Skip to content

fix(deps): update non-major dependencies - #62

Open
renovate[bot] wants to merge 1 commit into
mainfrom
renovate/non-major
Open

fix(deps): update non-major dependencies#62
renovate[bot] wants to merge 1 commit into
mainfrom
renovate/non-major

Conversation

@renovate

@renovate renovate Bot commented Oct 1, 2026 •
edited
Loading

Copy link
Copy Markdown

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package Change Age Confidence Type Update Pending
@ai-sdk/amazon-bedrock (source) 5.0.103 → 5.0.113 age confidence dependencies patch
@ai-sdk/anthropic (source) 4.0.70 → 4.0.78 age confidence dependencies patch
@ai-sdk/azure (source) 4.0.87 → 4.0.99 age confidence dependencies patch
@ai-sdk/google (source) 4.0.87 → 4.0.93 age confidence dependencies patch
@ai-sdk/google-vertex (source) 5.0.100 → 5.0.109 age confidence dependencies patch
@ai-sdk/openai (source) 4.0.83 → 4.0.91 age confidence dependencies patch
@ai-sdk/openai-compatible (source) 3.0.61 → 3.0.67 age confidence dependencies patch
@aws-sdk/credential-providers (source) 3.1144.0 → 3.1148.0 age confidence dependencies minor 3.1149.0
@event-driven-io/dumbo (source) 0.13.0-beta.56 → 0.13.0-betabeta.50 age confidence dependencies patch
@hono/node-server 2.1.3 → 2.1.4 age confidence dependencies patch
@modelcontextprotocol/client (source) 2.2.0 → 2.3.1 age confidence dependencies minor
@modelcontextprotocol/client (source) 2.2.0 → 2.3.1 age confidence devDependencies minor
@modelcontextprotocol/sdk (source) 1.31.0 → 1.32.1 age confidence devDependencies minor
@modelcontextprotocol/server (source) 2.2.0 → 2.3.1 age confidence devDependencies minor
@modelcontextprotocol/server (source) 2.2.0 → 2.3.1 age confidence dependencies minor
@types/node (source) 26.6.3 → 26.6.4 age confidence devDependencies patch 26.6.5
@vitest/coverage-v8 (source) 5.0.2 → 5.0.3 age confidence pnpm.catalog.default patch
actions/download-artifact v8.0.1 → v8.0.2 age confidence action patch
actions/setup-node v7.0.0 → v7.1.0 age confidence action minor
actions/upload-artifact v7.0.1 → v7.0.2 age confidence action patch
ai (source) 7.0.124 → 7.0.136 age confidence dependencies patch 7.0.137
effect (source) 4.0.0 → 4.0.2 age confidence pnpm.catalog.default patch
github/codeql-action v4.38.2 → v4.38.3 age confidence action patch
hono (source) 4.13.12 → 4.13.13 age confidence pnpm.catalog.default patch
knip (source) 6.38.0 → 6.40.0 age confidence devDependencies minor 6.41.0
lefthook 2.1.14 → 2.2.1 age confidence devDependencies minor
liquidjs 10.29.0 → 10.30.0 age confidence dependencies minor
node (source) 26.10.0 → 26.11.1 age confidence minor
node (source) 26.10.0 → 26.11.1 age confidence devEngines.runtime minor
node (source) 26.10.0-slim → 26.11.1-slim age confidence final minor
node (source) 26.10.0-slim → 26.11.1-slim age confidence stage minor
oxfmt (source) 0.71.0 → 0.72.0 age confidence devDependencies minor
oxlint (source) 1.86.0 → 1.87.0 age confidence devDependencies minor
pnpm (source) 12.8.1+sha512.f64ba907507f5ceafe06c8d38e6052d0179444580ec1279ddd5bfc11cb48aa8a2644b66598e07e761da84872a9fc57d5f902b87fa49d024198d558612aabbe45 → 12.10.1 age confidence packageManager minor
step-security/harden-runner v2.21.1 → v2.22.1 age confidence action minor
turbo (source) 2.11.5 → 2.11.7 age confidence devDependencies patch
vite (source) 8.3.1 → 8.3.4 age confidence devDependencies patch
vitest (source) 5.0.2 → 5.0.3 age confidence pnpm.catalog.default patch

Release Notes

vercel/ai (@​ai-sdk/amazon-bedrock)

v5.0.113

Compare Source

Patch Changes

v5.0.112

Compare Source

Patch Changes

v5.0.111

Compare Source

Patch Changes

v5.0.110

Compare Source

Patch Changes

v5.0.109

Compare Source

Patch Changes

  • 866e884: feat(anthropic): add Claude Haiku 5.5 support

    • add the claude-haiku-5-5 model ID to @ai-sdk/anthropic and @ai-sdk/google-vertex, anthropic.claude-haiku-5-5 and us.anthropic.claude-haiku-5-5 to @ai-sdk/amazon-bedrock, and anthropic/claude-haiku-5.5 to @ai-sdk/gateway
    • recognize claude-haiku-5-5 as a known model with a 128k max output token limit, adaptive thinking, and all five effort levels; thinking can be disabled up to high effort, and xhigh and max are lowered to high with a warning when thinking is disabled
    • claude-haiku-5-5 does not support thinking token budgets: thinking: { type: 'enabled', budgetTokens } is converted to adaptive thinking with a warning
    • use the JSON tool fallback for structured output on Amazon Bedrock for claude-haiku-5-5

  • Updated dependencies [866e884]

  • Updated dependencies [bccc1b7]

v5.0.108

Compare Source

Patch Changes

v5.0.107

Compare Source

Patch Changes

  • 268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.

