chore(deps): update dependency ai to v7.0.102 - #8
renovate[bot] wants to merge 1 commit into
Conversation
◈ PR Lens
Architecture 
1 component touched across 3 lanes. Data flow No data-flow sequence changed in this PR. View
Tip Add 🪧 More tips
Thanks for using PR Lens! It's built by Coldtea, and your support helps us grow. If you like it, consider giving us a shout-out. |
|
Important Review skippedBot user detected. To trigger a single review, invoke the ⚙️ Run configurationConfiguration used: Organization UI Review profile: QUIET Plan: Advanced Run ID: 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 |
b17ab17 to
8ed69e0
Compare
8ed69e0 to
f252ede
Compare
![macroscopeapp[bot]](https://avatars.githubusercontent.com/in/900172?s=60&v=4){kind=small}
ApprovabilityVerdict: Approved at Macroscope's review found this PR approvable — This is a narrowly scoped automated dependency update confined to ignored dependency metadata, with no source, workflow, security-sensitive, or deployment changes in scope. Its impact is limited to dependency resolution during installation and builds. Notes:
You can add or adjust custom eligibility rules. Learn more. |
This PR contains the following updates:
7.0.66→7.0.102Release Notes
vercel/ai (ai)
v7.0.102Compare Source
Patch Changes
5c0054d: Add optional browser-direct WebRTC for experimental client-delegated Live conversations alongside the existing WebSocket path. Exchange SDP through an application endpoint withapi.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 unifiedopenai.experimental_realtimefactory 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
apioverride 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.
8b92ba9: fix(ai): settle automatically denied tool calls in UI streams4b306c2: Report abnormal realtime WebSocket close codes and reasons through the session error path.4b306c2: Add the client-delegation-first realtime WebSocket runtime with session lifecycle, exact final duration, bounded event queues and command acknowledgement tracking, transcripts, context append, and reversible capture. Continuous sessions support PCM16 audio-chunk playback over an application relay with a recoverable live-edge buffer policy. Legacy turn-based WebSockets retain queued playback and frontend tool handling.Remove the deferred managed Responses coordinator, autoContinueTools option, backend usage state, and Live tool-result aliases. Continuous text and delegation handling belong to the application; sendTextMessage and addToolOutput reject continuous sessions. Server-confirmed provider delegation and turn-based audio-delta on the continuous profile fail explicitly. maxPlaybackBufferSeconds is supported only for continuous PCM sessions.
Fence callbacks, startup publications, tool results, and teardown by connection attempt. Validate token setup before opening a client-secret socket, require explicit relay transport mode, and include WebSocket URL, protocol values, and runtime timeouts/buffer settings in React session configuration keys.
Retain immediate local capture for explicit legacy preconnect streams, including owned-track cleanup and capture continuity through asynchronous setup. Signal transport closing before draining accepted terminal events, share reentrant close settlement, and cancel stale readiness and deadlines. Enforce 128 KiB frame and combined buffered-send budgets only for Live continuous sessions, using actual encoded wire bytes; oversized manual operations remain recoverable while startup and automatic audio failures close the session. Legacy startup, text, tool output, and audio retain their pre-Live behavior without these byte caps. Live pending-audio overflow drains accepted terminal usage within the existing one-second drain window. Validate final provider-transformed WebSocket URL syntax without removing native authentication query parameters.
Updated dependencies [
5c0054d]Updated dependencies [
39535af]v7.0.101Compare Source
Patch Changes
6aa7c54: fix(ai): serialize tool output JSON valuesv7.0.100Compare Source
Patch Changes
6431635: feat(ai): expose typed AI SDK errors for UI transport and completion failures23a0fff]v7.0.99Compare Source
Patch Changes
615ac89: feat(ai): use InvalidArgumentError for utility input validation7f76d83]v7.0.98Compare Source
Patch Changes
5ec21a6: fix: reject unsupported batch request typesdb59d78: feat(ai): add runtime context attribution to embed, embedMany and rerank7469a3b: feat: support image generation requests in batchesf87bf07: fix(ai): reject invalid reranking provider indicesbc5cb7a: fix(ai): accept inferred tools invalidateUIMessagesa5f449a: feat(ai): add a stable UI message type and type guard for tool output errors5ec21a6]7469a3b]dbd83a3]813bb36]c43e4b7]03f4e59]v7.0.97Compare Source
Patch Changes
ef3bac4: Observe video webhook receiver rejections before generation starts to prevent unhandled rejections during or after a failed start. Preserve start error precedence and assimilate custom receivers only once.9942196: feat: add batch cancel and list APIs9942196]v7.0.96Compare Source
Patch Changes
912fb01: feat: add batch cancel and list APIsc595e6e: fix(ai): callatobwithout a receiver for Cloudflare Workers compatibility912fb01]aa4cc14]f102e41]v7.0.95Compare Source
Patch Changes
27f6d7a: fix(ai): reject embedding model responses that contain no embeddingsv7.0.94Compare Source
Patch Changes
a4ba394: feat: support per-request models in batch36b3364: fix(ai): enforce tool choices in streamText45099da: 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.a4ba394]e9bf5e3]45099da]56c004c]9e1d1b2]a495511]v7.0.93Compare Source
Patch Changes
