xref: /aosp_15_r20/external/googleapis/google/assistant/embedded/v1alpha2/embedded_assistant.proto (revision d5c09012810ac0c9f33fe448fb6da8260d444cc9)

// Copyright 2018 Google Inc.
//
// 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.assistant.embedded.v1alpha2;

import "google/api/annotations.proto";
import "google/type/latlng.proto";

option go_package = "google.golang.org/genproto/googleapis/assistant/embedded/v1alpha2;embedded";
option java_multiple_files = true;
option java_outer_classname = "AssistantProto";
option java_package = "com.google.assistant.embedded.v1alpha2";
option objc_class_prefix = "ASTSDK";

// Service that implements the Google Assistant API.
service EmbeddedAssistant {
  // Initiates or continues a conversation with the embedded Assistant Service.
  // Each call performs one round-trip, sending an audio request to the service
  // and receiving the audio response. Uses bidirectional streaming to receive
  // results, such as the `END_OF_UTTERANCE` event, while sending audio.
  //
  // A conversation is one or more gRPC connections, each consisting of several
  // streamed requests and responses.
  // For example, the user says *Add to my shopping list* and the Assistant
  // responds *What do you want to add?*. The sequence of streamed requests and
  // responses in the first gRPC message could be:
  //
  // *   AssistRequest.config
  // *   AssistRequest.audio_in
  // *   AssistRequest.audio_in
  // *   AssistRequest.audio_in
  // *   AssistRequest.audio_in
  // *   AssistResponse.event_type.END_OF_UTTERANCE
  // *   AssistResponse.speech_results.transcript "add to my shopping list"
  // *   AssistResponse.dialog_state_out.microphone_mode.DIALOG_FOLLOW_ON
  // *   AssistResponse.audio_out
  // *   AssistResponse.audio_out
  // *   AssistResponse.audio_out
  //
  //
  // The user then says *bagels* and the Assistant responds
  // *OK, I've added bagels to your shopping list*. This is sent as another gRPC
  // connection call to the `Assist` method, again with streamed requests and
  // responses, such as:
  //
  // *   AssistRequest.config
  // *   AssistRequest.audio_in
  // *   AssistRequest.audio_in
  // *   AssistRequest.audio_in
  // *   AssistResponse.event_type.END_OF_UTTERANCE
  // *   AssistResponse.dialog_state_out.microphone_mode.CLOSE_MICROPHONE
  // *   AssistResponse.audio_out
  // *   AssistResponse.audio_out
  // *   AssistResponse.audio_out
  // *   AssistResponse.audio_out
  //
  // Although the precise order of responses is not guaranteed, sequential
  // `AssistResponse.audio_out` messages will always contain sequential portions
  // of audio.
  rpc Assist(stream AssistRequest) returns (stream AssistResponse);
}

// The top-level message sent by the client. Clients must send at least two, and
// typically numerous `AssistRequest` messages. The first message must
// contain a `config` message and must not contain `audio_in` data. All
// subsequent messages must contain `audio_in` data and must not contain a
// `config` message.
message AssistRequest {
  // Exactly one of these fields must be specified in each `AssistRequest`.
  oneof type {
    // The `config` message provides information to the recognizer that
    // specifies how to process the request.
    // The first `AssistRequest` message must contain a `config` message.
    AssistConfig config = 1;

    // The audio data to be recognized. Sequential chunks of audio data are sent
    // in sequential `AssistRequest` messages. The first `AssistRequest`
    // message must not contain `audio_in` data and all subsequent
    // `AssistRequest` messages must contain `audio_in` data. The audio bytes
    // must be encoded as specified in `AudioInConfig`.
    // Audio must be sent at approximately real-time (16000 samples per second).
    // An error will be returned if audio is sent significantly faster or
    // slower.
    bytes audio_in = 2;
  }
}

// The top-level message received by the client. A series of one or more
// `AssistResponse` messages are streamed back to the client.
message AssistResponse {
  // Indicates the type of event.
  enum EventType {
    // No event specified.
    EVENT_TYPE_UNSPECIFIED = 0;

    // This event indicates that the server has detected the end of the user's
    // speech utterance and expects no additional speech. Therefore, the server
    // will not process additional audio (although it may subsequently return
    // additional results). The client should stop sending additional audio
    // data, half-close the gRPC connection, and wait for any additional results
    // until the server closes the gRPC connection.
    END_OF_UTTERANCE = 1;
  }

