Skip to content

chore(deps): bump the ai-sdk group across 1 directory with 19 updates - #66

Open
dependabot[bot] wants to merge 1 commit into
mainfrom
dependabot/npm_and_yarn/AtomBase/ai-sdk-7a4f82a6a9
Open

chore(deps): bump the ai-sdk group across 1 directory with 19 updates#66
dependabot[bot] wants to merge 1 commit into
mainfrom
dependabot/npm_and_yarn/AtomBase/ai-sdk-7a4f82a6a9

Conversation

@dependabot

@dependabot dependabot Bot commented on behalf of github Oct 21, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Bumps the ai-sdk group with 19 updates in the /AtomBase directory:

Package From To
@ai-sdk/amazon-bedrock 3.0.57 5.0.130
@ai-sdk/anthropic 2.0.56 4.0.94
@ai-sdk/azure 2.0.82 4.0.114
@ai-sdk/cerebras 1.0.33 3.0.82
@ai-sdk/cohere 2.0.21 4.0.73
@ai-sdk/deepinfra 1.0.30 3.0.82
@ai-sdk/gateway 2.0.23 4.0.132
@ai-sdk/google 2.0.49 4.0.109
@ai-sdk/google-vertex 3.0.81 5.0.129
@ai-sdk/groq 2.0.33 4.0.74
@ai-sdk/mistral 2.0.26 4.0.77
@ai-sdk/openai 2.0.71 4.0.106
@ai-sdk/openai-compatible 1.0.29 3.0.82
@ai-sdk/perplexity 2.0.22 5.0.24
@ai-sdk/togetherai 1.0.30 3.0.83
@ai-sdk/vercel 1.0.31 3.0.30
@ai-sdk/xai 2.0.42 5.0.35
@openrouter/ai-sdk-provider 1.5.2 3.1.0
@ai-sdk/provider 2.0.0 4.0.35

Updates @ai-sdk/amazon-bedrock from 3.0.57 to 5.0.130

Release notes

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

@​ai-sdk/provider-utils@​5.0.74

Patch Changes

  • fa15312: Raise the minimum Undici version to 7.29.1 to include the fix for CVE-2026-84961.

@​ai-sdk/xai@​5.0.38

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/perplexity@​5.0.26

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/svelte@​4.0.322

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • ai@6.0.322
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/react@​4.0.166

Patch Changes

  • Updated dependencies [fa15312]
  • Updated dependencies [857ca45]
  • Updated dependencies [4d6d830]
    • @​ai-sdk/provider-utils@​5.0.74
    • ai@7.0.162
    • @​ai-sdk/mcp@​2.0.90

@​ai-sdk/vue@​4.0.162

Patch Changes

  • Updated dependencies [fa15312]
  • Updated dependencies [857ca45]
  • Updated dependencies [4d6d830]
    • @​ai-sdk/provider-utils@​5.0.74
    • ai@7.0.162

@​ai-sdk/openai@​4.0.108

Patch Changes

... (truncated)

Changelog

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

5.0.130

Patch Changes

  • Updated dependencies [f4c5f1e]
  • Updated dependencies [e10aebb]
  • Updated dependencies [b0d51fe]
    • @​ai-sdk/anthropic@​4.0.94

5.0.129

Patch Changes

  • 7716e18: Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.

    The experimental OpenAI Live getServerWebSocketConfig() method can now resolve asynchronously. Await its result before using the connection settings.

  • Updated dependencies [7716e18]

  • Updated dependencies [5c247e9]

  • Updated dependencies [dcd2f8d]

    • @​ai-sdk/openai@​4.0.106
    • @​ai-sdk/provider-utils@​5.0.72
    • @​ai-sdk/provider@​4.0.35
    • @​ai-sdk/anthropic@​4.0.93

5.0.128

Patch Changes

  • 61a315e: fix: map the top-level reasoning option consistently across providers

    Providers now resolve reasoning the same way:

