Class OrchestrationStreamResponse<T>

constructor

• new OrchestrationStreamResponse<T>(): OrchestrationStreamResponse<T>

  Type Parameters

  • T

  Returns OrchestrationStreamResponse<T>

  Deprecated

  Since v2.6.0. Provide an HttpResponse parameter when constructing OrchestrationStreamResponse. This constructor overload will be removed in v3.0.0. Creates an orchestration stream response.

• new OrchestrationStreamResponse<T>(
      rawResponse: HttpResponse,
  ): OrchestrationStreamResponse<T>

  Creates an orchestration stream response.

  Type Parameters

  • T

  Parameters

  • rawResponse: HttpResponse

    The raw HTTP response from the orchestration service. SSE data is not part of the immediate response.

  Returns OrchestrationStreamResponse<T>

_data

_openStream

rawResponse

• get rawResponse(): HttpResponse

  Gets the raw HTTP response from the orchestration service. SSE data is not part of the immediate response.

  Returns HttpResponse

  The raw HTTP response.

  Throws

  When OrchestrationStreamResponse was constructed without a raw response parameter (deprecated).

stream

• get stream(): OrchestrationStream<T>

  Returns OrchestrationStream<T>

• set stream(stream: OrchestrationStream<T>): void
  Internal

  Parameters

  • stream: OrchestrationStream<T>

  Returns void

findChoiceByIndex

• findChoiceByIndex(index: number): LlmChoice | undefined

  Parses the response and returns the choice by index.

  Parameters

  • index: number

    The index of the choice to find.

  Returns LlmChoice | undefined

  An LLMChoice object associated with the index.

getAllMessages

• getAllMessages(choiceIndex?: number): ChatMessages | undefined

  Messages that can be used for subsequent prompts as message history. When reasoning content is present, it is automatically included in the returned messages. Pass the result directly as messagesHistory in the next request to maintain reasoning context. Only available after the stream has been fully consumed.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to parse.

  Returns ChatMessages | undefined

  A list of all messages including any reasoning content, or undefined if the stream is still open.

getAssistantMessage

• getAssistantMessage(choiceIndex?: number): AssistantChatMessage | undefined

  Gets the assistant message from the response.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to use (default is 0).

  Returns AssistantChatMessage | undefined

  The assistant message.

getCitations

• getCitations(): Citation[] | undefined

  Gets the citations from the orchestration response. Citations are returned by models like Perplexity Sonar that provide source references.

  Returns Citation[] | undefined

  The citations, or undefined if there are none.

getContent

• getContent(choiceIndex?: number): string | undefined

  Parses the orchestration response and returns the content. If the response was filtered, an error is thrown.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to parse.

  Returns string | undefined

  The message content.

getFinishReason

• getFinishReason(choiceIndex?: number): string | undefined

  Gets the finish reason for a specific choice index.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to get the finish reason for.

  Returns string | undefined

  The finish reason for the specified choice index.

getIntermediateFailures

• getIntermediateFailures(): OrchestrationError[] | undefined

  Gets the intermediate failures from the orchestration response. When using module fallback, this contains errors from module configurations that failed before a successful one was found.

  Returns OrchestrationError[] | undefined

  The intermediate failures, or undefined if there were none.

getIntermediateResults

• getIntermediateResults(): ModuleResults | undefined

  Gets the intermediate results from the orchestration response.

  Returns ModuleResults | undefined

  The intermediate results.

getReasoningContent

• getReasoningContent(choiceIndex?: number): string[] | undefined

  Parses the orchestration stream response and returns the accumulated reasoning content generated by the model. Only available after the stream has been fully consumed. Returns only the user-visible reasoning text; encrypted or redacted reasoning blocks are excluded. To get reasoning content incrementally during streaming, use getDeltaReasoningContent on each chunk instead.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to parse.

  Returns string[] | undefined

  The content of each reasoning block as an array, or undefined if no reasoning content is present.

getRefusal

• getRefusal(choiceIndex?: number): string | undefined

  Parses the orchestration response and returns the refusal message generated by the model.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to parse.

  Returns string | undefined

  The refusal string.

getRequestId

• getRequestId(): string | undefined

  Gets the request ID for the stream response.

  Returns string | undefined

  The request ID, or undefined if the first chunk has not been received yet.

getTokenUsage

• getTokenUsage(): TokenUsage | undefined

  Gets the token usage for the response.

  Returns TokenUsage | undefined

  The token usage for the response.

getToolCalls

• getToolCalls(choiceIndex?: number): MessageToolCalls | undefined

  Parses the orchestration response and returns the tool calls generated by the model.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to parse.

  Returns MessageToolCalls | undefined

  The message tool calls.