  // *Output-only* Indicates the type of event.
  EventType event_type = 1;

  // *Output-only* The audio containing the Assistant's response to the query.
  AudioOut audio_out = 3;

  // *Output-only* Contains the Assistant's visual response to the query.
  ScreenOut screen_out = 4;

  // *Output-only* Contains the action triggered by the query with the
  // appropriate payloads and semantic parsing.
  DeviceAction device_action = 6;

  // *Output-only* This repeated list contains zero or more speech recognition
  // results that correspond to consecutive portions of the audio currently
  // being processed, starting with the portion corresponding to the earliest
  // audio (and most stable portion) to the portion corresponding to the most
  // recent audio. The strings can be concatenated to view the full
  // in-progress response. When the speech recognition completes, this list
  // will contain one item with `stability` of `1.0`.
  repeated SpeechRecognitionResult speech_results = 2;

  // *Output-only* Contains output related to the user's query.
  DialogStateOut dialog_state_out = 5;

  // *Output-only* Debugging info for developer. Only returned if request set
  // `return_debug_info` to true.
  DebugInfo debug_info = 8;
}

// Debug info for developer. Only returned if request set `return_debug_info`
// to true.
message DebugInfo {
  // The original JSON response from an Action-on-Google agent to Google server.
  // See
  // https://developers.google.com/actions/reference/rest/Shared.Types/AppResponse.
  // It will only be populated if the request maker owns the AoG project and the
  // AoG project is in preview mode.
  string aog_agent_to_assistant_json = 1;
}

// Specifies how to process the `AssistRequest` messages.
message AssistConfig {
  oneof type {
    // Specifies how to process the subsequent incoming audio. Required if
    // [AssistRequest.audio_in][google.assistant.embedded.v1alpha2.AssistRequest.audio_in]
    // bytes will be provided in subsequent requests.
    AudioInConfig audio_in_config = 1;

    // The text input to be sent to the Assistant. This can be populated from a
    // text interface if audio input is not available.
    string text_query = 6;
  }

  // *Required* Specifies how to format the audio that will be returned.
  AudioOutConfig audio_out_config = 2;

  // *Optional* Specifies the desired format to use when server returns a
  // visual screen response.
  ScreenOutConfig screen_out_config = 8;

  // *Required* Represents the current dialog state.
  DialogStateIn dialog_state_in = 3;

  // Device configuration that uniquely identifies a specific device.
  DeviceConfig device_config = 4;

  // *Optional* Debugging parameters for the whole `Assist` RPC.
  DebugConfig debug_config = 5;
}

// Specifies how to process the `audio_in` data that will be provided in
// subsequent requests. For recommended settings, see the Google Assistant SDK
// [best
// practices](https://developers.google.com/assistant/sdk/guides/service/python/best-practices/audio).
message AudioInConfig {
  // Audio encoding of the data sent in the audio message.
  // Audio must be one-channel (mono).
  enum Encoding {
    // Not specified. Will return result [google.rpc.Code.INVALID_ARGUMENT][].
    ENCODING_UNSPECIFIED = 0;

    // Uncompressed 16-bit signed little-endian samples (Linear PCM).
    // This encoding includes no header, only the raw audio bytes.
    LINEAR16 = 1;

    // [`FLAC`](https://xiph.org/flac/documentation.html) (Free Lossless Audio
    // Codec) is the recommended encoding because it is
    // lossless--therefore recognition is not compromised--and
    // requires only about half the bandwidth of `LINEAR16`. This encoding
    // includes the `FLAC` stream header followed by audio data. It supports
    // 16-bit and 24-bit samples, however, not all fields in `STREAMINFO` are
    // supported.
    FLAC = 2;
  }

  // *Required* Encoding of audio data sent in all `audio_in` messages.
  Encoding encoding = 1;

  // *Required* Sample rate (in Hertz) of the audio data sent in all `audio_in`
  // messages. Valid values are from 16000-24000, but 16000 is optimal.
  // For best results, set the sampling rate of the audio source to 16000 Hz.
  // If that's not possible, use the native sample rate of the audio source
  // (instead of re-sampling).
  int32 sample_rate_hertz = 2;
}

// Specifies the desired format for the server to use when it returns
// `audio_out` messages.
message AudioOutConfig {
  // Audio encoding of the data returned in the audio message. All encodings are
  // raw audio bytes with no header, except as indicated below.
  enum Encoding {
    // Not specified. Will return result [google.rpc.Code.INVALID_ARGUMENT][].
    ENCODING_UNSPECIFIED = 0;

