relay/.github/workflows/test-and-deploy.yaml

name: deploy on staging2.testrun.org, and run tests

on:
  push:
    branches:
      - main
      - j4n/docker-pr
  pull_request:
    paths-ignore:
      - 'scripts/**'
      - '**/README.md'
      - 'CHANGELOG.md'
      - 'LICENSE'

env:
  REGISTRY: ghcr.io
  IMAGE_NAME: ${{ github.repository }}

jobs:
  build-docker:
    name: Build Docker image
    runs-on: ubuntu-latest
    permissions:
      contents: read
      packages: write
    outputs:
      image: ${{ steps.image-ref.outputs.image }}
    steps:
      - uses: actions/checkout@v4

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3

      - name: Login to GHCR
        if: github.event_name == 'push'
        uses: docker/login-action@v3
        with:
          registry: ${{ env.REGISTRY }}
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Extract metadata (tags, labels)
        id: meta
        uses: docker/metadata-action@v5
        with:
          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
          tags: |
            # Tagged releases: v1.2.3 -> :1.2.3, :1.2, :latest
            type=semver,pattern={{version}}
            type=semver,pattern={{major}}.{{minor}}
            # Branch pushes: foo/docker-pr -> :foo-docker-pr
            type=ref,event=branch
            # Always: :sha-<hash>
            type=sha

      - name: Build and push
        uses: docker/build-push-action@v6
        with:
          context: .
          file: docker/chatmail_relay.dockerfile
          push: ${{ github.event_name == 'push' }}
          tags: ${{ steps.meta.outputs.tags }}
          labels: ${{ steps.meta.outputs.labels }}
          cache-from: type=gha
          cache-to: type=gha,mode=max
          build-args: |
            GIT_HASH=${{ github.sha }}

      - name: Output image reference
        id: image-ref
        run: |
          SHORT_SHA=$(echo "${{ github.sha }}" | cut -c1-7)
          IMAGE="${{ env.REGISTRY }}/$(echo "${{ env.IMAGE_NAME }}" | tr '[:upper:]' '[:lower:]'):sha-${SHORT_SHA}"
          echo "image=${IMAGE}" >> "$GITHUB_OUTPUT"

  deploy:
    name: deploy on staging2.testrun.org, and run tests
    runs-on: ubuntu-latest
    timeout-minutes: 30
    environment:
      name: staging2.testrun.org
      url: https://staging2.testrun.org/
    concurrency: staging2.testrun.org
    steps:
      - uses: actions/checkout@v4

      - name: prepare SSH
        run: |
          mkdir ~/.ssh
          echo "${{ secrets.STAGING_SSH_KEY }}" >> ~/.ssh/id_ed25519
          chmod 600 ~/.ssh/id_ed25519
          ssh-keyscan staging2.testrun.org > ~/.ssh/known_hosts
          # save previous acme & dkim state
          rsync -avz root@staging2.testrun.org:/var/lib/acme . || true
          rsync -avz root@staging2.testrun.org:/etc/dkimkeys . || true
          # store previous acme & dkim state on ns.testrun.org, if it contains useful certs
          if [ -f dkimkeys/opendkim.private ]; then rsync -avz -e "ssh -o StrictHostKeyChecking=accept-new" dkimkeys root@ns.testrun.org:/tmp/ || true; fi
          if [ "$(ls -A acme/certs)" ]; then rsync -avz -e "ssh -o StrictHostKeyChecking=accept-new" acme root@ns.testrun.org:/tmp/ || true; fi
          # make sure CAA record isn't set
          scp -o StrictHostKeyChecking=accept-new .github/workflows/staging.testrun.org-default.zone root@ns.testrun.org:/etc/nsd/staging2.testrun.org.zone
          ssh root@ns.testrun.org sed -i '/CAA/d' /etc/nsd/staging2.testrun.org.zone
          ssh root@ns.testrun.org nsd-checkzone staging2.testrun.org /etc/nsd/staging2.testrun.org.zone
          ssh root@ns.testrun.org systemctl reload nsd

      - name: rebuild staging2.testrun.org to have a clean VPS
        run: |
            curl -X POST \
            -H "Authorization: Bearer ${{ secrets.HETZNER_API_TOKEN }}" \
            -H "Content-Type: application/json" \
            -d '{"image":"debian-12"}' \
            "https://api.hetzner.cloud/v1/servers/${{ secrets.STAGING_SERVER_ID }}/actions/rebuild"

