classes for consistency

  • f7d4f01: feat(provider): add support for reasoning-file type for files that are part of reasoning

  • 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

  • 3887c70: feat(provider): add new top-level reasoning parameter to spec and support it in generateText and streamText

  • 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

  • 7f04802: feat(provider/google): add support for managed agents in the Interactions API
  • 38fc777: Add AI Gateway hint to provider READMEs
  • b71c0d7: feat(provider/google): support Google search grounding when using generateImage with Gemini
  • 6190649: chore(provider/google): remove obsolete Google image model
  • 55db546: fix(provider/google): fix Gemini service tier enum after upstream update
  • 9a0a618: fix(google): fix serviceTier to be correctly formatted for Vertex API

... (truncated)

Commits

Updates @ai-sdk/groq from 3.0.42 to 4.0.2

Release notes

Sourced from @​ai-sdk/groq's releases.

@​ai-sdk/mistral@​4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/perplexity@​4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/provider@​4.0.1

Patch Changes

  • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation

@​ai-sdk/react@​3.0.219

Patch Changes

  • Updated dependencies [fa850e6]
    • ai@6.0.217
    • @​ai-sdk/provider-utils@​4.0.34

@​ai-sdk/vue@​3.0.217

Patch Changes

  • Updated dependencies [fa850e6]
    • ai@6.0.217
    • @​ai-sdk/provider-utils@​4.0.34

@​ai-sdk/svelte@​3.0.209

Patch Changes

  • ai@5.0.209

@​ai-sdk/google-vertex@​3.0.146

Patch Changes

  • Updated dependencies [8260f89]
    • @​ai-sdk/google@​2.0.78

@​ai-sdk/xai@​3.0.101

Patch Changes

  • fa850e6: feat (video): add first-class frameImages and inputReferences call options for video generation
  • Updated dependencies [fa850e6]
    • @​ai-sdk/provider@​3.0.13

... (truncated)

Changelog

Sourced from @​ai-sdk/groq's changelog.

4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

4.0.1

Patch Changes

  • Updated dependencies [6a436e3]
    • @​ai-sdk/provider-utils@​5.0.1

4.0.0

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

  • 38fc777: Add AI Gateway hint to provider READMEs

  • 023550e: Deprecate streamText result fullStream in favor of stream.

  • 74d520f: feat: migrate providers to support new top-level reasoning parameter

  • 45b3d76: fix(security): prevent streaming tool calls from finalizing on parsable partial JSON

    Streaming tool call arguments were finalized using isParsableJson() as a heuristic for completion. If partial accumulated JSON happened to be valid JSON before all chunks arrived, the tool call would be executed with incomplete arguments. Tool call finalization now only occurs in flush() after the stream is fully consumed.

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

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

  • 7bf717f: feat: Groq support for performance service tier

  • f7295cb: revert incorrect fix vercel/ai#13172

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

  • f807e45: Extract shared StreamingToolCallTracker class into @ai-sdk/provider-utils to deduplicate streaming tool call handling across OpenAI-compatible providers. Also adds missing generateId() fallback for toolCallId in Alibaba's doGenerate path and ensures all providers finalize unfinished tool calls during stream flush.

  • 0c4c275: trigger initial canary release

  • 6fd51c0: fix(provider): preserve error type prefix in getErrorMessage

  • 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

  • b8396f0: trigger initial beta release

  • 90e2d8a: chore: fix unused vars not being flagged by our lint tooling

  • 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.

... (truncated)

Commits

Updates @ai-sdk/mistral from 3.0.40 to 4.0.2

Release notes

Sourced from @​ai-sdk/mistral's releases.

@​ai-sdk/mistral@​4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

@​ai-sdk/mistral@​3.0.44

Patch Changes

  • Updated dependencies [fa850e6]
    • @​ai-sdk/provider@​3.0.13
    • @​ai-sdk/provider-utils@​4.0.34
Changelog

Sourced from @​ai-sdk/mistral's changelog.

4.0.2

Patch Changes

  • Updated dependencies [0274f34]
    • @​ai-sdk/provider@​4.0.1
    • @​ai-sdk/provider-utils@​5.0.2

4.0.1

Patch Changes

  • Updated dependencies [6a436e3]
    • @​ai-sdk/provider-utils@​5.0.1

4.0.0

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.

... (truncated)

Commits

Updates @ai-sdk/openai from 3.0.72 to 4.0.4

Release notes

Sourced from @​ai-sdk/openai's releases.

@​ai-sdk/openai@​4.0.4

Patch Changes

@dependabot
feat(deps): bump the ai-sdk group with 14 updates
233fbbd 
Bumps the ai-sdk group with 14 updates:

