feat: homelab deployment - NPM + IONOS DNS + monitoring + NAS backup

- Restructured docker-compose for Nginx Proxy Manager (no custom nginx) - Added domain wordly.art configuration - Added Prometheus + Grafana monitoring stack with pre-configured dashboards - Added PostgreSQL backup script to NAS (daily/weekly/monthly rotation) - Added alert rules for backend, system, and Docker metrics - Updated deployment guide for NPM + IONOS DNS homelab setup - Added marketing plan document - PDF translator and watermark support - Enhanced middleware, routes, and translator modules Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-10 11:43:28 +02:00
parent 16ac7ca2b9
commit ce8e150a61
110 changed files with 6935 additions and 4301 deletions
--- a/docker/backend/Dockerfile
+++ b/docker/backend/Dockerfile
@@ -26,11 +26,15 @@ FROM python:3.12-slim AS production

 WORKDIR /app

-# Install runtime dependencies only
+# Install runtime dependencies + LibreOffice headless (required for DOCX→PDF)
 RUN apt-get update && apt-get install -y --no-install-recommends \
    libmagic1 \
    libpq5 \
    curl \
+    fonts-noto \
+    fonts-noto-cjk \
+    fonts-noto-cjk-extra \
+    libreoffice-writer-nogui \
    && rm -rf /var/lib/apt/lists/* \
    && apt-get clean

@@ -38,8 +42,11 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 COPY --from=builder /opt/venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"

-# Create non-root user for security
-RUN groupadd -r translator && useradd -r -g translator translator
+# Create non-root user with a proper home directory (LibreOffice needs it)
+RUN groupadd -r translator && \
+    useradd -r -g translator -m -d /home/translator translator && \
+    mkdir -p /home/translator/.cache && \
+    chown -R translator:translator /home/translator