    1. A provider-specific reasoning setting in providerOptions is sent unchanged. OpenAI no longer drops providerOptions.openai.reasoningEffort values that are not in its list for the model, and Fireworks no longer rewrites providerOptions.fireworks.reasoningEffort. Fireworks also sends top-level reasoning values directly instead of rounding them to 'high' at most, except for model families known to reject 'none' (GPT-OSS, GLM-5.3, Muse Spark) or 'minimal' (Nemotron, Inkling).
    2. Otherwise, reasoning maps to the closest level the model supports, rounding down, and rounds up only when there is no lower level. For example, 'xhigh' now maps to 'high' instead of 'max' on Anthropic and Bedrock models without xhigh effort, and 'medium' maps to 'low' instead of 'high' on DeepSeek, Kimi K3, and Mistral GLM-5.3 models.
    3. 'none' on a model that cannot disable reasoning maps to the model's lowest level with a compatibility warning, instead of being dropped or sending a request the API rejects. This affects GPT-6 models without 'none', xAI grok-4.5 and later, Groq GPT-OSS, Kimi K3, Perplexity, QuiverAI, Bedrock OpenAI gpt-oss models, and Gemini 2.5 Pro (minimum thinking budget). Gemini 3 and Anthropic and Bedrock between_tools mappings now emit the compatibility warning too.

    mapReasoningToProviderEffort now accepts any reasoning value, returns an optional providerOptionsEffort unchanged, and rounds levels that are missing from the effort map to the closest supported level. mapReasoningToProviderBudget maps 'none' to the minimum reasoning budget, always returns a budget, and uses the default percentage for levels missing from budgetPercentages. OpenAICompatibleChatConfig adds an optional mapReasoning function for mapping the top-level reasoning option.

  • Updated dependencies [47b1d8b]

  • Updated dependencies [d07b475]

  • Updated dependencies [61a315e]

    • @​ai-sdk/openai@​4.0.105
    • @​ai-sdk/provider-utils@​5.0.71
    • @​ai-sdk/anthropic@​4.0.92

5.0.127

Patch Changes

... (truncated)

Commits
Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​ai-sdk/amazon-bedrock since your current version.


Updates @ai-sdk/anthropic from 2.0.56 to 4.0.94

Release notes

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

@​ai-sdk/mistral@​4.0.79

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/klingai@​4.0.76

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/provider-utils@​4.0.64

Patch Changes

  • d900e58: fix(provider-utils): support cross-realm Uint8Array and ArrayBuffer in binary type guards and base64 conversion
  • d900e58: fix(provider-utils): decode base64 into a preallocated Uint8Array to avoid ~25x transient memory and long event-loop blocking on large files
  • d900e58: Add stringifyWithBigIntAndCycles for provider tool serialization that converts BigInt values to decimal strings and replaces ancestor cycles while preserving shared references and toJSON behavior.

@​ai-sdk/perplexity@​3.1.10

Patch Changes

  • d900e58: Honor toolChoice: 'none' by omitting function and native tools and disabling preset tool calls with max_tool_calls: 0.
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/react@​3.0.325

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • ai@6.0.322
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/vue@​3.0.322

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • ai@6.0.322
    • @​ai-sdk/provider-utils@​4.0.64

... (truncated)

Changelog

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

4.0.94

Patch Changes

  • f4c5f1e: fix(anthropic): use native structured outputs for Claude models that reject forced tool use (Sonnet 5.5, Opus 5.5, Fable 5.1) even when the provider disables them by default, as Amazon Bedrock and Google Vertex do. Self-referencing schemas keep the JSON response tool. Also keep definitions and $defs next to a top-level $ref when sanitizing structured output schemas, so the reference still resolves.
  • e10aebb: fix(anthropic): when the JSON response tool is in use but the model answers in text without calling it (for example with manual thinking, where the forced tool choice is downgraded to auto), return the final answer text instead of dropping it. Text before a tool call, result, or message continuation is still dropped.
  • b0d51fe: fix(anthropic): keep the JSON response tool for schemas that native structured outputs cannot represent when upgrading models that reject forced tool use. Schemas with open objects (maps, free-form objects) would otherwise come back as {}, and schemas with more than 10 optional properties can be rejected as too complex.

4.0.93

Patch Changes

  • dcd2f8d: Introduce a model entry contract with named capability sections and request configuration. Consolidate the OpenAI and Anthropic model catalogs so existing request behavior and generated capability documentation use the same source of truth. Catalogs also declare the provider options each provider accepts and which models support them.
  • Updated dependencies [7716e18]
  • Updated dependencies [5c247e9]
  • Updated dependencies [dcd2f8d]
    • @​ai-sdk/provider-utils@​5.0.72
    • @​ai-sdk/provider@​4.0.35

4.0.92

Patch Changes

  • 61a315e: fix: map the top-level reasoning option consistently across providers

    Providers now resolve reasoning the same way:

    1. A provider-specific reasoning setting in providerOptions is sent unchanged. OpenAI no longer drops providerOptions.openai.reasoningEffort values that are not in its list for the model, and Fireworks no longer rewrites providerOptions.fireworks.reasoningEffort. Fireworks also sends top-level reasoning values directly instead of rounding them to 'high' at most, except for model families known to reject 'none' (GPT-OSS, GLM-5.3, Muse Spark) or 'minimal' (Nemotron, Inkling).
    2. Otherwise, reasoning maps to the closest level the model supports, rounding down, and rounds up only when there is no lower level. For example, 'xhigh' now maps to 'high' instead of 'max' on Anthropic and Bedrock models without xhigh effort, and 'medium' maps to 'low' instead of 'high' on DeepSeek, Kimi K3, and Mistral GLM-5.3 models.
    3. 'none' on a model that cannot disable reasoning maps to the model's lowest level with a compatibility warning, instead of being dropped or sending a request the API rejects. This affects GPT-6 models without 'none', xAI grok-4.5 and later, Groq GPT-OSS, Kimi K3, Perplexity, QuiverAI, Bedrock OpenAI gpt-oss models, and Gemini 2.5 Pro (minimum thinking budget). Gemini 3 and Anthropic and Bedrock between_tools mappings now emit the compatibility warning too.

    mapReasoningToProviderEffort now accepts any reasoning value, returns an optional providerOptionsEffort unchanged, and rounds levels that are missing from the effort map to the closest supported level. mapReasoningToProviderBudget maps 'none' to the minimum reasoning budget, always returns a budget, and uses the default percentage for levels missing from budgetPercentages. OpenAICompatibleChatConfig adds an optional mapReasoning function for mapping the top-level reasoning option.

  • Updated dependencies [61a315e]

    • @​ai-sdk/provider-utils@​5.0.71

4.0.91

Patch Changes

  • 50da4c5: Fix workflow serialization of Anthropic models using API keys or synchronous auth tokens while preserving support for asynchronous token providers.

4.0.90

Patch Changes

  • 63bf860: Support synchronous and asynchronous authToken providers so applications can use refreshable credentials, including Anthropic workload identity federation helpers for inference. Resolve tokens before each request while preserving existing authentication headers and beta-header behavior.
  • Updated dependencies [57086ff]
  • Updated dependencies [95348b3]
    • @​ai-sdk/provider-utils@​5.0.70

... (truncated)

Commits
  • 028a025 Version Packages (#24280)
  • b0d51fe fix(anthropic): keep the JSON response tool for schemas native structured out...
  • e10aebb fix(anthropic): return the final text when the JSON response tool is never ca...
  • f4c5f1e fix(anthropic): use native structured outputs for forced-tool-rejecting model...
  • 9b603d3 Version Packages (#24224)
  • dcd2f8d feat(openai): centralize model capabilities in a unified catalog (#24174)
  • 5c247e9 feat(sandbox): add stat, listDirectory, and deleteFile to SandboxSession (#24...
  • d1067fd Version Packages (#24173)
  • 61a315e fix: map reasoning consistently across providers (#24123)
  • a5db0af Version Packages (#24143)
  • Additional commits viewable in compare view
Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​ai-sdk/anthropic since your current version.


Updates @ai-sdk/azure from 2.0.82 to 4.0.114

Release notes

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

@​ai-sdk/openai@​4.0.108

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/mistral@​4.0.79

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/klingai@​4.0.76

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/provider-utils@​4.0.64

Patch Changes

  • d900e58: fix(provider-utils): support cross-realm Uint8Array and ArrayBuffer in binary type guards and base64 conversion
  • d900e58: fix(provider-utils): decode base64 into a preallocated Uint8Array to avoid ~25x transient memory and long event-loop blocking on large files
  • d900e58: Add stringifyWithBigIntAndCycles for provider tool serialization that converts BigInt values to decimal strings and replaces ancestor cycles while preserving shared references and toJSON behavior.

@​ai-sdk/perplexity@​3.1.10

Patch Changes

  • d900e58: Honor toolChoice: 'none' by omitting function and native tools and disabling preset tool calls with max_tool_calls: 0.
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/react@​3.0.325

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • ai@6.0.322
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/vue@​3.0.322

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]

... (truncated)

Changelog

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

4.0.114

Patch Changes

  • 7716e18: Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.

