feat: add Prometheus system monitoring

api/src/infrastructure-monitoring/infrastructure-monitoring.contracts.ts

@@ -0,0 +1,65 @@
+export type InfrastructureMonitoringRange = '1h' | '24h' | '7d';
+
+export type InfrastructureMetricPoint = {
+  timestamp: string;
+  value: number;
+};
+
+export type InfrastructureServiceStatus = {
+  key: string;
+  name: string;
+  unit: string;
+  status: 'healthy' | 'unhealthy' | 'unknown';
+};
+
+export type InfrastructureAlert = {
+  fingerprint: string;
+  name: string;
+  severity: 'info' | 'warning' | 'critical';
+  status: string;
+  startedAt: string;
+  summary: string;
+  description?: string;
+  currentValue?: string;
+  threshold?: string;
+  service?: string;
+  instance?: string;
+};
+
+export type InfrastructureMonitoringOverview = {
+  available: boolean;
+  range: InfrastructureMonitoringRange;
+  collectedAt: string;
+  lastSampleAt: string | null;
+  error?: string;
+  summary: {
+    overallStatus: 'healthy' | 'warning' | 'critical' | 'unknown';
+    serviceTotal: number;
+    serviceHealthy: number;
+    warningAlerts: number;
+    criticalAlerts: number;
+    activeAlerts: number;
+  };
+  metrics: {
+    cpuUsagePercent: number | null;
+    memoryUsagePercent: number | null;
+    memoryTotalBytes: number | null;
+    memoryAvailableBytes: number | null;
+    diskUsagePercent: number | null;
+    diskTotalBytes: number | null;
+    diskAvailableBytes: number | null;
+    networkReceiveBytesPerSecond: number | null;
+    networkTransmitBytesPerSecond: number | null;
+    load1: number | null;
+    uptimeSeconds: number | null;
+  };
+  trends: {
+    cpuUsagePercent: InfrastructureMetricPoint[];
+    memoryUsagePercent: InfrastructureMetricPoint[];
+    diskUsagePercent: InfrastructureMetricPoint[];
+    networkReceiveBytesPerSecond: InfrastructureMetricPoint[];
+    networkTransmitBytesPerSecond: InfrastructureMetricPoint[];
+  };
+  services: InfrastructureServiceStatus[];
+  alerts: InfrastructureAlert[];
+};