 # Create necessary directories
 RUN mkdir -p /app/uploads /app/outputs /app/logs /app/temp \
--- a/docker/backend/entrypoint.sh
+++ b/docker/backend/entrypoint.sh
@@ -6,19 +6,28 @@ echo "🚀 Starting Document Translation API..."
 # Wait for database to be ready (if DATABASE_URL is set)
 if [ -n "$DATABASE_URL" ]; then
    echo "⏳ Waiting for database to be ready..."
-    
-    # Extract host and port from DATABASE_URL
-    # postgresql://user:pass@host:port/db
-    DB_HOST=$(echo $DATABASE_URL | sed -e 's/.*@\([^:]*\):.*/\1/')
-    DB_PORT=$(echo $DATABASE_URL | sed -e 's/.*:\([0-9]*\)\/.*/\1/')
-    
+
+    # Extract host and port from DATABASE_URL (handles postgresql+asyncpg:// and postgresql://)
+    DB_HOST=$(python -c "
+import re
+m = re.search(r'@([^:/]+)', '$DATABASE_URL')
+print(m.group(1) if m else 'postgres')
+")
+    DB_PORT=$(python -c "
+import re
+m = re.search(r'@[^:]+:(\d+)', '$DATABASE_URL')
+print(m.group(1) if m else '5432')
+")
+
+    echo "   Connecting to ${DB_HOST}:${DB_PORT}..."
+
    # Wait up to 30 seconds for database
-    for i in {1..30}; do
+    for i in $(seq 1 30); do
        if python -c "
 import socket
 s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
 try:
-    s.connect(('$DB_HOST', $DB_PORT))
+    s.connect(('$DB_HOST', int('$DB_PORT')))
    s.close()
    exit(0)
 except:
@@ -30,7 +39,7 @@ except:
        echo "   Waiting for database... ($i/30)"
        sleep 1
    done
-    
+
    # Run database migrations
    echo "📦 Running database migrations..."
    alembic upgrade head || echo "⚠️  Migration skipped (may already be up to date)"
@@ -39,15 +48,23 @@ fi
 # Wait for Redis if configured
 if [ -n "$REDIS_URL" ]; then
    echo "⏳ Waiting for Redis..."
-    REDIS_HOST=$(echo $REDIS_URL | sed -e 's/redis:\/\/\([^:]*\):.*/\1/')
-    REDIS_PORT=$(echo $REDIS_URL | sed -e 's/.*:\([0-9]*\)\/.*/\1/')
-    
-    for i in {1..10}; do
+    REDIS_HOST=$(python -c "
+import re
+m = re.search(r'://([^:/]+)', '$REDIS_URL')
+print(m.group(1) if m else 'redis')
+")
+    REDIS_PORT=$(python -c "
+import re
+m = re.search(r'://[^:]+:(\d+)', '$REDIS_URL')
+print(m.group(1) if m else '6379')
+")
+
+    for i in $(seq 1 10); do
        if python -c "
 import socket
 s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
 try:
-    s.connect(('$REDIS_HOST', $REDIS_PORT))
+    s.connect(('$REDIS_HOST', int('$REDIS_PORT')))
    s.close()
    exit(0)
 except:
--- a/docker/grafana/dashboards/wordly-infrastructure.json
+++ b/docker/grafana/dashboards/wordly-infrastructure.json
@@ -0,0 +1,168 @@
+{
+  "annotations": { "list": [] },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "CPU Usage (%)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
+      "targets": [
+        {
+          "expr": "100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)",
+          "legendFormat": "{{instance}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": { "lineWidth": 2, "fillOpacity": 20 },
+          "unit": "percent",
+          "max": 100
+        }
+      }
+    },
+    {
+      "title": "RAM Usage",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
+      "targets": [
+        {
+          "expr": "(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100",
+          "legendFormat": "Used %"
+        },
+        {
+          "expr": "node_memory_Buffers_bytes / node_memory_MemTotal_bytes * 100",
+          "legendFormat": "Buffers %"
+        },
+        {
+          "expr": "node_memory_Cached_bytes / node_memory_MemTotal_bytes * 100",
+          "legendFormat": "Cache %"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": { "lineWidth": 2, "fillOpacity": 15 },
+          "unit": "percent",
+          "max": 100
+        }
+      }
+    },
+    {
+      "title": "Disk Space",
+      "type": "gauge",
+      "gridPos": { "h": 6, "w": 6, "x": 0, "y": 8 },
+      "targets": [
+        {
+          "expr": "(1 - node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"}) * 100",
+          "legendFormat": "Used"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent",
+          "min": 0,
+          "max": 100,
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 70 },
+              { "color": "red", "value": 90 }
+            ]
+          }
+        }
+      }
+    },
+    {
+      "title": "Network I/O",
+      "type": "timeseries",
+      "gridPos": { "h": 6, "w": 10, "x": 6, "y": 8 },
+      "targets": [
+        {
+          "expr": "rate(node_network_receive_bytes_total{device!=\"lo\"}[5m]) * 8",
+          "legendFormat": "In {{device}}"
+        },
+        {
+          "expr": "-rate(node_network_transmit_bytes_total{device!=\"lo\"}[5m]) * 8",
+          "legendFormat": "Out {{device}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": { "lineWidth": 2 },
+          "unit": "bps"
+        }
+      }
+    },
+    {
+      "title": "Container Memory",
+      "type": "barchart",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 14 },
+      "targets": [
+        {
+          "expr": "container_memory_usage_bytes{name=~\"wordly.*|translate.*\"}",
+          "legendFormat": "{{name}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "bytes"
+        }
+      }
+    },
+    {
+      "title": "Container CPU %",
+      "type": "barchart",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 14 },
+      "targets": [
+        {
+          "expr": "rate(container_cpu_usage_seconds_total{name=~\"wordly.*|translate.*\"}[5m]) * 100",
+          "legendFormat": "{{name}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        }
+      }
+    },
+    {
+      "title": "Service Status (Up/Down)",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 24, "x": 0, "y": 22 },
+      "targets": [
+        {
+          "expr": "up",
+          "legendFormat": "{{job}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "thresholds": {
+            "steps": [
+              { "color": "red", "value": null },
+              { "color": "green", "value": 1 }
+            ]
+          },
