Function CountTokenRealtime

service/token_counter.go:287–339

(info *relaycommon.RelayInfo, request dto.RealtimeEvent, model string)

}

func CountTokenRealtime(info *relaycommon.RelayInfo, request dto.RealtimeEvent, model string) (int, int, error) {
	audioToken := 0
	textToken := 0
	switch request.Type {
	case dto.RealtimeEventTypeSessionUpdate:
		if request.Session != nil {
			msgTokens := CountTextToken(request.Session.Instructions, model)
			textToken += msgTokens
		}
	case dto.RealtimeEventResponseAudioDelta:
		// count audio token
		atk, err := CountAudioTokenOutput(request.Delta, info.OutputAudioFormat)
		if err != nil {
			return 0, 0, fmt.Errorf("error counting audio token: %v", err)
		}
		audioToken += atk
	case dto.RealtimeEventResponseAudioTranscriptionDelta, dto.RealtimeEventResponseFunctionCallArgumentsDelta:
		// count text token
		tkm := CountTextToken(request.Delta, model)
		textToken += tkm
	case dto.RealtimeEventInputAudioBufferAppend:
		// count audio token
		atk, err := CountAudioTokenInput(request.Audio, info.InputAudioFormat)
		if err != nil {
			return 0, 0, fmt.Errorf("error counting audio token: %v", err)
		}
		audioToken += atk
	case dto.RealtimeEventConversationItemCreated:
		if request.Item != nil {
			switch request.Item.Type {
			case "message":
				for _, content := range request.Item.Content {
					if content.Type == "input_text" {
						tokens := CountTextToken(content.Text, model)
						textToken += tokens
					}
				}
			}
		}
	case dto.RealtimeEventTypeResponseDone:
		// count tools token
		if !info.IsFirstRequest {
			if info.RealtimeTools != nil && len(info.RealtimeTools) > 0 {
				for _, tool := range info.RealtimeTools {
					toolTokens := CountTokenInput(tool, model)
					textToken += 8
					textToken += toolTokens
				}
			}
		}
	}
	return textToken, audioToken, nil
}

func CountTokenMessages(info *relaycommon.RelayInfo, messages []dto.Message, model string, stream bool) (int, error) {
	//recover when panic