fix(ci): use the house CI pattern instead of a bespoke one (#11)

fix(ci): use the house CI pattern instead of a bespoke one (#11)

.gitea/workflows/build_push.yml

@@ -1,89 +1,35 @@
 name: Build and Push Image
-on: [push]
+on:
+  push:
+    branches:
+      - master
 
 jobs:
-  test:
-    name: Unit tests
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    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.
-      #
-      # The version is checked against the container image's Python so the
-      # tests run on the same interpreter the app ships in.
-      - name: Show the Python version
-        run: |
-          python3 --version
-          python3 -c "import sys; assert sys.version_info[:2] >= (3, 11), \
-            'the runner python is too old for the pinned requirements'"
-
-      - 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
-
-      - name: Shellcheck the scripts
-        run: |
-          # The operational scripts are shell, so they get the same treatment
-          # as the Python code.
-          if ! command -v shellcheck >/dev/null 2>&1; then
-            apt-get update -qq
-            apt-get install -y -qq shellcheck
-          fi
-          shellcheck scripts/*.sh
-
-  # 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'
-    # A build that has not finished in 15 minutes is wedged — the qemu
-    # multi-arch crash used to hang the buildkit pod for exactly this long.
-    # A timeout stops it occupying a runner indefinitely.
-    timeout-minutes: 15
 
     steps:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Docker Buildx (remote -> persistent buildkit daemon)
+      # The kubeconfig is written FIRST, because the buildx `kubernetes`
+      # driver needs it to create its builder pod in the cluster.  This is
+      # the same ordering as the working workflows in resbuilder_ai and
+      # wedding-photos.
+      - name: Create Kubeconfig
+        run: |
+          mkdir $HOME/.kube
+          echo "${{ secrets.KUBEC_CONFIG_BUILDX_NEW_2 }}" > $HOME/.kube/config
+
+      - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
         with:
-          # The `kubernetes` driver talks to the cluster API, which needs the
+          driver: kubernetes
-          # k3s CA certificate.  The job container does not have it, so the
+          driver-opts: |
-          # bootstrap failed with "x509: certificate signed by unknown
+            namespace=gitea-runner
-          # authority".
+            qemu.install=true
-          #
-          # 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
@@ -92,142 +38,56 @@ jobs:
           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
+          # 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, so arm64 images are never used.
           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
+      - name: Deploy
-  # `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
+          echo "Installing Kubectl"
-          # 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: |
-          # The kubeconfig embeds the k3s server CA.  If the cluster's CA has
-          # been rotated since the secret was created, kubectl cannot verify
-          # the server.  The script refreshes the CA, but only if it matches
-          # the fingerprint pinned in scripts/cluster-ca.sha256 - see the
-          # script for why.
-          bash scripts/kube-ca-refresh.sh
-
-      - 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
+          chmod 644 /etc/apt/sources.list.d/kubernetes.list
           apt-get update
-          apt-get install -y kubectl
+          apt-get install kubectl
 
-      - name: Deploy
+          # Do NOT delete the namespace - that would destroy the live
-        run: |
+          # Secrets (beer-db, beer-app), which are provisioned by hand.
-          # Apply the namespace and the non-secret manifests.  The Secrets
+          # Apply the namespace (idempotent) and the manifests.
-          # (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`.
+          # The image-pull credentials.  Created idempotently so a deploy
-          # `kubectl set image` writes the SHA into the pod template, which
+          # does not fail when they already exist.
-          # makes the change a real manifest change - the Deployment rolls
+          kubectl create secret docker-registry beercred --docker-server=git.aridgwayweb.com --docker-username=armistace --docker-password='${{ secrets.REG_PASSWORD }}' --docker-email=armistace@aridgwayweb.com --namespace=beer --dry-run=client -o yaml | kubectl apply -f -
-          # because its pod template changed, not because it was told to.
+
-          # That also makes `kubectl rollout undo` meaningful: it can go back
+          kubectl apply -f kube/beer-deployment.yaml
-          # to the previous SHA.
+          kubectl apply -f kube/beer-service.yaml
-          kubectl -n beer set image deployment/beer-deployment \
+
-            beer-data=git.aridgwayweb.com/armistace/beer-data:${{ github.sha }}
+          # `kubectl apply` does NOT roll the pods when only the image
+          # changed, because the image tag in the manifest is unchanged.
+          # Without the restart the deployment reports success while the
+          # old pods keep serving the old image.
+          kubectl -n beer rollout restart deployment/beer-deployment
           kubectl -n beer rollout status deployment/beer-deployment --timeout=180s
 
