---
# cloudflared — the Cloudflare Tunnel connector. Outbound-only: it dials the Cloudflare edge on
# 7844 (QUIC, falling back to HTTP/2 over TCP) and carries requests for the tunnel's hostnames
# back to the shared Gateway. Nothing listens on the LAN and no router port is opened.
#
# HA: 2 replicas, hard-spread across nodes. Each replica registers its own set of edge
# connections for the SAME tunnel, so Cloudflare load-balances between them and losing one node
# (a kured reboot, a drain) loses no traffic. The PDB in this directory keeps a drain from taking
# both at once.
apiVersion: apps/v1
kind: Deployment
metadata:
  name: cloudflared
  namespace: cloudflared
  labels:
    app.kubernetes.io/name: cloudflared
spec:
  replicas: 2
  revisionHistoryLimit: 3
  strategy:
    type: RollingUpdate
    rollingUpdate:
      # Never drop below the running count during a rollout; with 3 nodes and a hard spread the
      # surge pod always has a node to land on.
      maxUnavailable: 0
      maxSurge: 1
  selector:
    matchLabels:
      app.kubernetes.io/name: cloudflared
  template:
    metadata:
      labels:
        app.kubernetes.io/name: cloudflared
        # internet, NEVER vpn. The vpn class steers egress through the PIA tunnel (ADR-0015), which
        # would put the edge connections behind a third party's exit and its kill-switch — the
        # tunnel would drop whenever PIA does. This namespace is outside the app-namespace scope
        # of require-egress-class-label, so the label is declared for the steering, not to pass
        # admission; the L0 check cloudflared-ingress-rules pins it.
        homelab.keithjackson.dev/egress-class: internet
    spec:
      # cloudflared never talks to the Kubernetes API. No token mounted, and the egress policy
      # does not admit the kube-apiserver entity either.
      automountServiceAccountToken: false
      enableServiceLinks: false
      securityContext:
        runAsNonRoot: true
        # The image is distroless `nonroot` (65532).
        runAsUser: 65532
        runAsGroup: 65532
        seccompProfile:
          type: RuntimeDefault
      topologySpreadConstraints:
        - maxSkew: 1
          topologyKey: kubernetes.io/hostname
          whenUnsatisfiable: DoNotSchedule
          labelSelector:
            matchLabels:
              app.kubernetes.io/name: cloudflared
      # cloudflared drains in-flight requests for up to its own 30s grace-period on SIGTERM.
      terminationGracePeriodSeconds: 45
      containers:
        - name: cloudflared
          # Tag + digest: Renovate's `kubernetes` manager (renovate.json5, platform/**) bumps both.
          image: docker.io/cloudflare/cloudflared:2026.10.7@sha256:4955524aeaa379e154023d5a027c250f7b35041a2e7e950cf13f144bc9b9c5ba
          # The image ENTRYPOINT is `cloudflared --no-autoupdate`; these replace its CMD. The tunnel
          # UUID, credentials path, metrics address and ingress rules all come from the file.
          args:
            - tunnel
            - --config
            - /etc/cloudflared/config/config.yaml
            - run
          ports:
            - name: metrics
              containerPort: 2000
              protocol: TCP
          # /ready is 200 only while this replica holds at least one live edge connection, so an
          # unenrolled or edge-isolated replica is NotReady and the Deployment says so.
          readinessProbe:
            httpGet:
              path: /ready
              port: metrics
            initialDelaySeconds: 5
            periodSeconds: 10
            failureThreshold: 3
          # Liveness is deliberately NOT /ready: an edge outage would otherwise restart-loop every
          # replica, which reconnects nothing faster and churns the pods. /healthcheck answers
          # whenever the process is serving.
          livenessProbe:
            httpGet:
              path: /healthcheck
              port: metrics
            initialDelaySeconds: 10
            periodSeconds: 20
            failureThreshold: 3
          resources:
            requests:
              cpu: 10m
              memory: 64Mi
            limits:
              cpu: 500m
              memory: 256Mi
          securityContext:
            allowPrivilegeEscalation: false
            readOnlyRootFilesystem: true
            capabilities:
              drop:
                - ALL
          volumeMounts:
            - name: config
              mountPath: /etc/cloudflared/config
              readOnly: true
            - name: creds
              mountPath: /etc/cloudflared/creds
              readOnly: true
      volumes:
        - name: config
          configMap:
            # Rewritten to the content-hashed name by kustomize (configMapGenerator).
            name: cloudflared-config
        - name: creds
          secret:
            # cloudflared-credentials.sops.yaml — the tunnel credentials JSON, by name only.
            secretName: cloudflared-credentials
            defaultMode: 0440
---
# One replica may be disrupted at a time — enough for kured's one-node-at-a-time drain to
# proceed, never enough to take the tunnel down. minAvailable 1 (not 2) on purpose: a 0-disruption
# PDB wedges a drain (platform/kured/alerts.yaml, KuredRebootPending).
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
  name: cloudflared
  namespace: cloudflared
  labels:
    app.kubernetes.io/name: cloudflared
spec:
  minAvailable: 1
  selector:
    matchLabels:
      app.kubernetes.io/name: cloudflared