      - run: scripts/initenv.sh

      - name: append venv/bin to PATH
        run: echo venv/bin >>$GITHUB_PATH

      - name: upload TLS cert after rebuilding
        id: wait-for-vps
        run: |
          echo " --- wait until staging2.testrun.org VPS is rebuilt --- "
          rm ~/.ssh/known_hosts
          while ! ssh -o ConnectTimeout=180 -o StrictHostKeyChecking=accept-new -v root@staging2.testrun.org id -u ; do sleep 1 ; done
          ssh -o StrictHostKeyChecking=accept-new -v root@staging2.testrun.org id -u
          # download acme & dkim state from ns.testrun.org
          rsync -e "ssh -o StrictHostKeyChecking=accept-new" -avz root@ns.testrun.org:/tmp/acme acme-restore || true
          rsync -avz root@ns.testrun.org:/tmp/dkimkeys dkimkeys-restore || true
          # restore acme & dkim state to staging2.testrun.org
          rsync -avz acme-restore/acme root@staging2.testrun.org:/var/lib/ || true
          rsync -avz dkimkeys-restore/dkimkeys root@staging2.testrun.org:/etc/ || true
          ssh -o StrictHostKeyChecking=accept-new -v root@staging2.testrun.org chown root:root -R /var/lib/acme || true

      - name: add hpk42 key to staging server
        run: ssh root@staging2.testrun.org 'curl -s https://github.com/hpk42.keys >> .ssh/authorized_keys'

      - name: run deploy-chatmail offline tests
        run: pytest --pyargs cmdeploy

      - run: |
          cmdeploy init staging2.testrun.org
          sed -i 's/#\s*mtail_address/mtail_address/' chatmail.ini

      - run: cmdeploy run --verbose --skip-dns-check

      - name: set DNS entries
        run: |
          cmdeploy dns --zonefile staging-generated.zone --verbose
          cat staging-generated.zone >> .github/workflows/staging.testrun.org-default.zone
          cat .github/workflows/staging.testrun.org-default.zone
          scp .github/workflows/staging.testrun.org-default.zone root@ns.testrun.org:/etc/nsd/staging2.testrun.org.zone
          ssh root@ns.testrun.org nsd-checkzone staging2.testrun.org /etc/nsd/staging2.testrun.org.zone
          ssh root@ns.testrun.org systemctl reload nsd

      - name: cmdeploy test
        run: CHATMAIL_DOMAIN2=ci-chatmail.testrun.org cmdeploy test --slow

      - name: cmdeploy dns
        run: cmdeploy dns -v

      # --- Docker deploy (push only, runs even if bare failed) ---

      - name: stop bare services
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          ssh root@staging2.testrun.org 'systemctl stop postfix dovecot nginx opendkim unbound filtermail doveauth chatmail-metadata iroh-relay mtail fcgiwrap acmetool 2>/dev/null || true'

      - name: install Docker on VPS
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          ssh root@staging2.testrun.org 'apt-get update && apt-get install -y ca-certificates curl'
          ssh root@staging2.testrun.org 'install -m 0755 -d /etc/apt/keyrings'
          ssh root@staging2.testrun.org 'curl -fsSL https://download.docker.com/linux/debian/gpg -o /etc/apt/keyrings/docker.asc && chmod a+r /etc/apt/keyrings/docker.asc'
          ssh root@staging2.testrun.org 'echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/debian $(. /etc/os-release && echo $VERSION_CODENAME) stable" > /etc/apt/sources.list.d/docker.list'
          ssh root@staging2.testrun.org 'apt-get update && apt-get install -y docker-ce docker-ce-cli containerd.io docker-compose-plugin'

      - name: prepare Docker bind mounts
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          ssh root@staging2.testrun.org 'mkdir -p /srv/chatmail/certs /srv/chatmail/dkim'
          ssh root@staging2.testrun.org 'cp -a /var/lib/acme/. /srv/chatmail/certs/ && cp -a /etc/dkimkeys/. /srv/chatmail/dkim/' || true

      - name: upload chatmail.ini for Docker
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          # Reuse chatmail.ini already created by the bare-metal deploy steps
          scp chatmail.ini root@staging2.testrun.org:/srv/chatmail/chatmail.ini

