Run.streamVNext() (Experimental)
Experimental API:
This is a new streaming implementation that supports multiple output formats (including AI SDK v5). It will replace .stream() and may change as we refine the feature based on feedback.
The .streamVNext() method enables real-time streaming of responses from a workflow. This enhanced streaming capability will eventually replace the current stream() method.
Usage example
const run = await workflow.createRunAsync();
const stream = run.streamVNext({
inputData: {
value: "initial data",
},
});Parameters
inputData?:
z.infer<TInput>
Input data that matches the workflow's input schema
runtimeContext?:
RuntimeContext
Runtime context data to use during workflow execution
tracingContext?:
TracingContext
AI tracing context for creating child spans and adding metadata.
currentSpan?:
AISpan
Current AI span for creating child spans and adding metadata.
tracingOptions?:
TracingOptions
Options for AI tracing configuration.
metadata?:
Record<string, any>
Metadata to add to the root trace span.
closeOnSuspend?:
boolean
Whether to close the stream when the workflow is suspended, or to keep the stream open until the workflow is finished (by success or error). Default value is true.
Returns
stream:
MastraWorkflowStream<ChunkType>
A custom stream that extends ReadableStream<ChunkType> with additional workflow-specific properties
stream.status:
Promise<RunStatus>
A promise that resolves to the current workflow run status
stream.result:
Promise<WorkflowResult<TOutput, TSteps>>
A promise that resolves to the final workflow result
stream.usage:
Promise<{ inputTokens: number; outputTokens: number; totalTokens: number, reasoningTokens?: number, cacheInputTokens?: number }>
A promise that resolves to token usage statistics
stream.traceId?:
string
The trace ID associated with this execution when AI tracing is enabled.
Extended usage example
const run = await workflow.createRunAsync();
const stream = run.streamVNext({
inputData: {
value: "initial data",
},
});
const result = await stream.result;Stream Events
The stream emits various event types during workflow execution. Each event has a type field and a payload containing relevant data:
workflow-start: Workflow execution beginsworkflow-step-start: A step begins executionworkflow-step-output: Custom output from a stepworkflow-step-result: A step completes with resultsworkflow-finish: Workflow execution completes with usage statistics