    Compatibility notes:

    • TypeScript source compatibility: Adding max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.
    • Amazon Bedrock: Existing Nova 2 calls using portable reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.
    • Fireworks: Existing portable minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior.

    Release classification: This remains a patch changeset under the repository's explicit release policy, which uses patch releases for both fixes and features. The TypeScript source-compatibility caveat for exhaustive consumers is disclosed above. Maintainers can override this classification with a major label if they decide to align the provider-spec addition with a future AI SDK major release.

  • Updated dependencies [fc1e19e]

  • Updated dependencies [5094ebd]

  • Updated dependencies [99bdcd2]

  • Updated dependencies [268225c]

  • Updated dependencies [0af2f7c]

v5.0.106

Compare Source

Patch Changes

v5.0.105

Compare Source

Patch Changes
  • 2850ad8: Add requestMetadata support to the Converse and ConverseStream APIs via providerOptions.amazonBedrock.requestMetadata. Accepts a Record<string, string> for per-request tagging in Amazon Bedrock invocation logs for cost attribution.

v5.0.104

Compare Source

Patch Changes
vercel/ai (@​ai-sdk/anthropic)

v4.0.78

Compare Source

Patch Changes

v4.0.77

Compare Source

Patch Changes
  • c01cbb8: fix(anthropic): avoid unsupported strict mode warnings when tools set strict: false

v4.0.76

Compare Source

Patch Changes

v4.0.75

Compare Source

Patch Changes

  • 866e884: feat(anthropic): add Claude Haiku 5.5 support

    • add the claude-haiku-5-5 model ID to @ai-sdk/anthropic and @ai-sdk/google-vertex, anthropic.claude-haiku-5-5 and us.anthropic.claude-haiku-5-5 to @ai-sdk/amazon-bedrock, and anthropic/claude-haiku-5.5 to @ai-sdk/gateway
    • recognize claude-haiku-5-5 as a known model with a 128k max output token limit, adaptive thinking, and all five effort levels; thinking can be disabled up to high effort, and xhigh and max are lowered to high with a warning when thinking is disabled
    • claude-haiku-5-5 does not support thinking token budgets: thinking: { type: 'enabled', budgetTokens } is converted to adaptive thinking with a warning
    • use the JSON tool fallback for structured output on Amazon Bedrock for claude-haiku-5-5

v4.0.74

Compare Source

Patch Changes

v4.0.73

Compare Source

Patch Changes

  • fc1e19e: fix: limit jsonl rows to 64mb during batch result downloads

  • 268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.

    Compatibility notes:

    • TypeScript source compatibility: Adding max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.
    • Amazon Bedrock: Existing Nova 2 calls using portable reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.
    • Fireworks: Existing portable minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior.

    Release classification: This remains a patch changeset under the repository's explicit release policy, which uses patch releases for both fixes and features. The TypeScript source-compatibility caveat for exhaustive consumers is disclosed above. Maintainers can override this classification with a major label if they decide to align the provider-spec addition with a future AI SDK major release.

  • 0af2f7c: chore: upgrade to TypeScript 6

  • Updated dependencies [fc1e19e]

  • Updated dependencies [5094ebd]

  • Updated dependencies [268225c]

  • Updated dependencies [0af2f7c]

v4.0.72

Compare Source

Patch Changes

v4.0.71

Compare Source

Patch Changes
  • c35458e: fix(anthropic): preserve invalid toolset calls
vercel/ai (@​ai-sdk/azure)

v4.0.99

Compare Source

Patch Changes

v4.0.98

Compare Source

Patch Changes

v4.0.97

Compare Source

Patch Changes

v4.0.96

Compare Source

Patch Changes

v4.0.95

Compare Source

Patch Changes

v4.0.94

Compare Source

Patch Changes

v4.0.93

Compare Source

Patch Changes

v4.0.92

Compare Source

Patch Changes
  • 35347c3: feat(azure): support MAI-Image models through the MAI image API

v4.0.91

Compare Source

Patch Changes
  • 9210b70: fix(azure): report the Azure Speech voice-reset 502 as a non-retryable 400. An unknown voice or unsupported style on MAI-Voice-2.1 makes Azure Speech reset the connection with an Envoy protocol error 502; since this is a client input error, the resulting APICallError now carries statusCode: 400 so HTTP clients and gateways do not retry it as a server error.
  • Updated dependencies [2959d35]
  • Updated dependencies [5b8e63b]
  • Updated dependencies [59116e6]

v4.0.90

Compare Source

Patch Changes
  • 8952233: feat(azure): support MAI-Voice-2.1 and MAI-Voice-2.1-Flash speech generation, and MAI-Transcribe-2-Streaming streaming transcription through the MAI realtime API. Adds the maiBaseURL and webSocket settings and providerOptions.azure.api: 'mai'. Unknown MAI voices or styles now fail with a descriptive, non-retryable error.

