feat(services): add monitoring (Loki + Grafana config, health-check)

- Copied as-is from learning_voice_ai_agent/services/monitoring
- Grafana dashboards + provisioning for Loki datasource
- health-check.ts for service health polling
- Updated pnpm-workspace.yaml to include services/*

pnpm-workspace.yaml

@@ -1,2 +1,3 @@
 packages:
   - "packages/*"
+  - "services/*"

services/monitoring/grafana/dashboards/lysnrai-services.json

@@ -0,0 +1,128 @@
+{
+  "annotations": { "list": [] },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "All Service Logs",
+      "type": "logs",
+      "gridPos": { "h": 12, "w": 24, "x": 0, "y": 0 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "{compose_service=~\".+\"}",
+          "refId": "A"
+        }
+      ],
+      "options": {
+        "showTime": true,
+        "showLabels": true,
+        "showCommonLabels": false,
+        "wrapLogMessage": true,
+        "prettifyLogMessage": false,
+        "enableLogDetails": true,
+        "sortOrder": "Descending",
+        "dedupStrategy": "none"
+      }
+    },
+    {
+      "title": "Logs by Service",
+      "type": "logs",
+      "gridPos": { "h": 10, "w": 12, "x": 0, "y": 12 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "{compose_service=\"backend\"}",
+          "refId": "A",
+          "legendFormat": "backend"
+        }
+      ],
+      "options": {
+        "showTime": true,
+        "showLabels": true,
+        "wrapLogMessage": true,
+        "enableLogDetails": true,
+        "sortOrder": "Descending"
+      }
+    },
+    {
+      "title": "Billing Service Logs",
+      "type": "logs",
+      "gridPos": { "h": 10, "w": 12, "x": 12, "y": 12 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "{compose_service=\"billing-service\"}",
+          "refId": "A"
+        }
+      ],
+      "options": {
+        "showTime": true,
+        "showLabels": true,
+        "wrapLogMessage": true,
+        "enableLogDetails": true,
+        "sortOrder": "Descending"
+      }
+    },
+    {
+      "title": "Error Rate (all services)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 22 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "sum by (compose_service) (rate({compose_service=~\".+\"} |= \"error\" [5m]))",
+          "refId": "A",
+          "legendFormat": "{{compose_service}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 15,
+            "pointSize": 5
+          },
+          "unit": "reqps"
+        }
+      }
+    },
+    {
+      "title": "Log Volume by Service",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 30 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "sum by (compose_service) (rate({compose_service=~\".+\"} [5m]))",
+          "refId": "A",
+          "legendFormat": "{{compose_service}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "drawStyle": "bars",
+            "lineWidth": 1,
+            "fillOpacity": 50,
+            "stacking": { "mode": "normal" }
+          },
+          "unit": "reqps"
+        }
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["lysnrai", "logs", "monitoring"],
+  "templating": { "list": [] },
+  "time": { "from": "now-1h", "to": "now" },
+  "timepicker": {},
+  "timezone": "browser",
+  "title": "LysnrAI — Service Logs",
+  "uid": "lysnrai-service-logs",
+  "version": 1
+}

services/monitoring/grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+  - name: default
+    orgId: 1
+    folder: ""
+    type: file
+    disableDeletion: false
+    editable: true
+    options:
+      path: /var/lib/grafana/dashboards
+      foldersFromFilesStructure: false

services/monitoring/grafana/provisioning/datasources/loki.yml

@@ -0,0 +1,9 @@
+apiVersion: 1
+
+datasources:
+  - name: Loki
+    type: loki
+    access: proxy
+    url: http://loki:3100
+    isDefault: true
+    editable: false

