Repository navigation
chore(deps): update dependency ai to v7.0.148 - #601
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
|
Important Review skippedBot user detected. To trigger a single review, invoke the ⚙️ Run configuration
You can disable this status message by setting the Use the checkbox below for a quick retry:
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Dependency Review✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.OpenSSF Scorecard
Scanned Files
|
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 2, 2026 02:22
5f04c60 to
ed55720
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
2 times, most recently
from
October 5, 2026 21:31
20cce97 to
7fa5ac5
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 7, 2026 01:43
7fa5ac5 to
834dfe7
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 7, 2026 05:44
834dfe7 to
9b5b254
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 7, 2026 23:25
9b5b254 to
af727a4
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 8, 2026 01:25
af727a4 to
ba5acb9
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 8, 2026 19:14
ba5acb9 to
2921b63
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 8, 2026 22:43
2921b63 to
f4070ac
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
2 times, most recently
from
October 9, 2026 06:37
071a6fe to
b3749a1
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
2 times, most recently
from
October 9, 2026 19:58
a9ae9ab to
2c23618
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 13, 2026 01:41
2c23618 to
2f64caa
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 14, 2026 04:33
2f64caa to
d4814b4
Compare
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
2 times, most recently
from
October 15, 2026 23:36
8b0aac8 to
338be88
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
3 times, most recently
from
October 17, 2026 02:37
5941a97 to
888dfe1
Compare
renovate
Bot
changed the title
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
2 times, most recently
from
October 20, 2026 20:32
1a319ac to
52bf844
Compare
renovate
Bot
changed the title
renovate
Bot
force-pushed
the
renovate/ai-7.x-lockfile
branch
from
October 21, 2026 05:39
52bf844 to
98414cd
Compare
renovate
Bot
changed the title
This branch has not been 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.
This PR contains the following updates:
7.0.105→7.0.148Release Notes
vercel/ai (ai)
v7.0.148Compare Source
Patch Changes
b089ce8]39a776b]f1b550e]v7.0.147Compare Source
Patch Changes
66e74dc: fix(ai): preserve repaired tool names in streamed UI message parts9bec2c3]v7.0.146Compare Source
Patch Changes
0c2a9de: AddmaxOutputTokensandreasoningto 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.3785b2e: fix(ai): remove orphaned reasoning, including consecutive summary and reasoning-file parts, when pruning tool callsab8eb61: Fix optional tools adding an incorrectundefinedmember to tool call, result, error, denied output, and execution event types.9d13c4d]0c2a9de]200c47f]v7.0.145Compare Source
Patch Changes
1c47fee]v7.0.144Compare Source
Patch Changes
60cc252: feat(perplexity): add decisions api support0ed59e2: FixstreamTextreturn types for reusable options andReturnTypeby moving low-memory streaming toexperimental_streamTextLowMemory. Replace experimentalstreamText({ experimental_lowMemory: true, ...options })calls withexperimental_streamTextLowMemory(options).60cc252]6b7fb8f]v7.0.143Compare Source
Patch Changes
8a5233b: Generate default chat IDs on first access souseChat()can prerender without reading a random value when the ID is not used during rendering.894e130: fix(ai): addexperimental_lowMemory: truetostreamTextfor single-consumer streaming without a replay buffer or retained final-content results, reducing memory retention.0957554: Addboxdecision question type with image bounds for TypeSafe AI.0957554]v7.0.142Compare Source
Patch Changes
130e871: 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.130e871]5bdb816]v7.0.141Compare Source
Patch Changes
88ea0d7: fix(workflow): pass runtime context allowed by 'telemetry.includeRuntimeContext'2e89fa4]b658e85]v7.0.140Compare Source
Patch Changes
9523eb0: feat(ai): add configurable tool call execution concurrency42a2895]v7.0.139Compare Source
Patch Changes
685667c]bdbeba3]ec2af7b]v7.0.138Compare Source
Patch Changes
