// Copyright 2024 Google LLC // // Licensed under the Apache License, Version 2.0 (the "License"); // you may not use this file except in compliance with the License. // You may obtain a copy of the License at // // http://www.apache.org/licenses/LICENSE-2.0 // // Unless required by applicable law or agreed to in writing, software // distributed under the License is distributed on an "AS IS" BASIS, // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. // See the License for the specific language governing permissions and // limitations under the License. syntax = "proto3"; package google.cloud.dialogflow.cx.v3beta1; import "google/api/field_behavior.proto"; import "google/cloud/dialogflow/cx/v3beta1/tool_call.proto"; import "google/protobuf/struct.proto"; option cc_enable_arenas = true; option csharp_namespace = "Google.Cloud.Dialogflow.Cx.V3Beta1"; option go_package = "cloud.google.com/go/dialogflow/cx/apiv3beta1/cxpb;cxpb"; option java_multiple_files = true; option java_outer_classname = "ResponseMessageProto"; option java_package = "com.google.cloud.dialogflow.cx.v3beta1"; option objc_class_prefix = "DF"; option ruby_package = "Google::Cloud::Dialogflow::CX::V3beta1"; // Represents a response message that can be returned by a conversational agent. // // Response messages are also used for output audio synthesis. The approach is // as follows: // // * If at least one OutputAudioText response is present, then all // OutputAudioText responses are linearly concatenated, and the result is used // for output audio synthesis. // * If the OutputAudioText responses are a mixture of text and SSML, then the // concatenated result is treated as SSML; otherwise, the result is treated as // either text or SSML as appropriate. The agent designer should ideally use // either text or SSML consistently throughout the bot design. // * Otherwise, all Text responses are linearly concatenated, and the result is // used for output audio synthesis. // // This approach allows for more sophisticated user experience scenarios, where // the text displayed to the user may differ from what is heard. message ResponseMessage { // The text response message. message Text { // Required. A collection of text responses. repeated string text = 1 [(google.api.field_behavior) = REQUIRED]; // Output only. Whether the playback of this message can be interrupted by // the end user's speech and the client can then starts the next Dialogflow // request. bool allow_playback_interruption = 2 [(google.api.field_behavior) = OUTPUT_ONLY]; } // Indicates that the conversation should be handed off to a live agent. // // Dialogflow only uses this to determine which conversations were handed off // to a human agent for measurement purposes. What else to do with this signal // is up to you and your handoff procedures. // // You may set this, for example: // * In the // [entry_fulfillment][google.cloud.dialogflow.cx.v3beta1.Page.entry_fulfillment] // of a [Page][google.cloud.dialogflow.cx.v3beta1.Page] if // entering the page indicates something went extremely wrong in the // conversation. // * In a webhook response when you determine that the customer issue can only // be handled by a human. message LiveAgentHandoff { // Custom metadata for your handoff procedure. Dialogflow doesn't impose // any structure on this. google.protobuf.Struct metadata = 1; } // Indicates that the conversation succeeded, i.e., the bot handled the issue // that the customer talked to it about. // // Dialogflow only uses this to determine which conversations should be // counted as successful and doesn't process the metadata in this message in // any way. Note that Dialogflow also considers conversations that get to the // conversation end page as successful even if they don't return // [ConversationSuccess][google.cloud.dialogflow.cx.v3beta1.ResponseMessage.ConversationSuccess]. // // You may set this, for example: // * In the // [entry_fulfillment][google.cloud.dialogflow.cx.v3beta1.Page.entry_fulfillment] // of a [Page][google.cloud.dialogflow.cx.v3beta1.Page] if // entering the page indicates that the conversation succeeded. // * In a webhook response when you determine that you handled the customer // issue. message ConversationSuccess { // Custom metadata. Dialogflow doesn't impose any structure on this. google.protobuf.Struct metadata = 1; } // A text or ssml response that is preferentially used for TTS output audio // synthesis, as described in the comment on the ResponseMessage message. message OutputAudioText { // The source, which is either plain text or SSML. oneof source { // The raw text to be synthesized. string text = 1; // The SSML text to be synthesized. For more information, see // [SSML](/speech/text-to-speech/docs/ssml). string ssml = 2; } // Output only. Whether the playback of this message can be interrupted by // the end user's speech and the client can then starts the next Dialogflow // request. bool allow_playback_interruption = 3 [(google.api.field_behavior) = OUTPUT_ONLY]; } // Indicates that interaction with the Dialogflow agent has ended. // This message is generated by Dialogflow only and not supposed to be // defined by the user. message EndInteraction {} // Specifies an audio clip to be played by the client as part of the response. message PlayAudio { // Required. URI of the audio clip. Dialogflow does not impose any // validation on this value. It is specific to the client that reads it. string audio_uri = 1 [(google.api.field_behavior) = REQUIRED]; // Output only. Whether the playback of this message can be interrupted by // the end user's speech and the client can then starts the next Dialogflow // request. bool allow_playback_interruption = 2 [(google.api.field_behavior) = OUTPUT_ONLY]; } // Represents an audio message that is composed of both segments // synthesized from the Dialogflow agent prompts and ones hosted externally // at the specified URIs. // The external URIs are specified via // [play_audio][google.cloud.dialogflow.cx.v3beta1.ResponseMessage.play_audio]. // This message is generated by Dialogflow only and not supposed to be // defined by the user. message MixedAudio { // Represents one segment of audio. message Segment { // Content of the segment. oneof content { // Raw audio synthesized from the Dialogflow agent's response using // the output config specified in the request. bytes audio = 1; // Client-specific URI that points to an audio clip accessible to the // client. Dialogflow does not impose any validation on it. string uri = 2; } // Output only. Whether the playback of this segment can be interrupted by // the end user's speech and the client should then start the next // Dialogflow request. bool allow_playback_interruption = 3 [(google.api.field_behavior) = OUTPUT_ONLY]; } // Segments this audio response is composed of. repeated Segment segments = 1; } // Represents the signal that telles the client to transfer the phone call // connected to the agent to a third-party endpoint. message TelephonyTransferCall { // Endpoint to transfer the call to. oneof endpoint { // Transfer the call to a phone number // in [E.164 format](https://en.wikipedia.org/wiki/E.164). string phone_number = 1; } } // Represents info card response. If the response contains generative // knowledge prediction, Dialogflow will return a payload with Infobot // Messenger compatible info card. // // Otherwise, the info card response is skipped. message KnowledgeInfoCard {} // Required. The rich response message. oneof message { // Returns a text response. Text text = 1; // Returns a response containing a custom, platform-specific payload. google.protobuf.Struct payload = 2; // Indicates that the conversation succeeded. ConversationSuccess conversation_success = 9; // A text or ssml response that is preferentially used for TTS output audio // synthesis, as described in the comment on the ResponseMessage message. OutputAudioText output_audio_text = 8; // Hands off conversation to a human agent. LiveAgentHandoff live_agent_handoff = 10; // Output only. A signal that indicates the interaction with the Dialogflow // agent has ended. This message is generated by Dialogflow only when the // conversation reaches `END_SESSION` page. It is not supposed to be defined // by the user. // // It's guaranteed that there is at most one such message in each response. EndInteraction end_interaction = 11 [(google.api.field_behavior) = OUTPUT_ONLY]; // Signal that the client should play an audio clip hosted at a // client-specific URI. Dialogflow uses this to construct // [mixed_audio][google.cloud.dialogflow.cx.v3beta1.ResponseMessage.mixed_audio]. // However, Dialogflow itself does not try to read or process the URI in any // way. PlayAudio play_audio = 12; // Output only. An audio response message composed of both the synthesized // Dialogflow agent responses and responses defined via // [play_audio][google.cloud.dialogflow.cx.v3beta1.ResponseMessage.play_audio]. // This message is generated by Dialogflow only and not supposed to be // defined by the user. MixedAudio mixed_audio = 13 [(google.api.field_behavior) = OUTPUT_ONLY]; // A signal that the client should transfer the phone call connected to // this agent to a third-party endpoint. TelephonyTransferCall telephony_transfer_call = 18; // Represents info card for knowledge answers, to be better rendered in // Dialogflow Messenger. KnowledgeInfoCard knowledge_info_card = 20; // Returns the definition of a tool call that should be executed by the // client. google.cloud.dialogflow.cx.v3beta1.ToolCall tool_call = 22; } // The channel which the response is associated with. Clients can specify the // channel via // [QueryParameters.channel][google.cloud.dialogflow.cx.v3beta1.QueryParameters.channel], // and only associated channel response will be returned. string channel = 19; }