Repository navigation
Update dependency ai to v7.0.155 - #2274
renovate[bot] wants to merge 1 commit into
Conversation
|
Important Review skippedAuto reviews are limited based on label configuration. 🏷️ Required labels (at least one): 1
Please check the settings in the CodeRabbit UI or the
 |
Review statusThis PR was opened by an automated account. A human maintainer must verify the change intent, provenance, and validation before merging. Current step: Awaiting fresh human maintainer or CODEOWNER approval. Review-state labels are managed by this workflow; do not edit them manually. |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
github-actions
Bot
added
the
awaiting-maintainer
This PR contains the following updates:
7.0.148→7.0.155Release Notes
vercel/ai (ai)
v7.0.155Compare Source
Patch Changes
b6b9dca: chore(ai): remove runtime validation of inputs that TypeScript types already guaranteestreamText,generateText,generateObjectandstreamObjectno longer validate messages against theModelMessageschema. This removes a cost that grew linearly with message history and was paid on everystreamTextstep. Type checks on call settings, steering messages, tool caller configuration,smoothStreamchunking,experimental_streamSpeechtext input, the shape ofdecidestate and questions, and the batch reference version have also been removed. Value constraints that types cannot express, such as integer ranges, non-empty collections, unknown keys, and non-finite numbers or cycles indecideJSON input, are still validated.Updated dependencies [
57086ff]Updated dependencies [
01d7a03]Updated dependencies [
95348b3]v7.0.154Compare Source
Patch Changes
47236dd: add onStepError callback to generateText, streamText, ToolLoopAgent and telemetry integrations, and onError and onAbort to ToolLoopAgentc8e8866: AddaiVersionto telemetry events so tracing-channel subscribers and telemetry integrations can identify the emittingaipackage version, including in bundled applications and applications with multiple SDK versions.1cf95c6: add experimental steering to generateText, streamText and ToolLoopAgente64ed82]v7.0.153Compare 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.5475347]e729d58]v7.0.152Compare Source
Patch Changes
a706678]v7.0.151Compare Source
Patch Changes
1bf6d85]v7.0.150Compare Source
Patch Changes
8e18d59: feat(ai): add experimental_streamSpeechStreams speech audio from a string, or an array, iterable, or stream of text deltas and/or text parts (each with an optional
voiceandproviderOptions) using speech models that implement the experimentalExperimental_StreamingSpeechModelV4extension. Returns a single-consumeraudioStream/fullStreamplususage,warnings,responses, andproviderMetadatapromises. Providererrorparts are non-fatal and reported throughonError(defaultconsole.error). A user abort or a cancel rejects the result promises immediately. Exports theExperimental_SpeechTextPart,Experimental_SpeechStreamPart,Experimental_SpeechStreamUsage, andExperimental_StreamSpeechResulttypes, adds an optionalcausetoNoSpeechGeneratedError, and addsExperimental_MockStreamingSpeechModelV4toai/test.Updated dependencies [
8202f5b]Updated dependencies [
85d84a1]v7.0.149Compare Source
Patch Changes
1727442: fix(ai): process only the first approval response per tool call, so repeated or conflicting responses in the final tool message no longer execute a tool twice or both execute and deny it0a5d0e7: FixtoolChoice: 'none'by forwarding it to the Hugging Face Responses API and rejecting tool calls before local execution ingenerateText,streamText, andWorkflowAgent. Streamed tool parts are withheld so client-side tools cannot act on them, andrepairToolCallandexperimental_refineToolInputare not invoked for rejected tool calls.10026d1: Add theinterruptedfinish reason for provider streams that end without a completion signal. Preserve partial output without introducing an error solely for interruption, and stop tool execution, agent continuation, and automatic UI follow-ups for interrupted responses, including late tool results and approvals. Provider detection and emission will be added separately.Compatibility notice: Adding
interruptedto the public finish-reason types can break type checking after upgrading, even though this is a patch release. Exhaustive switches (for example, using anassertNeverfallback) and mappings such asRecord<FinishReason, string>must handle the new value. Update any custom validation or application logic that assumes the existing set of finish reasons is exhaustive.When providers begin emitting
interrupted, a stream ending without a completion signal will preserve partial output and report this finish reason without emitting an error solely for the interruption. Applications that need to detect incomplete responses should checkfinishReason === 'interrupted'as well as their existing error handling.Updated dependencies [
101ce42]Updated dependencies [
e104368]Updated dependencies [
eb1f056]Updated dependencies [
10026d1]Updated dependencies [
5893e99]Configuration
📅 Schedule: (in timezone America/Los_Angeles)
🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.
♻ Rebasing: Whenever PR becomes conflicted, 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.