slp-modular-cms/.gitea/workflows/deploy-scp.yaml

name: Deploy (SCP)

# Reusable deploy workflow, invoked by continuous_integration.yaml (U5) for both the automatic
# test deploy and the opt-in production deploy. One workflow, one input contract, so a second
# transport (e.g. FTPS for a future shared-hosting target) can be added later as an alternative
# without restructuring this workflow or its callers (FR-02, D-02, NFR-09).
on:
  workflow_call:
    inputs:
      artifact_name:
        description: 'Build artifact to download and deploy'
        required: true
        type: string
      environment:
        description: 'Environment label, used in log output and step naming'
        required: true
        type: string
      deploy_path:
        description: 'Release root on the target host for this environment'
        required: true
        type: string
      service_name:
        description: 'systemd --user unit to restart after switching releases'
        required: true
        type: string
      health_check_url:
        description: 'Public /health URL to verify after restart'
        required: true
        type: string
      run_db_backup:
        description: 'Take a database backup before deploying (production only)'
        required: false
        type: boolean
        default: false
      transport:
        description: 'Transport mechanism. Only "scp" is implemented today; reserved for FTPS later'
        required: false
        type: string
        default: scp

jobs:
  deploy:
    runs-on: ubuntu-latest
    steps:
      # TEMPORARY — diagnosing a persistent "Permission denied, please try again." (sshpass exit 5)
      # on the SSH steps below. Never prints the actual secret values, only lengths and a boolean
      # match against the expected username, so it's safe to leave in a log — but remove this step
      # once the PI_MAIN_* secrets are confirmed correct; it has no purpose beyond that diagnosis.
      - name: Debug - verify PI_MAIN_USERNAME/PASSWORD secrets (remove after diagnosis)
        run: |
          echo "PI_MAIN_USERNAME length: ${#PI_MAIN_USERNAME}"
          echo "PI_MAIN_USERNAME equals 'gitea-workflow': $([ "$PI_MAIN_USERNAME" = "gitea-workflow" ] && echo yes || echo no)"
          echo "PI_MAIN_PASSWORD length: ${#PI_MAIN_PASSWORD}"
        env:
          PI_MAIN_USERNAME: ${{ secrets.PI_MAIN_USERNAME }}
          PI_MAIN_PASSWORD: ${{ secrets.PI_MAIN_PASSWORD }}

      - name: Compute release timestamp
        id: release
        run: echo "timestamp=$(date -u +%Y%m%d%H%M%S)" >> "$GITHUB_OUTPUT"

      - name: Download build artifact
        uses: actions/download-artifact@v3
        with:
          name: ${{ inputs.artifact_name }}
          path: ${{ inputs.artifact_name }}

      # Production-only database backup, taken before anything on the host changes (FR-20, D-26).
      # The backup script itself lives on the host (created once during Operations host setup) and
      # is only invoked here — no database connection string or credential is ever known to this
      # workflow, keeping D-16 ("runtime secrets live in host environment variables") intact.
      # Gitea Actions does not resolve `${{ inputs.* }}` inside a step's `name:` (unlike inside
      # `run:`, where it works fine — see the echo below) — kept static rather than showing the
      # literal, unresolved `${{ inputs.environment }}` text in the log.
      - name: Back up database
        if: ${{ inputs.run_db_backup }}
        run: |
          echo "Environment: ${{ inputs.environment }}"
          sudo apt-get update && sudo apt-get install -y sshpass
          sshpass -p "${{ secrets.PI_MAIN_PASSWORD }}" ssh \
            -p ${{ secrets.PI_MAIN_PORT }} \
            -o StrictHostKeyChecking=no \
            ${{ secrets.PI_MAIN_USERNAME }}@${{ secrets.PI_MAIN_ADDRESS }} \
            "bash ~/scripts/backup-slpsoftware-db.sh ${{ inputs.environment }}"

