MastraModelOutput

The MastraModelOutput class is returned by .stream() 이며 Model 출력에 대한 스트리밍 방식과 Promise 기반 접근을 모두 제공합니다. 구조화된 출력 생성, Tool 호출, 추론 및 상세한 사용량 추적을 지원합니다.

// MastraModelOutput is returned by agent.stream()
const stream = await agent.stream('Hello world')

For setup and basic usage, see the .stream() method documentation.

Streaming properties

다음 속성은 Model 출력이 생성되는 동안 실시간으로 접근할 수 있게 해 줍니다:

fullStream:

ReadableStream<ChunkType<OUTPUT>>

Complete stream of all chunk types including text, tool calls, reasoning, metadata, and control chunks. Provides granular access to every aspect of the model's response.

ReadableStream

ChunkType:

ChunkType<OUTPUT>

All possible chunk types that can be emitted during streaming

textStream:

ReadableStream<string>

Stream of incremental text content only. Filters out all metadata, tool calls, and control chunks to provide just the text being generated.

objectStream:

ReadableStream<Partial<OUTPUT>>

Stream of progressive structured object updates when using output schemas. Emits partial objects as they're built up, allowing real-time visualization of structured data generation.

ReadableStream

PartialSchemaOutput:

Partial<OUTPUT>

Partially completed object matching the defined schema

elementStream:

ReadableStream<OUTPUT extends (infer T)[] ? T : never>

Stream of individual array elements when the output schema defines an array type. Each element is emitted as it's completed rather than waiting for the entire array.

Promise-based properties

다음 속성은 스트림이 완료된 후 최종 값으로 결정됩니다:

text:

Promise<string>

The complete concatenated text response from the model. Resolves when text generation is finished.

object:

Promise<OUTPUT>

The complete structured object response when using output schemas. Validated against the schema before resolving. Rejects if validation fails.

Promise

InferSchemaOutput:

OUTPUT

Fully typed object matching the exact schema definition

reasoning:

Promise<string>

Complete reasoning text for models that support reasoning (like OpenAI's o1 series). Returns empty string for models without reasoning capability.

reasoningText:

Promise<string | undefined>

Alternative access to reasoning content. May be undefined for models that don't support reasoning, while 'reasoning' returns empty string.

toolCalls:

Promise<ToolCallChunk[]>

Array of all tool call chunks made during execution. Each chunk contains tool metadata and execution details.

ToolCallChunk

type:

'tool-call'

Chunk type identifier

runId:

string

Execution run identifier

from:

ChunkFrom

Source of the chunk (AGENT, WORKFLOW, etc.)

payload:

ToolCallPayload

Tool call data including toolCallId, toolName, args, and execution details

toolResults:

Promise<ToolResultChunk[]>

Array of all tool result chunks corresponding to the tool calls. Contains execution results and error information.

ToolResultChunk

type:

'tool-result'

Chunk type identifier

runId:

string

Execution run identifier

from:

ChunkFrom

Source of the chunk (AGENT, WORKFLOW, etc.)

payload:

ToolResultPayload

Tool result data including toolCallId, toolName, result, and error status

usage:

Promise<LanguageModelUsage>

Token usage statistics including input tokens, output tokens, total tokens, and reasoning tokens (for reasoning models).

Record

inputTokens:

number

Tokens consumed by the input prompt

outputTokens:

number

Tokens generated in the response

totalTokens:

number

Sum of input and output tokens

reasoningTokens?:

number

Hidden reasoning tokens (for reasoning models)

cachedInputTokens?:

number

Number of input tokens that were a cache hit

finishReason:

Promise<string | undefined>

Reason why generation stopped (e.g., 'stop', 'length', 'tool_calls', 'content_filter'). Undefined if the stream hasn't finished.

enum

stop:

'stop'

Model finished naturally

length:

'length'

Hit maximum token limit

tool_calls:

'tool_calls'

Model called tools

content_filter:

'content_filter'

Content was filtered

response:

Promise<Response>

Response metadata and messages from the model provider.

