feat(observability): add metrics and monitoring for all 15 backends

- Add MetricsModule to 8 backends missing it (photos, zitare, mukke,
  planta, picture, storage, presi, nutriphi)
- Enable Prometheus scraping for all 15 backends in prometheus.yml
  (was only 6, with 3 commented out and 6 missing entirely)
- Update ServiceDown alert rule to cover all 15 backends
- Update Grafana dashboards (backends, master-overview, system-overview)
  with all backend services in health panels
- Fix imprecise regex in application-details dashboard

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

apps/mukke/apps/backend/package.json

@@ -25,6 +25,7 @@
 		"@manacore/shared-drizzle-config": "workspace:*",
 		"@manacore/shared-nestjs-auth": "workspace:*",
 		"@manacore/shared-nestjs-health": "workspace:*",
+		"@manacore/shared-nestjs-metrics": "workspace:*",
 		"@manacore/shared-nestjs-setup": "workspace:*",
 		"@manacore/shared-storage": "workspace:*",
 		"@mukke/shared": "workspace:*",

apps/mukke/apps/backend/src/app.module.ts

@@ -12,6 +12,7 @@ import { SongModule } from './song/song.module';
 import { PlaylistModule } from './playlist/playlist.module';
 import { LibraryModule } from './library/library.module';
 import { HealthModule } from '@manacore/shared-nestjs-health';
+import { MetricsModule } from '@manacore/shared-nestjs-metrics';
 
 @Module({
 	imports: [
@@ -31,6 +32,10 @@ import { HealthModule } from '@manacore/shared-nestjs-health';
 		PlaylistModule,
 		LibraryModule,
 		HealthModule.forRoot({ serviceName: 'mukke-backend' }),
+		MetricsModule.register({
+			prefix: 'mukke_',
+			excludePaths: ['/health'],
+		}),
 	],
 })
 export class AppModule {}

apps/nutriphi/apps/backend/package.json

@@ -27,6 +27,7 @@
 		"@nutriphi/shared": "workspace:*",
 		"@manacore/shared-nestjs-auth": "workspace:*",
 		"@manacore/shared-nestjs-health": "workspace:*",
+		"@manacore/shared-nestjs-metrics": "workspace:*",
 		"@manacore/shared-nestjs-setup": "workspace:*",
 		"@google/generative-ai": "^0.21.0",
 		"@nestjs/common": "^10.4.15",

apps/nutriphi/apps/backend/src/app.module.ts

@@ -2,6 +2,7 @@ import { Module } from '@nestjs/common';
 import { ConfigModule } from '@nestjs/config';
 import { DatabaseModule } from './db/database.module';
 import { HealthModule } from '@manacore/shared-nestjs-health';
+import { MetricsModule } from '@manacore/shared-nestjs-metrics';
 import { MealModule } from './meal/meal.module';
 import { GoalsModule } from './goals/goals.module';
 import { FavoritesModule } from './favorites/favorites.module';
@@ -17,6 +18,10 @@ import { RecommendationsModule } from './recommendations/recommendations.module'
 		}),
 		DatabaseModule,
 		HealthModule.forRoot({ serviceName: 'nutriphi-backend' }),
+		MetricsModule.register({
+			prefix: 'nutriphi_',
+			excludePaths: ['/health'],
+		}),
 		MealModule,
 		GoalsModule,
 		FavoritesModule,

apps/photos/apps/backend/package.json

@@ -19,6 +19,7 @@
 		"@manacore/shared-error-tracking": "workspace:*",
 		"@manacore/shared-nestjs-auth": "workspace:*",
 		"@manacore/shared-nestjs-health": "workspace:*",
+		"@manacore/shared-nestjs-metrics": "workspace:*",
 		"@nestjs/common": "^10.4.9",
 		"@nestjs/config": "^3.3.0",
 		"@nestjs/core": "^10.4.9",

apps/photos/apps/backend/src/app.module.ts

@@ -1,6 +1,7 @@
 import { Module } from '@nestjs/common';
 import { ConfigModule } from '@nestjs/config';
 import { HealthModule } from '@manacore/shared-nestjs-health';
+import { MetricsModule } from '@manacore/shared-nestjs-metrics';
 import { DatabaseModule } from './db/database.module';
 import { AlbumModule } from './album/album.module';
 import { FavoriteModule } from './favorite/favorite.module';
@@ -15,6 +16,10 @@ import { AdminModule } from './admin/admin.module';
 			envFilePath: '.env',
 		}),
 		HealthModule.forRoot({ serviceName: 'photos-backend' }),
+		MetricsModule.register({
+			prefix: 'photos_',
+			excludePaths: ['/health'],
+		}),
 		DatabaseModule,
 		AlbumModule,
 		FavoriteModule,