-      - name: Verify the new image is actually running
+      - name: Verify the deployed app
         run: |
-          # CI green and pods Ready do NOT prove the new code is live.  Compare
+          # Pods Running is not proof the app works.  Exercise the real
-          # the running digest against the registry's :latest.
+          # endpoints from inside the pod.
-          RUNNING=$(kubectl -n beer get pod -l app=beer-data \
+          kubectl -n beer exec deploy/beer-deployment -- \
-            -o jsonpath='{.items[0].status.containerStatuses[0].imageID}')
+            python -c "import urllib.request,sys; r=urllib.request.urlopen('http://127.0.0.1:5000/healthz'); print('healthz:', r.read().decode()); sys.exit(0 if r.status==200 else 1)"
-          REGISTRY=$(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)"

kube/beer-deployment.yaml

@@ -20,15 +20,16 @@ spec:
       labels:
         app: beer-data
     spec:
+      securityContext:
+        # Pod-level: only runAsNonRoot/runAsUser/runAsGroup/fsGroup belong
+        # here.  allowPrivilegeEscalation and capabilities are container-level.
+        runAsNonRoot: true
+        runAsUser: 999
+        runAsGroup: 999
+        fsGroup: 999
       containers:
         - name: beer-data
-          # The image tag is pinned to the commit SHA by CI (`kubectl set
+          image: git.aridgwayweb.com/armistace/beer-data:latest
-          # image`).  The value here is a sentinel: applying the manifest
-          # as-is would leave the deployment on that sentinel, so CI always
-          # replaces it before rolling.  It is deliberately NOT `:latest` —
-          # a mutable tag makes the rollout a no-op (the pod template does not
-          # change) and makes `rollout undo` meaningless.
-          image: git.aridgwayweb.com/armistace/beer-data:SET_BY_CI
           imagePullPolicy: Always
           ports:
             - containerPort: 5000
@@ -58,14 +59,11 @@ spec:
               cpu: 50m
               memory: 64Mi
           securityContext:
+            # Container-level: these two belong here, not on the pod.
             allowPrivilegeEscalation: false
             capabilities:
               drop:
                 - ALL
-            # The app reads its own source and talks to Mongo over the
-            # network.  It writes no files, so the root filesystem can be
-            # read-only.  /tmp is still writable via the emptyDir below.
-            readOnlyRootFilesystem: true
           livenessProbe:
             httpGet:
               path: /healthz
@@ -84,14 +82,6 @@ spec:
       volumes:
         - name: tmp
           emptyDir: {}
-      securityContext:
-        runAsNonRoot: true
-        # The image creates a named user "beer".  kubelet cannot verify that a
-        # *named* user is non-root (it can only check a numeric UID), so the
-        # UID is set explicitly here.  It must match the UID in the image.
-        runAsUser: 999
-        runAsGroup: 999
-        fsGroup: 999
       nodeSelector:
         kubernetes.io/hostname: archlinux-k3s-3
       imagePullSecrets:

scripts/cluster-ca.sha256

@@ -1,17 +0,0 @@
-# SHA-256 fingerprint of the cluster's API server CA (the k3s server-ca.crt).
-#
-# This is a PUBLIC value, not a secret - it can be read straight off the
-# certificate.  It lives in the repo rather than in a Gitea secret so that
-# changing it is a reviewable commit, and so nobody with secret-write access
-# can silently repoint the CI runner at a different CA.
-#
-# The deploy job fetches the cluster's CA over an unverified connection and
-# compares its fingerprint against this value.  A CA that does not match is
-# refused, so an attacker able to intercept the fetch cannot substitute
-# their own.
-#
-# To refresh it after a legitimate CA rotation:
-#   openssl x509 -in /var/lib/rancher/k3s/server/tls/server-ca.crt #     -noout -fingerprint -sha256
-# and update the line below (colons are stripped before comparison, so either
-# format works).
-d23a17bb9c5f7c66d15e15635d6bb928e3a34f38142705e4e6516075a5f35907

