@ai-sdk/provider

0c2a9de: Add maxOutputTokens and reasoning to experimental decision calls and forward them to language-model-backed decisions. Language-model adapters keep reasoning disabled when omitted. Native decision providers warn when either setting is unsupported.

60cc252: feat(perplexity): add decisions api support

0957554: Add box decision question type with image bounds for TypeSafe AI.

130e871: Restore raw OpenAI custom-tool input deltas for consumers that forward them to Responses API clients. Mark streamed input with inputEncoding: 'text' so UI clients can display it progressively without JSON parsing. Preserve the encoding when partial UI messages are saved and resumed. Final provider tool-call inputs remain JSON-encoded.

e57803c: Add an optional shared citation representation to generated text and text-end stream events, separate from retrieved sources. Preserve citations in core result content and UI message text parts, including validation and persistence, without changing content or stream event discriminants.

4dbc902: feat(ai): add a top level 'dimensions' setting for embeddding functions

9184a35: Add ordered text, file, and JSON parts to experimental decision state. Support image input in OpenAI Decisions and language model adapters. Gateway retains its existing string and JSON request format and rejects files, as does TypeSafe AI.

Arrays passed directly as state now contain decision state parts. Wrap JSON arrays in an object or a json part.

Normalize all public state forms into an array of parts before calling decision providers. Providers receive text and JSON objects as text and json parts.

Serialize decision file bytes as base64 in OpenTelemetry state attributes. Model-call spans record normalized state parts, while outer spans retain public state inputs.

Preserve native JSON state in TypeSafe AI when state contains one JSON part. Label shared state in language-model decision prompts.

d3bcad9: feat(provider): report decision refusals as refusal answers

268225c: feat(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.

2959d35: feat: rename evaluate to decide

8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle callbacks

ede5b89: chore: migrate package builds from tsup to tsdown

525efc5: feat(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.

ffb0e76: fix(provider): preserve opaque file URI strings for provider serialization

a7dd893: Add experimental evaluation model aliases and registry resolution. customProvider accepts evaluationModels, registries expose evaluationModel, and experimental_evaluate accepts string IDs when an evaluation-capable default provider is explicitly configured. Evaluation never implicitly falls back to Gateway. Model-resolution errors now identify evaluationModel while stable provider contracts remain unchanged.

d06bb2a: Allow readonly arrays and objects containing them to be used as JSON values.

123d71f: Add experimental_evaluate and the isolated experimental v4 evaluation model specification for Choice, Score, and Boolean questions against shared state. Includes typed answers, optional Choice/Score distributions, required Boolean probabilities, validation, retries, cancellation, and Experimental_EvaluationUnsupportedQuestionTypeError for unsupported questions.

5c0054d: Add optional browser-direct WebRTC for experimental client-delegated Live conversations alongside the existing WebSocket path. Exchange SDP through an application endpoint with api.session, configure server-owned data-channel permissions, and preserve committed React session ownership. Capture follows the selected sender track, borrowed tracks remain caller-owned, and disconnect recovery and finalization stay bounded. Applications continue to handle client delegation and submit context; Live session updates and Responses delegation remain unsupported.

Serialize microphone sender changes and close the peer if detachment fails, without stopping borrowed tracks. Validate nonempty SDP setup answers with a bounded response body, and document the same-origin broker authentication contract.

39535af: Add experimental OpenAI Live provider support through the unified openai.experimental_realtime factory for server WebSocket sessions with client delegation. Applications own their agents and tools, receive continuous audio/transcript events and delegation metadata, and return context through validated channels. Support immutable startup options, microphone mute controls, graceful session close, and cumulative voice usage. Responses delegation and Live session updates reject before sending.

Route known Live model IDs to Live, allow an OpenAI-specific api override for early-access models, and preserve legacy Realtime defaults for unknown IDs. Token minting follows the same selection rules and rejects Live before requesting unsupported credentials. Extend the realtime v4 specification with optional server WebSocket configuration, per-connection raw-event parsers, and model-wide startup/finalization capabilities. This provider layer supplies connection settings and protocol mapping for server adapters; browser lifecycle and UI integration belong to the core runtime and framework hooks.

Preserve Realtime client event IDs for session updates and audio appends, and correlate server errors with the originating client event.

5ec21a6: fix: reject unsupported batch request types

7469a3b: feat: support image generation requests in batches

9942196: feat: add batch cancel and list APIs

912fb01: feat: add batch cancel and list APIs

a4ba394: feat: support per-request models in batch

45099da: Retry unclassified empty image results, preserve retry-attempt accounting, add provider-independent result retryability classification, and mark Google and Google Vertex prompt blocks as terminal.

5190b67: feat(provider): extend the FilesV4 interface with optional getFileMetadata, downloadFile (streaming), and deleteFile operations, plus abortSignal/headers call options and a { type: 'stream' } upload data variant; upload results now expose byteSize, createdAt, and expiresAt (also surfaced by the core uploadFile() helper, which now forwards abortSignal/headers); add postMultipartStreamToApi (streaming multipart uploads with deterministic part ordering and failure-path stream teardown), deleteFromApi, and createBinaryStreamResponseHandler to provider-utils

aa45741: fix(provider/anthropic): preserve native message batch request counts in provider metadata and support the full language-model option surface in batch requests

591d25b: feat: add batch completion webhooks. experimental_startTextBatch accepts a webhookUrl, and the gateway provider registers it through the batch callbackUrl contract and exports typed async-job metadata. Direct Anthropic and OpenAI batch providers return an unsupported warning when the option is provided.

ad6a650: feat(video): allow aspectRatio: 'adaptive' on generateVideo

Some video models derive the output ratio from the input and reject explicit {width}:{height} values — BytePlus Seedance 2.5 does this for first-frame, first-and-last-frame, editing, and extension tasks. aspectRatio on VideoModelV3CallOptions, VideoModelV4CallOptions, and experimental_generateVideo is now `${number}:${number}` | 'adaptive', so those calls no longer need a type assertion. Support is provider-specific.

3469d0c: feat: add batch APIs

79e133c: async APIs for generateVideo (poll, webhook)

Adds an asynchronous start/status flow to the experimental video model interface (VideoModelV4): models may now implement doStart, doStatus, and handleWebhookOption instead of (or in addition to) doGenerate, and experimental_generateVideo accepts poll and webhook options to orchestrate completion via polling or webhooks. Polling configuration can use a custom delay implementation for durable workflow compatibility.

1e2f324: feat: add experimental speech translation model specification (Experimental_SpeechTranslationModelV4) and experimental_streamTranslate for streaming speech-to-speech translation

739e9f6: Restore raw OpenAI custom-tool input deltas for consumers that forward them to Responses API clients. Mark streamed input with inputEncoding: 'text' so UI clients can display it progressively without JSON parsing. Preserve the encoding when partial UI messages are saved and resumed. Final provider tool-call inputs remain JSON-encoded.