    The experimental OpenAI Live getServerWebSocketConfig() method can now resolve asynchronously. Await its result before using the connection settings.

  • Updated dependencies [7716e18]

  • Updated dependencies [5c247e9]

  • Updated dependencies [dcd2f8d]

    • @​ai-sdk/deepseek@​3.0.77
    • @​ai-sdk/openai@​4.0.106
    • @​ai-sdk/provider-utils@​5.0.72
    • @​ai-sdk/provider@​4.0.35

4.0.113

Patch Changes

  • Updated dependencies [47b1d8b]
  • Updated dependencies [d07b475]
  • Updated dependencies [61a315e]
    • @​ai-sdk/openai@​4.0.105
    • @​ai-sdk/provider-utils@​5.0.71
    • @​ai-sdk/deepseek@​3.0.76

4.0.112

Patch Changes

  • c3b6fef: fix(azure): treat all Azure Speech 502s as retryable again. MAI-Voice-2.1 now rejects unknown voices and unsupported styles with a 400, so the Envoy protocol-error 502 special case is removed.
  • Updated dependencies [57086ff]
  • Updated dependencies [01d7a03]
  • Updated dependencies [599a97f]
  • Updated dependencies [8375141]
  • Updated dependencies [7eac057]
  • Updated dependencies [436374e]
  • Updated dependencies [9026c7d]
  • Updated dependencies [95348b3]
    • @​ai-sdk/provider-utils@​5.0.70
    • @​ai-sdk/openai@​4.0.104
    • @​ai-sdk/deepseek@​3.0.75

4.0.111

Patch Changes

  • 02dbab1: add azure.tools.toolSearch and support azure provider options on responses function tools
  • Updated dependencies [e64ed82]

... (truncated)

Commits
Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​ai-sdk/azure since your current version.


Updates @ai-sdk/cerebras from 1.0.33 to 3.0.82

Release notes

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

@​ai-sdk/mistral@​3.0.79

Patch Changes

  • d900e58: fix(mistral): preserve string tool call arguments and safely serialize BigInt and circular structures in tool calls and outputs
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/luma@​3.0.75

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/replicate@​3.0.75

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/hume@​3.0.74

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/revai@​3.0.74

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/valibot@​3.0.74

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/minimax@​3.0.73

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74
    • @​ai-sdk/anthropic@​4.0.96

@​ai-sdk/klingai@​3.0.56

Patch Changes

  • Updated dependencies [d900e58]

... (truncated)

Changelog

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

3.0.82

Patch Changes

  • 7716e18: Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.

    The experimental OpenAI Live getServerWebSocketConfig() method can now resolve asynchronously. Await its result before using the connection settings.

  • Updated dependencies [7716e18]

  • Updated dependencies [5c247e9]

  • Updated dependencies [dcd2f8d]

    • @​ai-sdk/openai-compatible@​3.0.82
    • @​ai-sdk/provider-utils@​5.0.72
    • @​ai-sdk/provider@​4.0.35

3.0.81

Patch Changes

  • Updated dependencies [61a315e]
    • @​ai-sdk/provider-utils@​5.0.71
    • @​ai-sdk/openai-compatible@​3.0.81

3.0.80

Patch Changes

  • Updated dependencies [57086ff]
  • Updated dependencies [95348b3]
    • @​ai-sdk/provider-utils@​5.0.70
    • @​ai-sdk/openai-compatible@​3.0.80

3.0.79

Patch Changes

  • Updated dependencies [e64ed82]
  • Updated dependencies [27a53b4]
    • @​ai-sdk/provider-utils@​5.0.69
    • @​ai-sdk/openai-compatible@​3.0.79

3.0.78

Patch Changes

  • e729d58: chore(docs): update README.md for consistent format and to avoid duplication
  • Updated dependencies [5475347]
  • Updated dependencies [e729d58]
    • @​ai-sdk/provider@​4.0.34
    • @​ai-sdk/openai-compatible@​3.0.78

... (truncated)

Commits
Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​ai-sdk/cerebras since your current version.


Updates @ai-sdk/cohere from 2.0.21 to 4.0.73

Release notes

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

@​ai-sdk/provider-utils@​4.0.64

Patch Changes

  • d900e58: fix(provider-utils): support cross-realm Uint8Array and ArrayBuffer in binary type guards and base64 conversion
  • d900e58: fix(provider-utils): decode base64 into a preallocated Uint8Array to avoid ~25x transient memory and long event-loop blocking on large files
  • d900e58: Add stringifyWithBigIntAndCycles for provider tool serialization that converts BigInt values to decimal strings and replaces ancestor cycles while preserving shared references and toJSON behavior.