apps/picture/apps/backend/package.json

@@ -27,6 +27,7 @@
 		"@manacore/shared-errors": "workspace:*",
 		"@manacore/shared-nestjs-auth": "workspace:*",
 		"@manacore/shared-nestjs-health": "workspace:*",
+		"@manacore/shared-nestjs-metrics": "workspace:*",
 		"@manacore/shared-storage": "workspace:*",
 		"@nestjs/common": "^10.4.15",
 		"@nestjs/config": "^3.3.0",

apps/picture/apps/backend/src/app.module.ts

@@ -4,6 +4,7 @@ import { ThrottlerModule } from '@nestjs/throttler';
 import { ManaCoreModule } from '@manacore/nestjs-integration';
 import { DatabaseModule } from './db/database.module';
 import { HealthModule } from '@manacore/shared-nestjs-health';
+import { MetricsModule } from '@manacore/shared-nestjs-metrics';
 import { ModelModule } from './model/model.module';
 import { TagModule } from './tag/tag.module';
 import { ImageModule } from './image/image.module';
@@ -35,6 +36,10 @@ import { AdminModule } from './admin/admin.module';
 		}),
 		DatabaseModule,
 		HealthModule.forRoot({ serviceName: 'picture-backend' }),
+		MetricsModule.register({
+			prefix: 'picture_',
+			excludePaths: ['/health'],
+		}),
 		ModelModule,
 		TagModule,
 		ImageModule,

apps/planta/apps/backend/package.json

@@ -22,6 +22,7 @@
 		"@google/generative-ai": "^0.21.0",
 		"@manacore/shared-nestjs-auth": "workspace:*",
 		"@manacore/shared-nestjs-health": "workspace:*",
+		"@manacore/shared-nestjs-metrics": "workspace:*",
 		"@manacore/shared-nestjs-setup": "workspace:*",
 		"@manacore/shared-storage": "workspace:*",
 		"@nestjs/common": "^10.4.15",

apps/planta/apps/backend/src/app.module.ts

@@ -2,6 +2,7 @@ import { Module } from '@nestjs/common';
 import { ConfigModule } from '@nestjs/config';
 import { DatabaseModule } from './db/database.module';
 import { HealthModule } from '@manacore/shared-nestjs-health';
+import { MetricsModule } from '@manacore/shared-nestjs-metrics';
 import { PlantModule } from './plant/plant.module';
 import { PhotoModule } from './photo/photo.module';
 import { AnalysisModule } from './analysis/analysis.module';
@@ -15,6 +16,10 @@ import { WateringModule } from './watering/watering.module';
 		}),
 		DatabaseModule,
 		HealthModule.forRoot({ serviceName: 'planta-backend' }),
+		MetricsModule.register({
+			prefix: 'planta_',
+			excludePaths: ['/health'],
+		}),
 		PlantModule,
 		PhotoModule,
 		AnalysisModule,

apps/presi/apps/backend/package.json

@@ -22,6 +22,7 @@
 		"@manacore/shared-error-tracking": "workspace:*",
 		"@manacore/shared-nestjs-auth": "workspace:*",
 		"@manacore/shared-nestjs-health": "workspace:*",
+		"@manacore/shared-nestjs-metrics": "workspace:*",
 		"@manacore/shared-nestjs-setup": "workspace:*",
 		"@nestjs/common": "^10.4.15",
 		"@nestjs/config": "^3.3.0",

apps/presi/apps/backend/src/app.module.ts

@@ -9,6 +9,7 @@ import { ThemeModule } from './theme/theme.module';
 import { ShareModule } from './share/share.module';
 import { AdminModule } from './admin/admin.module';
 import { HealthModule } from '@manacore/shared-nestjs-health';
+import { MetricsModule } from '@manacore/shared-nestjs-metrics';
 
 @Module({
 	imports: [
@@ -24,6 +25,10 @@ import { HealthModule } from '@manacore/shared-nestjs-health';
 		ShareModule,
 		AdminModule,
 		HealthModule.forRoot({ serviceName: 'presi-backend' }),
+		MetricsModule.register({
+			prefix: 'presi_',
+			excludePaths: ['/health'],
+		}),
 	],
 	providers: [
 		{

apps/storage/apps/backend/package.json

@@ -24,6 +24,7 @@
 		"@manacore/shared-error-tracking": "workspace:*",
 		"@manacore/shared-nestjs-auth": "workspace:*",
 		"@manacore/shared-nestjs-health": "workspace:*",
+		"@manacore/shared-nestjs-metrics": "workspace:*",
 		"@manacore/shared-storage": "workspace:*",
 		"@nestjs/common": "^10.4.15",
 		"@nestjs/config": "^3.3.0",

