name: Disk Maintenance

# Daily safety net for flagship disk usage. The deploy workflows prune
# superseded image layers after their own runs, but that protection
# disappears exactly when it's needed most: a deploy that fails early
# never reaches its prune step, while other workflows keep pulling
# fresh images (2026-06-07 incident: cd-apps red all day, ~10 staging
# deploys, disk 100% full, postgres down on a Saturday morning).
#
# Also doubles as a redundant alert channel: the run FAILS when the
# disk is still above the threshold after pruning, so a scheduled-run
# failure email lands even if the Grafana disk alert drowns in other
# noise (which is what happened during the incident).

on:
  schedule:
    # Daily at 04:30 UTC (offset from staging-cleanup's Monday 04:00)
    - cron: "30 4 * * *"
  workflow_dispatch: {}

concurrency:
  group: disk-maintenance
  cancel-in-progress: false

jobs:
  prune-flagship:
    name: Prune unused images (flagship)
    runs-on: ubuntu-latest
    environment: production
    steps:
      - name: Prune and check disk headroom
        uses: appleboy/ssh-action@v1
        with:
          host: ${{ secrets.DEPLOY_HOST }}
          username: root
          key: ${{ secrets.DEPLOY_SSH_KEY }}
          script: |
            set -euo pipefail
            echo "before: $(df -h / | tail -1)"
            # 12h filter: never touch layers a same-day deploy may still
            # be assembling; running containers' images are never pruned.
            # `|| true`: a concurrent deploy's prune can make this collide
            # with "a prune operation is already running" — that's benign
            # (the other prune is freeing space too), and the disk-% gate
            # below is the real assertion, so don't fail on the collision.
            docker image prune -af --filter "until=12h" || true
            echo "after:  $(df -h / | tail -1)"

            PCT=$(df --output=pcent / | tail -1 | tr -dc '0-9')
            if [ "$PCT" -ge 85 ]; then
              echo "Disk still at ${PCT}% after pruning — needs a human."
              echo "Largest docker consumers:"
              docker system df
              exit 1
            fi
            echo "Disk at ${PCT}% — healthy."