mission-control-v2/deploy/restore.sh

#!/usr/bin/env bash
# Wiederherstellung eines mc2-state-Backups (siehe backup.sh).
# Stoppt die Dienste, spielt den Zustand zurück, startet neu — und macht VORHER
# automatisch ein Sicherheits-Backup des aktuellen Zustands (Restore ist reversibel).
#
# Nutzung:
#   bash restore.sh --list                      # vorhandene Backups zeigen (lokal + Off-Box)
#   bash restore.sh --dry-run <datei|latest>    # nur anzeigen, was passieren würde
#   bash restore.sh [--yes] <datei|latest>      # wiederherstellen (--yes = ohne Rückfrage)
#   bash restore.sh --pull-offsite              # Off-Box-Kopie (Proxmox) nach lokal holen
#
# Off-Box (C12): fehlt ein Backup lokal (z. B. Box-Platte neu), wird es automatisch
# vom Zweitgerät (Proxmox) geholt. Ziel/Key wie in backup.sh (überschreibbar per Env).
set -euo pipefail

MODELS_DIR="${MC_MODELS_DIR:-/srv/models}"
DEST_DIR="$MODELS_DIR/mc2-backups"
MEM0_DIR="${MC_MEM0_DIR:-/srv/models/mem0}"
LSWAP="${MC_CONFIG_PATH:-/etc/llama-swap/config.yaml}"
HERMES="${HERMES_HOME:-$HOME/.hermes}"
SRC="${MC2_SRC:-$HOME/mission-control-v2}"
SERVICES="mem0-service mission-control-2 hermes-gateway"
OFFSITE="${MC_BACKUP_OFFSITE:-root@192.168.178.108:/var/lib/vz/mc2-backups}"
OFFSITE_KEY="${MC_BACKUP_OFFSITE_KEY:-$HOME/.ssh/mc2_offsite}"
OFFSITE_SSH="ssh -i $OFFSITE_KEY -o BatchMode=yes -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new"

# Off-Box-Tarballs (Dateinamen) auflisten — leer, wenn nicht erreichbar/konfiguriert.
offsite_ls() {
  [ -n "$OFFSITE" ] && [ -f "$OFFSITE_KEY" ] || return 0
  local host="${OFFSITE%%:*}" path="${OFFSITE#*:}"
  $OFFSITE_SSH "$host" "ls -1 $path/mc2-state-*.tar.gz 2>/dev/null" 2>/dev/null | xargs -r -n1 basename || true
}
# Ein einzelnes Off-Box-Tarball nach lokal holen. $1 = Dateiname (basename).
offsite_fetch() {
  [ -n "$OFFSITE" ] && [ -f "$OFFSITE_KEY" ] || return 1
  mkdir -p "$DEST_DIR"
  echo "→ hole $1 vom Zweitgerät ($OFFSITE)…" >&2
  rsync -a -e "$OFFSITE_SSH" "$OFFSITE/$1" "$DEST_DIR/"
}

usage() { echo "Nutzung: restore.sh --list | restore.sh --pull-offsite | restore.sh [--dry-run] [--yes] <datei|latest>"; }
list_backups() {
  echo "Verfügbare Backups in $DEST_DIR:"
  local found=0 f
  for f in $(ls -1t "$DEST_DIR"/mc2-state-*.tar.gz 2>/dev/null || true); do
    printf "  %s  (%s)\n" "$(basename "$f")" "$(du -h "$f" | cut -f1)"
    found=1
  done
  [ "$found" = 1 ] || echo "  (keine)"
  local off; off="$(offsite_ls || true)"
  if [ -n "$off" ]; then
    echo "Off-Box ($OFFSITE):"
    echo "$off" | sed 's/^/  /'
  fi
}

