stream()
The stream() method enables real-time streaming of responses from an agent. This method accepts messages and an optional options object as parameters, similar to generate().
Parameters
messages
The messages parameter can be:
- A single string
- An array of strings
- An array of message objects with
roleandcontentproperties
The message object structure:
interface Message {
role: 'system' | 'user' | 'assistant';
content: string;
}options (Optional)
An optional object that can include configuration for output structure, memory management, tool usage, telemetry, and more.
abortSignal?:
AbortSignal
Signal object that allows you to abort the agent's execution. When the signal is aborted, all ongoing operations will be terminated.
context?:
CoreMessage[]
Additional context messages to provide to the agent.
experimental_output?:
Zod schema | JsonSchema7
Enables structured output generation alongside text generation and tool calls. The model will generate responses that conform to the provided schema.
instructions?:
string
Custom instructions that override the agent's default instructions for this specific generation. Useful for dynamically modifying agent behavior without creating a new agent instance.
maxSteps?:
number
= 5
Maximum number of steps allowed during streaming.
memoryOptions?:
MemoryConfig
Configuration options for memory management. See MemoryConfig section below for details.
onFinish?:
(result: string) => Promise<void> | void
Callback function called when streaming is complete.
onStepFinish?:
(step: string) => void
Callback function called after each step during streaming.
output?:
Zod schema | JsonSchema7
Defines the expected structure of the output. Can be a JSON Schema object or a Zod schema.
resourceId?:
string
Identifier for the user or resource interacting with the agent. Must be provided if threadId is provided.
telemetry?:
TelemetrySettings
Settings for telemetry collection during streaming. See TelemetrySettings section below for details.
temperature?:
number
Controls randomness in the model's output. Higher values (e.g., 0.8) make the output more random, lower values (e.g., 0.2) make it more focused and deterministic.
threadId?:
string
Identifier for the conversation thread. Allows for maintaining context across multiple interactions. Must be provided if resourceId is provided.
toolChoice?:
'auto' | 'none' | 'required' | { type: 'tool'; toolName: string }
= 'auto'
Controls how the agent uses tools during streaming.
toolsets?:
ToolsetsInput
Additional toolsets to make available to the agent during this stream.
MemoryConfig
Configuration options for memory management:
lastMessages?:
number | false
Number of most recent messages to include in context. Set to false to disable.
semanticRecall?:
boolean | object
Configuration for semantic memory recall. Can be boolean or detailed config.
number
topK?:
number
Number of most semantically similar messages to retrieve.
number | object
messageRange?:
number | { before: number; after: number }
Range of messages to consider for semantic search. Can be a single number or before/after configuration.
workingMemory?:
object
Configuration for working memory.
boolean
enabled?:
boolean
Whether to enable working memory.
string
template?:
string
Template to use for working memory.
'text-stream' | 'tool-call'
type?:
'text-stream' | 'tool-call'
Type of content to use for working memory.
threads?:
object
Thread-specific memory configuration.
boolean
generateTitle?:
boolean
Whether to automatically generate titles for new threads.
TelemetrySettings
Settings for telemetry collection during streaming:
isEnabled?:
boolean
= false
Enable or disable telemetry. Disabled by default while experimental.
recordInputs?:
boolean
= true
Enable or disable input recording. You might want to disable this to avoid recording sensitive information, reduce data transfers, or increase performance.
recordOutputs?:
boolean
= true
Enable or disable output recording. You might want to disable this to avoid recording sensitive information, reduce data transfers, or increase performance.
functionId?:
string
Identifier for this function. Used to group telemetry data by function.
metadata?:
Record<string, AttributeValue>
Additional information to include in the telemetry data. AttributeValue can be string, number, boolean, array of these types, or null.
tracer?:
Tracer
A custom OpenTelemetry tracer instance to use for the telemetry data. See OpenTelemetry documentation for details.
Returns
The return value of the stream() method depends on the options provided, specifically the output option.
PropertiesTable for Return Values
textStream?:
AsyncIterable<string>
Stream of text chunks. Present when output is 'text' (no schema provided) or when using `experimental_output`.
objectStream?:
AsyncIterable<object>
Stream of structured data. Present only when using `output` option with a schema.
partialObjectStream?:
AsyncIterable<object>
Stream of structured data. Present only when using `experimental_output` option.
object?:
Promise<object>
Promise that resolves to the final structured output. Present when using either `output` or `experimental_output` options.
Examples
Basic Text Streaming
const stream = await myAgent.stream([
{ role: "user", content: "Tell me a story." }
]);
for await (const chunk of stream.textStream) {
process.stdout.write(chunk);
}Structured Output Streaming with Thread Context
const schema = {
type: 'object',
properties: {
summary: { type: 'string' },
nextSteps: { type: 'array', items: { type: 'string' } }
},
required: ['summary', 'nextSteps']
};
const response = await myAgent.stream(
"What should we do next?",
{
output: schema,
threadId: "project-123",
onFinish: text => console.log("Finished:", text)
}
);
for await (const chunk of response.textStream) {
console.log(chunk);
}
const result = await response.object;
console.log("Final structured result:", result);The key difference between Agent’s stream() and LLM’s stream() is that Agents maintain conversation context through threadId, can access tools, and integrate with the agent’s memory system.