Repository navigation
chore(deps): update ai provider sdks - #2160
renovate[bot] wants to merge 1 commit into
Conversation
|
|
Important Review skippedBot user detected. To trigger a single review, invoke the
|
27b5e71 to
821d2f3
Compare
|
| Command | Status | Duration | Result |
|---|---|---|---|
nx run-many --targets=build --exclude=examples/... |
❌ Failed | 2m 17s | View ↗ |
💡 With Ultracache enabled, Nx Cloud learns each task's file inputs in CI and uses them on later runs. Turn on Ultracache in workspace settings ↗ · Read docs ↗
☁️ Nx Cloud last updated this comment at 2026-11-19 22:50:40 UTC
992744e to
13abf77
Compare
c11d85e to
a6d0f28
Compare
|
8bbe6fa to
fe102db
Compare
fe102db to
dfc1458
Compare

Note
This PR body was truncated due to platform limits.
This PR contains the following updates:
4.0.99→4.0.1214.0.152→4.0.181^0.135.0→^0.137.0^0.19.0→^0.22.0^3.1057.0→^3.1173.0^3.1057.0→^3.1173.0^3.1057.0→^3.1173.0^2.10.0→^2.32.02.2.0→2.7.00.13.20→0.13.67^1.9.0→^1.10.0^0.6.3→^0.6.4^7.30.0→^7.62.0Release Notes
vercel/ai (@ai-sdk/openai)
v4.0.121Compare Source
Patch Changes
1a7440b: return input transformations in responses provider metadatav4.0.120Compare Source
Patch Changes
ed981f8: feat(openai): add GPT-6.2 Astra and GPT-6.2 Sol model supportv4.0.119Compare Source
Patch Changes
5aa836f: fix(openai): sendadditionalToolsdefinitions only for tools registered in the requestadditionalToolsentries can come from replayed, client-supplied conversation history. The Responses provider now uses an entry only to select a tool registered in the call'stoolsand sends the definition derived from that tool: its description, input schema,strictsetting, anddeferLoadingoption instead of the values in the history. Entries for tools that are not registered are dropped with a warning, and a namespace entry loads only the registered tools it names.Updated dependencies [
10ff0b1]Updated dependencies [
e878ab3]Updated dependencies [
d99098a]v4.0.118Compare Source
Patch Changes
f5fc6ba: 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.v4.0.117Compare Source
Patch Changes
6d50947: add experimental extraction models backed by structured language model output6d50947]v4.0.116Compare Source
Patch Changes
2ebc78b: Forward the provider's configured fetch transport when downloading file inputs. Add afetchoption tocreateDownloadso core downloads can also useguarded-fetchfor opt-in DNS validation on Node.js. The function returned bycreateDownloadcan now also be passed asexperimental_downloadtogenerateTextandstreamText, andexperimental_downloadnow also handles generated file URLs returned by the model, so one hook covers all core downloads. Document that the default URL checks do not resolve DNS and recommend the guarded transport or network egress controls for untrusted URLs.Keep Azure image and Vertex tool-result downloads separate from provider authentication wrappers so file hosts never receive Azure bearer tokens or Vertex Express Mode API keys.
