Feat: Voll-Zustands-Backup + getesteter Restore + taeglicher Timer
Behebt 3 von 4 Backup-Luecken (Schicht 1, lokal): - backup.sh sichert jetzt den ECHTEN Zustand als ein Tarball mc2-state-<ts>.tar.gz: mem0 (Chroma+history.db), ~/.hermes (config.yaml, .env, plugins/), llama-swap config. Vorher wurde nur die alte/leere mc2-memory.db gesichert. chmod 600 (enthaelt .env). - restore.sh: --list / --dry-run / [--yes] <datei|latest>; macht VOR dem Zurueckspielen ein Sicherheits-Backup, stoppt/startet Dienste, Health-Check. Live round-trip verifiziert. - mc2-backup.timer/.service: taegliches Backup ~03:30 (vorher gab es KEINE Automatik). - backend/services/backup.py delegiert an backup.sh (eine Quelle der Wahrheit); UI-Button + /api/system/backups zeigen die Tarballs. - docs/BACKUP.md: Backup/Restore-Anleitung. Offen (Schicht 2): Off-Box-Spiegel (Box ist Bare Metal -> PBS-Client oder rsync in LXC). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
+40
-11
@@ -1,18 +1,47 @@
|
||||
#!/usr/bin/env bash
|
||||
# Backup der Shared-Memory-SQLite + Configs (cron-bar auf der Box).
|
||||
# Behält die letzten 7 Snapshots. Identisch zur /api/system/backup-Logik.
|
||||
# Voll-Zustands-Backup der AI-Box: alles, was NICHT aus Git oder per Re-Download
|
||||
# zurückkommt. Erzeugt EIN Tarball mc2-state-<ts>.tar.gz, behält die letzten N.
|
||||
# Läuft per systemd-Timer (täglich), manuell, oder über den UI-Snapshot-Button.
|
||||
#
|
||||
# Inhalt: mem0 (Chroma + history.db) · ~/.hermes (config.yaml, .env, plugins/) ·
|
||||
# /etc/llama-swap/config.yaml
|
||||
# NICHT enthalten (bewusst): GGUF-Modelle (riesig, neu ladbar), MC2-Code (Git), venvs.
|
||||
#
|
||||
# ACHTUNG: das Tarball enthält ~/.hermes/.env (Secrets) → chmod 600, nicht in Git.
|
||||
set -euo pipefail
|
||||
|
||||
MODELS_DIR="${MC_MODELS_DIR:-/srv/models}"
|
||||
MEM_DB="${MC_MEMORY_DB:-$MODELS_DIR/mc2-memory.db}"
|
||||
DEST_DIR="$MODELS_DIR/mc2-backups"
|
||||
RETAIN="${MC_BACKUP_RETAIN:-14}"
|
||||
MEM0_DIR="${MC_MEM0_DIR:-/srv/models/mem0}"
|
||||
LSWAP="${MC_CONFIG_PATH:-/etc/llama-swap/config.yaml}"
|
||||
DEST="$MODELS_DIR/mc2-backups/$(date +%Y%m%d-%H%M%S)"
|
||||
HERMES="${HERMES_HOME:-$HOME/.hermes}"
|
||||
TS="$(date +%Y%m%d-%H%M%S)"
|
||||
|
||||
mkdir -p "$DEST"
|
||||
for f in "$MEM_DB" "$MEM_DB-wal" "$MEM_DB-shm" "$LSWAP"; do
|
||||
[ -f "$f" ] && cp -p "$f" "$DEST/" || true
|
||||
done
|
||||
STAGE="$(mktemp -d)"
|
||||
trap 'rm -rf "$STAGE"' EXIT
|
||||
mkdir -p "$STAGE/mem0" "$STAGE/hermes" "$STAGE/llama-swap"
|
||||
|
||||
# nur die letzten 7 behalten
|
||||
ls -1dt "$MODELS_DIR"/mc2-backups/*/ 2>/dev/null | tail -n +8 | xargs -r rm -rf
|
||||
echo "OK — Backup unter $DEST"
|
||||
[ -d "$MEM0_DIR" ] && cp -a "$MEM0_DIR/." "$STAGE/mem0/" || true