df6c009: fix(ai): use new message ID when replacing a message insendMessage6ee74a3: fix(ai): preserve tool part titles when validating UI messagesf13d371: fix(ai): preserve provider metadata when converting failed tool callsd4485fe: feat(ai): support minItems and maxItems in array outputs4f201cc: chore(ai): formally include already supportedonLanguageModelCallStartandonLanguageModelCallEndinToolLoopAgentSettingstype8cdb2a7: fix(ai): decode text data URLs in Node.js0f2281e: fix(ai): reject embedding responses whose count does not match the input valuesfc8e8ac: fix(ai): preserve image call diagnostics when no image is generatedee8391e: fix(ai): support abort signals when the global AbortSignal is not a constructor3cfc1fc]v7.0.92Compare Source
Patch Changes
a51cc94: fix(ai): preserve provider metadata from empty smooth stream deltasd1904d3: fix(ai): surface fallback errors for empty HTTP response bodies84e5a79: fix(ai): skipsmoothStreamdelays while the document is hiddena8e8ad0: fix(ai): expose call ID and abort reason in streamText onAbort callbacksa7e324b]v7.0.91Compare Source
Patch Changes
802af1e: Add configurable recovery for provider errors received afterstreamTextresponse streaming begins. Explicitly configuringstreamRetriesenables isolated retry attempts, including one bounded callback-directed recovery throughStreamTextOnErrorRetryCallbackwithstreamRetries: 0; recovered results and metadata reflect only the successful attempt, while the existingStreamTextOnErrorCallbackcontract and logging-only observer behavior remain compatible.5484f27]36eb7ee]622fa7f]v7.0.90Compare Source
Patch Changes
4d25a08]6bcc0f8]v7.0.89Compare Source
Patch Changes
5190b67: feat(provider): extend the FilesV4 interface with optionalgetFileMetadata,downloadFile(streaming), anddeleteFileoperations, plusabortSignal/headerscall options and a{ type: 'stream' }upload data variant; upload results now exposebyteSize,createdAt, andexpiresAt(also surfaced by the coreuploadFile()helper, which now forwardsabortSignal/headers); addpostMultipartStreamToApi(streaming multipart uploads with deterministic part ordering and failure-path stream teardown),deleteFromApi, andcreateBinaryStreamResponseHandlerto provider-utils5190b67]v7.0.88Compare Source
Patch Changes
8b6b756: fix(ai): prevent generateText from accepting responses that violate required tool choicese07b577: feat: add tool calling support to batchv7.0.87Compare Source
Patch Changes
850d863: fix(ai): preserve approval descriptors in UI message streamsv7.0.86Compare Source
Patch Changes
11109ae: feat(ai): support signed tool approvals in WorkflowAgent1329d5a]v7.0.85Compare Source
Patch Changes
55a9981: Ensure canonical hashes preserve undefined array element positions.dd32de2: fix(ai): sum Gateway image-generation costs across split requestsaa45741: fix(provider/anthropic): preserve native message batch request counts in provider metadata and support the full language-model option surface in batch requestscc29073: feat(ai): expose individual image generation callsd2507af]aa45741]v7.0.84Compare Source
Patch Changes
6669d69: Expose parsed structured output instreamTextend callbacks.a6463ca: fix(ai): allow tool approval secrets in ToolLoopAgent settings and prepareCalle604532: fix(ai): handle stateful and empty-match regular expressions in smoothStream805bbfc]90192f1]v7.0.83Compare Source
Patch Changes
8dd86a9: Validate persisted typed tool calls against current input and output schemas.Schema-incompatible empty or error inputs and terminal history from unavailable
tools remain loadable as dynamic tool parts instead of exposing unvalidated
values under current static tool types.
fda13b3: Allow chats to continue automatically after tool approval denials reach theoutput-deniedstate.957146c: add operation-level outcomes to UI message stream end callbacksce6849a: fix(ai): handle stitchable stream cancellation before an inner stream is registeredv7.0.82Compare Source
Patch Changes
3e125ba: Allow manual tool approval statuses to include a reason and preserve it acrosscore, model, and UI approval requests. OPA
requires-approvaldecisions nowsurface their reason to human approvers. UI request chunks serialize the
optional
reason, while UI messages retain it asapproval.requestReasonseparately from an approver's response
reason.0e7994c]3e125ba]v7.0.79Compare Source
Patch Changes
b251584: Preserve active text and reasoning parts when another merged UI message stream finishes a step, and align workflow stream normalization with the explicit part end chunks.591d25b: feat: add batch completion webhooks.experimental_startTextBatchaccepts awebhookUrl, and the gateway provider registers it through the batchcallbackUrlcontract and exports typed async-job metadata. Direct Anthropic and OpenAI batch providers return an unsupported warning when the option is provided.9de0baf: Parse structured generateText output when providers omit finishReason but return text.591d25b]v7.0.78Compare Source
Patch Changes
96970bb: Continue approvedgenerateText,streamText, andWorkflowAgentturns with a model-visible tool error when revalidated tool input is invalid.e12e068]v7.0.77Compare Source
Patch Changes
b74971f]a371615]v7.0.76Compare Source
Patch Changes
c6d57f3: fix(ai): prevent duplicate text and reasoning part ids677a707: fix(ai): allow nullish metadata schemas for UI messages with branded IDsv7.0.74Compare Source
Patch Changes
5941bd6]9a4337d]v7.0.73Patch Changes
f607a12]v7.0.71Patch Changes
9a37469: Prevent exceptions in streamingonChunkandonErrorcallbacks from terminating the stream or masking provider errors.936719b]v7.0.70Patch Changes
9566914: Stop multi-step text generation for client tool approval even when a provider-executed tool has a deferred result.b181020: fix: rejectstreamObjectresult promises and report failed completion when the provider stream errors7054073: Filter preliminary tool outputs whenignoreIncompleteToolCallsis enabled.a828527: Prevent automatic tool execution when a model call ends with an unsafe finish reason.d3cc3fe: Clear partial UI message parts when a WorkflowAgent model-call step is retried.e6087c9]v7.0.69Patch Changes
1f7a464]v7.0.68Patch Changes
257632b]v7.0.67Patch Changes
a0b1ffc]Configuration
📅 Schedule: (in timezone Europe/Warsaw)
🚦 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.