@​ai-sdk/perplexity@​3.1.10

Patch Changes

  • d900e58: Honor toolChoice: 'none' by omitting function and native tools and disabling preset tool calls with max_tool_calls: 0.
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/react@​3.0.325

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • ai@6.0.322
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/vue@​3.0.322

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • ai@6.0.322
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/svelte@​3.0.285

Patch Changes

  • Updated dependencies [0a069bd]
  • Updated dependencies [0a069bd]
  • Updated dependencies [0a069bd]
  • Updated dependencies [0a069bd]
  • Updated dependencies [0a069bd]
    • ai@5.0.285
    • @​ai-sdk/provider-utils@​3.0.44

@​ai-sdk/langchain@​3.0.162

... (truncated)

Changelog

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

4.0.73

Patch Changes

  • 7716e18: Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.

    The experimental OpenAI Live getServerWebSocketConfig() method can now resolve asynchronously. Await its result before using the connection settings.

  • Updated dependencies [7716e18]

  • Updated dependencies [5c247e9]

  • Updated dependencies [dcd2f8d]

    • @​ai-sdk/provider-utils@​5.0.72
    • @​ai-sdk/provider@​4.0.35

4.0.72

Patch Changes

  • 61a315e: fix: map the top-level reasoning option consistently across providers

    Providers now resolve reasoning the same way:

    1. A provider-specific reasoning setting in providerOptions is sent unchanged. OpenAI no longer drops providerOptions.openai.reasoningEffort values that are not in its list for the model, and Fireworks no longer rewrites providerOptions.fireworks.reasoningEffort. Fireworks also sends top-level reasoning values directly instead of rounding them to 'high' at most, except for model families known to reject 'none' (GPT-OSS, GLM-5.3, Muse Spark) or 'minimal' (Nemotron, Inkling).
    2. Otherwise, reasoning maps to the closest level the model supports, rounding down, and rounds up only when there is no lower level. For example, 'xhigh' now maps to 'high' instead of 'max' on Anthropic and Bedrock models without xhigh effort, and 'medium' maps to 'low' instead of 'high' on DeepSeek, Kimi K3, and Mistral GLM-5.3 models.
    3. 'none' on a model that cannot disable reasoning maps to the model's lowest level with a compatibility warning, instead of being dropped or sending a request the API rejects. This affects GPT-6 models without 'none', xAI grok-4.5 and later, Groq GPT-OSS, Kimi K3, Perplexity, QuiverAI, Bedrock OpenAI gpt-oss models, and Gemini 2.5 Pro (minimum thinking budget). Gemini 3 and Anthropic and Bedrock between_tools mappings now emit the compatibility warning too.

    mapReasoningToProviderEffort now accepts any reasoning value, returns an optional providerOptionsEffort unchanged, and rounds levels that are missing from the effort map to the closest supported level. mapReasoningToProviderBudget maps 'none' to the minimum reasoning budget, always returns a budget, and uses the default percentage for levels missing from budgetPercentages. OpenAICompatibleChatConfig adds an optional mapReasoning function for mapping the top-level reasoning option.

  • Updated dependencies [61a315e]

    • @​ai-sdk/provider-utils@​5.0.71

4.0.71

Patch Changes

  • 7a93864: Decode base64-encoded file data before sending it as document text to Cohere.
  • Updated dependencies [57086ff]
  • Updated dependencies [95348b3]
    • @​ai-sdk/provider-utils@​5.0.70

4.0.70

Patch Changes

  • Updated dependencies [e64ed82]
    • @​ai-sdk/provider-utils@​5.0.69

4.0.69

Patch Changes

... (truncated)

Commits
Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​ai-sdk/cohere since your current version.


Updates @ai-sdk/deepinfra from 1.0.30 to 3.0.82

Release notes

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

@​ai-sdk/mistral@​3.0.79

Patch Changes

  • d900e58: fix(mistral): preserve string tool call arguments and safely serialize BigInt and circular structures in tool calls and outputs
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/luma@​3.0.75

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/replicate@​3.0.75

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/hume@​3.0.74

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/revai@​3.0.74

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/valibot@​3.0.74

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/minimax@​3.0.73

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74
    • @​ai-sdk/anthropic@​4.0.96

@​ai-sdk/klingai@​3.0.56

Patch Changes

  • Updated dependencies [d900e58]

... (truncated)

Changelog

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

3.0.82

Patch Changes

  • 7716e18: Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.