Pass the call's abort signal to custom download requests, including prompt assets and generated files, so
experimental_download: createDownload({ fetch })preserves cancellation and timeouts.6eff958: feat(openai): add positioned additionalTools and accept custom and namespace toolsa279e86: fix(openai): keep tool-result additionalTools for parallel results and openai optionsUpdated dependencies [
2ebc78b]Updated dependencies [
cb4fa52]v4.0.115Compare Source
Patch Changes
5a645e9: Support positioned Responses API format updates so changing structured output schemas can preserve earlier reasoning and prompt cache reuse. Add a stable request-level text format override and expose prompt cache comparison diagnostics for generation, streaming, and batch results.v4.0.114Compare Source
Patch Changes
4311fa1]4311fa1]v4.0.113Compare Source
Patch Changes
22b8158: Avoid repeating the complete parallel-tool wrapper input in every expanded tool call's metadata while preserving wrapper reconstruction for follow-up Responses API requests.88b9575]v4.0.111Compare Source
Patch Changes
6400cf8: AddresolveProviderOptionsto parse provider options that a model accepts under severalproviderOptionskeys, 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.6400cf8]f608c05]cab9c1f]c70adf6]v4.0.110Compare Source
Patch Changes
c6efa4b: Refactor Azure model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Export the OpenAI catalog internally for Azure to reuse. Request behavior is unchanged.f6dbf04: fix(openai): surface Chat Completions refusals as text contentThe Chat Completions model ignored
message.refusal(non-streaming) anddelta.refusal(streaming). When the model refused to answer,contentwasnull, so the AI SDK returned empty text with astopfinish reason and silently dropped the refusal. Refusal text is now emitted as text content in bothgenerateTextandstreamTextresults, and it is emitted in addition to content when the API returns both. A refusal with astopfinish reason is now reported as acontent-filterfinish reason, matching the Anthropic provider and the Responses API.646a7e3: fix(openai,openai-compatible): surface refusal logprobs and openai-compatible refusals@ai-sdk/openai: Chat Completions responses that contain a refusal can returnlogprobs.refusalnext tologprobs.content. The provider previously read onlylogprobs.content, soproviderMetadata.openai.logprobswas empty or missing for refusals. Refusal logprobs are now included in emission order (content logprobs followed by refusal logprobs) in bothgenerateTextandstreamText.Streaming logprobs are now collected across all chunks in
streamText: previously only the logprobs of the last streamed chunk were reported. This applies to content logprobs as well, soproviderMetadata.openai.logprobsnow contains the logprobs of every streamed token instead of only the last chunk's tokens. Explicitly empty logprobs (logprobs: { content: [], refusal: null }) are reported as an empty array, as before.A refusal that arrives in the same streamed chunk as the
finish_reasonis now taken into account: such a response is reported with acontent-filterfinish reason instead ofstop.@ai-sdk/openai-compatible: Chat Completions responses that carrymessage.refusal(non-streaming) ordelta.refusal(streaming) were ignored, so providers such as OpenAI served throughcreateOpenAICompatiblelost the refusal text and reported an emptystopresponse. Refusals are now returned as text content after any content text, and a non-empty refusal with astopfinish reason is reported as acontent-filterfinish reason. This also applies when the refusal and the finish reason arrive in the same streamed chunk. Non-string refusals (for examplerefusal: falsefrom servers that use booleans) are ignored instead of failing the response.6b97088: fix(openai): handle refusal content parts in the Responses APIThe Responses API returns a
refusalcontent part instead ofoutput_textwhen the model declines a request. The response schema rejected these parts, so non-streaming calls failed with anAPICallError("Invalid JSON response"), and streamedresponse.refusal.delta/response.refusal.doneevents were dropped, producing empty text. Refusal content parts and stream events are now parsed: the refusal explanation is surfaced as text and the finish reason is mapped tocontent-filter. When the response also contains a client-side function call, the finish reason staystool-callsso the tools are still executed.v4.0.109Compare Source
Patch Changes