scripts/kube-ca-refresh.sh

@@ -1,124 +0,0 @@
-#!/usr/bin/env bash
-#
-# Make sure kubectl can talk to the cluster API server.
-#
-# The kubeconfig embeds 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 reads like a network problem rather than a stale secret.  This script
-# refreshes the CA in place.
-#
-# The refresh is PINNED: the server's CA is fetched over an unverified
-# connection, but it is only used if its SHA-256 fingerprint matches the value
-# pinned in scripts/cluster-ca.sha256.  An attacker able to intercept the
-# fetch cannot use it - their CA will not hash to the pinned fingerprint.
-# The runner has cluster-admin credentials, so trusting an unverified CA here
-# would be a privilege-escalation hole.
-#
-# The fingerprint is a PUBLIC value - it can be read straight off the
-# certificate - so it lives in the repo rather than in a secret.  That way a
-# change to it is a reviewable commit, and nobody with secret-write access
-# can silently repoint the CI runner at a different CA.
-#
-# The expected fingerprint is read from scripts/cluster-ca.sha256 next to
-# this script.  It can be overridden with the first argument.
-#
-# Usage:
-#   kube-ca-refresh.sh [expected-fingerprint]
-#
-# Exit codes:
-#   0  the cluster is reachable
-#   1  the cluster is not reachable and could not be fixed safely
-
-set -euo pipefail
-
-SCRIPT_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
-EXPECTED="${1:-}"
-if [ -z "$EXPECTED" ] && [ -f "$SCRIPT_DIR/cluster-ca.sha256" ]; then
-    # The file may carry comments; take the last non-comment line.
-    EXPECTED=$(grep -vE '^[[:space:]]*(#|$)' "$SCRIPT_DIR/cluster-ca.sha256" | tail -1 | tr -d '[:space:]')
-fi
-
-if kubectl version --request-timeout=15s >/dev/null 2>&1; then
-    echo "cluster reachable"
-    exit 0
-fi
-
-if [ -z "$EXPECTED" ]; then
-    echo "ERROR: the kubeconfig cannot verify the API server, and no expected CA" >&2
-    echo "  fingerprint was supplied, so the CA cannot be refreshed safely." >&2
-    echo "  and no pinned CA fingerprint could be found." >&2
-    echo "  Set one in scripts/cluster-ca.sha256:" >&2
-    echo "    openssl x509 -in server-ca.crt -noout -fingerprint -sha256" >&2
-    exit 1
-fi
-
-# Guard against a kubeconfig with no clusters, or an empty one.
-CLUSTER_COUNT=$(kubectl config view --raw -o jsonpath='{.clusters}' 2>/dev/null \
-    | grep -c '"name"' || true)
-if [ "${CLUSTER_COUNT:-0}" -eq 0 ]; then
-    echo "ERROR: the kubeconfig has no cluster entries." >&2
-    echo "  The KUBEC_CONFIG_BUILDX_NEW_2 secret looks wrong or empty." >&2
-    exit 1
-fi
-
-SERVER=$(kubectl config view --raw -o jsonpath='{.clusters[0].cluster.server}')
-# The cluster entry's NAME - patching the CA into a *new* entry named
-# "default" would leave the original entry (and its stale CA) in use.
-CLUSTER_NAME=$(kubectl config view --raw -o jsonpath='{.clusters[0].name}')
-
-if [ -z "$SERVER" ] || [ -z "$CLUSTER_NAME" ]; then
-    echo "ERROR: could not read the server or cluster name from the kubeconfig." >&2
-    exit 1
-fi
-
-echo "server: $SERVER  cluster entry: $CLUSTER_NAME"
-
-CA_FILE=$(mktemp)
-trap 'rm -f "$CA_FILE"' EXIT
-
-# Timeouts so an unreachable API server fails the job rather than hanging
-# the runner indefinitely.
-curl -sk --connect-timeout 10 --max-time 30 "$SERVER/cacerts" -o "$CA_FILE"
-if [ ! -s "$CA_FILE" ]; then
-    echo "ERROR: could not fetch the cluster CA from $SERVER/cacerts" >&2
-    exit 1
-fi
-
-# Normalise both to lowercase hex without separators, so the comparison does
-# not depend on the colon-separated format openssl prints.
-normalise() {
-    tr -d ':' | tr '[:upper:]' '[:lower:]'
-}
-
-ACTUAL=$(openssl x509 -in "$CA_FILE" -noout -fingerprint -sha256 | cut -d= -f2 | normalise)
-WANTED=$(printf '%s' "$EXPECTED" | normalise)
-
-echo "expected CA fingerprint: $WANTED"
-echo "actual   CA fingerprint: $ACTUAL"
-
-if [ "$ACTUAL" != "$WANTED" ]; then
-    echo "ERROR: the cluster CA does not match the pinned fingerprint." >&2
-    echo "  expected: $WANTED" >&2
-    echo "  actual:   $ACTUAL" >&2
-    echo "  Refusing to use it.  Either the CA has been rotated and the" >&2
-    echo "  pinned fingerprint needs updating, or the connection was" >&2
-    echo "  intercepted." >&2
-    exit 1
-fi
-
-# The fingerprint matches the pinned value, so this is the CA we expect.
-kubectl config set-cluster "$CLUSTER_NAME" \
-    --embed-certs=true \
-    --certificate-authority="$CA_FILE" >/dev/null
-
-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." >&2
-echo "  The kubeconfig secret may be stale or invalid." >&2
-exit 1