Class ChatSessionSummaryAgent

Protected additionalToolRequests

Protected chatToolRequestService

Protected contentMatcherProviders

Protected contentMatchers

Protected defaultContentFactory

Protected languageModelRegistry

Protected languageModelService

Protected logger

Protected promptService

Protected systemPromptId

Protected toolCallResponseContentFactory

Protected addContentsToResponse

• addContentsToResponse(languageModelResponse, request): Promise<void>

• Parameters

  • languageModelResponse: LanguageModelResponse
  • request: MutableChatRequestModel

  Returns Promise<void>

Protected addStreamResponse

• addStreamResponse(languageModelResponse, request): Promise<void>

• Parameters

  • languageModelResponse: LanguageModelStreamResponse
  • request: MutableChatRequestModel

  Returns Promise<void>

Protected createToolCallResponseContent

• createToolCallResponseContent(toolCall): ChatResponseContent

• Creates a ToolCallChatResponseContent instance from the provided tool call data.

  This method is called when parsing stream response tokens that contain tool call data. Subclasses can override this method to customize the creation of tool call response contents.

  Parameters

  • toolCall: ToolCall

    The ToolCall.

  Returns ChatResponseContent

  A ChatResponseContent representing the tool call.

Protected getLanguageModel

• getLanguageModel(languageModelPurpose): Promise<LanguageModel>

• Parameters

  • languageModelPurpose: string

  Returns Promise<LanguageModel>

Protected getLanguageModelSelector

• getLanguageModelSelector(languageModelPurpose): LanguageModelRequirement

• Parameters

  • languageModelPurpose: string

  Returns LanguageModelRequirement

Protected getLlmSettings

• getLlmSettings(): undefined | {
      [key: string]: unknown;
  }

• Returns undefined | {
      [key: string]: unknown;
  }

  the settings, such as temperature, to be used in all language model requests. Returns undefined by default.

Protected getMessages

• getMessages(model, includeResponseInProgress?): Promise<LanguageModelMessage[]>

• Parameters

  • model: ChatModel
  • includeResponseInProgress: boolean = false

  Returns Promise<LanguageModelMessage[]>

Protected getSystemMessageDescription

• getSystemMessageDescription(context): Promise<undefined | SystemMessageDescription>

• Parameters

  • context: AIVariableContext

  Returns Promise<undefined | SystemMessageDescription>

Protected handleError

• handleError(request, error): void

• Parameters

  • request: MutableChatRequestModel
  • error: Error

  Returns void

Protected initializeContentMatchers

• initializeContentMatchers(): void

• Returns void

Protected onResponseComplete

• onResponseComplete(request): Promise<void>

• Invoked after the response by the LLM completed successfully.

  The default implementation sets the state of the response to complete. Subclasses may override this method to perform additional actions or keep the response open for processing further requests.

  Parameters

  • request: MutableChatRequestModel

  Returns Promise<void>

Protected parse

• parse(token, request): ChatResponseContent | ChatResponseContent[]

• Parameters

  • token: LanguageModelStreamResponsePart
  • request: MutableChatRequestModel

  Returns ChatResponseContent | ChatResponseContent[]

Protected parseContents

• parseContents(text, request): ChatResponseContent[]

• Parameters

  • text: string
  • request: MutableChatRequestModel

  Returns ChatResponseContent[]

Protected selectLanguageModel

• selectLanguageModel(selector): Promise<LanguageModel>

• Parameters

  • selector: LanguageModelRequirement

  Returns Promise<LanguageModel>

Protected sendLlmRequest

• sendLlmRequest(request, messages, toolRequests, languageModel): Promise<LanguageModelResponse>

• Parameters

  • request: MutableChatRequestModel
  • messages: LanguageModelMessage[]
  • toolRequests: ChatToolRequest[]
  • languageModel: LanguageModel

  Returns Promise<LanguageModelResponse>