27528db: ExposecustomToolthroughazure.toolsfor Azure Responses models, sharing the OpenAI custom tool factory and its raw string input support.7bb309d: add memoryLimit and networkPolicy properties in codeInterpreter tool7a90522: Add Secure MCP tunnel support to the OpenAI MCP tool viatunnelId. Tunnel targets cannot be combined withserverUrlorconnectorId; existing URL and connector configurations remain compatible.6549344: feat(openai): support GPT Image 2.6 models withcomplexity, markup-guided edits (markup), animated GIF output (outputFormat: 'gif',frameCount,frameDurationMs), andsafetyIdentifierfor image models5f9bb8e: feat (provider/openai): forward themoderationoption to/images/edits934100c: 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.892af4d: feat (provider/openai): implement server-side realtime extensionsOpenAIRealtimeModelnow implementsgetServerWebSocketConfig(), returning the upstream realtime WebSocket URL forconversationandtranscriptionintents plus header auth derived from the model's configured credentials. Dedicated transcription sessions serialize withsession.type: "transcription"and the selected realtime model id. Translation is rejected until the normalized realtime codec supports its distinct wire protocol. The event mapper now populates normalizedusageonresponse-doneandinput-transcription-completed(gross input/output token counts with cached portions reported separately; duration usage for duration-billed transcription).Transcription serialization honors the explicit transcription model and rejects unsupported output settings. Gross token totals and reported modality/cache counts are retained; duration uses
seconds. OpenAI Live retains its existing connection API and rejects unsupported intents.243bf22: Forward per-messageproviderOptions.openai.nameon Chat Completions system, developer, user, and assistant messages. Validate names as strings and warn when configured on unsupported tool messages.5cc6d28: Exposeazure.tools.shellfor local and hosted shell execution through the Azure Responses API.41465fd: Expose optional transcription word timings separately from segments and accept shared timestampGranularities. Explicit provider timing settings take precedence. OpenAI now sends timestamp_granularities only with verbose_json and warns when a requested timing is unavailable or excluded.Updated dependencies [
36802d4]Updated dependencies [
e0143b0]Updated dependencies [
934100c]Updated dependencies [
892af4d]Updated dependencies [
89aff56]Updated dependencies [
41465fd]Updated dependencies [
9754014]Updated dependencies [
4bb73b0]Updated dependencies [
2e44144]v4.0.108Compare Source
Patch Changes
fa15312]v4.0.107Compare Source
Patch Changes
4ae6986: fix(openai): preserve valid JSON string tool arguments and serialize BigInt and cycles in tool calls and results, retaining malformed argument replay fallbacks226b7da: Forwardlanguagesandkeywordstranscription hints as repeated multipart fields instead of silently dropping them. Warn when these REST-only options are supplied to streaming transcription.51ca5b7]dc6f1c3]4ae6986]v4.0.106Compare Source
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.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]v4.0.105Compare Source
Patch Changes
47b1d8b: feat(openai): send native JSON input and prompt cache keys to Decisionsd07b475: fix(openai): map top-levelreasoningto efforts supported by GPT-5.x models instead of sending unsupported values that OpenAI rejects with a 400.maxis now only sent on the Responses API, and GPT-5.6 on Chat Completions sendsreasoning_effort: 'none'when function tools are used, since it rejects function tools with reasoning. A warning is emitted when a reasoning level was requested.61a315e: fix: map the top-levelreasoningoption consistently across providersProviders now resolve reasoning the same way:
providerOptionsis sent unchanged. OpenAI no longer dropsproviderOptions.openai.reasoningEffortvalues that are not in its list for the model, and Fireworks no longer rewritesproviderOptions.fireworks.reasoningEffort. Fireworks also sends top-levelreasoningvalues 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).reasoningmaps 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 withoutxhigheffort, and'medium'maps to'low'instead of'high'on DeepSeek, Kimi K3, and Mistral GLM-5.3 models.'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 OpenAIgpt-ossmodels, and Gemini 2.5 Pro (minimum thinking budget). Gemini 3 and Anthropic and Bedrockbetween_toolsmappings now emit the compatibility warning too.mapReasoningToProviderEffortnow accepts anyreasoningvalue, returns an optionalproviderOptionsEffortunchanged, and rounds levels that are missing from the effort map to the closest supported level.mapReasoningToProviderBudgetmaps'none'to the minimum reasoning budget, always returns a budget, and uses the default percentage for levels missing frombudgetPercentages.OpenAICompatibleChatConfigadds an optionalmapReasoningfunction for mapping the top-levelreasoningoption.Updated dependencies [
61a315e]v4.0.104Compare Source
Patch Changes