Response

id?:

string

Response ID from the model provider

timestamp?:

Date

Response timestamp

modelId?:

string

Model identifier used for this response

headers?:

Record<string, string>

Response headers from the model provider

messages?:

ResponseMessage[]

Response messages in model format

uiMessages?:

UIMessage[]

Response messages in UI format, includes any metadata added by output processors

Error properties

error:

string | Error | { message: string; stack: string; } | undefined

Error information if the stream encountered an error. Undefined if no errors occurred. Can be a string message, Error object, or serialized error with stack trace.

Methods

getFullOutput:

() => Promise<FullOutput>

Returns a comprehensive output object containing all results: text, structured object, tool calls, usage statistics, reasoning, and metadata. Convenient single method to access all stream results.

FullOutput

text:

string

Complete text response

object?:

OUTPUT

Structured output if schema was provided

toolCalls:

ToolCallChunk[]

All tool call chunks made

toolResults:

ToolResultChunk[]

All tool result chunks

usage:

Record<string, number>

Token usage statistics

reasoning?:

string

Reasoning text if available

finishReason?:

string

Why generation finished

response:

Response

Response metadata and messages from the model provider

consumeStream:

(options?: ConsumeStreamOptions) => Promise<void>

Manually consume the entire stream without processing chunks. Useful when you only need the final promise-based results and want to trigger stream consumption.

ConsumeStreamOptions

onError?:

(error: Error) => void

Callback for handling stream errors

Usage examples

Basic Text Streaming

const stream = await agent.stream('Write a haiku')

// Stream text as it's generated
for await (const text of stream.textStream) {
  process.stdout.write(text)
}

// Or get the complete text
const fullText = await stream.text
console.log(fullText)

Structured Output Streaming

const stream = await agent.stream('Generate user data', {
  structuredOutput: {
    schema: z.object({
      name: z.string(),
      age: z.number(),
      email: z.string(),
    }),
  },
})

// Stream partial objects
for await (const partial of stream.objectStream) {
  console.log('Progress:', partial) // { name: "John" }, { name: "John", age: 30 }, ...
}

// Get final validated object
const user = await stream.object
console.log('Final:', user) // { name: "John", age: 30, email: "john@example.com" }

### Tool Calls and Results

```typescript
const stream = await agent.stream("What's the weather in NYC?", {
  tools: { weather: weatherTool }
});

// Monitor tool calls
const toolCalls = await stream.toolCalls;
const toolResults = await stream.toolResults;

console.log("Tools called:", toolCalls);
console.log("Results:", toolResults);

Complete Output Access

const stream = await agent.stream('Analyze this data')

const output = await stream.getFullOutput()
console.log({
  text: output.text,
  usage: output.usage,
  reasoning: output.reasoning,
  finishReason: output.finishReason,
})

Full Stream Processing

const stream = await agent.stream('Complex task')

for await (const chunk of stream.fullStream) {
  switch (chunk.type) {
    case 'text-delta':
      process.stdout.write(chunk.payload.text)
      break
    case 'tool-call':
      console.log(`Calling ${chunk.payload.toolName}...`)
      break
    case 'reasoning-delta':
      console.log(`Reasoning: ${chunk.payload.text}`)
      break
    case 'finish':
      console.log(`Done! Reason: ${chunk.payload.stepResult.reason}`)
      // Access response messages with any metadata added by output processors
      const uiMessages = chunk.payload.response?.uiMessages
      if (uiMessages) {
        console.log('Response messages:', uiMessages)
      }
      break
  }
}

Error handling

const stream = await agent.stream('Analyze this data')

try {
  // Option 1: Handle errors in consumeStream
  await stream.consumeStream({
    onError: error => {
      console.error('Stream error:', error)
    },
  })

  const result = await stream.text
} catch (error) {
  console.error('Failed to get result:', error)
}

// Option 2: Check error property
const result = await stream.getFullOutput()
if (stream.error) {
  console.error('Stream had errors:', stream.error)
}

Related types

• .stream(): Method that returns MastraModelOutput
• ChunkType: 전체 스트림에서 가능한 모든 청크 유형