+          "mappings": [
+            { "type": "value", "options": { "0": { "text": "DOWN", "color": "red" }, "1": { "text": "UP", "color": "green" } } }
+          ]
+        }
+      }
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "tags": ["wordly", "infrastructure"],
+  "time": { "from": "now-1h", "to": "now" },
+  "timezone": "Europe/Paris",
+  "title": "Wordly - Infrastructure",
+  "uid": "wordly-infra",
+  "version": 1
+}
--- a/docker/grafana/dashboards/wordly-overview.json
+++ b/docker/grafana/dashboards/wordly-overview.json
@@ -0,0 +1,206 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "title": "Traductions (dernières 24h)",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
+      "targets": [
+        {
+          "expr": "sum(increase(translation_total[24h]))",
+          "legendFormat": "Total"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "thresholds": {
+            "steps": [
+              { "color": "blue", "value": null },
+              { "color": "green", "value": 10 },
+              { "color": "orange", "value": 50 }
+            ]
+          },
+          "unit": "none"
+        }
+      }
+    },
+    {
+      "title": "Temps moyen (secondes)",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
+      "targets": [
+        {
+          "expr": "avg(rate(translation_duration_seconds_sum[5m]) / rate(translation_duration_seconds_count[5m]))",
+          "legendFormat": "Avg"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 30 },
+              { "color": "red", "value": 60 }
+            ]
+          },
+          "unit": "s"
+        }
+      }
+    },
+    {
+      "title": "Taux d'erreur (%)",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 },
+      "targets": [
+        {
+          "expr": "sum(rate(http_requests_total{status=~\"5..\"}[5m])) / sum(rate(http_requests_total[5m])) * 100",
+          "legendFormat": "Error %"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 1 },
+              { "color": "red", "value": 5 }
+            ]
+          },
+          "unit": "percent",
+          "max": 100
+        }
+      }
+    },
+    {
+      "title": "Utilisateurs actifs (1h)",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 },
+      "targets": [
+        {
+          "expr": "count(increase(http_requests_total{path!=\"/health\",path!=\"/metrics\"}[1h]) > 0)",
+          "legendFormat": "Active"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "thresholds": {
+            "steps": [
+              { "color": "blue", "value": null },
+              { "color": "green", "value": 5 }
+            ]
+          }
+        }
+      }
+    },
+    {
+      "title": "Requetes par minute (par endpoint)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
+      "targets": [
+        {
+          "expr": "sum by (path) (rate(http_requests_total[5m]) * 60)",
+          "legendFormat": "{{path}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "unit": "req/min"
+        }
+      }
+    },
+    {
+      "title": "Temps de traduction (percentiles)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
+      "targets": [
+        {
+          "expr": "histogram_quantile(0.5, sum(rate(translation_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "p50"
+        },
+        {
+          "expr": "histogram_quantile(0.95, sum(rate(translation_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "p95"
+        },
+        {
+          "expr": "histogram_quantile(0.99, sum(rate(translation_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "p99"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "lineWidth": 2,
+            "fillOpacity": 5
+          },
+          "unit": "s"
+        }
+      }
+    },
+    {
+      "title": "Traductions par provider",
+      "type": "piechart",
+      "gridPos": { "h": 8, "w": 8, "x": 0, "y": 12 },
+      "targets": [
+        {
+          "expr": "sum by (provider) (increase(translation_total[24h]))",
+          "legendFormat": "{{provider}}"
+        }
+      ]
+    },
+    {
+      "title": "Taille des fichiers uploades",
+      "type": "histogram",
+      "gridPos": { "h": 8, "w": 8, "x": 8, "y": 12 },
+      "targets": [
+        {
+          "expr": "sum by (le) (increase(file_size_bytes_bucket[24h]))",
+          "legendFormat": "{{le}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "bytes"
+        }
+      }
+    },
+    {
+      "title": "Fichiers par type",
+      "type": "piechart",
+      "gridPos": { "h": 8, "w": 8, "x": 16, "y": 12 },
+      "targets": [
+        {
+          "expr": "sum by (file_type) (increase(translation_total[24h]))",
+          "legendFormat": "{{file_type}}"
+        }
+      ]
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "tags": ["wordly", "application"],
+  "templating": { "list": [] },
+  "time": { "from": "now-24h", "to": "now" },
+  "timepicker": {},
+  "timezone": "Europe/Paris",
+  "title": "Wordly - Application",
+  "uid": "wordly-app",
+  "version": 1
+}
--- a/docker/grafana/provisioning/dashboards/dashboards.yml
+++ b/docker/grafana/provisioning/dashboards/dashboards.yml
@@ -0,0 +1,13 @@
+apiVersion: 1
+
+providers:
+  - name: 'Wordly Dashboards'
+    orgId: 1
+    folder: 'Wordly'
+    type: file
+    disableDeletion: false
+    editable: true
+    updateIntervalSeconds: 30
+    options:
+      path: /var/lib/grafana/dashboards
+      foldersFromFilesStructure: true
--- a/docker/grafana/provisioning/datasources/datasources.yml
+++ b/docker/grafana/provisioning/datasources/datasources.yml
@@ -0,0 +1,12 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://wordly-prometheus:9090
+    isDefault: true
+    editable: false
+    jsonData:
+      timeInterval: '15s'
+      httpMethod: POST
--- a/docker/nginx/conf.d/default.conf
+++ b/docker/nginx/conf.d/default.conf
@@ -1,18 +1,11 @@
-# Document Translation API - Main Server Block
-# HTTP to HTTPS redirect and main application routing
+# Wordly.art - Production Nginx Config
+# HTTP to HTTPS redirect + main application routing