eab278a: fix: resume interrupted chat streams when the page becomes visible againuseChatwithresume: trueno longer starts a second resume request on mount when the chat is already submitted or streaming, e.g. when remounting with a sharedChatinstance mid-stream.26d64e9: fix(ai): update tool outputs in the message containing the matching tool call75b3ea2: fix(ai): prevent duplicate message parts when resuming replayed streams69f4b82: fix(ai): prevent global type conflicts across SDK versionse57803c: 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.4c705d9: Fix validation of rounded choice probabilities inexperimental_decide.5150d50: fix(ai): update streaming chat messages by stable ID9aef724: fix(workflow): report incomplete no-output model streams as errors7d0458b: fix(ai): reject approved tool calls without results before sending later context to providersUpdated dependencies [
9667bf2]Updated dependencies [
e57803c]Updated dependencies [
81663cc]v7.0.137Compare Source
Patch Changes
e27cc64: fix(ai): discard unrelated message state when reading resumed streamsv7.0.136Compare Source
Patch Changes
7b5497c: Fix streaming output timeouts: stopchunkMsandfirstChunkMswhen the model response ends, so long-running local tools do not trigger model output timeouts. Give each retry fresh output timeout budgets.stepMscontinues to cover the complete step, including local tools.e280aa1]v7.0.135Compare Source
Patch Changes
5ddbb70: fix(ai): prevent duplicate continuation requests for repeated tool approval responses7c40a09: feat(ai): log warning when default step limit stops a tool loop4dbc902: feat(ai): add a top level 'dimensions' setting for embeddding functionsff18b73: fix(ai): wait for chat stream cleanup when stopping9be846c: feat(ai): add a persistent WebSocket chat transport with correlated streaming, serialized backpressure, cancellation, validated protocol frames, explicit lifecycle, and sequence-based resume support5cf13d2]4dbc902]908fd12]v7.0.134Compare Source
Patch Changes
8281ec4: fix(ai): propagate async sendAutomaticallyWhen failures from tool updates46c2b05: fix(ai): preserve provider-executed tool calls when resuming streamsv7.0.133Compare Source
Patch Changes
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.
Updated dependencies [
9184a35]v7.0.132Compare Source
Patch Changes
3ebefff: feat(ai): introduce 'onUIMessageStepEnd' callback to persist messagesv7.0.131Compare Source
Patch Changes
866e884]04fdf5e]v7.0.130Compare Source
Patch Changes
6f6b9c0: fix(ai): reject pending result promises and cancel the pending stream when the abort signal firesd3bcad9: feat(provider): report decision refusals as refusal answersd3bcad9]v7.0.129Compare Source
Patch Changes
e37d213: feat(ai): emit deprecation warnings with stable codes and deduplicate them73d8343: fix(ai): preserve V2 provider-reported total tokens in raw usage268225c: feat(provider): add a portablemaxreasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.Compatibility notes:
maxwidensLanguageModelV4CallOptions['reasoning']and the derivedReasoningLeveltype. Third-party providers and consumers with exhaustive switches orRecord<ReasoningLevel, ...>mappings must handlemaxbefore upgrading. Ordinary calls using existing reasoning levels remain accepted.reasoning: 'xhigh'now sendmaxReasoningEffort: 'high'instead of the unsupported'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existingxhighbehavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.minimalandxhighcalls keep their request mappings tolowandhigh, respectively, and now return compatibility warnings in generation and streaming results. Portablemaxmaps tohighwith the same warning behavior.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
majorlabel if they decide to align the provider-spec addition with a future AI SDK major release.d83366e: fix(ai): publish the latest error after repeated failed stream resume attempts34905a2: fix(ai): preserve provider options from approval-only tool messages16ab882: fix(ai): recognize WebKit network errorsf810ea3: fix(ai): prevent unavailable tools from exposing persisted output to models19a127b: fix(ai): avoid duplicate slashes in chat reconnect URLs0af2f7c: chore: upgrade to TypeScript 64c6979c: fix(harness): preserve adapter warnings in agent stream results and declaretheir compatibility warning shapes
Updated dependencies [
fc1e19e]Updated dependencies [
5094ebd]Updated dependencies [
753f2e1]Updated dependencies [
268225c]Updated dependencies [
0af2f7c]Updated dependencies [
ad64697]Updated dependencies [
0c82824]v7.0.128Compare Source
Patch Changes