      # Uploads the published output to a fresh, timestamped release directory rather than
      # overwriting the live one (FR-06, D-27) — the atomic switch happens in a later step, once
      # this upload and the website-symlink step below have both succeeded.
      #
      # Plain shell step rather than a container SCP action: container-based actions fail on this
      # runner with "failed to attach to container: unable to upgrade to tcp, received 409", a known
      # limitation of Podman's Docker-compatible API for the attach/log-streaming that container
      # actions rely on (D-05). A plain scp command needs no nested container.
      # Same Gitea Actions limitation as the step above — static name, value logged via echo instead.
      - name: Upload release
        run: |
          echo "Environment: ${{ inputs.environment }}, transport: ${{ inputs.transport }}"
          sudo apt-get update && sudo apt-get install -y sshpass
          RELEASE_DIR="${{ inputs.deploy_path }}/releases/${{ steps.release.outputs.timestamp }}"
          sshpass -p "${{ secrets.PI_MAIN_PASSWORD }}" ssh \
            -p ${{ secrets.PI_MAIN_PORT }} \
            -o StrictHostKeyChecking=no \
            ${{ secrets.PI_MAIN_USERNAME }}@${{ secrets.PI_MAIN_ADDRESS }} \
            "mkdir -p $RELEASE_DIR"
          sshpass -p "${{ secrets.PI_MAIN_PASSWORD }}" scp \
            -P ${{ secrets.PI_MAIN_PORT }} \
            -o StrictHostKeyChecking=no \
            -r ${{ inputs.artifact_name }}/* \
            ${{ secrets.PI_MAIN_USERNAME }}@${{ secrets.PI_MAIN_ADDRESS }}:"$RELEASE_DIR"/

      # The customer's public website (wwwroot/web) must survive every CMS deploy (FR-08, ASM-01).
      # It lives outside the swapped release directory in a persistent shared/ folder, and is
      # symlinked into each new release. mkdir -p is idempotent, so this is also correct on the very
      # first-ever deploy, before any website workspace has published anything there (U1 already
      # tolerates a missing wwwroot/web at startup). The publish output's own wwwroot/web (empty, or
      # containing only the placeholder page) is removed before the symlink is created, so it never
      # shadows the persistent content.
      - name: Link persistent website content
        run: |
          RELEASE_DIR="${{ inputs.deploy_path }}/releases/${{ steps.release.outputs.timestamp }}"
          sshpass -p "${{ secrets.PI_MAIN_PASSWORD }}" ssh \
            -p ${{ secrets.PI_MAIN_PORT }} \
            -o StrictHostKeyChecking=no \
            ${{ secrets.PI_MAIN_USERNAME }}@${{ secrets.PI_MAIN_ADDRESS }} \
            "mkdir -p ${{ inputs.deploy_path }}/shared/wwwroot-web && \
             rm -rf $RELEASE_DIR/wwwroot/web && \
             ln -s ../../../shared/wwwroot-web $RELEASE_DIR/wwwroot/web"

      # Atomic release switch (FR-06, D-27): `ln -sfn` replaces the `current` symlink target in a
      # single filesystem operation, so there is no moment where `current` points at a half-written
      # directory. The process is then restarted so it picks up the new assemblies — a running .NET
      # process holds on to the ones it already loaded.
      - name: Switch current release and restart service
        run: |
          RELEASE_DIR="${{ inputs.deploy_path }}/releases/${{ steps.release.outputs.timestamp }}"
          sshpass -p "${{ secrets.PI_MAIN_PASSWORD }}" ssh \
            -p ${{ secrets.PI_MAIN_PORT }} \
            -o StrictHostKeyChecking=no \
            ${{ secrets.PI_MAIN_USERNAME }}@${{ secrets.PI_MAIN_ADDRESS }} \
            "ln -sfn $RELEASE_DIR ${{ inputs.deploy_path }}/current && \
             systemctl --user restart ${{ inputs.service_name }}"

      # Verifies the restart actually produced a healthy process before this run is allowed to
      # report success. Retries absorb ordinary process-startup time; a run that never turns healthy
      # fails the job without touching `current` or pruning (see below) — no automatic rollback.
      # A previous release is always still on disk to restore from manually (D-26).
      - name: Verify /health
        run: |
          for attempt in $(seq 1 10); do
            if curl -f -s -o /dev/null "${{ inputs.health_check_url }}"; then
              echo "Health check passed on attempt $attempt"
              exit 0
            fi
            echo "Health check attempt $attempt failed, retrying..."
            sleep 3
          done
          echo "Health check did not pass after 10 attempts"
          exit 1

      # Retention: keep `current` plus exactly one previous release, so a manual rollback is always
      # a re-point-and-restart away without rebuilding. Only runs after a passing health check —
      # pruning after a failed check could leave the only other release as the sole survivor.
      - name: Prune old releases
        run: |
          sshpass -p "${{ secrets.PI_MAIN_PASSWORD }}" ssh \
            -p ${{ secrets.PI_MAIN_PORT }} \
            -o StrictHostKeyChecking=no \
            ${{ secrets.PI_MAIN_USERNAME }}@${{ secrets.PI_MAIN_ADDRESS }} \
            "cd ${{ inputs.deploy_path }}/releases && ls -1t | tail -n +3 | xargs -r rm -rf"