name: Build and Push Image
on: [push]

jobs:
  test:
    name: Unit tests
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      # NOTE: no actions/setup-python here.  That action downloads a Python
      # build from GitHub, which this runner cannot reach reliably - the job
      # hung on it.  The runner image already carries a usable python3, so
      # the tests use it directly.
      - name: Show the Python version
        run: python3 --version

      - name: Install dependencies
        run: |
          python3 -m venv .venv
          . .venv/bin/activate
          pip install --upgrade pip
          pip install -r requirements-dev.txt

      - name: Run tests
        run: |
          . .venv/bin/activate
          python -m pytest tests/ -q

  # NOTE: the build job deliberately does NOT have a kubeconfig.  The
  # `KUBEC_CONFIG_BUILDX` secret is cluster-admin-equivalent, and a build step
  # that has no need of the cluster should not be able to read it.  The deploy
  # step, added in a later PR, gets its own job with the kubeconfig - that way
  # a compromised dependency in the build cannot reach the cluster.
  build:
    name: Build and push image
    runs-on: ubuntu-latest
    container: catthehacker/ubuntu:act-latest
    needs: test
    if: gitea.ref == 'refs/heads/master'

    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Set up Docker Buildx (remote -> persistent buildkit daemon)
        uses: docker/setup-buildx-action@v3
        with:
          # The `kubernetes` driver talks to the cluster API, which needs the
          # k3s CA certificate.  The job container does not have it, so the
          # bootstrap failed with "x509: certificate signed by unknown
          # authority".
          #
          # The `remote` driver talks straight to the buildkit daemon that is
          # already running in the cluster, so no cluster API access (and no
          # kubeconfig) is needed at all.  This is the same pattern the
          # wedding-photos workflow uses successfully.
          #
          # NOTE: `endpoint` must be passed as a top-level key.  The action
          # appends it as the POSITIONAL argument to
          # `buildx create --driver remote <endpoint>`; putting it in
          # driver-opts instead yields "ERROR: no remote endpoint provided".
          driver: remote
          endpoint: tcp://buildkit.gitea-runner.svc:1234

      - name: Login to Docker Registry
        uses: docker/login-action@v3
        with:
          registry: git.aridgwayweb.com
          username: armistace
          password: ${{ secrets.REG_PASSWORD }}

      - name: Build Base Image
        uses: docker/build-push-action@v5
        with:
          context: .
          push: true
          file: base.Dockerfile
          # amd64 only.  A multi-arch build runs qemu emulation, which crashes
          # the buildkit pod on this NUC (exit 255, SandboxChanged) and the
          # build then hangs for many minutes.  The cluster is amd64.
          platforms: linux/amd64
          tags: |
            git.aridgwayweb.com/armistace/beer_base_image:latest

      - name: Build and Push
        uses: docker/build-push-action@v5
        with:
          context: .
          push: true
          file: flask.Dockerfile
          platforms: linux/amd64
          tags: |
            git.aridgwayweb.com/armistace/beer-data:latest
            git.aridgwayweb.com/armistace/beer-data:${{ github.sha }}

  # The deploy job is separate from the build job on purpose.  The
  # `KUBEC_CONFIG_BUILDX` secret is cluster-admin-equivalent, and a build
  # step that never talks to the cluster should not be able to read it - a
  # compromised dependency in the build would otherwise have a direct path to
  # the cluster.
  deploy:
    name: Deploy to the cluster
    runs-on: ubuntu-latest
    needs: build
    if: gitea.ref == 'refs/heads/master'
    timeout-minutes: 10

    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Create Kubeconfig
        run: |
          mkdir -p $HOME/.kube
          # Written with restrictive permissions: the kubeconfig is
          # cluster-admin-equivalent, so it should not be readable by
          # anything else on the runner.
          install -m 600 /dev/null $HOME/.kube/config
          echo "${{ secrets.KUBEC_CONFIG_BUILDX_NEW_2 }}" > $HOME/.kube/config
          chmod 600 $HOME/.kube/config

      - name: Verify the cluster is reachable
        run: |
          # Fail fast, and with a useful message, if the kubeconfig cannot
          # talk to the API server.
          #
          # The certificate-authority-data inside the kubeconfig is the k3s
          # server CA.  If the cluster's CA has been rotated since the secret
          # was created, kubectl fails with:
          #   tls: failed to verify certificate: x509: certificate signed by
          #   unknown authority
          # which is a confusing way to learn that a secret is stale.
          if kubectl version --request-timeout=15s >/dev/null 2>&1; then
            echo "cluster reachable"
            exit 0
          fi

          echo "the kubeconfig could not verify the API server - refreshing the CA"

