foxhunt/bin/fxt/proto/monitoring.proto

syntax = "proto3";
package monitoring;

service MonitoringService {
  // Single snapshot of all active training sessions
  rpc GetLiveTrainingMetrics(GetLiveTrainingMetricsRequest)
      returns (GetLiveTrainingMetricsResponse);

  // Server-streaming: pushes updates every N seconds
  rpc StreamTrainingMetrics(StreamTrainingMetricsRequest)
      returns (stream GetLiveTrainingMetricsResponse);

  // Epoch history for a specific session (ring buffer, max 50 epochs)
  rpc GetEpochHistory(GetEpochHistoryRequest)
      returns (GetEpochHistoryResponse);
}

message GetLiveTrainingMetricsRequest {
  string model_filter = 1;  // optional: "dqn", "ppo", etc.
}

message StreamTrainingMetricsRequest {
  string model_filter = 1;
  uint32 interval_seconds = 2;  // 0 = server default (3s)
}

message GetLiveTrainingMetricsResponse {
  repeated TrainingSession sessions = 1;
  GpuSnapshot gpu = 2;
  uint32 active_k8s_jobs = 3;
  int64 timestamp = 4;
}

message TrainingSession {
  string model = 1;
  string fold = 2;
  bool is_hyperopt = 3;

  // Epoch/progress
  float current_epoch = 4;
  float epoch_loss = 5;
  float validation_loss = 6;

  // Throughput
  float batches_per_second = 7;
  float batches_processed = 8;
  float iteration_seconds = 9;

  // Eval metrics
  float eval_accuracy = 10;
  float eval_precision = 11;
  float eval_recall = 12;
  float eval_f1 = 13;

  // Checkpoint
  float checkpoint_size_bytes = 14;
  uint32 checkpoint_saves = 15;
  uint32 checkpoint_failures = 16;

  // Health counters
  uint32 nan_detected = 17;
  uint32 gradient_explosions = 18;
  uint32 feature_errors = 19;

  // Hyperopt fields (populated when is_hyperopt=true)
  uint32 hyperopt_trial_current = 20;
  uint32 hyperopt_trial_total = 21;
  float hyperopt_best_objective = 22;
  uint32 hyperopt_trials_failed = 23;

  // RL diagnostics
  float q_value_mean = 24;
  float q_value_max = 25;
  float policy_entropy = 26;
  float kl_divergence = 27;
  float advantage_mean = 28;
  uint32 replay_buffer_size = 29;

  // Gradient & training health
  float gradient_norm = 30;
  float learning_rate = 31;
  float epoch_duration_seconds = 32;

  // Hyperopt intra-trial
  uint32 hyperopt_trial_epoch = 33;
  float hyperopt_trial_best_loss = 34;
  float hyperopt_elapsed_seconds = 35;

  // Epoch-level financial metrics
  float epoch_sharpe = 36;
  float epoch_sortino = 37;
  float epoch_win_rate = 38;
  float epoch_max_drawdown = 39;
  float epoch_profit_factor = 40;
  float epoch_total_return = 41;
  float epoch_avg_return = 42;
  uint32 epoch_total_trades = 43;
  // Action distribution
  float action_buy_pct = 44;
  float action_sell_pct = 45;
  float action_hold_pct = 46;
}

message GpuSnapshot {
  float utilization_percent = 1;
  float memory_used_mb = 2;
  float memory_total_mb = 3;
  float temperature_celsius = 4;
  float power_watts = 5;
}

message GetEpochHistoryRequest {
  string model = 1;
  string fold = 2;
  uint32 max_epochs = 3;  // 0 = all (up to 50)
}

message EpochFinancialSnapshot {
  uint32 epoch = 1;
  float sharpe = 2;
  float sortino = 3;
  float win_rate = 4;
  float max_drawdown = 5;
  float profit_factor = 6;
  float total_return = 7;
  float avg_return = 8;
  uint32 total_trades = 9;
  float loss = 10;
  float val_loss = 11;
  float learning_rate = 12;
  float action_buy_pct = 13;
  float action_sell_pct = 14;
  float action_hold_pct = 15;
}

message GetEpochHistoryResponse {
  string model = 1;
  string fold = 2;
  repeated EpochFinancialSnapshot epochs = 3;
}