      - name: deploy with Docker
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          SHORT_SHA=$(echo "${{ github.sha }}" | cut -c1-7)
          GHCR_IMAGE="${{ env.REGISTRY }}/$(echo "${{ env.IMAGE_NAME }}" | tr '[:upper:]' '[:lower:]'):sha-${SHORT_SHA}"
          rsync -avz --exclude='.git' --exclude='venv' --exclude='__pycache__' ./ root@staging2.testrun.org:/srv/chatmail/relay/
          # Login to GHCR on VPS and pull pre-built image
          echo "${{ secrets.GITHUB_TOKEN }}" | ssh root@staging2.testrun.org 'docker login ghcr.io -u ${{ github.actor }} --password-stdin'
          ssh root@staging2.testrun.org "docker pull ${GHCR_IMAGE}"
          ssh root@staging2.testrun.org "cd /srv/chatmail/relay && CHATMAIL_IMAGE=${GHCR_IMAGE} MAIL_DOMAIN=staging2.testrun.org docker compose -f docker/docker-compose.yaml -f docker/docker-compose.ci.yaml up -d"

      - name: wait for container healthy
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          # Stream journald inside the container
          ssh root@staging2.testrun.org 'docker exec chatmail journalctl -f --no-pager' &
          LOG_PID=$!
          trap "kill $LOG_PID 2>/dev/null || true" EXIT
          for i in $(seq 1 60); do
            status=$(ssh root@staging2.testrun.org 'docker inspect --format={{.State.Health.Status}} chatmail 2>/dev/null' || echo "missing")
            echo "  [$i/60] status=$status"
            if [ "$status" = "healthy" ]; then
              echo "Container is healthy."
              exit 0
            fi
            if [ "$status" = "unhealthy" ]; then
              echo "Container is unhealthy!"
              break
            fi
            sleep 5
          done
          echo "Container did not become healthy."
          kill $LOG_PID 2>/dev/null || true
          echo "--- failed units ---"
          ssh root@staging2.testrun.org 'docker exec chatmail systemctl --failed --no-pager' || true
          echo "--- service logs ---"
          ssh root@staging2.testrun.org 'docker exec chatmail journalctl -u dovecot -u postfix -u nginx -u unbound --no-pager -n 50' || true
          echo "--- listening ports ---"
          ssh root@staging2.testrun.org 'docker exec chatmail ss -tlnp' || true
          echo "--- chatmail.ini ---"
          ssh root@staging2.testrun.org 'docker exec chatmail cat /etc/chatmail/chatmail.ini' || true
          exit 1

      - name: show container state
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          echo "--- listening ports ---"
          ssh root@staging2.testrun.org 'docker exec chatmail ss -tlnp'
          echo "--- chatmail.ini ---"
          ssh root@staging2.testrun.org 'docker exec chatmail cat /etc/chatmail/chatmail.ini'

      - name: Docker integration tests
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          ssh root@staging2.testrun.org 'docker exec chatmail cmdeploy test --slow --ssh-host @local'

      - name: Docker DNS
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: |
          # Reset zone file in case bare DNS already appended to it
          git checkout .github/workflows/staging.testrun.org-default.zone
          ssh root@staging2.testrun.org 'docker exec chatmail chown opendkim:opendkim -R /etc/dkimkeys'
          ssh root@staging2.testrun.org 'docker exec chatmail cmdeploy dns --ssh-host @local --zonefile /opt/chatmail/staging.zone --verbose'
          ssh root@staging2.testrun.org 'docker cp chatmail:/opt/chatmail/staging.zone /tmp/staging.zone'
          scp root@staging2.testrun.org:/tmp/staging.zone staging-generated.zone
          cat staging-generated.zone >> .github/workflows/staging.testrun.org-default.zone
          cat .github/workflows/staging.testrun.org-default.zone
          scp .github/workflows/staging.testrun.org-default.zone root@ns.testrun.org:/etc/nsd/staging2.testrun.org.zone
          ssh root@ns.testrun.org nsd-checkzone staging2.testrun.org /etc/nsd/staging2.testrun.org.zone
          ssh root@ns.testrun.org systemctl reload nsd

      - name: Docker final DNS check
        if: >-
          !cancelled() && github.event_name == 'push'
          && steps.wait-for-vps.outcome == 'success'
        run: ssh root@staging2.testrun.org 'docker exec chatmail cmdeploy dns -v --ssh-host @local'

      # --- Cleanup ---

      - name: add SSH keys
        if: >-
          !cancelled()
          && steps.wait-for-vps.outcome == 'success'
        run: ssh root@staging2.testrun.org 'curl -s https://github.com/hpk42.keys https://github.com/j4n.keys >> .ssh/authorized_keys'