          # The API server publishes its own CA at /cacerts.  Fetch it over an
          # insecure connection - we cannot verify it yet, that is the problem
          # being solved - and pin it explicitly.  This makes the deploy
          # self-healing after a CA rotation, instead of needing the secret
          # to be regenerated by hand.
          SERVER=$(kubectl config view --raw -o jsonpath='{.clusters[0].cluster.server}')
          echo "server: $SERVER"
          curl -sk "$SERVER/cacerts" -o $HOME/.kube/ca.crt

          if [ ! -s $HOME/.kube/ca.crt ]; then
            echo "ERROR: could not fetch the cluster CA from $SERVER/cacerts"
            exit 1
          fi

          kubectl config set-cluster default \
            --embed-certs=true \
            --certificate-authority=$HOME/.kube/ca.crt >/dev/null
          rm -f $HOME/.kube/ca.crt

          if kubectl version --request-timeout=15s >/dev/null 2>&1; then
            echo "cluster reachable after refreshing the CA"
            exit 0
          fi

          echo "ERROR: cannot reach the cluster API server even with a refreshed CA."
          echo "  The kubeconfig in the KUBEC_CONFIG_BUILDX_NEW_2 secret may be"
          echo "  stale or invalid, and needs regenerating."
          exit 1

      - name: Install kubectl
        run: |
          # Skip the whole apt dance if the runner already has a kubectl.
          if command -v kubectl >/dev/null 2>&1; then
            kubectl version --client
            exit 0
          fi
          apt-get update
          apt-get install -y apt-transport-https ca-certificates curl gnupg
          curl -fsSL https://pkgs.k8s.io/core:/stable:/v1.33/deb/Release.key | gpg --dearmor -o /etc/apt/keyrings/kubernetes-apt-keyring.gpg
          chmod 644 /etc/apt/keyrings/kubernetes-apt-keyring.gpg
          echo 'deb [signed-by=/etc/apt/keyrings/kubernetes-apt-keyring.gpg] https://pkgs.k8s.io/core:/stable:/v1.33/deb/ /' | tee /etc/apt/sources.list.d/kubernetes.list
          apt-get update
          apt-get install -y kubectl

      - name: Deploy
        run: |
          # Apply the namespace and the non-secret manifests.  The Secrets
          # (beer-db, beer-app) are hand-provisioned and are NOT in the repo,
          # so they are deliberately not in the apply set.
          kubectl apply -f kube/beer_namespace.yaml
          kubectl apply -f kube/beer-service.yaml
          # The deployment manifest carries a sentinel image tag; the real
          # SHA-pinned image is set immediately below.  Applying it here
          # keeps the rest of the spec (probes, resources, security context)
          # in the repo and under review.
          kubectl apply -f kube/beer-deployment.yaml

          # The image is pinned to the commit SHA rather than `:latest`.
          # `kubectl set image` writes the SHA into the pod template, which
          # makes the change a real manifest change - the Deployment rolls
          # because its pod template changed, not because it was told to.
          # That also makes `kubectl rollout undo` meaningful: it can go back
          # to the previous SHA.
          kubectl -n beer set image deployment/beer-deployment \
            beer-data=git.aridgwayweb.com/armistace/beer-data:${{ github.sha }}
          kubectl -n beer rollout status deployment/beer-deployment --timeout=180s

      - name: Verify the new image is actually running
        run: |
          # CI green and pods Ready do NOT prove the new code is live.  Compare
          # the running digest against the registry's :latest.
          RUNNING=$(kubectl -n beer get pod -l app=beer-data \
            -o jsonpath='{.items[0].status.containerStatuses[0].imageID}')
          REGISTRY=$(curl -s -u "armistace:${{ secrets.REG_PASSWORD }}" -I \
            "https://git.aridgwayweb.com/v2/armistace/beer-data/manifests/latest" \
            -H "Accept: application/vnd.docker.distribution.manifest.v2+json" \
            | grep -i docker-content-digest | awk '{print $2}' | tr -d '\r')
          echo "running:  $RUNNING"
          echo "registry: $REGISTRY"
          if [ "$RUNNING" != "$REGISTRY" ]; then
            echo "ERROR: the running pod is not the image that was just pushed"
            exit 1
          fi

      - name: Remove the kubeconfig
        if: always()
        run: rm -f $HOME/.kube/config

      - name: Smoke test the deployed app
        run: |
          # Check the app's own port from inside the pod, AND the Service in
          # front of it.  The pod check alone would pass even if the Service
          # selector or the port mapping were wrong, which is exactly the
          # kind of breakage a deploy can introduce silently.
          for i in $(seq 1 12); do
            if kubectl -n beer exec deploy/beer-deployment -- \
                python -c "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:5000/healthz').status==200 else 1)"; then
              echo "healthz OK"
              break
            fi
            echo "waiting for the app to come up ($i/12)"
            sleep 5
          done
          kubectl -n beer exec deploy/beer-deployment -- \
            python -c "import urllib.request,sys; r=urllib.request.urlopen('http://127.0.0.1:5000/readyz'); print('readyz:', r.read().decode()); sys.exit(0 if r.status==200 else 1)"

          # Through the Service - the path a real client takes.
          kubectl -n beer run smoke --rm -i --restart=Never --image=python:3.14-slim -- \
            python -c "import urllib.request,sys; r=urllib.request.urlopen('http://beer-service.beer.svc.cluster.local/healthz'); print('service healthz:', r.read().decode()); sys.exit(0 if r.status==200 else 1)"