Class OpenAiResponseApiUtils

Utility class for handling OpenAI Response API requests and tool calling cycles.

This class encapsulates the complexity of the Response API's multi-turn conversation patterns for tool calling, keeping the main language model class clean and focused.

Index

Constructors

constructor

Methods

convertToolsForResponseApi createSimpleResponseApiStreamIterator handleRequest processMessages processSystemMessages

Constructors

constructor

new OpenAiResponseApiUtils(): OpenAiResponseApiUtils
Returns OpenAiResponseApiUtils

Methods

convertToolsForResponseApi

convertToolsForResponseApi(tools?: ToolRequest[]): undefined | FunctionTool[]
Converts ToolRequest objects to the format expected by the Response API.
Parameters
- Optionaltools: ToolRequest[]
Returns undefined | FunctionTool[]
- Defined in src/node/openai-response-api-utils.ts:143

`Protected`createSimpleResponseApiStreamIterator

createSimpleResponseApiStreamIterator(
    stream: AsyncIterable<ResponseStreamEvent>,
    requestId: string,
    modelId: string,
    tokenUsageService?: TokenUsageService,
    cancellationToken?: CancellationToken,
): AsyncIterable<LanguageModelStreamResponsePart>
Parameters
- stream: AsyncIterable<ResponseStreamEvent>
- requestId: string
- modelId: string
- OptionaltokenUsageService: TokenUsageService
- OptionalcancellationToken: CancellationToken
Returns AsyncIterable<LanguageModelStreamResponsePart>
- Defined in src/node/openai-response-api-utils.ts:166

handleRequest

handleRequest(
    openai: OpenAI,
    request: UserRequest,
    settings: Record<string, unknown>,
    model: string,
    modelUtils: OpenAiModelUtils,
    developerMessageSettings: DeveloperMessageSettings,
    runnerOptions: RunnerOptions,
    modelId: string,
    isStreaming: boolean,
    tokenUsageService?: TokenUsageService,
    cancellationToken?: CancellationToken,
): Promise<LanguageModelResponse>
Handles Response API requests with proper tool calling cycles. Works for both streaming and non-streaming cases.
Parameters
- openai: OpenAI
- request: UserRequest
- settings: Record<string, unknown>
- model: string
- modelUtils: OpenAiModelUtils
- developerMessageSettings: DeveloperMessageSettings
- runnerOptions: RunnerOptions
- modelId: string
- isStreaming: boolean
- OptionaltokenUsageService: TokenUsageService
- OptionalcancellationToken: CancellationToken
Returns Promise<LanguageModelResponse>
- Defined in src/node/openai-response-api-utils.ts:67

processMessages

processMessages(
    messages: LanguageModelMessage[],
    developerMessageSettings: DeveloperMessageSettings,
    model: string,
): { input: ResponseInputItem[]; instructions?: string }
Processes the provided list of messages by applying system message adjustments and converting them directly to the format expected by the OpenAI Response API.

This method converts messages directly without going through ChatCompletionMessageParam types.
Parameters
- messages: LanguageModelMessage[]
  the list of messages to process.
- developerMessageSettings: DeveloperMessageSettings
  how system and developer messages are handled during processing.
- model: string
  the OpenAI model identifier. Currently not used, but allows subclasses to implement model-specific behavior.
Returns { input: ResponseInputItem[]; instructions?: string }
an object containing instructions and input formatted for the Response API.
- Defined in src/node/openai-response-api-utils.ts:220

`Protected`processSystemMessages

processSystemMessages(
messages: LanguageModelMessage[],
developerMessageSettings: DeveloperMessageSettings,
): LanguageModelMessage[]
Parameters
- messages: LanguageModelMessage[]
- developerMessageSettings: DeveloperMessageSettings
Returns LanguageModelMessage[]
- Defined in src/node/openai-response-api-utils.ts:300

Class OpenAiResponseApiUtils

Index

Constructors

Methods

Constructors

constructor

Returns OpenAiResponseApiUtils

Methods

convertToolsForResponseApi

Parameters

Returns undefined | FunctionTool[]

ProtectedcreateSimpleResponseApiStreamIterator

Parameters

Returns AsyncIterable<LanguageModelStreamResponsePart>

handleRequest

Parameters

Returns Promise<LanguageModelResponse>

processMessages

Parameters

Returns { input: ResponseInputItem[]; instructions?: string }

ProtectedprocessSystemMessages

Parameters

Returns LanguageModelMessage[]

Settings

On This Page

`Protected`createSimpleResponseApiStreamIterator

`Protected`processSystemMessages