apiVersion: apps/v1
kind: Deployment
metadata:
  name: hermes
  namespace: platform-engineer
  labels:
    app: hermes
spec:
  replicas: 1   # MUST be 1 — Hermes' /opt/data is single-writer.
  strategy:
    type: Recreate   # never run two pods against the same PVC
  selector:
    matchLabels:
      app: hermes
  template:
    metadata:
      labels:
        app: hermes
    spec:
      # No serviceAccountName — the agent has NO k8s API access. It manages the
      # cluster via git commits (→ ArgoCD sync) and reads via Loki/Prometheus/ArgoCD.

      # Pin to the powerful amd64 node (image is linux/amd64; the NUC has 24 GiB).
      nodeSelector:
        kubernetes.io/arch: amd64
      affinity:
        nodeAffinity:
          preferredDuringSchedulingIgnoredDuringExecution:
          - weight: 100
            preference:
              matchExpressions:
              - key: hardware
                operator: In
                values: ["high-memory"]
        podAntiAffinity:
          preferredDuringSchedulingIgnoredDuringExecution:
          - weight: 100
            podAffinityTerm:
              labelSelector:
                matchLabels:
                  app: hermes
              topologyKey: kubernetes.io/hostname

      initContainers:
      # Clone the k3s-cluster repo into a persistent workspace so the agent can
      # commit + push remediations. The token is injected via envFrom.
      - name: git-clone
        image: alpine/git:2.43.0
        command: ["sh", "-c"]
        args:
        - |
          set -e
          cd /workspace
          if [ -d k3s-cluster/.git ]; then
            echo "Repo exists, pulling latest..."
            cd k3s-cluster && git pull --rebase || true
          else
            echo "Cloning repo..."
            git clone "${GITEA_REPO_URL}" k3s-cluster
            cd k3s-cluster
            git config user.name "Platform Engineer"
            git config user.email "platform-engineer@rogi.casa"
          fi
        envFrom:
        - secretRef:
            name: hermes-env
        volumeMounts:
        - name: workspace
          mountPath: /workspace

      # Seed /opt/data with config.yaml + SOUL.md + .env on first boot only.
      # ArgoCD owns the manifests; the PVC is runtime state and is NOT reconciled.
      - name: seed-data
        image: busybox:1.36
        command: ["sh", "-c"]
        args:
        - |
          set -e
          if [ ! -f /opt/data/config.yaml ]; then
            echo "First boot: seeding /opt/data from ConfigMap + env..."
            cp /seed/config.yaml /opt/data/config.yaml
            cp /seed/SOUL.md /opt/data/SOUL.md
            chmod 600 /opt/data/config.yaml
            # Write .env from the injected Secret env vars so the s6 gateway
            # finds API keys (the hermes container reads keys from /opt/data/.env).
            : > /opt/data/.env
            chmod 600 /opt/data/.env
            for k in OPENAI_API_KEY OPENAI_BASE_URL DISCORD_BOT_TOKEN DISCORD_HOME_CHANNEL \
                     DISCORD_ALLOW_ALL_USERS DISCORD_FREE_RESPONSE_CHANNELS \
                     GITEA_TOKEN GITEA_REPO_URL ARGOCD_API_TOKEN ARGOCD_SERVER \
                     HERMES_DASHBOARD HERMES_DASHBOARD_BASIC_AUTH_USERNAME \
                     HERMES_DASHBOARD_BASIC_AUTH_PASSWORD HERMES_DASHBOARD_BASIC_AUTH_SECRET \
                     API_SERVER_KEY; do
              eval "v=\${$k:-}"
              [ -n "$v" ] && echo "$k=$v" >> /opt/data/.env
            done
          else
            echo "/opt/data already initialized — leaving runtime state intact."
          fi
          mkdir -p /opt/data/home/.kube /opt/data/cron/output /opt/data/scripts
        envFrom:
        - secretRef:
            name: hermes-env
        volumeMounts:
        - name: data
          mountPath: /opt/data
        - name: seed
          mountPath: /seed

      containers:
      - name: hermes
        image: nousresearch/hermes-agent:latest
        imagePullPolicy: Always
        # IMPORTANT: do NOT set `command:` — it would override the image's
        # ENTRYPOINT (/init, s6-overlay), which sets up the hermes user, seeds
        # config on first boot, and supervises the gateway.
        args: ["gateway", "run"]
        ports:
        - name: gateway
          containerPort: 8642
        - name: dashboard
          containerPort: 9119
        envFrom:
        - secretRef:
            name: hermes-env
        env:
        - name: HERMES_HOME
          value: /opt/data
        # Hermes' file-write tool refuses any path outside HERMES_WRITE_SAFE_ROOT.
        # When unset it defaults to HERMES_HOME (/opt/data), which blocks the
        # agent's only GitOps remediation path (editing manifests under
        # /workspace/k3s-cluster). Whitelist the whole filesystem — consistent
        # with yolo:true, approvals.mode:off, and the agent having no k8s RBAC.
        - name: HERMES_WRITE_SAFE_ROOT
          value: "/"
        # Expose the Hermes gateway HTTP API on port 8642 (the Service routes
        # 80 → 8642). Used by Open WebUI and other in-cluster clients to talk
        # to the agent as an OpenAI-compatible endpoint.
        - name: API_SERVER_ENABLED
          value: "true"
        # Bind the gateway API on all interfaces so other pods can reach it
        # via the Service (default is 127.0.0.1/loopback, which is unreachable
        # cross-pod). Auth is still enforced via API_SERVER_KEY.
        - name: API_SERVER_HOST
          value: "0.0.0.0"
        # Distinct model id advertised on GET /v1/models. Without this both
        # agents report "hermes-agent" and Open WebUI dedupes them, hiding one.
        - name: API_SERVER_MODEL_NAME
          value: "platform-engineer"
        # NOTE: API_SERVER_KEY comes from the hermes-env Secret (via envFrom)
        # and is also seeded into /opt/data/.env by the init container. Clients
        # (e.g. Open WebUI) authenticate with `Authorization: Bearer <key>`.
        volumeMounts:
        - name: data
          mountPath: /opt/data
        - name: workspace
          mountPath: /workspace
        resources:
          requests:
            memory: "512Mi"
            cpu: "250m"
          limits:
            memory: "2Gi"
            cpu: "1000m"
        livenessProbe:
          # Probe the dashboard port (9119, always enabled via HERMES_DASHBOARD=1
          # and binds 0.0.0.0). The gateway API on 8642 is enabled via
          # API_SERVER_ENABLED=true above.
          tcpSocket:
            port: 9119
          initialDelaySeconds: 90
          periodSeconds: 30
          timeoutSeconds: 5
          failureThreshold: 5
        securityContext:
          allowPrivilegeEscalation: false

      volumes:
      - name: data
        persistentVolumeClaim:
          claimName: hermes-data
      - name: workspace
        emptyDir: {}
      - name: seed
        configMap:
          name: hermes-seed
---
apiVersion: v1
kind: Service
metadata:
  name: hermes
  namespace: platform-engineer
spec:
  type: ClusterIP
  selector:
    app: hermes
  ports:
    - name: gateway
      port: 80
      targetPort: 8642
    - name: dashboard
      port: 9119
      targetPort: 9119