01d7a03: feat(openai): add GPT-6.1 Terra model support599a97f: fix(openai): read transcription duration fromusagefor duration-billedjsonresponsesdurationInSecondsnow falls back tousage.secondswhenusage.typeisdurationand the response has no top-levelduration(e.g.gpt-transcribewith the defaultjsonresponse format).8375141: Support streaming transcription withgpt-live-transcribeandgpt-transcribe. For these models thelanguageprovider option is sent as a single-entrylanguageslist.gpt-transcribewarns about and omitsstreaming.delay, which it does not support.gpt-live-transcriberejects non-streaming transcription, since it has no REST endpoint.7eac057: fix(openai): strippropertyNamesschemas that omittype: 'string'(e.g. Zod 3 records with constrained keys) instead of throwing an unsupported functionality error436374e: fix(openai): report unfinished web searches as tool errors9026c7d: fix(openai): only send transcription response format and timestamp defaults when neededTranscription requests no longer send
response_format=verbose_jsonortimestamp_granularities[]=segmentunless the caller sets them or the model needs them. Previously, anyproviderOptions.openaivalue (such as aprompt) causedverbose_jsonto be sent for models likegpt-transcribe, which rejected the request.Updated dependencies [
57086ff]Updated dependencies [
95348b3]v4.0.103Compare Source
Patch Changes
02dbab1: add azure.tools.toolSearch and support azure provider options on responses function tools27a53b4: Fix string interpolation in Amazon Bedrock unsupported provider tool warnings and OpenAI / OpenAI-compatible completion errors for unexpected system messages.e64ed82]v4.0.102Compare Source
Patch Changes
5475347: Fix non-streaming Responses API structured output failing when multiple assistant messages contain JSON. Providers can supply separate structured-output text for parsing, allowing OpenAI and Azure Responses models to select the lastfinal_answerwhile preserving all generated content, annotations, conversation history, and token usage.e729d58: chore(docs): updateREADME.mdfor consistent format and to avoid duplication5475347]e729d58]v4.0.101Compare Source
Patch Changes
8202f5b]85d84a1]v4.0.100Compare Source
Patch Changes
43ad966: Reportinterruptedwhen 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
otheror omitted the finish part. Applications must now handleinterruptedin finish-reason switches, mappings, and custom validation. CheckfinishReason === '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 asothernow reporterror. OpenAI-compatible remains unchanged.Updated dependencies [
10026d1]vercel/ai (@ai-sdk/react)
v4.0.181Compare Source
Patch Changes
e403988]b792b56]v4.0.180Compare Source
Patch Changes
95b78c9]v4.0.179Compare Source
Patch Changes
v4.0.178Compare Source
Patch Changes
3bea041]30d35eb]fab7478]10ff0b1]718824c]e878ab3]d99098a]v4.0.177Compare Source
Patch Changes
3c09e00]f43ee39]7ce7ffc]f6809e3]2559173]f1de9cb]v4.0.176Compare Source
Patch Changes
6d50947]79d2004]v4.0.175Compare Source
Patch Changes
11323f9]2ebc78b]2ebc78b]cb4fa52]ceeee29]1a94af3]v4.0.174Compare Source
Patch Changes
37dfe49: Allow MCP Apps to load scripts and styles from origins declared inresourceDomains.6309382: Add support forbaseUriDomainsin MCP App CSP metadata.91a67c2]6309382]84b1cb0]v4.0.173Compare Source
Patch Changes
4311fa1]6141e6f]4311fa1]d9dd2b7]v4.0.172Compare Source
Patch Changes
65aa669: add experimental_queue to useChat to queue messages sent while a response is in progress65aa669]8585d7e]88b9575]v4.0.170Compare Source
Patch Changes
v4.0.169Compare Source
Patch Changes
dc0f7f2]6400cf8]f608c05]883fcde]cab9c1f]6d21e8e]c70adf6]v4.0.168Compare Source
Patch Changes
ae13fce]v4.0.167Compare Source
Patch Changes
e0143b0: feat(ai): support provider-owned realtime transportsAdd an optional
createTransportinterface andproviderconnection capability.Updated dependencies [
5d18351]Updated dependencies [
8da48db]Updated dependencies [
fd7e8a7]Updated dependencies [
36802d4]Updated dependencies [
933dae3]Updated dependencies [
e0143b0]Updated dependencies [
934100c]Updated dependencies [
c389374]Updated dependencies [
892af4d]Updated dependencies [
892af4d]Updated dependencies [
89aff56]Updated dependencies [
1a1da8d]Updated dependencies [
41465fd]Updated dependencies [
9754014]Updated dependencies [
4bb73b0]Updated dependencies [
2e44144]v4.0.166Compare Source
Patch Changes
fa15312]857ca45]4d6d830]v4.0.165Compare Source
Patch Changes
51ca5b7]51ca5b7]51ca5b7]51ca5b7]dc6f1c3]4ae6986]v4.0.164Compare Source
Patch Changes
a71172d]cf27969]17b6923]v4.0.163[Compare Source](https://redirect.github.com/vercel/ai/compare/@ai-sdk/react@4.0.162...@ai-s
Configuration
📅 Schedule: (UTC)
* 0-3 * * 1)🚦 Automerge: Enabled.
♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.
👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.
This PR was generated by Mend Renovate. View the repository job log.