services/monitoring/health-check.ts

@@ -0,0 +1,119 @@
+/**
+ * Monitoring & Health Check — aggregates health from all services.
+ *
+ * Standalone script that polls each service's /health endpoint and
+ * reports combined status. Can be run as a cron job, GitHub Action,
+ * or standalone HTTP endpoint.
+ *
+ * Usage:
+ *   npx tsx services/monitoring/health-check.ts          # one-shot check
+ *   npx tsx services/monitoring/health-check.ts --serve   # HTTP server on :4004
+ *
+ * Environment:
+ *   BACKEND_URL          (default: http://localhost:8000)
+ *   GROWTH_SERVICE_URL   (default: http://localhost:4001)
+ *   BILLING_SERVICE_URL  (default: http://localhost:4002)
+ *   PLATFORM_SERVICE_URL (default: http://localhost:4003)
+ *   ADMIN_DASHBOARD_URL  (default: http://localhost:3001)
+ *   USER_DASHBOARD_URL   (default: http://localhost:3002)
+ */
+
+export {};
+
+interface ServiceCheck {
+  name: string;
+  url: string;
+  status: "healthy" | "unhealthy" | "unreachable";
+  responseTimeMs: number;
+  details?: Record<string, unknown>;
+  error?: string;
+}
+
+interface HealthReport {
+  overall: "healthy" | "degraded" | "down";
+  timestamp: string;
+  services: ServiceCheck[];
+  summary: { healthy: number; unhealthy: number; unreachable: number; total: number };
+}
+
+const SERVICES = [
+  { name: "Backend API", url: process.env.BACKEND_URL || "http://localhost:8000", path: "/health" },
+  { name: "Growth Service", url: process.env.GROWTH_SERVICE_URL || "http://localhost:4001", path: "/health" },
+  { name: "Billing Service", url: process.env.BILLING_SERVICE_URL || "http://localhost:4002", path: "/health" },
+  { name: "Platform Service", url: process.env.PLATFORM_SERVICE_URL || "http://localhost:4003", path: "/health" },
+  { name: "Admin Dashboard", url: process.env.ADMIN_DASHBOARD_URL || "http://localhost:3001", path: "/api/health" },
+  { name: "User Dashboard", url: process.env.USER_DASHBOARD_URL || "http://localhost:3002", path: "/api/health" },
+];
+
+async function checkService(svc: { name: string; url: string; path: string }): Promise<ServiceCheck> {
+  const fullUrl = `${svc.url}${svc.path}`;
+  const start = performance.now();
+
+  try {
+    const res = await fetch(fullUrl, { signal: AbortSignal.timeout(5_000) });
+    const elapsed = Math.round(performance.now() - start);
+
+    if (res.ok) {
+      let details: Record<string, unknown> | undefined;
+      try { details = await res.json() as Record<string, unknown>; } catch { /* ignore */ }
+      return { name: svc.name, url: svc.url, status: "healthy", responseTimeMs: elapsed, details };
+    }
+    return { name: svc.name, url: svc.url, status: "unhealthy", responseTimeMs: elapsed, error: `HTTP ${res.status}` };
+  } catch (err) {
+    const elapsed = Math.round(performance.now() - start);
+    return { name: svc.name, url: svc.url, status: "unreachable", responseTimeMs: elapsed, error: String(err) };
+  }
+}
+
+async function generateReport(): Promise<HealthReport> {
+  const checks = await Promise.all(SERVICES.map(checkService));
+
+  const healthy = checks.filter((c) => c.status === "healthy").length;
+  const unhealthy = checks.filter((c) => c.status === "unhealthy").length;
+  const unreachable = checks.filter((c) => c.status === "unreachable").length;
+
+  let overall: HealthReport["overall"] = "healthy";
+  if (unreachable === checks.length) overall = "down";
+  else if (unhealthy > 0 || unreachable > 0) overall = "degraded";
+
+  return {
+    overall,
+    timestamp: new Date().toISOString(),
+    services: checks,
+    summary: { healthy, unhealthy, unreachable, total: checks.length },
+  };
+}
+
+// ── CLI / HTTP server mode ──
+
+const args = process.argv.slice(2);
+
+if (args.includes("--serve")) {
+  // Run as HTTP server for continuous monitoring
+  const { createServer } = await import("http");
+  const PORT = Number(process.env.MONITOR_PORT || 4004);
+
+  const server = createServer(async (_req, res) => {
+    const report = await generateReport();
+    res.writeHead(report.overall === "healthy" ? 200 : 503, { "Content-Type": "application/json" });
+    res.end(JSON.stringify(report, null, 2));
+  });
+
+  server.listen(PORT, () => {
+    console.log(`🩺 Monitoring dashboard running on http://localhost:${PORT}`);
+    console.log(`   Checking ${SERVICES.length} services every request`);
+  });
+} else {
+  // One-shot check
+  const report = await generateReport();
+  const icon = { healthy: "✅", degraded: "⚠️", down: "❌" };
+  console.log(`\n${icon[report.overall]} Overall: ${report.overall.toUpperCase()}\n`);
+
+  for (const svc of report.services) {
+    const sIcon = { healthy: "✅", unhealthy: "⚠️", unreachable: "❌" };
+    console.log(`  ${sIcon[svc.status]} ${svc.name.padEnd(20)} ${svc.responseTimeMs}ms${svc.error ? ` — ${svc.error}` : ""}`);
+  }
+
+  console.log(`\nHealthy: ${report.summary.healthy}/${report.summary.total}`);
+  process.exit(report.overall === "healthy" ? 0 : 1);
+}

services/monitoring/loki/loki-config.yml

@@ -0,0 +1,34 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+
+common:
+  path_prefix: /loki
+  storage:
+    filesystem:
+      chunks_directory: /loki/chunks
+      rules_directory: /loki/rules
+  replication_factor: 1
+  ring:
+    kvstore:
+      store: inmemory
+
+schema_config:
+  configs:
+    - from: "2024-01-01"
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+limits_config:
+  reject_old_samples: true
+  reject_old_samples_max_age: 168h   # 7 days
+  ingestion_rate_mb: 10
+  ingestion_burst_size_mb: 20
+
+analytics:
+  reporting_enabled: false

services/monitoring/package.json

@@ -0,0 +1,16 @@
+{
+  "name": "@lysnrai/monitoring",
+  "version": "0.1.0",
+  "private": true,
+  "description": "Health check and monitoring for all LysnrAI services",
+  "type": "module",
+  "scripts": {
+    "check": "tsx health-check.ts",
+    "serve": "tsx health-check.ts --serve"
+  },
+  "devDependencies": {
+    "@types/node": "^22.12.0",
+    "tsx": "^4.19.2",
+    "typescript": "^5.7.3"
+  }
+}

services/monitoring/tsconfig.json

@@ -0,0 +1,11 @@
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "strict": true,
+    "esModuleInterop": true,
+    "types": ["node"]
+  },
+  "include": ["*.ts"]
+}