homey/modules/backup.nix

{ config, lib, pkgs, homeyConfig, ... }:

# Restic backup module.
#
# Backs up all service data directories from the external HD.
# Schedule: daily at 03:00, keep 7 daily / 4 weekly / 6 monthly snapshots.
#
# Before a backup, Nextcloud is put into maintenance mode and postgres is
# pg_dump'd to a file.  This ensures consistent DB backups.
#
# Backup strategy — two tiers:
#
#   1. Automatic daily backup to an S3-compatible bucket (primary offsite copy).
#      Set the repository URL to your bucket in hosts/pi-main/default.nix, e.g.:
#        homey.backup.repository = "s3:https://s3.us-west-002.backblazeb2.com/your-bucket";
#      S3 credentials are injected via environment variables from sops secrets:
#        restic/s3_access_key_id  →  AWS_ACCESS_KEY_ID
#        restic/s3_secret_access_key  →  AWS_SECRET_ACCESS_KEY
#
#   2. Manual offload to a local disk (USB drive plugged into Pi, or workstation disk).
#      Use scripts/offload-backup.sh --target /path/to/mounted/disk
#      That script uses `restic copy` to clone snapshots from the S3 repo into a
#      local restic repo on the target disk, preserving deduplication.
#
# Secrets consumed from sops:
#   restic/password
#   restic/s3_access_key_id        (if using S3 backend)
#   restic/s3_secret_access_key    (if using S3 backend)
#
# The backup repository URL is set per-host in default.nix:
#   homey.backup.repository = "s3:https://s3.us-west-002.backblazeb2.com/bucket";
#
# Restore:
#   restic -r <repo> restore latest --target /mnt/data
#   (or restore a single path: --include /mnt/data/openldap)

let
  cfg     = config.homey.backup;
  dataDir = config.homey.storage.mountPoint;
in
{
  options.homey.backup = {
    enable = lib.mkEnableOption "Restic backup jobs";

    repository = lib.mkOption {
      type        = lib.types.str;
      example     = "sftp:user@nas.local:/backups/homey";
      description = ''
        Restic repository URL. Examples:
          sftp:user@host:/path
          b2:bucket-name:prefix
          rclone:remote:path
          /local/path  (for testing)
      '';
    };

    schedule = lib.mkOption {
      type    = lib.types.str;
      default = "03:00";
      description = "systemd OnCalendar expression for the daily backup.";
    };

    pruneRetention = lib.mkOption {
      type = lib.types.attrsOf lib.types.str;
      default = {
        daily   = "7";
        weekly  = "4";
        monthly = "6";
      };
    };
  };

  config = lib.mkIf cfg.enable {
    # -----------------------------------------------------------------------
    # Secrets
    # -----------------------------------------------------------------------
    sops.secrets."restic/password"              = { owner = "root"; };
    sops.secrets."restic/s3_access_key_id"      = { owner = "root"; };
    sops.secrets."restic/s3_secret_access_key"  = { owner = "root"; };

    # -----------------------------------------------------------------------
    # Pre-backup hook: pg_dump + nextcloud maintenance mode
    # -----------------------------------------------------------------------
    systemd.services."homey-backup-pre" = {
      description = "Pre-backup hooks (pg_dump, NC maintenance mode, secrets env)";
      serviceConfig = {
        Type = "oneshot";
        ExecStart = pkgs.writeShellScript "backup-pre" ''
          set -euo pipefail
          podman="${pkgs.podman}/bin/podman"

          # Write S3 credentials env file now, before restic-backups-homey.service
          # starts — systemd loads EnvironmentFile= before ExecStartPre runs, so
          # the file must already exist when the restic unit activates.
          install -m 0600 /dev/null /run/restic-homey-secrets.env
          {
            printf 'AWS_ACCESS_KEY_ID=%s\n' \
              "$(cat ${config.sops.secrets."restic/s3_access_key_id".path})"
            printf 'AWS_SECRET_ACCESS_KEY=%s\n' \
              "$(cat ${config.sops.secrets."restic/s3_secret_access_key".path})"
            printf 'RESTIC_CACHE_DIR=%s\n' "${dataDir}/restic-cache"
          } >> /run/restic-homey-secrets.env

          # Put Nextcloud into maintenance mode (if running)
          if systemctl is-active --quiet podman-nextcloud.service; then
            $podman exec nextcloud php occ maintenance:mode --on || true
          fi

          # Dump postgres (if running)
          if systemctl is-active --quiet podman-nextcloud-postgres.service; then
            install -d -m 700 ${dataDir}/nextcloud/db-dump
            $podman exec nextcloud-postgres \
              pg_dump -U postgres nextcloud_db \
              > ${dataDir}/nextcloud/db-dump/nextcloud.sql
          fi
        '';
      };
    };

    # -----------------------------------------------------------------------
    # Restic backup service
    # -----------------------------------------------------------------------
    services.restic.backups.homey = {
      repository    = cfg.repository;
      passwordFile  = config.sops.secrets."restic/password".path;

      # Runtime env file written by homey-backup-pre.service (which runs first)
      environmentFile = "/run/restic-homey-secrets.env";

      paths = [
        "${dataDir}/openldap"
        "${dataDir}/authelia"
        "${dataDir}/gitea"
        "${dataDir}/nextcloud"
        # media and transmission config included when those services are enabled:
        "${dataDir}/jellyfin"
        "${dataDir}/transmission"
        # Deliberately excluded: media/* (large, can be re-downloaded)
        # Monitoring — uptime-kuma has monitors/history, ntfy has user accounts
        "${dataDir}/uptime-kuma"
        "${dataDir}/ntfy"
      ];

      # Exclude Nextcloud's raw DB directory in favour of the pg_dump file
      exclude = [
        "${dataDir}/nextcloud/db"
        "${dataDir}/restic-cache"
      ];

      timerConfig = {
        OnCalendar = cfg.schedule;
        Persistent = true;  # run on next boot if missed
      };

      pruneOpts = [
        "--keep-daily   ${cfg.pruneRetention.daily}"
        "--keep-weekly  ${cfg.pruneRetention.weekly}"
        "--keep-monthly ${cfg.pruneRetention.monthly}"
      ];
    };

    # Wire the pre/post hooks around the restic job
    systemd.services."restic-backups-homey" = {
      requires = [ "homey-backup-pre.service" ];
      after    = [ "homey-backup-pre.service" ];
      serviceConfig = {
        ExecStopPost = [
          (pkgs.writeShellScript "restic-post-hooks" ''
            # Always runs on stop, success or failure
            rm -f /run/restic-homey-secrets.env
            if systemctl is-active --quiet podman-nextcloud.service; then
              ${pkgs.podman}/bin/podman exec nextcloud php occ maintenance:mode --off || true
            fi
          '')
        ];
      };
    };
  };
}