    // Uncompressed 16-bit signed little-endian samples (Linear PCM).
    LINEAR16 = 1;

    // MP3 audio encoding. The sample rate is encoded in the payload.
    MP3 = 2;

    // Opus-encoded audio wrapped in an ogg container. The result will be a
    // file which can be played natively on Android and in some browsers (such
    // as Chrome). The quality of the encoding is considerably higher than MP3
    // while using the same bitrate. The sample rate is encoded in the payload.
    OPUS_IN_OGG = 3;
  }

  // *Required* The encoding of audio data to be returned in all `audio_out`
  // messages.
  Encoding encoding = 1;

  // *Required* The sample rate in Hertz of the audio data returned in
  // `audio_out` messages. Valid values are: 16000-24000.
  int32 sample_rate_hertz = 2;

  // *Required* Current volume setting of the device's audio output.
  // Valid values are 1 to 100 (corresponding to 1% to 100%).
  int32 volume_percentage = 3;
}

// Specifies the desired format for the server to use when it returns
// `screen_out` response.
message ScreenOutConfig {
  // Possible modes for visual screen-output on the device.
  enum ScreenMode {
    // No video mode specified.
    // The Assistant may respond as if in `OFF` mode.
    SCREEN_MODE_UNSPECIFIED = 0;

    // Screen is off (or has brightness or other settings set so low it is
    // not visible). The Assistant will typically not return a screen response
    // in this mode.
    OFF = 1;

    // The Assistant will typically return a partial-screen response in this
    // mode.
    PLAYING = 3;
  }

  // Current visual screen-mode for the device while issuing the query.
  ScreenMode screen_mode = 1;
}

// Provides information about the current dialog state.
message DialogStateIn {
  // *Required* This field must always be set to the
  // [DialogStateOut.conversation_state][google.assistant.embedded.v1alpha2.DialogStateOut.conversation_state]
  // value that was returned in the prior `Assist` RPC. It should only be
  // omitted (field not set) if there was no prior `Assist` RPC because this is
  // the first `Assist` RPC made by this device after it was first setup and/or
  // a factory-default reset.
  bytes conversation_state = 1;

  // *Required* Language of the request in
  // [IETF BCP 47 syntax](https://tools.ietf.org/html/bcp47) (for example,
  // "en-US"). See [Language
  // Support](https://developers.google.com/assistant/sdk/reference/rpc/languages)
  // for more information. If you have selected a language for this `device_id`
  // using the
  // [Settings](https://developers.google.com/assistant/sdk/reference/assistant-app/assistant-settings)
  // menu in your phone's Google Assistant app, that selection will override
  // this value.
  string language_code = 2;

  // *Optional* Location of the device where the query originated.
  DeviceLocation device_location = 5;

  // *Optional* If true, the server will treat the request as a new conversation
  // and not use state from the prior request. Set this field to true when the
  // conversation should be restarted, such as after a device reboot, or after a
  // significant lapse of time since the prior query.
  bool is_new_conversation = 7;
}

// *Required* Fields that identify the device to the Assistant.
//
// See also:
//
// *   [Register a Device - REST
// API](https://developers.google.com/assistant/sdk/reference/device-registration/register-device-manual)
// *   [Device Model and Instance
// Schemas](https://developers.google.com/assistant/sdk/reference/device-registration/model-and-instance-schemas)
// *   [Device
// Proto](https://developers.google.com/assistant/sdk/reference/rpc/google.assistant.devices.v1alpha2#device)
message DeviceConfig {
  // *Required* Unique identifier for the device. The id length must be 128
  // characters or less. Example: DBCDW098234. This MUST match the device_id
  // returned from device registration. This device_id is used to match against
  // the user's registered devices to lookup the supported traits and
  // capabilities of this device. This information should not change across
  // device reboots. However, it should not be saved across
  // factory-default resets.
  string device_id = 1;

  // *Required* Unique identifier for the device model. The combination of
  // device_model_id and device_id must have been previously associated through
  // device registration.
  string device_model_id = 3;
}

// The audio containing the Assistant's response to the query. Sequential chunks
// of audio data are received in sequential `AssistResponse` messages.
message AudioOut {
  // *Output-only* The audio data containing the Assistant's response to the
  // query. Sequential chunks of audio data are received in sequential
  // `AssistResponse` messages.
  bytes audio_data = 1;
}

