Repository navigation
⬆️ upgrade minor and patch updates - #372
Open
renovate[bot] wants to merge 1 commit into
Open
renovate[bot] wants to merge 1 commit into
renovate[bot] wants to merge 1 commit into
Conversation
Contributor
Author
Branch automerge failureThis PR was configured for branch automerge. However, this is not possible, so it has been raised as a PR instead. |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Important Review skippedBot user detected. To trigger a single review, invoke the
|
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 4, 2026 06:02
a0b486c to
fd4e70e
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 5, 2026 10:37
fd4e70e to
2d41e11
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 5, 2026 14:54
2d41e11 to
8e766e7
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 5, 2026 18:07
8e766e7 to
474f047
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 5, 2026 21:55
474f047 to
79eac4c
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 6, 2026 00:52
79eac4c to
50dbbe2
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 6, 2026 12:46
50dbbe2 to
10f6634
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 6, 2026 18:30
10f6634 to
5eed51a
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 7, 2026 12:35
5eed51a to
3a9163b
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 7, 2026 18:27
3a9163b to
14dd7b9
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 7, 2026 21:15
14dd7b9 to
03986a6
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 8, 2026 06:03
03986a6 to
e2f44d5
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 8, 2026 09:49
e2f44d5 to
6f2abce
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 05:01
c47890f to
9ce95fe
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 13:38
9ce95fe to
c1db9f6
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 21:42
c1db9f6 to
eddc690
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 22:02
eddc690 to
47d7450
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 22:45
47d7450 to
008f27b
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 23:07
008f27b to
478716a
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 23:08
478716a to
b08ff77
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 23:10
b08ff77 to
38adcbf
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 23:43
38adcbf to
74deacb
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 10, 2026 23:52
74deacb to
bfdfef1
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 11, 2026 00:22
bfdfef1 to
858909a
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 11, 2026 03:24
858909a to
e04248b
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 11, 2026 15:52
e04248b to
f8e639b
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 11, 2026 22:33
f8e639b to
edcdbd7
Compare
renovate
Bot
force-pushed
the
renovate/minor-patch
branch
from
January 12, 2026 01:11
edcdbd7 to
3205ad0
Compare
This branch had an error being deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Note
This PR body was truncated due to platform limits.
This PR contains the following updates:
3.0.2→3.0.1442.29.8→2.31.15.2.3→5.3.05.2.2→5.9.216.1.1→16.4.61.2.12→1.3.11.1.12→1.2.11.1.15→1.3.12.1.16→2.2.11.2.14→1.4.11.2.4→1.5.01.1.13→1.2.11.2.15→1.3.10.13.10→0.13.114.1.18→4.3.52.0.13→2.0.1425.0.3→25.9.922.19.3→22.20.519.2.7→19.3.019.2.3→19.3.0^0.8.0→^0.11.06.0.5→6.0.3332.6.1→2.7.0^0.562.0→^0.577.012.23.26→12.43.02.1.7→2.1.1210.26.2+sha512.0e308ff2005fc7410366f154f625f6631ab2b16b1d2e70238444dd6ae9d630a8482d92a451144debc492416896ed16f7b114a86ec68b8404b2443869e68ffda6→10.34.919.2.3→19.3.119.2.3→19.3.17.69.0→7.92.05.0.3→5.1.03.4.0→3.7.04.1.18→4.3.54.21.0→4.23.155.0.0→5.2.0Release Notes
vercel/ai (@ai-sdk/openai)
v3.0.144Compare Source
Patch Changes
7be5eed: 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 [
d59eee0]v3.0.143Compare Source
Patch Changes
61c32d9: feat(openai): support Responses contextManagement and compaction itemsv3.0.142Compare Source
Patch Changes
5a14668: feat(openai): add positioned additionalTools and accept custom and namespace tools5a14668: feat(openai): support ordered 'additional_tools' from tool resultsv3.0.141Compare Source
Patch Changes
cbfe771: 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 and streaming results.v3.0.140Compare Source
Patch Changes
e38b209: 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.88bb257]v3.0.139Compare Source
Patch Changes
f0dee4b]v3.0.138Compare Source