apps/storage/apps/backend/src/app.module.ts

@@ -3,6 +3,7 @@ import { ConfigModule } from '@nestjs/config';
 import { ThrottlerModule } from '@nestjs/throttler';
 import { DatabaseModule } from './db/database.module';
 import { HealthModule } from '@manacore/shared-nestjs-health';
+import { MetricsModule } from '@manacore/shared-nestjs-metrics';
 import { FileModule } from './file/file.module';
 import { FolderModule } from './folder/folder.module';
 import { ShareModule } from './share/share.module';
@@ -25,6 +26,10 @@ import { AdminModule } from './admin/admin.module';
 		]),
 		DatabaseModule,
 		HealthModule.forRoot({ serviceName: 'storage-backend', route: 'api/v1/health' }),
+		MetricsModule.register({
+			prefix: 'storage_',
+			excludePaths: ['/health'],
+		}),
 		StorageModule,
 		FileModule,
 		FolderModule,

apps/zitare/apps/backend/package.json

@@ -21,6 +21,7 @@
 		"@manacore/shared-error-tracking": "workspace:*",
 		"@manacore/shared-nestjs-auth": "workspace:*",
 		"@manacore/shared-nestjs-health": "workspace:*",
+		"@manacore/shared-nestjs-metrics": "workspace:*",
 		"@manacore/shared-nestjs-setup": "workspace:*",
 		"@nestjs/common": "^10.4.15",
 		"@nestjs/config": "^3.3.0",

apps/zitare/apps/backend/src/app.module.ts

@@ -4,6 +4,7 @@ import { DatabaseModule } from './db/database.module';
 import { FavoriteModule } from './favorite/favorite.module';
 import { ListModule } from './list/list.module';
 import { HealthModule } from '@manacore/shared-nestjs-health';
+import { MetricsModule } from '@manacore/shared-nestjs-metrics';
 import { AdminModule } from './admin/admin.module';
 
 @Module({
@@ -16,6 +17,10 @@ import { AdminModule } from './admin/admin.module';
 		FavoriteModule,
 		ListModule,
 		HealthModule.forRoot({ serviceName: 'quote-backend' }),
+		MetricsModule.register({
+			prefix: 'zitare_',
+			excludePaths: ['/health'],
+		}),
 		AdminModule,
 	],
 })

docker/grafana/dashboards/application-details.json

@@ -850,14 +850,14 @@
 				"allValue": ".*",
 				"current": { "selected": true, "text": "All", "value": "$__all" },
 				"datasource": { "type": "prometheus", "uid": "${datasource}" },
-				"definition": "label_values(up{job=~\".*backend|mana-core-auth\"}, job)",
+				"definition": "label_values(up{job=~\".*-backend|mana-core-auth\"}, job)",
 				"hide": 0,
 				"includeAll": true,
 				"multi": true,
 				"name": "service",
 				"options": [],
 				"query": {
-					"query": "label_values(up{job=~\".*backend|mana-core-auth\"}, job)",
+					"query": "label_values(up{job=~\".*-backend|mana-core-auth\"}, job)",
 					"refId": "PrometheusVariableQueryEditor-VariableQuery"
 				},
 				"refresh": 2,

docker/grafana/dashboards/backends.json

@@ -58,7 +58,7 @@
 			"targets": [
 				{
 					"datasource": { "type": "prometheus", "uid": "${datasource}" },
-					"expr": "up{job=~\"mana-core-auth|chat-backend|todo-backend|calendar-backend|clock-backend|contacts-backend\"}",
+					"expr": "up{job=~\"mana-core-auth|chat-backend|todo-backend|calendar-backend|clock-backend|contacts-backend|storage-backend|presi-backend|nutriphi-backend|skilltree-backend|photos-backend|zitare-backend|mukke-backend|planta-backend|picture-backend\"}",
 					"legendFormat": "{{job}}",
 					"refId": "A"
 				}

docker/grafana/dashboards/master-overview.json

@@ -444,6 +444,60 @@
 					"legendFormat": "Contacts",
 					"refId": "F"
 				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"storage-backend\"}",
+					"legendFormat": "Storage",
+					"refId": "J"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"presi-backend\"}",
+					"legendFormat": "Presi",
+					"refId": "K"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"nutriphi-backend\"}",
+					"legendFormat": "NutriPhi",
+					"refId": "L"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"skilltree-backend\"}",
+					"legendFormat": "SkillTree",
+					"refId": "M"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"photos-backend\"}",
+					"legendFormat": "Photos",
+					"refId": "N"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"zitare-backend\"}",
+					"legendFormat": "Zitare",
+					"refId": "O"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"mukke-backend\"}",
+					"legendFormat": "Mukke",
+					"refId": "P"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"planta-backend\"}",
+					"legendFormat": "Planta",
+					"refId": "Q"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"picture-backend\"}",
+					"legendFormat": "Picture",
+					"refId": "R"
+				},
 				{
 					"datasource": { "type": "prometheus", "uid": "${datasource}" },
 					"expr": "pg_up",