v4.0.89

Compare Source

Patch Changes
  • d08102b: Add test coverage for resourceName validation edge cases: labels at the 63-character limit, underscores, non-ASCII characters, and invalid AZURE_RESOURCE_NAME values for non-language models.
vercel/ai (@​ai-sdk/google)

v4.0.93

Compare Source

Patch Changes

v4.0.92

Compare Source

Patch Changes

v4.0.91

Compare Source

Patch Changes
  • 32ff7ad: Preserve tool errors in OpenAI Chat Completions and Responses by wrapping their payloads in an error object. Send Google tool errors and denied executions under functionResponse.response.error.

v4.0.90

Compare Source

Patch Changes

v4.0.89

Compare Source

Patch Changes

  • fc1e19e: fix: limit jsonl rows to 64mb during batch result downloads

  • 8c0e699: feat(google): preserve file search custom metadata in retrieved context grounding chunks

  • 753f2e1: feat(google): add the 'gemini-nano-banana-2.1' model ID

  • 268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.

    Compatibility notes:

    • TypeScript source compatibility: Adding max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.
    • Amazon Bedrock: Existing Nova 2 calls using portable reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.
    • Fireworks: Existing portable minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior.

    Release classification: This remains a patch changeset under the repository's explicit release policy, which uses patch releases for both fixes and features. The TypeScript source-compatibility caveat for exhaustive consumers is disclosed above. Maintainers can override this classification with a major label if they decide to align the provider-spec addition with a future AI SDK major release.

  • Updated dependencies [fc1e19e]

  • Updated dependencies [5094ebd]

  • Updated dependencies [268225c]

  • Updated dependencies [0af2f7c]

v4.0.88

Compare Source

Patch Changes
vercel/ai (@​ai-sdk/google-vertex)

v5.0.109

Compare Source

Patch Changes

v5.0.108

Compare Source

Patch Changes

v5.0.107

Compare Source

Patch Changes

v5.0.106

Compare Source

Patch Changes

v5.0.105

Compare Source

Patch Changes

  • 866e884: feat(anthropic): add Claude Haiku 5.5 support

    • add the claude-haiku-5-5 model ID to @ai-sdk/anthropic and @ai-sdk/google-vertex, anthropic.claude-haiku-5-5 and us.anthropic.claude-haiku-5-5 to @ai-sdk/amazon-bedrock, and anthropic/claude-haiku-5.5 to @ai-sdk/gateway
    • recognize claude-haiku-5-5 as a known model with a 128k max output token limit, adaptive thinking, and all five effort levels; thinking can be disabled up to high effort, and xhigh and max are lowered to high with a warning when thinking is disabled
    • claude-haiku-5-5 does not support thinking token budgets: thinking: { type: 'enabled', budgetTokens } is converted to adaptive thinking with a warning
    • use the JSON tool fallback for structured output on Amazon Bedrock for claude-haiku-5-5

  • Updated dependencies [866e884]

v5.0.104

Compare Source

Patch Changes

v5.0.103

Compare Source

Patch Changes

v5.0.102

Compare Source

Patch Changes

v5.0.101

Compare Source

Patch Changes
vercel/ai (@​ai-sdk/openai)

v4.0.91

Compare Source

Patch Changes
  • 5cf13d2: feat: map the top level embedding dimensions to provider settings
  • 72e9d38: feat(openai): send image detail in decisions
  • fb933f9: Report failed and incomplete web searches as tool errors instead of successful tool results in OpenAI Responses API calls and batch results.
  • Updated dependencies [4dbc902]

v4.0.90

Compare Source

Patch Changes
  • 6c59fb1: fix(openai): preserve sampling parameters for GPT-6 Sol and Luna when reasoning is disabled, acco

❗ Important

✂ PR body was truncated to here.

Configuration

📅 Schedule: (UTC)

  • Branch creation
    • At any time (no schedule defined)
  • Automerge
    • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.

  • If you want to rebase/retry this PR, check this box

This PR was generated by Mend Renovate. View the repository job log.

@renovate
renovate Bot force-pushed the renovate/non-major branch 3 times, most recently from 35a281f to c764c7d Compare October 2, 2026 09:16
@renovate renovate Bot changed the title chore(deps): update non-major dependencies fix(deps): update non-major dependencies Oct 2, 2026
@renovate
renovate Bot force-pushed the renovate/non-major branch 26 times, most recently from 60a896b to 53efcbe Compare October 8, 2026 21:00
@renovate
renovate Bot force-pushed the renovate/non-major branch 4 times, most recently from 4a2a5ba to edc2f5f Compare October 9, 2026 21:46
@renovate
renovate Bot force-pushed the renovate/non-major branch from edc2f5f to db58a33 Compare October 10, 2026 01:37
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

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

0 participants