Packages

@ai-sdk/amazon-bedrock

5.0.145 · 17 Nov 2026Apache-2.06.9M / weekRepositoryHomepagenpmAtom feed

Your version

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

  1. 5.0.143 – 5.0.1453 releases that only update dependencies@ai-sdk/openai 4.0.121@ai-sdk/provider 4.0.39@ai-sdk/provider-utils 5.0.82and 1 moreShow each
  2. 5.0.142

    13 Nov 2026
    • amazon-bedrock: Send block_binding.prefix_mismatch_behavior to Bedrock again instead of the deprecated mismatch_behavior alias

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

  3. 5.0.137 – 5.0.1415 releases that only update dependencies@ai-sdk/provider-utils 5.0.81@ai-sdk/openai 4.0.117@ai-sdk/anthropic 4.0.104and 1 moreShow each
  4. 5.0.135

    7 Nov 2026
    • Add resolveProviderOptions to parse provider options that a model accepts under several providerOptions keys, either as aliases (first) or merged in order (merge), and use it for the existing multi-key lookups in the OpenAI, OpenAI-compatible, Anthropic, Google, and Amazon Bedrock models. Resolution behavior for these models is unchanged.

  5. 5.0.134

    6 Nov 2026
    • Refactor Amazon Bedrock model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Export the Anthropic catalog capability helper under its compatibility name for Bedrock to reuse. Request behavior is unchanged.

  6. 5.0.133

    5 Nov 2026
    • Preserve the order of text and complete function calls in streamed Google responses, including standalone thought signatures on empty text or reasoning parts.

      Keep provider metadata on empty text parts when converting results to response messages so it can be passed back in subsequent requests.

      Omit foreign-provider empty signature text when replaying history through Anthropic or Bedrock, preserving Bedrock’s existing native reasoning-history handling.

    • Pass through seed: 0 instead of dropping it in image and video models. KlingAI now reports seed: 0 as an unsupported setting like any other seed.

    • Report the actual OpenAI Chat HTTP endpoint (also used by Azure Chat and Bedrock Mantle Chat) through optional request metadata and model-call end events. Record its host and port on OpenTelemetry chat spans without exposing URL credentials, paths, queries, or fragments. Expose only the sanitized HTTP origin in text and object generation results and step/finish callbacks. Providers that do not report an endpoint leave these attributes unset.

  7. 5.0.131

    2 Nov 2026
    • Enable native structured output and strict tools for supported Claude 5 models on Bedrock. In automatic mode, Bedrock and Anthropic now fall back for schemas that native structured output cannot represent: recursive references, open objects, or more than ten optional properties. Anthropic uses the JSON response tool; Bedrock Converse uses the JSON tool or JSON instructions for models that reject forced tool use. The JSON-tool fallback excludes disabled and unselected application tools. Explicit outputFormat selection remains unchanged.

    • amazon-bedrock: Keep every function tool on a named tool choice for Anthropic models

      Anthropic models that accept forced tool use now receive every function tool on a named tool choice, as with @ai-sdk/anthropic, so a forced step no longer invalidates the prompt cache. Parallel tool use is disabled on that step by default, so the model still calls only the named tool. Set providerOptions.anthropic.disableParallelToolUse: false to allow parallel calls. Other models, and Anthropic models that reject forced tool use, still receive only the named tool.

    • amazon-bedrock: Parse JSON string tool inputs and safely serialize BigInt and cycles in tool outputs

  8. 5.0.130

    30 Oct 2026

    Only updates a dependency:@ai-sdk/anthropic 4.0.94

  9. 5.0.129

    30 Oct 2026
    • 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.

  10. 5.0.128

    29 Oct 2026
    • Map the top-level reasoning option consistently across providers

      Providers now resolve reasoning the same way:

      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.

  11. 5.0.127

    28 Oct 2026

    Only updates a dependency:@ai-sdk/anthropic 4.0.91

  12. 5.0.126

    27 Oct 2026
    • amazon-bedrock: Make document names unique within a request

      Bedrock Converse rejects requests that contain duplicate document names. Different filenames could sanitize to the same name (e.g. rates.v1.pdf and rates.v2.pdf both became rates), and repeated filenames were sent as-is, so these requests failed. Repeated names now get a numeric suffix such as invoice (2).

