Packages

@ai-sdk/anthropic

4.0.106 · 17 Nov 2026Apache-2.024.5M / weekRepositoryHomepagenpmAtom feed

Your version

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

  1. 4.0.105

    13 Nov 2026
    • 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.

  2. 4.0.104

    13 Nov 2026
    • Add experimental extraction models backed by structured language model output

  3. 4.0.102

    10 Nov 2026
    • Add MiniMax H3 Image and H3 Image Highspeed support for text-to-image generation and image editing, including output controls and token usage details.

  4. 4.0.101

    10 Nov 2026

    Only updates a dependency:@ai-sdk/provider-utils 5.0.78

  5. 4.0.99

    7 Nov 2026
    • Keep computer toolset actions tied to the returned member name and reject disabled or unavailable members before emitting tool calls. Apply member configuration to local input validation and reject malformed or non-object member input.

    • 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.

    • Reject conflicting inline tool additions when a named tool choice falls back to auto or the internal JSON response tool limits available application tools, including definitions replayed from conversation history.

  6. 4.0.98

    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.

    • Refactor Anthropic AWS model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Export Anthropic catalog metadata internally for Anthropic AWS to reuse. Request behavior is unchanged.

    • anthropic: Support adding tools by value in mid-conversation toolChanges (inline-tools-2026-09-15)

  7. 4.0.97

    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.

    • Add MiniMax serviceTier support for standard and priority admission. Omit tiers belonging to another known provider with an unsupported-setting warning instead of forwarding incompatible values. Expose the applied serviceTier, when returned, in Anthropic-compatible generation, stream and batch metadata without changing existing metadata construction types.

    • Add typed streaming heartbeat parts. Anthropic emits them only with includePings: true (disabled by default), without requiring raw chunks. Core forwards pings through stream retries without storing them as generated content or sending them to UI message streams. Consumers with exhaustive stream-part switches must handle the new ping union variant when upgrading, even when the opt-in is disabled. Typed pings do not flush partial words during stream smoothing.

  8. 4.0.96

    3 Nov 2026

    Only updates a dependency:@ai-sdk/provider-utils 5.0.74

  9. 4.0.95

    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.

    • anthropic: Parse valid JSON string tool input and safely serialize BigInt and cycles in tool results

  10. 4.0.94

    30 Oct 2026
    • 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.

    • 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.

    • 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.

  11. 4.0.93

    30 Oct 2026
    • 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.

  12. 4.0.92

    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.

  13. 4.0.91

    28 Oct 2026
    • Fix workflow serialization of Anthropic models using API keys or synchronous auth tokens while preserving support for asynchronous token providers.

  14. 4.0.90

    27 Oct 2026
    • 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.

  15. 4.0.87 – 4.0.893 releases that only update dependencies@ai-sdk/provider-utils 5.0.69@ai-sdk/provider 4.0.34Show each
  16. 4.0.86

    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.

    • anthropic: Preserve empty-stream rejection for interrupted responses

  17. 4.0.85

    21 Oct 2026
    • Add a shared encodePathSegment helper and use it to encode provider-returned identifiers in credentialed follow-up request paths.

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

    • Defer construction of Anthropic provider option schemas until they are first used to reduce package import time.

  18. 4.0.84

    20 Oct 2026
    • Add the MiniMax M3.1 Flash model ID to the MiniMax and AI Gateway providers.

  19. 4.0.82 – 4.0.832 releases that only update dependencies@ai-sdk/provider 4.0.30@ai-sdk/provider-utils 5.0.63Show each
  20. 4.0.81

    15 Oct 2026
    • anthropic: Support provider-referenced files in tool results

  21. 4.0.80

    15 Oct 2026
    • vertex-anthropic: Forward 'providerOptions.vertex.labels' as a header

    • Fall back to automatic tool choice with a warning when manual thinking is enabled with a required or named tool choice, avoiding an Anthropic API 400 error. Named tool choices send only the selected tool.

  22. 4.0.79

    12 Oct 2026
    • anthropic: Preserve tools when disabling tool calls

    • anthropic: Preserve failed tool search results in conversation history

    • Keep retrieved web-search sources separate from normalized inline citations on text parts and text-end events. Preserve every supported web and document citation kind in generation, streaming, and batch results, with typed AnthropicCitation and AnthropicTextProviderMetadata exports. Retain document source compatibility and web citation source fallbacks when retrieval results are unavailable.

  23. 4.0.77

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

  24. 4.0.75

    7 Oct 2026
    • anthropic: Add Claude Haiku 5.5 support

  25. 4.0.73

    6 Oct 2026
    • Limit jsonl rows to 64mb during batch result downloads

    • 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.

  26. 4.0.72

    5 Oct 2026
    • Rename evaluate to decide

    • anthropic: Expose message-start usage through custom stream parts

    • anthropic: Add the required beta when replaying server-side fallback blocks

  27. 4.0.71

    30 Sep 2026
    • anthropic: Preserve invalid toolset calls

  28. 4.0.69

    30 Sep 2026
    • anthropic: Preserve server-side fallback boundaries when replaying assistant messages

  29. 4.0.68

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

  30. 4.0.67

    28 Sep 2026
    • anthropic: Add Claude Sonnet 5.5 support

    • Normalize dangling programmatic tool caller references in conversation history after pruning. Before a subsequent user message, omit caller metadata whose source code execution call is missing and emit a warning, preserving the retained tool calls and results. Keep caller metadata unchanged for active tool continuations.

  31. 4.0.65 – 4.0.662 releases that only update dependencies@ai-sdk/provider-utils 5.0.50@ai-sdk/provider 4.0.19Show each
  32. 4.0.63

    24 Sep 2026
    • anthropic: Support on-demand compaction and preserve signed compaction blocks

  33. 4.0.62

    23 Sep 2026

    Only updates a dependency:@ai-sdk/provider-utils 5.0.47

  34. 4.0.61

    23 Sep 2026
    • anthropic: Omit empty compaction blocks from replay

  35. 4.0.60

    22 Sep 2026
    • anthropic: Add Claude Opus 5.5 support

  36. 4.0.59

    22 Sep 2026
    • provider/anthropic: Add safeguards provider option and safeguardResults provider metadata (dangerous tool use classifier)

  37. 4.0.57 – 4.0.582 releases that only update dependencies@ai-sdk/provider-utils 5.0.45Show each
  38. 4.0.56

    16 Sep 2026
    • Add anthropic.evaluationModel() for experimental Choice, Score, and Boolean evaluations through Messages structured output, with exact labels, validated score bounds, and prompted Boolean P(true) estimates validated to be in [0, 1]. Boolean estimates are not guaranteed to be calibrated; application code chooses thresholds.

  39. 4.0.55

    16 Sep 2026
    • anthropic: Add 20260318 web search and web fetch tools with response inclusion controls

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.