Patch Changes
c6d995a: 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.98eb47b: 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.c21fadf: 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.v3.0.137Compare Source
Patch Changes
afde897: feat(openai): support GPT Image 2.6 models withcomplexity, markup-guided edits (markup), animated GIF output (outputFormat: 'gif',frameCount,frameDurationMs), andsafetyIdentifierfor image modelsv3.0.136Compare Source
Patch Changes
d900e58: fix(openai): preserve valid JSON string tool arguments and serialize BigInt and cycles in tool calls and results, retaining malformed argument replay fallbacksd900e58: Forwardlanguagesandkeywordstranscription hints as repeated multipart fields instead of silently dropping them.d900e58]d900e58]d900e58]v3.0.135Compare Source
Patch Changes
28252da]v3.0.134Compare Source
Patch Changes
84a2231: fix(openai): report unfinished web searches as tool errors84a2231: Report failed and incomplete web searches as tool errors instead of successful tool results in OpenAI Responses API calls.v3.0.133Compare Source
Patch Changes
90fad7b: feat(openai): add GPT-6.1 Terra model support529492f: Fixgpt-transcribeREST transcription. Requests with OpenAI provider options now useresponse_format: 'json'forgpt-transcribeand datedgpt-4o-mini-transcribesnapshots, which rejectverbose_json.durationInSecondsis read fromusage.secondswhen a duration-billed response has no top-levelduration.v3.0.132Compare Source
Patch Changes
766eebd: add azure.tools.toolSearch and support azure provider options on responses function toolsv3.0.131Compare Source
Patch Changes
6afa8a8: Defer validation schema construction until first use to reduce provider import time.aad3b66: feat(openai): support 12h prompt cache writes and cache prewarming1183cc4]d726591]v3.0.130Patch Changes
5aa3086]v3.0.129Patch Changes
739e9f6: Restore raw OpenAI custom-tool input deltas for consumers that forward them to Responses API clients. Mark streamed input withinputEncoding: '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.739e9f6]v3.0.128Compare Source
Patch Changes
d5e7d82]v3.0.127Compare Source
Patch Changes
347b939: fix(openai): send assistant text with content instead of an item reference when its reasoning was removedWith reasoning models, pruning reasoning (e.g.
pruneMessages({ reasoning: 'all' })) caused follow-up requests to fail with "Item 'msg_...' of type 'message' was provided without its required 'reasoning' item". Assistant text parts are now only sent as item references, or with their item id, when they are preceded by reasoning in the same assistant message.Updated dependencies [
604b4d3]v3.0.126Compare Source
Patch Changes
e8ce454: fix(openai): JSON-encode custom tool input deltas for progressive UI updatesv3.0.125Compare Source
Patch Changes
ce4202b: fix(openai): replay web search results when response storage is disabledfde0b6c: fix(openai): classify Responses stream errors with null codesv3.0.124Compare Source
Patch Changes
d131a3b: fix(openai): rewrite recursive Zod schemas that useallOfwrappersv3.0.123Compare Source
Patch Changes
f56545c: feat(openai): add support for ultrafast service tierv3.0.122Compare Source
Patch Changes
a9cea74]a9cea74]a9cea74]v3.0.121Compare Source
Patch Changes
4972874: feat(openai): add GPT-6.1 Sol model supportv3.0.120Compare Source
Patch Changes
29dc427: fix(provider-utils): preserve streamed tool calls with unreliable IDs and indices29dc427]v3.0.119Compare Source
Patch Changes
3983fea]v3.0.118Compare Source
Patch Changes
0fb3a22: The OpenAI Responses provider now acceptsproviderOptions.openai.reasoningEffortUpdateon empty system messages and sends each update at its position in the conversation. This lets applications change reasoning effort during a conversation while preserving the prompt prefix for caching.v3.0.117Compare Source
Patch Changes
a3e970b: fix(openai): expose Chat Completions audio transcripts as generated textf7f36d2: chore: enable dead code lint rules57256a0: fix(openai): preserve retryability for early stream errors069a945]d1a36d2]f7f36d2]v3.0.116Compare Source
Patch Changes
ad8de8d: fix(openai): acceptincompletefunction_call and custom_tool_call items on the Responses stream, so a call truncated bymax_output_tokensfinishes withlengthinstead of aTypeValidationError0b9d00b: feat: GPT-6 Sol and Luna model IDsda2e17b]v3.0.115Compare Source
Patch Changes
82e18b0]v3.0.114Compare Source
Patch Changes