    The experimental OpenAI Live getServerWebSocketConfig() method can now resolve asynchronously. Await its result before using the connection settings.

  • Updated dependencies [7716e18]

  • Updated dependencies [5c247e9]

  • Updated dependencies [dcd2f8d]

    • @​ai-sdk/openai-compatible@​3.0.82
    • @​ai-sdk/provider-utils@​5.0.72
    • @​ai-sdk/provider@​4.0.35

3.0.81

Patch Changes

  • Updated dependencies [61a315e]
    • @​ai-sdk/provider-utils@​5.0.71
    • @​ai-sdk/openai-compatible@​3.0.81

3.0.80

Patch Changes

  • Updated dependencies [57086ff]
  • Updated dependencies [95348b3]
    • @​ai-sdk/provider-utils@​5.0.70
    • @​ai-sdk/openai-compatible@​3.0.80

3.0.79

Patch Changes

  • Updated dependencies [e64ed82]
  • Updated dependencies [27a53b4]
    • @​ai-sdk/provider-utils@​5.0.69
    • @​ai-sdk/openai-compatible@​3.0.79

3.0.78

Patch Changes

  • e729d58: chore(docs): update README.md for consistent format and to avoid duplication
  • Updated dependencies [5475347]
  • Updated dependencies [e729d58]
    • @​ai-sdk/provider@​4.0.34
    • @​ai-sdk/openai-compatible@​3.0.78

... (truncated)

Commits
Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​ai-sdk/deepinfra since your current version.


Updates @ai-sdk/gateway from 2.0.23 to 4.0.132

Release notes

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

@​ai-sdk/openai@​4.0.108

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/mistral@​4.0.79

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/klingai@​4.0.76

Patch Changes

  • Updated dependencies [fa15312]
    • @​ai-sdk/provider-utils@​5.0.74

@​ai-sdk/provider-utils@​4.0.64

Patch Changes

  • d900e58: fix(provider-utils): support cross-realm Uint8Array and ArrayBuffer in binary type guards and base64 conversion
  • d900e58: fix(provider-utils): decode base64 into a preallocated Uint8Array to avoid ~25x transient memory and long event-loop blocking on large files
  • d900e58: Add stringifyWithBigIntAndCycles for provider tool serialization that converts BigInt values to decimal strings and replaces ancestor cycles while preserving shared references and toJSON behavior.

@​ai-sdk/perplexity@​3.1.10

Patch Changes

  • d900e58: Honor toolChoice: 'none' by omitting function and native tools and disabling preset tool calls with max_tool_calls: 0.
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/react@​3.0.325

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]
    • ai@6.0.322
    • @​ai-sdk/provider-utils@​4.0.64

@​ai-sdk/vue@​3.0.322

Patch Changes

  • Updated dependencies [d900e58]
  • Updated dependencies [d900e58]

... (truncated)

Changelog

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

4.0.132

Patch Changes

  • cbc9ac0: chore(provider/gateway): update gateway model settings files

4.0.131

Patch Changes

  • 7716e18: Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.

    The experimental OpenAI Live getServerWebSocketConfig() method can now resolve asynchronously. Await its result before using the connection settings.

  • f850782: chore(provider/gateway): update gateway model settings files

  • Updated dependencies [7716e18]

  • Updated dependencies [5c247e9]

  • Updated dependencies [dcd2f8d]

    • @​ai-sdk/provider-utils@​5.0.72
    • @​ai-sdk/provider@​4.0.35

4.0.130

Patch Changes

  • 9ca8bcf: fix(gateway): Preserve AbortError and TimeoutError cancellation reasons instead of wrapping them in retryable GatewayResponseError errors with status 500. Propagate these errors from speech and transcription input streams to their output streams without leaving reads pending or causing unhandled rejections.
  • Updated dependencies [61a315e]
    • @​ai-sdk/provider-utils@​5.0.71

4.0.129

Patch Changes

  • 9f19c79: chore(provider/gateway): update gateway model settings files

4.0.128

Patch Changes

  • 01d7a03: feat(openai): add GPT-6.1 Terra model support
  • Updated dependencies [57086ff]
  • Updated dependencies [95348b3]
    • @​ai-sdk/provider-utils@​5.0.70

4.0.127

Patch Changes

  • Updated dependencies [e64ed82]
    • @​ai-sdk/provider-utils@​5.0.69

... (truncated)

Commits

@dependabot @github

dependabot Bot commented on behalf of github Oct 21, 2026

Copy link
Copy Markdown
Contributor Author

Labels

The following labels could not be found: dependencies, javascript. Please create them before Dependabot can add them to a pull request.