0fe8c67: fix: preserve tool approval state when resuming streams2959d35: feat: renameevaluatetodecide0ca1ab9: Add durable non-streamingWorkflowAgent.generate()with a shared tool loop, a 20-step default, typed output, and core generation result semantics. Reuse core result and content construction through internal exports while preserving existing Workflow streaming behavior. Transport-independent approval creation remains separate follow-up work.d6b42fd: feat(ai): support custom reasoning delimiters in extractReasoningMiddlewareed6e72d: fix(ai): return successful empty transcripts for silent audio2136151: ThrowInvalidResponseDataErrorinstead of a genericErrorwhen a generated audio file's format cannot be determined from its media type, so callers can identify the failure withAISDKError.isInstance.131532b]2959d35]59116e6]6ac923a]v7.0.127Compare Source
Patch Changes
158a718: feat(ai): select and rank eligible deferred tools via 'search()' callback in tool searchbb8d33e: fix(ai): cancel merged UI message streams when the consumer disconnects284dc11: fix(ai): accept unchanged tool approval inputs created in another JavaScript realmba8afe9: feat(ai): add a configurable maxResults for number of tools returned in tool searchd1bb9e8]v7.0.126Compare Source
Patch Changes
4f3d236: fix: clear tool approvals whenaddToolOutputrunsv7.0.124Compare Source
Patch Changes
8c65988: feat(ai): add telemetry to speech generation and transcription, includingprovider usage propagation and experimental streaming lifecycle callbacks
8c65988]e25994e]527a163]e74afc5]v7.0.123Compare Source
Patch Changes
05cdac6: fix(ai): keep idle UI message streams open with optional SSE heartbeats4514fc1: fix(ai): prune all tool content when retaining zero trailing messagesede5b89: chore: migrate package builds from tsup to tsdown2a625cf: fix(ai): preserve partial reasoning tags when streamed text parts end50a26d5: fix(ai): ignore pending tool approvals superseded by user messages040033b]ede5b89]v7.0.122Compare Source
Patch Changes
f3575f8: Clarify that provider-executed tool execution errors bypass the UI stream'sonErrorcallback to preserve provider error data and harness runtime messages. Stream errors and invalid tool calls still use the callback. Runtime behavior is unchanged.27ab8d4: Encode chat IDs in default stream reconnection URLs so slashes, query delimiters, and fragments stay within the ID. Reject standalone.and..IDs before fetching. Custom URLs returned byprepareReconnectToStreamRequestremain unchanged.870f509]a75f1fd]v7.0.120Compare Source
Patch Changes
b032d70: fix(ai): preserve tool metadata from tool output chunkse21b98b: fix(ai): continue active UI message parts when resuming after a disconnecte361d39]v7.0.119Compare Source
Patch Changes
33e94ba: fix(ai): cancel response streams when clients disconnect34d869e: fix(ai): prevent unhandled stream completion rejections in non-Node runtimesdef4df8: fix(ai): store static tool input errors in the current input field525efc5: feat(provider): advertise image model file and mask input supportUse 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.
Updated dependencies [
e3605f6]Updated dependencies [
525efc5]v7.0.118Compare Source
Patch Changes
e6a7996]e19f0fc]v7.0.117Compare Source
Patch Changes
b67b1b7]v7.0.116Compare Source
Patch Changes
af9597b: Compile packages for ES2022 runtime targetbc49f78: Preserve original opaque URI strings in tagged file URLs during prompt conversion. Match explicit supported URL MIME types exactly so unsupported subtypes are not forwarded to providers.af9597b]bc49f78]v7.0.114Compare Source
Patch Changes
b5679a7: fix(ai): filter tracing-channel context with telemetry allowlistsca31b89: Clarify in the prompt validation code thatallowSystemInMessagespermits all system messages, including instruction text.124b6ef]v7.0.113Compare Source
Patch Changes
dcdb011: fix(ai): route completed streamed tool input callbacks to repaired tools8f72832: fix(ai): preserve video models from legacy fallback providersfe07867: Fix GoogleembedManycalls with more than 100 values by keeping per-value multimodal content aligned across automatic batches, including text-only entries. Validate content length before sending requests and validate each batch's provider options after middleware transforms them.b74c0cb: fix(ai): resume tool approvals from earlier messagesa4b0940: fix(ai): execute manually approved tool inputs produced by schema transformsPreserve approved inputs during revalidation and reject histories whose reconstructed schema output differs, including signed approvals with missing original input. Validate transformed UI tool inputs against the reconstructed output before returning them as static tool parts.
