Interface: InvokeFunctionArgs<Input, Output, Stream>

Arguments for the invoke function.

Type parameters

Name	Type
`Input`	`Input`
`Output`	`Output`
`Stream`	extends `boolean` = `false`

Properties

function_id

• Optional function_id: string

The ID of the function to invoke.

globalFunction

• Optional globalFunction: string

The name of the global function to invoke.

input

• input: Input

The input to the function. This will be logged as the input field in the span.

• Optional messages: ({ content: {} ; name?: string ; role: "system" } | { content: {} ; name?: string ; role: "user" } | { content?: null | string | { cache_control?: { type: "ephemeral" } ; text: string ; type: "text" }[] ; function_call?: { arguments: string ; name: string } ; name?: string ; reasoning?: { content?: string ; id?: string }[] ; role: "assistant" ; tool_calls?: { function: { arguments: string ; name: string } ; id: string ; type: "function" }[] } | { content: {} ; role: "tool" ; tool_call_id: string } | { content: null | string ; name: string ; role: "function" } | { content?: null | string ; role: "model" })[]

Additional OpenAI-style messages to add to the prompt (only works for llm functions).

metadata

• Optional metadata: Record<string, unknown>

Additional metadata to add to the span. This will be logged as the metadata field in the span. It will also be available as the {{metadata}} field in the prompt and as the metadata argument to the function.

mode

• Optional mode: "auto" | "parallel"

The mode of the function. If "auto", will return a string if the function returns a string, and a JSON object otherwise. If "parallel", will return an array of JSON objects with one object per tool call.

parent

• Optional parent: string | Exportable

The parent of the function. This can be an existing span, logger, or experiment, or the output of .export() if you are distributed tracing. If unspecified, will use the same semantics as traced() to determine the parent and no-op if not in a tracing context.

projectName

• Optional projectName: string

The name of the project containing the function to invoke.

promptSessionFunctionId

• Optional promptSessionFunctionId: string

The ID of the function in the prompt session to invoke.

promptSessionId

• Optional promptSessionId: string

The ID of the prompt session to invoke the function from.

schema

• Optional schema: Stream extends true ? never : ZodType<Output, ZodTypeDef, Output>

A Zod schema to validate the output of the function and return a typed value. This is only used if stream is false.

slug

• Optional slug: string

The slug of the function to invoke.

state

• Optional state: BraintrustState

(Advanced) This parameter allows you to pass in a custom login state. This is useful for multi-tenant environments where you are running functions from different Braintrust organizations.

stream

• Optional stream: Stream

Whether to stream the function's output. If true, the function will return a BraintrustStream, otherwise it will return the output of the function as a JSON object.

strict

• Optional strict: boolean

Whether to use strict mode for the function. If true, the function will throw an error if the variable names in the prompt do not match the input keys.

version

• Optional version: string

The version of the function to invoke.