Please fix the above issues or remove invalid values from dependabot.yml.

@dependabot dependabot Bot changed the title chore(deps): bump the ai-sdk group across 1 directory with 19 updates build(deps): bump the ai-sdk group across 1 directory with 19 updates Oct 23, 2026
@dependabot
dependabot Bot force-pushed the dependabot/npm_and_yarn/AtomBase/ai-sdk-7a4f82a6a9 branch 2 times, most recently from c281df6 to 1e70dba Compare October 28, 2026 21:05
@dependabot
chore(deps): bump the ai-sdk group across 1 directory with 19 updates
7091205 
Bumps the ai-sdk group with 19 updates in the /AtomBase directory:

| Package | From | To |
| --- | --- | --- |
| [@ai-sdk/amazon-bedrock](https://github.com/vercel/ai/tree/HEAD/packages/amazon-bedrock) | `3.0.57` | `5.0.130` |
| [@ai-sdk/anthropic](https://github.com/vercel/ai/tree/HEAD/packages/anthropic) | `2.0.56` | `4.0.94` |
| [@ai-sdk/azure](https://github.com/vercel/ai/tree/HEAD/packages/azure) | `2.0.82` | `4.0.114` |
| [@ai-sdk/cerebras](https://github.com/vercel/ai/tree/HEAD/packages/cerebras) | `1.0.33` | `3.0.82` |
| [@ai-sdk/cohere](https://github.com/vercel/ai/tree/HEAD/packages/cohere) | `2.0.21` | `4.0.73` |
| [@ai-sdk/deepinfra](https://github.com/vercel/ai/tree/HEAD/packages/deepinfra) | `1.0.30` | `3.0.82` |
| [@ai-sdk/gateway](https://github.com/vercel/ai/tree/HEAD/packages/gateway) | `2.0.23` | `4.0.132` |
| [@ai-sdk/google](https://github.com/vercel/ai/tree/HEAD/packages/google) | `2.0.49` | `4.0.109` |
| [@ai-sdk/google-vertex](https://github.com/vercel/ai/tree/HEAD/packages/google-vertex) | `3.0.81` | `5.0.129` |
| [@ai-sdk/groq](https://github.com/vercel/ai/tree/HEAD/packages/groq) | `2.0.33` | `4.0.74` |
| [@ai-sdk/mistral](https://github.com/vercel/ai/tree/HEAD/packages/mistral) | `2.0.26` | `4.0.77` |
| [@ai-sdk/openai](https://github.com/vercel/ai/tree/HEAD/packages/openai) | `2.0.71` | `4.0.106` |
| [@ai-sdk/openai-compatible](https://github.com/vercel/ai/tree/HEAD/packages/openai-compatible) | `1.0.29` | `3.0.82` |
| [@ai-sdk/perplexity](https://github.com/vercel/ai/tree/HEAD/packages/perplexity) | `2.0.22` | `5.0.24` |
| [@ai-sdk/togetherai](https://github.com/vercel/ai/tree/HEAD/packages/togetherai) | `1.0.30` | `3.0.83` |
| [@ai-sdk/vercel](https://github.com/vercel/ai/tree/HEAD/packages/vercel) | `1.0.31` | `3.0.30` |
| [@ai-sdk/xai](https://github.com/vercel/ai/tree/HEAD/packages/xai) | `2.0.42` | `5.0.35` |
| [@openrouter/ai-sdk-provider](https://github.com/OpenRouterTeam/ai-sdk-provider) | `1.5.2` | `3.1.0` |
| [@ai-sdk/provider](https://github.com/vercel/ai/tree/HEAD/packages/provider) | `2.0.0` | `4.0.35` |



Updates `@ai-sdk/amazon-bedrock` from 3.0.57 to 5.0.130
- [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@5.0.130/packages/amazon-bedrock)

Updates `@ai-sdk/anthropic` from 2.0.56 to 4.0.94
- [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@4.0.94/packages/anthropic)