2693319: Add Gemini 3.8 TTS support with structured speech metadata and per-turn speaker and style controls for prebuilt voices. Preserve native WAV responses without adding a second header, support explicit raw PCM, mu-law, and A-law output, and identify headerless audio formats correctly. Add the Gemini 3.8 speech model IDs to Google and Gateway types.Share transcript and custom-voice inspection through the Google provider internal export, and reject empty speech transcripts before sending a request. Default newer and custom model IDs to structured speech while preserving the legacy format for Gemini 2.5 and 3.1.
c93ee90: fix(ai): preserve message history for direct transport stream callbacks771e74b: chore: enable dead code lint rulesUpdated dependencies [
fe07867]Updated dependencies [
a4b0940]Updated dependencies [
2693319]Updated dependencies [
b73f2f9]Updated dependencies [
771e74b]v7.0.112Compare Source
Patch Changes
9a98fd9: fix(ai): prune reasoning file parts when removing reasoninga0553d6: feat(ai): report consumer cancellation in UI message stream end callbacksffb0e76: fix(provider): preserve opaque file URI strings for provider serializationfde0d66: fix(ai): preserve parsed metadata and data values when validating UI messagesed5a1d7]ffb0e76]618dc11]v7.0.111Compare Source
Patch Changes
31d24ce: feat: add telemetry support toexperimental_evaluatea65bfd9: fix(ai): securely download URL-backed language model file outputs so generated files expose actual base64 and byte content and UI streams contain valid data URLs. Propagate cancellation to batch file downloads.v7.0.110Compare Source
Patch Changes
49295bb]v7.0.109Compare Source
Patch Changes
0343bb1: fix(ai): keep replacement completion requests loading and cancellable when an earlier request settles2b105fa: fix(ai): preserve overlapping text blocks in reasoning extraction streams125f493: fix(harness): forward validatedtoolsContextto host-executed tools in alignment withToolLoopAgentv7.0.108Patch Changes
3f6852a: fix(ai): prevent direct execution of tools governed by tool callers6317504: fix(ai): stop pending tool-call repairs when generation is cancelled3cb2dcd: fix(ai): preserve file data when adapting v3 language modelsccf98e7: fix(ai): preventstreamTextfrom executing tool calls that violate tool choice20dd00a]7cf7cee]c42576a]d85dcf5]fd9b3f3]v7.0.107Patch Changes
79681c4: fix(ai): preserve provider file and skill upload APIs in wrapProvider98c7275: fix(ai): preserve query parameters in chat reconnect URLsa105059: fix(workflow): support deferred tool discovery in WorkflowAgent31532f3: fix(ai): prevent preliminary tool outputs from completing chatse61cbd8: fix(ai): preserve raw speech audio format metadata8ade040: fix(ai): pass tool-specific context to input callbacks970a01e: fix(ai): enforce polling timeouts for in-flight video status requests85539c5: fix(ai): preserve multiple Set-Cookie headers in Node stream responses611d301: fix(ai): prevent duplicate content types in chat transport requestsc415657: fix(ai): decode base64 text data URLs using their declared charset2973485]a4db5ea]2937ea2]v7.0.106Patch Changes
4775577: fix(ai): preserve provider metadata when simulating text streams6696728: fix(ai): report the prepareStep model in streamed step results09516a1: fix(ai): prevent unhandled rejections when UI message stream reading stops early1aef01e: fix(ai): preserve prototype-named properties in serialized tool outputs9c1ea74: fix(ai): close telemetry spans when provider response streams fail107343a: fix(ai): use the prepareStep-selected model for streamed response metadata fallbacks03c3e33: fix(ai): preserve tool calls required by retained pending approvals5d42ebd: fix(ai): skip input available callbacks for invalid streamed tool calls4a67783: fix(ai): cancel prompt attachment downloads when model calls are aborted or time out1058ed5: fix(ai): strip streamed JSON fences before arbitrary trailing whitespace84f5d1b: fix(ai): stream null and empty string JSON partial outputs2d53a5d: fix(ai): prevent onEnd after aborting a multi-step text stream2a5ed55: fix(ai): stream structured output from the final tool-loop step4fdf51e]0455398]Configuration
📅 Schedule: (in timezone Asia/Singapore)
🚦 Automerge: Enabled.
♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR was generated by Mend Renovate. View the repository job log.