docker/grafana/dashboards/system-overview.json

@@ -528,6 +528,60 @@
 					"legendFormat": "Contacts",
 					"refId": "F"
 				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"storage-backend\"}",
+					"legendFormat": "Storage",
+					"refId": "J"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"presi-backend\"}",
+					"legendFormat": "Presi",
+					"refId": "K"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"nutriphi-backend\"}",
+					"legendFormat": "NutriPhi",
+					"refId": "L"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"skilltree-backend\"}",
+					"legendFormat": "SkillTree",
+					"refId": "M"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"photos-backend\"}",
+					"legendFormat": "Photos",
+					"refId": "N"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"zitare-backend\"}",
+					"legendFormat": "Zitare",
+					"refId": "O"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"mukke-backend\"}",
+					"legendFormat": "Mukke",
+					"refId": "P"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"planta-backend\"}",
+					"legendFormat": "Planta",
+					"refId": "Q"
+				},
+				{
+					"datasource": { "type": "prometheus", "uid": "${datasource}" },
+					"expr": "up{job=\"picture-backend\"}",
+					"legendFormat": "Picture",
+					"refId": "R"
+				},
 				{
 					"datasource": { "type": "prometheus", "uid": "${datasource}" },
 					"expr": "pg_up",

docker/prometheus/alerts.yml

@@ -3,7 +3,7 @@ groups:
     rules:
       # Service Down Alert
       - alert: ServiceDown
-        expr: up{job=~"mana-core-auth|chat-backend|todo-backend|calendar-backend|clock-backend|contacts-backend"} == 0
+        expr: up{job=~"mana-core-auth|chat-backend|todo-backend|calendar-backend|clock-backend|contacts-backend|storage-backend|presi-backend|nutriphi-backend|skilltree-backend|photos-backend|zitare-backend|mukke-backend|planta-backend|picture-backend"} == 0
         for: 1m
         labels:
           severity: critical

docker/prometheus/prometheus.yml

@@ -91,26 +91,68 @@ scrape_configs:
     metrics_path: '/metrics'
     scrape_interval: 30s
 
-  # Storage Backend (disabled - no /metrics endpoint yet)
-  # - job_name: 'storage-backend'
-  #   static_configs:
-  #     - targets: ['storage-backend:3035']
-  #   metrics_path: '/metrics'
-  #   scrape_interval: 30s
+  # Storage Backend
+  - job_name: 'storage-backend'
+    static_configs:
+      - targets: ['storage-backend:3035']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
 
-  # Presi Backend (disabled - no /metrics endpoint yet)
-  # - job_name: 'presi-backend'
-  #   static_configs:
-  #     - targets: ['presi-backend:3036']
-  #   metrics_path: '/metrics'
-  #   scrape_interval: 30s
+  # Presi Backend
+  - job_name: 'presi-backend'
+    static_configs:
+      - targets: ['presi-backend:3036']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
 
-  # Nutriphi Backend (disabled - no /metrics endpoint yet)
-  # - job_name: 'nutriphi-backend'
-  #   static_configs:
-  #     - targets: ['nutriphi-backend:3037']
-  #   metrics_path: '/metrics'
-  #   scrape_interval: 30s
+  # Nutriphi Backend
+  - job_name: 'nutriphi-backend'
+    static_configs:
+      - targets: ['nutriphi-backend:3037']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
+
+  # SkillTree Backend
+  - job_name: 'skilltree-backend'
+    static_configs:
+      - targets: ['skilltree-backend:3038']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
+
+  # Photos Backend
+  - job_name: 'photos-backend'
+    static_configs:
+      - targets: ['photos-backend:3039']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
+
+  # Zitare Backend
+  - job_name: 'zitare-backend'
+    static_configs:
+      - targets: ['zitare-backend:3007']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
+
+  # Mukke Backend
+  - job_name: 'mukke-backend'
+    static_configs:
+      - targets: ['mukke-backend:3010']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
+
+  # Planta Backend
+  - job_name: 'planta-backend'
+    static_configs:
+      - targets: ['planta-backend:3022']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
+
+  # Picture Backend
+  - job_name: 'picture-backend'
+    static_configs:
+      - targets: ['picture-backend:3040']
+    metrics_path: '/metrics'
+    scrape_interval: 30s
 
   # ============================================
   # Pushgateway (deploy metrics, batch jobs)