e53d917: fix(openai): preserve provider file references in Responses tool resultsv3.0.113Compare Source
Patch Changes
90757ce: fix(openai): report apply patch responses with a tool-calls finish reasonv3.0.112Compare Source
Patch Changes
1336501: fix(openai): return an AI SDK error for empty chat completion choices1a4dbb1]v3.0.111Compare Source
Patch Changes
1f75808: Include explicit message item types in Azure AI Foundry Responses requests.65150c2: feat(openai): add GPT Image 2.5 Flare and Sunburst model IDsv3.0.110Compare Source
Patch Changes
447ba18: feat(openai): add async tool calling46c6820: Addxhighandmaxquality support for GPT Image 2.5 Flare and Sunburst in image generation, image editing, and the Responses API image generation tool.v3.0.109Compare Source
Patch Changes
7f3b8f0: feat(openai): add GPT-6 reasoning configuration updatesv3.0.108Compare Source
Patch Changes
019eec8: feat(openai): add support for the gpt-6-astrav3.0.107Compare Source
Patch Changes
8844beb: fix(openai): flatten mid-stream Responses error eventscf1ba03: fix(openai): preserve complete Responses API raw usage objectsv3.0.106Compare Source
Patch Changes
85ba0b0: Preserve explicit prompt cache breakpoints on scalar Responses tool results.v3.0.105Compare Source
Patch Changes
cc23556]v3.0.104Compare Source
Patch Changes
426c9b3: Normalize non-object replayed Chat Completions tool arguments to empty objects.34d045d: Fix Responses history serialization for regular functions namedtool_search.v3.0.102Compare Source
Patch Changes
087d7e2: Signal schema-invalid known Responses stream events and preserve the error finish reason.v3.0.101Compare Source
Patch Changes
313a441: Prevent negative text output token counts when providers report reasoning tokens. Perplexity reasoning tokens are now treated as separate from completion tokens.5642849]v3.0.100Compare Source
Patch Changes
2d172fb]v3.0.99Compare Source
Patch Changes
f40afcf: fix(openai): expand internal parallel tool call wrappers from the Responses API while preserving stateful continuation and streaming fallbacksv3.0.98Compare Source
Patch Changes
91880b9: fix(openai): support built-in and provider-defined tools in the ResponsesallowedToolsoptionallowedToolsemitted every allow-list entry as{ type: 'function', name }, but OpenAI identifiesbuilt-in tools by type. Allow-listing a declared provider-defined tool (web search, image generation,
MCP, custom, ...) therefore failed with
Tool choice '<name>' not found in 'tools' parameter. Entriesare now derived from the declared tool, including the MCP server label and custom tool name.
Tools that OpenAI cannot allow-list (the tool search tool, deferred tools, and namespaced tools) are
dropped from the allow-list with a warning, and an error is thrown if that would leave the allow-list
empty rather than silently sending an unrestricted request.
Ambiguous names are now reported instead of resolved silently. A name that matches both a declared tool
and another tool's provider tool name resolves to the declared tool and warns; a provider tool name
shared by several tools in the same request (two MCP servers, for example) is dropped with a warning.
A name that matches no declared tool keeps its existing behavior and is now warned about.
v3.0.97Compare Source
Patch Changes
31205a4]v3.0.96Compare Source
Patch Changes
64facff: Reconstruct provider-executed shell calls when continuing OpenAI Responses with storage disabled.v3.0.95Compare Source
Patch Changes
bdb46fe: Avoid duplicate MCP approval request references when continuing stored OpenAI Responses.v3.0.94Compare Source
Patch Changes
d3247d7: Keep client-executed function calls paired with their outputs when chaining OpenAI Responses with a previous response ID.b2a4d5a]v3.0.93Compare Source
Patch Changes
f471a1c: AcceptserviceTier: 'fast'on OpenAI chat and responses models. OpenAI renamed priority processing to Fast mode and acceptsservice_tier: 'fast'and'priority'interchangeably, so'fast'is now passed through verbatim and gated on the same model capability as'priority'.2171d15]v3.0.92Compare Source
Patch Changes
dab0a08]v3.0.91Patch Changes
ee2bf30]v3.0.41Patch Changes
ad4cfc2]v3.0.40Patch Changes
824b295]v3.0.39Patch Changes
08336f1]v3.0.38Patch Changes
64a8fae: chore: remove obsolete model IDs for Anthropic, Google, OpenAI, xAIv3.0.37Patch Changes
58bc42d](https://reConfiguration
📅 Schedule: (UTC)
🚦 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.