| Package | From | To |
| --- | --- | --- |
| [ai](https://github.com/vercel/ai/tree/HEAD/packages/ai) | `6.0.207` | `7.0.9` |
| [@ai-sdk/amazon-bedrock](https://github.com/vercel/ai/tree/HEAD/packages/amazon-bedrock) | `4.0.118` | `5.0.6` |
| [@ai-sdk/anthropic](https://github.com/vercel/ai/tree/HEAD/packages/anthropic) | `3.0.85` | `4.0.4` |
| [@ai-sdk/cohere](https://github.com/vercel/ai/tree/HEAD/packages/cohere) | `3.0.39` | `4.0.2` |
| [@ai-sdk/deepseek](https://github.com/vercel/ai/tree/HEAD/packages/deepseek) | `2.0.39` | `3.0.2` |
| [@ai-sdk/google](https://github.com/vercel/ai/tree/HEAD/packages/google) | `3.0.83` | `4.0.4` |
| [@ai-sdk/groq](https://github.com/vercel/ai/tree/HEAD/packages/groq) | `3.0.42` | `4.0.2` |
| [@ai-sdk/mistral](https://github.com/vercel/ai/tree/HEAD/packages/mistral) | `3.0.40` | `4.0.2` |
| [@ai-sdk/openai](https://github.com/vercel/ai/tree/HEAD/packages/openai) | `3.0.72` | `4.0.4` |
| [@ai-sdk/openai-compatible](https://github.com/vercel/ai/tree/HEAD/packages/openai-compatible) | `2.0.51` | `3.0.2` |
| [@ai-sdk/xai](https://github.com/vercel/ai/tree/HEAD/packages/xai) | `3.0.96` | `4.0.3` |
| [@ai-sdk/gateway](https://github.com/vercel/ai/tree/HEAD/packages/gateway) | `3.0.133` | `4.0.7` |
| [@ai-sdk/provider](https://github.com/vercel/ai/tree/HEAD/packages/provider) | `3.0.10` | `4.0.1` |
| [@ai-sdk/provider-utils](https://github.com/vercel/ai/tree/HEAD/packages/provider-utils) | `4.0.30` | `5.0.2` |


Updates `ai` from 6.0.207 to 7.0.9
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/ai/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/ai@7.0.9/packages/ai)

Updates `@ai-sdk/amazon-bedrock` from 4.0.118 to 5.0.6
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/amazon-bedrock/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/amazon-bedrock@5.0.6/packages/amazon-bedrock)

Updates `@ai-sdk/anthropic` from 3.0.85 to 4.0.4
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/anthropic/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/anthropic@4.0.4/packages/anthropic)

Updates `@ai-sdk/cohere` from 3.0.39 to 4.0.2
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/cohere/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/cohere@4.0.2/packages/cohere)

Updates `@ai-sdk/deepseek` from 2.0.39 to 3.0.2
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/deepseek/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/deepseek@3.0.2/packages/deepseek)

Updates `@ai-sdk/google` from 3.0.83 to 4.0.4
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/google/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/google@4.0.4/packages/google)

Updates `@ai-sdk/groq` from 3.0.42 to 4.0.2
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/groq/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/groq@4.0.2/packages/groq)

Updates `@ai-sdk/mistral` from 3.0.40 to 4.0.2
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/mistral/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/mistral@4.0.2/packages/mistral)

Updates `@ai-sdk/openai` from 3.0.72 to 4.0.4
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/openai/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/openai@4.0.4/packages/openai)

Updates `@ai-sdk/openai-compatible` from 2.0.51 to 3.0.2
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/openai-compatible/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/openai-compatible@3.0.2/packages/openai-compatible)

Updates `@ai-sdk/xai` from 3.0.96 to 4.0.3
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/xai/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/xai@4.0.3/packages/xai)

Updates `@ai-sdk/gateway` from 3.0.133 to 4.0.7
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/gateway/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/gateway@4.0.7/packages/gateway)

Updates `@ai-sdk/provider` from 3.0.10 to 4.0.1
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/provider/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/provider@4.0.1/packages/provider)

Updates `@ai-sdk/provider-utils` from 4.0.30 to 5.0.2
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/provider-utils/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/provider-utils@5.0.2/packages/provider-utils)

---
updated-dependencies:
- dependency-name: ai
  dependency-version: 7.0.9
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/amazon-bedrock"
  dependency-version: 5.0.6
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/anthropic"
  dependency-version: 4.0.4
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/cohere"
  dependency-version: 4.0.2
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/deepseek"
  dependency-version: 3.0.2
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/google"
  dependency-version: 4.0.4
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/groq"
  dependency-version: 4.0.2
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/mistral"
  dependency-version: 4.0.2
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/openai"
  dependency-version: 4.0.4
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/openai-compatible"
  dependency-version: 3.0.2
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/xai"
  dependency-version: 4.0.3
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/gateway"
  dependency-version: 4.0.7
  dependency-type: indirect
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/provider"
  dependency-version: 4.0.1
  dependency-type: indirect
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/provider-utils"
  dependency-version: 5.0.2
  dependency-type: indirect
  update-type: version-update:semver-major
  dependency-group: ai-sdk
...

Signed-off-by: dependabot[bot] <support@github.com>
@dependabot dependabot Bot added dependencies Pull requests that update a dependency file javascript Pull requests that update javascript code labels Jul 1, 2026
@mcarvin8 mcarvin8 closed this Jul 1, 2026
@dependabot @github

dependabot Bot commented on behalf of github Jul 1, 2026

Copy link
Copy Markdown
Contributor Author

This pull request was built based on a group rule. Closing it will not ignore any of these versions in future pull requests.

To ignore these dependencies, configure ignore rules in dependabot.yml

@mcarvin8 mcarvin8 deleted the dependabot/npm_and_yarn/ai-sdk-fa3f6ff32e branch July 1, 2026 16:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

dependencies Pull requests that update a dependency file javascript Pull requests that update javascript code

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@mcarvin8