// The Assistant's visual output response to query. Enabled by
// `screen_out_config`.
message ScreenOut {
  // Possible formats of the screen data.
  enum Format {
    // No format specified.
    FORMAT_UNSPECIFIED = 0;

    // Data will contain a fully-formed HTML5 layout encoded in UTF-8, e.g.
    // `<html><body><div>...</div></body></html>`. It is intended to be rendered
    // along with the audio response. Note that HTML5 doctype should be included
    // in the actual HTML data.
    HTML = 1;
  }

  // *Output-only* The format of the provided screen data.
  Format format = 1;

  // *Output-only* The raw screen data to be displayed as the result of the
  // Assistant query.
  bytes data = 2;
}

// The response returned to the device if the user has triggered a Device
// Action. For example, a device which supports the query *Turn on the light*
// would receive a `DeviceAction` with a JSON payload containing the semantics
// of the request.
message DeviceAction {
  // JSON containing the device command response generated from the triggered
  // Device Action grammar. The format is given by the
  // `action.devices.EXECUTE` intent for a given
  // [trait](https://developers.google.com/assistant/sdk/reference/traits/).
  string device_request_json = 1;
}

// The estimated transcription of a phrase the user has spoken. This could be
// a single segment or the full guess of the user's spoken query.
message SpeechRecognitionResult {
  // *Output-only* Transcript text representing the words that the user spoke.
  string transcript = 1;

  // *Output-only* An estimate of the likelihood that the Assistant will not
  // change its guess about this result. Values range from 0.0 (completely
  // unstable) to 1.0 (completely stable and final). The default of 0.0 is a
  // sentinel value indicating `stability` was not set.
  float stability = 2;
}

// The dialog state resulting from the user's query. Multiple of these messages
// may be received.
message DialogStateOut {
  // Possible states of the microphone after a `Assist` RPC completes.
  enum MicrophoneMode {
    // No mode specified.
    MICROPHONE_MODE_UNSPECIFIED = 0;

    // The service is not expecting a follow-on question from the user.
    // The microphone should remain off until the user re-activates it.
    CLOSE_MICROPHONE = 1;

    // The service is expecting a follow-on question from the user. The
    // microphone should be re-opened when the `AudioOut` playback completes
    // (by starting a new `Assist` RPC call to send the new audio).
    DIALOG_FOLLOW_ON = 2;
  }

  // *Output-only* Supplemental display text from the Assistant. This could be
  // the same as the speech spoken in `AssistResponse.audio_out` or it could
  // be some additional information which aids the user's understanding.
  string supplemental_display_text = 1;

  // *Output-only* State information for the subsequent `Assist` RPC. This
  // value should be saved in the client and returned in the
  // [`DialogStateIn.conversation_state`](#dialogstatein) field with the next
  // `Assist` RPC. (The client does not need to interpret or otherwise use this
  // value.) This information should be saved across device reboots. However,
  // this value should be cleared (not saved in the client) during a
  // factory-default reset.
  bytes conversation_state = 2;

  // *Output-only* Specifies the mode of the microphone after this `Assist`
  // RPC is processed.
  MicrophoneMode microphone_mode = 3;

  // *Output-only* Updated volume level. The value will be 0 or omitted
  // (indicating no change) unless a voice command such as *Increase the volume*
  // or *Set volume level 4* was recognized, in which case the value will be
  // between 1 and 100 (corresponding to the new volume level of 1% to 100%).
  // Typically, a client should use this volume level when playing the
  // `audio_out` data, and retain this value as the current volume level and
  // supply it in the `AudioOutConfig` of the next `AssistRequest`. (Some
  // clients may also implement other ways to allow the current volume level to
  // be changed, for example, by providing a knob that the user can turn.)
  int32 volume_percentage = 4;
}

// Debugging parameters for the current request.
message DebugConfig {
  // When this field is set to true, the `debug_info` field in `AssistResponse`
  // may be populated. However it will significantly increase latency of
  // responses. Do not set this field true in production code.
  bool return_debug_info = 6;
}

// There are three sources of locations. They are used with this precedence:
//
// 1. This `DeviceLocation`, which is primarily used for mobile devices with
//    GPS .
// 2. Location specified by the user during device setup; this is per-user, per
//    device. This location is used if `DeviceLocation` is not specified.
// 3. Inferred location based on IP address. This is used only if neither of the
//    above are specified.
message DeviceLocation {
  oneof type {
    // Latitude and longitude of device.
    google.type.LatLng coordinates = 1;
  }
}