apiVersion: apps/v1
kind: Deployment
metadata:
  name: bot
  namespace: conjurer
spec:
  replicas: 1                     # NIGDY więcej — jedna sesja gateway na token
  strategy: { type: Recreate }    # NIE RollingUpdate — dwa pody = wojna o sesję Discord
  selector: { matchLabels: { app: bot } }
  template:
    metadata: { labels: { app: bot } }
    spec:
      imagePullSecrets: [{ name: gitea-registry }]
      containers:
        - name: bot
          image: gitea.czernobog.pl/gitea/conjurer-bot:c8aae106
          ports: [{ containerPort: 5000 }]
          env:
            - { name: CONJURER_DATA_DIR,      value: "/data" }
            - { name: CONJURER_DISCORD_HOST,  value: "0.0.0.0" }
            - { name: CONJURER_DISCORD_PORT,  value: "5000" }
            - { name: CONJURER_API_KEY,  value: "d97008b3-7a5a-11f1-acd1-000b0e0f00ed" }
            - { name: CONJURER_NETRC_FILE, value: "/secrets/.netrc" }
            # ↓ NAZWY PODSTAW WG WYNIKU grepa z 0.2 ↓
            - { name: CONJURER_LIBRARIAN_SERVICE, value: "http://librarian:5001" }
            - { name: CONJURER_MUSICIAN_SERVICE,  value: "http://192.168.1.89:5000" }
            - { name: CONJURER_RADIO_SERVICE,     value: "http://192.168.1.79:5005" }
            - { name: CONJURER_FILE_SERVICE,     value: "http://192.168.1.89:5000" }

            - { name: CONJURER_RADIO_HARBOR,      value: "http://192.168.1.79:54321" }
            # Where the librarian sends THIS bot's results/pongs back to (its own
            # NodePort). Lets one librarian serve both bots - see deploy-bot.yaml.
            - { name: CONJURER_SELF_CALLBACK,     value: "http://192.168.1.73:32442" }
            # Self-hosted models (Ollama). No API key - the endpoint IS the
            # configuration, and the backend stays unselectable while unset.
            # Pick a model at runtime with: $gadaj_teraz ollama <model>
            # ($modele_ai lists what the server actually has pulled).
            - { name: CONJURER_OLLAMA_URL,        value: "http://192.168.1.72:11434" }
            # The server currently has exactly one model pulled (verified via
            # /v1/models): gemma4:e2b. Without this the built-in default
            # (llama3.1:8b) would be requested and every reply would fail.
            - { name: CONJURER_OLLAMA_MODEL,      value: "gemma4:e2b" }
            # Self-hosted generation is far slower than a hosted API, especially
            # the first request after the model is evicted from VRAM. Applies to
            # every backend, so keep it only as high as you actually need.
            - { name: CONJURER_AI_TIMEOUT_SECONDS, value: "240" }
          volumeMounts:
            - { name: data,  mountPath: /data }
            - { name: netrc, mountPath: /secrets, readOnly: true }
          resources:
            requests: { cpu: "200m", memory: "256Mi" }
            limits:   { cpu: "2",    memory: "1Gi" }
      volumes:
        - name: data
          persistentVolumeClaim: { claimName: bot-data }
        - name: netrc
          secret: { secretName: conjurer-netrc }
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata: { name: bot-data, namespace: conjurer }
spec:
  accessModes: [ReadWriteOnce]
  resources: { requests: { storage: 2Gi } }
---
apiVersion: v1
kind: Service
metadata: { name: bot, namespace: conjurer }
spec:
  type: NodePort                  # radio/musician z Dockera muszą go dosięgnąć
  selector: { app: bot }
  # nodePort PRZYPIĘTY na sztywno. Bez tego k8s losuje port z 30000-32767 przy
  # (od)tworzeniu Service, a musician/betoniarka z Dockera adresują bota po
  # http://192.168.1.73:32442 na sztywno - rozjazd = wyniki/eventy giną w locie.
  ports: [{ port: 5000, targetPort: 5000, nodePort: 32442 }]