    • Forward disabled thinking in Anthropic Converse requests when using reasoning: 'none' or reasoningConfig: { type: 'disabled' }, omitting the unsupported thinking field for Claude 3.5 and earlier. Apply model-specific fallbacks and effort limits when disabled thinking is unsupported, preserving explicit reasoning effort during the adaptive fallback.

  13. 5.0.125

    26 Oct 2026
    • Fix string interpolation in Amazon Bedrock unsupported provider tool warnings and OpenAI / OpenAI-compatible completion errors for unexpected system messages.

  14. 5.0.123 – 5.0.1242 releases that only update dependencies@ai-sdk/openai 4.0.102@ai-sdk/provider 4.0.34@ai-sdk/provider-utils 5.0.68and 1 moreShow each
  15. 5.0.122

    22 Oct 2026
    • Report interrupted when a stream ends cleanly without its provider completion signal, preserving partial output without emitting an error solely for the interruption.

      This applies to OpenAI (Chat, Responses, and Completions), Anthropic, Google (Generate Content and Interactions), Alibaba, Amazon Bedrock Converse, Cohere, DeepSeek, Groq, Hugging Face Responses, Mistral Chat, Moonshot AI, Open Responses, Perplexity, and xAI Responses. It also covers cutoffs in later Anthropic messages and Google automatic continuations.

      Compatibility notice: These streams previously fell back to other or omitted the finish part. Applications must now handle interrupted in finish-reason switches, mappings, and custom validation. Check finishReason === 'interrupted' to detect incomplete responses; interruption alone does not trigger error handling.

      Explicit unknown completion reasons still map to other. Actual provider, parsing, and transport errors retain their error paths; affected error paths that previously left the finish reason as other now report error. OpenAI-compatible remains unchanged.

  16. 5.0.121

    21 Oct 2026
    • Defer construction of provider validation schemas until first use to reduce package import time.

  17. 5.0.115 – 5.0.1206 releases that only update dependencies@ai-sdk/anthropic 4.0.84@ai-sdk/provider 4.0.31@ai-sdk/provider-utils 5.0.64and 1 moreShow each
  18. 5.0.114

    12 Oct 2026
    • Use known supported Claude models for native structured output and strict tools on Bedrock. Future Claude model IDs omit those unsupported fields and use JSON instructions for structured output by default.

  19. 5.0.113

    8 Oct 2026
    • Map the top level embedding dimensions to provider settings

  20. 5.0.112

    8 Oct 2026
    • anthropic: Avoid unsupported strict mode warnings when tools set strict: false

  21. 5.0.110

    7 Oct 2026
    • amazon-bedrock,anthropic-aws: Skip SigV4 signing for non-ASCII header values

  22. 5.0.109

    7 Oct 2026
    • anthropic: Add Claude Haiku 5.5 support

  23. 5.0.107

    6 Oct 2026
    • provider: Add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.

      Compatibility notes:

      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.

  24. 5.0.105

    1 Oct 2026
    • 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.

  25. 5.0.104

    30 Sep 2026

    Only updates a dependency:@ai-sdk/anthropic 4.0.71

  26. 5.0.103

    30 Sep 2026
    • Validate hostname parts using isValidHostnamePart

  27. 5.0.101 – 5.0.1022 releases that only update dependencies@ai-sdk/openai 4.0.82@ai-sdk/anthropic 4.0.69@ai-sdk/provider 4.0.20and 1 moreShow each
  28. 5.0.100

    28 Sep 2026
    • Use standards-compliant User-Agent header

  29. 5.0.99

    28 Sep 2026
    • anthropic: Add Claude Sonnet 5.5 support

  30. 5.0.98

    28 Sep 2026
    • amazon-bedrock: Omit max output tokens for Nova 2 Lite high reasoning

    • provider: Advertise image model file and mask input support

      Use confirmed model IDs for capability declarations so unrecognized model names remain unknown. Include Together AI FLUX.2 Pro and Flex single-image editing, and allow asynchronous capability lookups and middleware overrides to resolve to unknown.

      Advertise QuiverAI Arrow 2 and Arrow 2 Telos file-input support, and mark Together AI Gemini image inputs unsupported by the current single-image request mapping.

  31. 5.0.94 – 5.0.973 releases that only update dependencies@ai-sdk/openai 4.0.78@ai-sdk/provider-utils 5.0.49@ai-sdk/anthropic 4.0.65Show each

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