From 33d3cf2dd2445a84631a5e03e81ff2275d45a78b Mon Sep 17 00:00:00 2001
From: jgrusewski <jgrusewski@localhost>
Date: Mon, 2 Mar 2026 21:21:29 +0100
Subject: [PATCH] feat(monitoring): add monitoring.proto with gRPC service
 definition

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 .../monitoring_service/proto/monitoring.proto | 74 +++++++++++++++++++
 1 file changed, 74 insertions(+)
 create mode 100644 services/monitoring_service/proto/monitoring.proto

diff --git a/services/monitoring_service/proto/monitoring.proto b/services/monitoring_service/proto/monitoring.proto
new file mode 100644
index 000000000..c3f90f4ab
--- /dev/null
+++ b/services/monitoring_service/proto/monitoring.proto
@@ -0,0 +1,74 @@
+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);
+}
+
+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;
+}
+
+message GpuSnapshot {
+  float utilization_percent = 1;
+  float memory_used_mb = 2;
+  float memory_total_mb = 3;
+  float temperature_celsius = 4;
+  float power_watts = 5;
+}