apiVersion: v1
kind: Service
metadata:
  name: scraper-worker
  namespace: dispensary-scraper
  labels:
    app: scraper-worker
spec:
  clusterIP: None  # Headless service required for StatefulSet
  selector:
    app: scraper-worker
  ports:
  - port: 3010
    name: http
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: scraper-worker
  namespace: dispensary-scraper
spec:
  serviceName: scraper-worker
  replicas: 8
  podManagementPolicy: Parallel  # Start all pods at once
  updateStrategy:
    type: OnDelete  # Pods only update when manually deleted - no automatic restarts
  selector:
    matchLabels:
      app: scraper-worker
  template:
    metadata:
      labels:
        app: scraper-worker
    spec:
      terminationGracePeriodSeconds: 60
      imagePullSecrets:
      - name: regcred
      containers:
      - name: worker
        image: code.cannabrands.app/creationshop/dispensary-scraper:latest
        imagePullPolicy: Always
        command: ["node"]
        args: ["dist/tasks/task-worker.js"]
        env:
        - name: WORKER_MODE
          value: "true"
        - name: POD_NAME
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
        - name: MAX_CONCURRENT_TASKS
          value: "50"
        - name: API_BASE_URL
          value: http://scraper
        - name: NODE_OPTIONS
          value: --max-old-space-size=1500
        envFrom:
        - configMapRef:
            name: scraper-config
        - secretRef:
            name: scraper-secrets
        resources:
          requests:
            cpu: 100m
            memory: 1Gi
          limits:
            cpu: 500m
            memory: 2Gi
        livenessProbe:
          exec:
            command:
            - /bin/sh
            - -c
            - pgrep -f 'task-worker' > /dev/null
          initialDelaySeconds: 10
          periodSeconds: 30
          failureThreshold: 3