[ $# -eq 0 ] && { usage; exit 1; }
DRY=0; YES=0; TARGET=""
for a in "$@"; do
  case "$a" in
    --list) list_backups; exit 0 ;;
    --pull-offsite)
      mkdir -p "$DEST_DIR"
      [ -n "$OFFSITE" ] && [ -f "$OFFSITE_KEY" ] || { echo "Off-Box nicht konfiguriert."; exit 1; }
      echo "→ spiegle Off-Box → lokal ($DEST_DIR)…"
      rsync -a -e "$OFFSITE_SSH" --include='mc2-state-*.tar.gz' --exclude='*' "$OFFSITE/" "$DEST_DIR/"
      list_backups; exit 0 ;;
    --dry-run) DRY=1 ;;
    --yes) YES=1 ;;
    -*) usage; exit 1 ;;
    *) TARGET="$a" ;;
  esac
done
[ -z "$TARGET" ] && { usage; exit 1; }
# 'latest' bevorzugt lokal; fehlt lokal alles, das jüngste Off-Box-Tarball holen.
if [ "$TARGET" = "latest" ]; then
  TARGET="$(ls -1t "$DEST_DIR"/mc2-state-*.tar.gz 2>/dev/null | head -1 || true)"
  if [ -z "$TARGET" ]; then
    latest_off="$(offsite_ls | sort | tail -1 || true)"
    [ -n "$latest_off" ] && offsite_fetch "$latest_off" && TARGET="$DEST_DIR/$latest_off"
  fi
fi
# Konkreten Namen zuerst lokal suchen, sonst vom Zweitgerät holen.
if [ ! -f "$TARGET" ]; then
  base="$(basename "${TARGET:-}")"
  if [ -f "$DEST_DIR/$base" ]; then
    TARGET="$DEST_DIR/$base"
  elif [ -n "$base" ] && offsite_ls | grep -qx "$base"; then
    offsite_fetch "$base" && TARGET="$DEST_DIR/$base"
  fi
fi
[ -f "$TARGET" ] || { echo "Backup nicht gefunden: ${TARGET:-<leer>}"; echo; list_backups; exit 1; }

echo "Restore-Quelle: $TARGET"
STAGE="$(mktemp -d)"; trap 'rm -rf "$STAGE"' EXIT
tar -xzf "$TARGET" -C "$STAGE"
echo "--- Inhalt ---"; cat "$STAGE/MANIFEST.txt" 2>/dev/null || true; echo "--------------"

if [ "$DRY" = 1 ]; then
  echo "[dry-run] würde zurücksetzen:"
  [ -d "$STAGE/mem0" ]                 && echo "  • mem0 → $MEM0_DIR (wird ersetzt)"
  [ -f "$STAGE/hermes/config.yaml" ]   && echo "  • $HERMES/config.yaml"
  [ -f "$STAGE/hermes/.env" ]          && echo "  • $HERMES/.env"
  [ -d "$STAGE/hermes/plugins" ]       && echo "  • $HERMES/plugins/"
  [ -f "$STAGE/llama-swap/config.yaml" ] && echo "  • $LSWAP"
  echo "  • Dienste neu starten: $SERVICES"
  exit 0
fi

if [ "$YES" != 1 ]; then
  echo "WARNUNG: Das überschreibt den AKTUELLEN Zustand und startet die Dienste neu."
  read -r -p "Fortfahren? (tippe 'ja'): " ans
  [ "$ans" = "ja" ] || { echo "Abgebrochen."; exit 1; }
fi

echo "→ Sicherheits-Backup des aktuellen Zustands…"
bash "$SRC/deploy/backup.sh" || echo "  (Pre-Restore-Backup fehlgeschlagen — fahre fort)"

echo "→ Dienste stoppen…"
systemctl --user stop $SERVICES 2>/dev/null || true

if [ -d "$STAGE/mem0" ]; then rm -rf "$MEM0_DIR"; mkdir -p "$MEM0_DIR"; cp -a "$STAGE/mem0/." "$MEM0_DIR/"; fi
[ -f "$STAGE/hermes/config.yaml" ]   && { mkdir -p "$HERMES"; cp -a "$STAGE/hermes/config.yaml" "$HERMES/"; }
[ -f "$STAGE/hermes/.env" ]          && cp -a "$STAGE/hermes/.env" "$HERMES/"
[ -d "$STAGE/hermes/plugins" ]       && { mkdir -p "$HERMES/plugins"; cp -a "$STAGE/hermes/plugins/." "$HERMES/plugins/"; }
[ -f "$STAGE/llama-swap/config.yaml" ] && cp -a "$STAGE/llama-swap/config.yaml" "$LSWAP" 2>/dev/null || true

echo "→ Dienste starten…"
systemctl --user start $SERVICES 2>/dev/null || true
sleep 4
printf "→ Health: "; curl -sf http://127.0.0.1:9001/api/health && echo || echo "(Backend nicht erreichbar — Logs prüfen)"
echo "OK — Restore abgeschlossen."