datalog.proto

// Copyright 2021 AI Redefined Inc. <dev+cogment@ai-r.com>
//
// 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 cogmentAPI;

import "cogment/api/common.proto";
import "cogment/api/environment.proto";

import "google/protobuf/any.proto";

service DatalogSP {
  // Expected headers:
  // - trial-id
  // - user-id
  rpc RunTrialDatalog(stream RunTrialDatalogInput) returns (stream RunTrialDatalogOutput) {}

  // Expected headers: None
  rpc Version(VersionRequest) returns (VersionInfo) {}
}

// Received by datalog service on rpc call
message RunTrialDatalogInput {
  oneof msg {
    TrialParams trial_params = 1;
    DatalogSample sample = 2;
  }
}

// Sent by datalog service on rpc call
message RunTrialDatalogOutput {}

message SampleInfo {
  uint64 tick_id = 1;
  fixed64 timestamp = 2;
  TrialState state = 3;

  // Events that happened during this sample's tick.  E.g. Terminate call, agent disconnect, etc
  repeated string special_events = 4;
}

message DatalogSample {
  SampleInfo info = 1;              // Sample info
  
  ObservationSet observations = 2;  // Incoming observation from environment
  repeated Action actions = 3;      // Incoming actions from actors
  repeated Reward rewards = 4;      // Incoming rewards from environment and actors
  repeated Message messages = 5;    // Incoming messages from environment and actors
}


// ************************************************************************************************
// API 1.0 version of the log data.
// This is provided to facilitate the extraction/deserialization of older (1.0) log data.
// ************************************************************************************************

message TrialConfig_v1 {
  bytes content = 1;
}

message ActorConfig_v1 {
  bytes content = 1;
}

message EnvironmentConfig_v1 {
  bytes content = 1;
}

message EnvironmentParams_v1 {
  string endpoint = 1;
  EnvironmentConfig_v1 config = 2;
  string implementation = 3;
}

message ActorParams_v1 {
  string name = 1;
  string actor_class = 2;
  string endpoint = 3;  
  string implementation = 4;
  ActorConfig_v1 config = 5;
}

message TrialParams_v1 {
  TrialConfig_v1 trial_config = 1;
  EnvironmentParams_v1 environment = 2;
  repeated ActorParams_v1 actors = 3;
  uint32 max_steps = 4;
  uint32 max_inactivity = 5;
}

message ObservationData_v1 {
  bytes content = 1;
  bool snapshot = 2;
}

message ObservationSet_v1 {
  sint64 tick_id = 1;
  fixed64 timestamp = 2;
  repeated ObservationData_v1 observations = 3;
  repeated int32 actors_map = 4;
}

message Action_v1 {
  bytes content = 1;
  sint64 tick_id = 2;
}

message RewardSource_v1 {
  string sender_name = 1;
  float value = 2;
  float confidence = 3;
  google.protobuf.Any user_data = 4;
}

message Reward_v1 {
  string receiver_name = 1;
  sint64 tick_id = 2;
  float value = 3;
  repeated RewardSource_v1 sources = 4;
}

message Message_v1 {
  sint64 tick_id = 1;
  string sender_name = 2;
  string receiver_name = 3;
  google.protobuf.Any payload = 4;
}

message DatalogSample_v1 {
  string user_id = 1;
  ObservationSet_v1 observations = 2;
  repeated Action_v1 actions = 3;
  repeated Reward_v1 rewards = 4;
  repeated Message_v1 messages = 5;
  TrialData_v1 trial_data = 6;
}

message TrialData_v1 {
  uint64 tick_id = 1;
  fixed64 timestamp = 2;
  TrialState state = 3;
}