deploy/k8s/backend.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: voiceforge-backend
  namespace: voiceforge
  labels:
    app: voiceforge-backend
spec:
  replicas: 2
  selector:
    matchLabels:
      app: voiceforge-backend
  template:
    metadata:
      labels:
        app: voiceforge-backend
      annotations:
        prometheus.io/scrape: "true"
        prometheus.io/port: "8000"
        prometheus.io/path: "/metrics"
    spec:
      containers:
      - name: backend
        image: voiceforge/backend:latest
        ports:
        - containerPort: 8000
        env:
        - name: REDIS_URL
          valueFrom:
            secretKeyRef:
              name: voiceforge-secrets
              key: redis-url
        - name: ENCRYPTION_KEY
          valueFrom:
            secretKeyRef:
              name: voiceforge-secrets
              key: encryption-key
        - name: HF_TOKEN
          valueFrom:
            secretKeyRef:
              name: voiceforge-secrets
              key: hf-token
        resources:
          requests:
            memory: "512Mi"
            cpu: "250m"
          limits:
            memory: "2Gi"
            cpu: "1000m"
        livenessProbe:
          httpGet:
            path: /health
            port: 8000
          initialDelaySeconds: 30
          periodSeconds: 10
        readinessProbe:
          httpGet:
            path: /health
            port: 8000
          initialDelaySeconds: 5
          periodSeconds: 5
        volumeMounts:
        - name: uploads
          mountPath: /app/uploads
      volumes:
      - name: uploads
        persistentVolumeClaim:
          claimName: voiceforge-uploads-pvc
---
apiVersion: v1
kind: Service
metadata:
  name: voiceforge-backend
  namespace: voiceforge
spec:
  selector:
    app: voiceforge-backend
  ports:
  - port: 80
    targetPort: 8000
  type: ClusterIP
---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: voiceforge-backend-hpa
  namespace: voiceforge
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: voiceforge-backend
  minReplicas: 2
  maxReplicas: 10
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 70