-# HTTP server - redirect to HTTPS
+# HTTP server - redirect to HTTPS + Let's Encrypt
 server {
    listen 80;
    listen [::]:80;
-    server_name _;
-
-    # Allow health checks on HTTP
-    location /health {
-        proxy_pass http://backend/health;
-        proxy_http_version 1.1;
-        proxy_set_header Connection "";
-    }
+    server_name wordly.art www.wordly.art;

    # ACME challenge for Let's Encrypt
    location /.well-known/acme-challenge/ {
@@ -21,7 +14,7 @@ server {

    # Redirect all other traffic to HTTPS
    location / {
-        return 301 https://$host$request_uri;
+        return 301 https://wordly.art$request_uri;
    }
 }

@@ -29,19 +22,16 @@ server {
 server {
    listen 443 ssl http2;
    listen [::]:443 ssl http2;
-    server_name _;
+    server_name wordly.art;

-    # SSL certificates (replace with your paths)
+    # SSL certificates
    ssl_certificate /etc/nginx/ssl/fullchain.pem;
    ssl_certificate_key /etc/nginx/ssl/privkey.pem;
-    ssl_trusted_certificate /etc/nginx/ssl/chain.pem;

-    # SSL configuration
+    # SSL hardening
    ssl_session_timeout 1d;
    ssl_session_cache shared:SSL:50m;
    ssl_session_tickets off;
-
-    # Modern SSL configuration
    ssl_protocols TLSv1.2 TLSv1.3;
    ssl_ciphers ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384;
    ssl_prefer_server_ciphers off;
@@ -58,9 +48,16 @@ server {
    add_header X-XSS-Protection "1; mode=block" always;
    add_header Referrer-Policy "strict-origin-when-cross-origin" always;
    add_header Strict-Transport-Security "max-age=31536000; includeSubDomains" always;
-    add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval'; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob:; font-src 'self' data:; connect-src 'self' ws: wss:;" always;
+    add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval'; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob:; font-src 'self' data:; connect-src 'self' https://wordly.art ws: wss:;" always;