Updates `@ai-sdk/azure` from 2.0.82 to 4.0.114
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/azure/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/azure@4.0.114/packages/azure)

Updates `@ai-sdk/cerebras` from 1.0.33 to 3.0.82
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/cerebras/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/cerebras@3.0.82/packages/cerebras)

Updates `@ai-sdk/cohere` from 2.0.21 to 4.0.73
- [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@4.0.73/packages/cohere)

Updates `@ai-sdk/deepinfra` from 1.0.30 to 3.0.82
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/deepinfra/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/deepinfra@3.0.82/packages/deepinfra)

Updates `@ai-sdk/gateway` from 2.0.23 to 4.0.132
- [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@4.0.132/packages/gateway)

Updates `@ai-sdk/google` from 2.0.49 to 4.0.109
- [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@4.0.109/packages/google)

Updates `@ai-sdk/google-vertex` from 3.0.81 to 5.0.129
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/google-vertex/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/google-vertex@5.0.129/packages/google-vertex)

Updates `@ai-sdk/groq` from 2.0.33 to 4.0.74
- [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@4.0.74/packages/groq)

Updates `@ai-sdk/mistral` from 2.0.26 to 4.0.77
- [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@4.0.77/packages/mistral)

Updates `@ai-sdk/openai` from 2.0.71 to 4.0.106
- [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@4.0.106/packages/openai)

Updates `@ai-sdk/openai-compatible` from 1.0.29 to 3.0.82
- [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@3.0.82/packages/openai-compatible)

Updates `@ai-sdk/perplexity` from 2.0.22 to 5.0.24
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/perplexity/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/perplexity@5.0.24/packages/perplexity)

Updates `@ai-sdk/togetherai` from 1.0.30 to 3.0.83
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/togetherai/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/@ai-sdk/togetherai@3.0.83/packages/togetherai)

Updates `@ai-sdk/vercel` from 1.0.31 to 3.0.30
- [Release notes](https://github.com/vercel/ai/releases)
- [Commits](https://github.com/vercel/ai/commits/ai@3.0.30/packages/vercel)

Updates `@ai-sdk/xai` from 2.0.42 to 5.0.35
- [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@5.0.35/packages/xai)

Updates `@openrouter/ai-sdk-provider` from 1.5.2 to 3.1.0
- [Release notes](https://github.com/OpenRouterTeam/ai-sdk-provider/releases)
- [Changelog](https://github.com/OpenRouterTeam/ai-sdk-provider/blob/main/CHANGELOG.md)
- [Commits](https://github.com/OpenRouterTeam/ai-sdk-provider/commits/3.1.0)

Updates `@ai-sdk/provider` from 2.0.0 to 4.0.35
- [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@4.0.35/packages/provider)

---
updated-dependencies:
- dependency-name: "@ai-sdk/amazon-bedrock"
  dependency-version: 5.0.118
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/anthropic"
  dependency-version: 4.0.82
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/azure"
  dependency-version: 4.0.104
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/cerebras"
  dependency-version: 3.0.71
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/cohere"
  dependency-version: 4.0.63
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/deepinfra"
  dependency-version: 3.0.71
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/gateway"
  dependency-version: 4.0.116
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/google"
  dependency-version: 4.0.99
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/google-vertex"
  dependency-version: 5.0.115
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/groq"
  dependency-version: 4.0.63
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/mistral"
  dependency-version: 4.0.66
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/openai"
  dependency-version: 4.0.96
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/openai-compatible"
  dependency-version: 3.0.71
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/perplexity"
  dependency-version: 5.0.14
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/provider"
  dependency-version: 4.0.29
  dependency-type: direct:development
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/togetherai"
  dependency-version: 3.0.72
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/vercel"
  dependency-version: 3.0.30
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@ai-sdk/xai"
  dependency-version: 5.0.24
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
- dependency-name: "@openrouter/ai-sdk-provider"
  dependency-version: 3.1.0
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: ai-sdk
...

Signed-off-by: dependabot[bot] <support@github.com>
@dependabot dependabot Bot changed the title build(deps): bump the ai-sdk group across 1 directory with 19 updates chore(deps): bump the ai-sdk group across 1 directory with 19 updates Nov 4, 2026
@dependabot
dependabot Bot force-pushed the dependabot/npm_and_yarn/AtomBase/ai-sdk-7a4f82a6a9 branch from 1e70dba to 7091205 Compare November 4, 2026 21:04
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