-    # API routes - proxy to backend (preserve full path so FastAPI receives /api/v1/...)
+    # File upload size
+    client_max_body_size 100M;
+    client_body_timeout 300s;
+    proxy_buffer_size 128k;
+    proxy_buffers 4 256k;
+    proxy_busy_buffers_size 256k;
+
+    # API routes -> Backend
    location /api/ {
        limit_req zone=api_limit burst=20 nodelay;
        limit_conn conn_limit 10;
@@ -72,8 +69,7 @@ server {
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
        proxy_set_header Connection "";
-        
-        # CORS headers for API (Origin restricted to same-origin/localhost via map in nginx.conf)
+
        add_header Access-Control-Allow-Origin $cors_origin always;
        add_header Access-Control-Allow-Methods "GET, POST, PUT, DELETE, OPTIONS" always;
        add_header Access-Control-Allow-Headers "Authorization, Content-Type, X-Requested-With, X-API-Key" always;
@@ -84,7 +80,7 @@ server {
        }
    }

-    # File upload endpoint - special handling
+    # Translation endpoint - extended timeouts
    location /translate {
        limit_req zone=upload_limit burst=5 nodelay;
        limit_conn conn_limit 5;
@@ -95,21 +91,51 @@ server {
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
-        
-        # Increased timeouts for file processing
+
        proxy_connect_timeout 60s;
        proxy_send_timeout 600s;
        proxy_read_timeout 600s;
    }

-    # Health check endpoint
+    # Health check
    location /health {
        proxy_pass http://backend/health;
        proxy_http_version 1.1;
        proxy_set_header Connection "";
    }

-    # Admin UI -> Frontend (Next.js page)
+    # Prometheus metrics (internal only - restrict access)
+    location /metrics {
+        # Allow only from Docker network and localhost
+        allow 172.28.0.0/16;
+        allow 127.0.0.1;
+        deny all;
+
+        proxy_pass http://backend/metrics;
+        proxy_http_version 1.1;
+        proxy_set_header Connection "";
+    }
+
+    # API docs
+    location /docs {
+        proxy_pass http://backend/docs;
+        proxy_http_version 1.1;
+        proxy_set_header Host $host;
+    }
+
+    location /redoc {
+        proxy_pass http://backend/redoc;
+        proxy_http_version 1.1;
+        proxy_set_header Host $host;
+    }
+
+    location /openapi.json {
+        proxy_pass http://backend/openapi.json;
+        proxy_http_version 1.1;
+        proxy_set_header Host $host;
+    }
+
+    # Admin -> Frontend
    location /admin {
        proxy_pass http://frontend;
        proxy_http_version 1.1;
@@ -119,7 +145,13 @@ server {
        proxy_set_header X-Forwarded-Proto $scheme;
    }

-    # Frontend - Next.js application
+    # Frontend static assets with aggressive caching
+    location /_next/static/ {
+        proxy_pass http://frontend;
+        add_header Cache-Control "public, max-age=31536000, immutable";
+    }
+
+    # Frontend -> Next.js
    location / {
        proxy_pass http://frontend;
        proxy_http_version 1.1;
@@ -131,16 +163,21 @@ server {
        proxy_set_header Connection "upgrade";
    }

-    # Static files caching
-    location /_next/static/ {
-        proxy_pass http://frontend;
-        proxy_cache_valid 200 365d;
-        add_header Cache-Control "public, max-age=31536000, immutable";
-    }
-
    # Error pages
    error_page 500 502 503 504 /50x.html;
    location = /50x.html {
        root /usr/share/nginx/html;
    }
 }
+
+# Redirect www to non-www
+server {
+    listen 443 ssl http2;
+    listen [::]:443 ssl http2;
+    server_name www.wordly.art;
+
+    ssl_certificate /etc/nginx/ssl/fullchain.pem;
+    ssl_certificate_key /etc/nginx/ssl/privkey.pem;
+
+    return 301 https://wordly.art$request_uri;
+}
--- a/docker/prometheus/alerts.yml
+++ b/docker/prometheus/alerts.yml
@@ -0,0 +1,101 @@
+# Wordly.art - Prometheus Alert Rules
+
+groups:
+  # Application alerts
+  - name: wordly_app
+    rules:
+      - alert: BackendDown
+        expr: up{job="wordly-backend"} == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Wordly backend is down"
+          description: "Backend has been down for more than 2 minutes."
+
+      - alert: HighErrorRate
+        expr: rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m]) > 0.1
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High error rate detected"
+          description: "More than 10% of requests are returning 5xx errors."
+
+      - alert: SlowTranslations
+        expr: histogram_quantile(0.95, rate(translation_duration_seconds_bucket[5m])) > 120
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Translations are slow"
+          description: "95th percentile translation time is over 120 seconds."
+
+      - alert: HighTranslationQueue
+        expr: translation_queue_size > 20
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Translation queue is backing up"
+          description: "More than 20 translations queued."
+
+  # System alerts
+  - name: wordly_system
+    rules:
+      - alert: HighMemoryUsage
+        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes > 0.9
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High memory usage"
+          description: "Server memory usage is above 90%."
+
+      - alert: DiskSpaceLow
+        expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) < 0.15
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Low disk space"
+          description: "Less than 15% disk space remaining on /."
+
+      - alert: DiskSpaceCritical
+        expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) < 0.05
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Critical disk space"
+          description: "Less than 5% disk space remaining on /."
+
+      - alert: HighCPUUsage
+        expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU usage"
+          description: "CPU usage is above 85% for 10 minutes."
+
+  # Docker alerts
+  - name: wordly_docker
+    rules:
+      - alert: ContainerRestarted
+        expr: increase(container_restart_count[1h]) > 2
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Container restarting"
+          description: "Container {{ $labels.name }} has restarted more than 2 times in the last hour."
+
+      - alert: ContainerOOM
+        expr: increase(container_oom_events_total[1h]) > 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Container OOM killed"
+          description: "Container {{ $labels.name }} was OOM killed."
--- a/docker/prometheus/prometheus.yml
+++ b/docker/prometheus/prometheus.yml
@@ -1,37 +1,34 @@
-# Prometheus Configuration for Document Translation API
+# Wordly.art - Prometheus Configuration

 global:
  scrape_interval: 15s
  evaluation_interval: 15s
  external_labels:
-    monitor: 'translate-api'
+    monitor: 'wordly-homelab'
+    environment: 'production'

-alerting:
-  alertmanagers:
-    - static_configs:
-        - targets: []
-
-rule_files: []
+rule_files:
+  - 'alerts.yml'

 scrape_configs:
-  # Backend API metrics
-  - job_name: 'translate-backend'
+  # Backend FastAPI
+  - job_name: 'wordly-backend'
    static_configs:
      - targets: ['backend:8000']
    metrics_path: /metrics
    scrape_interval: 10s

-  # Nginx metrics (requires nginx-prometheus-exporter)
-  - job_name: 'nginx'
-    static_configs:
-      - targets: ['nginx-exporter:9113']
-
-  # Node exporter for system metrics
+  # Systeme (CPU, RAM, Disk, Reseau)
  - job_name: 'node'
    static_configs:
      - targets: ['node-exporter:9100']

-  # Docker metrics
+  # Containers Docker
  - job_name: 'docker'
    static_configs:
      - targets: ['cadvisor:8080']
+
+  # Prometheus lui-meme
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']