|
||||
[ -f "$HERMES/config.yaml" ] && cp -a "$HERMES/config.yaml" "$STAGE/hermes/" || true
|
||||
[ -f "$HERMES/.env" ] && cp -a "$HERMES/.env" "$STAGE/hermes/" || true
|
||||
[ -d "$HERMES/plugins" ] && cp -a "$HERMES/plugins" "$STAGE/hermes/plugins" || true
|
||||
[ -f "$LSWAP" ] && cp -a "$LSWAP" "$STAGE/llama-swap/" || true
|
||||
|
||||
cat > "$STAGE/MANIFEST.txt" <<EOF
|
||||
mc2-state backup
|
||||
created : $TS
|
||||
host : $(hostname)
|
||||
inhalt : mem0 (chroma + history.db), hermes (config.yaml, .env, plugins/), llama-swap (config.yaml)
|
||||
restore : bash ~/mission-control-v2/deploy/restore.sh mc2-state-$TS.tar.gz
|
||||
EOF
|
||||
|
||||
mkdir -p "$DEST_DIR"
|
||||
OUT="$DEST_DIR/mc2-state-$TS.tar.gz"
|
||||
tar -czf "$OUT" -C "$STAGE" .
|
||||
chmod 600 "$OUT" # enthält .env (Secrets)
|
||||
|
||||
# Retention: nur die letzten N behalten.
|
||||
ls -1t "$DEST_DIR"/mc2-state-*.tar.gz 2>/dev/null | tail -n +$((RETAIN + 1)) | xargs -r rm -f
|
||||
|
||||
echo "OK — Backup: $OUT ($(du -h "$OUT" | cut -f1))"
|
||||
|
||||
@@ -48,10 +48,14 @@ cp "$SRC/deploy/mission-control-2.service" "$HOME/.config/systemd/user/mission-c
|
||||
cp "$SRC/deploy/hermes-terminal.service" "$HOME/.config/systemd/user/hermes-terminal.service"
|
||||
# Mem0-Sidecar-Unit (nur wenn das venv existiert).
|
||||
[ -x "$HOME/.mem0/venv/bin/python" ] && cp "$SRC/deploy/mem0-service.service" "$HOME/.config/systemd/user/mem0-service.service"
|
||||
# Tägliches Zustands-Backup (mem0 + Configs/Secrets) — Timer + oneshot-Service. Siehe docs/BACKUP.md.
|
||||
cp "$SRC/deploy/mc2-backup.service" "$HOME/.config/systemd/user/mc2-backup.service"
|
||||
cp "$SRC/deploy/mc2-backup.timer" "$HOME/.config/systemd/user/mc2-backup.timer"
|
||||
systemctl --user daemon-reload
|
||||
systemctl --user enable mission-control-2 >/dev/null 2>&1 || true
|
||||
systemctl --user enable hermes-terminal >/dev/null 2>&1 || true
|
||||
systemctl --user enable mem0-service >/dev/null 2>&1 || true
|
||||
systemctl --user enable --now mc2-backup.timer >/dev/null 2>&1 || true
|
||||
loginctl enable-linger "$USER" >/dev/null 2>&1 || true
|
||||
# Mem0-Sidecar VOR dem Backend (re)starten, damit /api/memory sofort bedient wird.
|
||||
[ -x "$HOME/.mem0/venv/bin/python" ] && systemctl --user restart mem0-service 2>/dev/null || true
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
[Unit]
|
||||
Description=MC2 Zustands-Backup (mem0 + Hermes-Configs/Secrets + llama-swap config)
|
||||
Documentation=file:%h/mission-control-v2/docs/BACKUP.md
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
ExecStart=/bin/bash %h/mission-control-v2/deploy/backup.sh
|
||||
@@ -0,0 +1,10 @@
|
||||
[Unit]
|
||||
Description=Tägliches MC2 Zustands-Backup
|
||||
|
||||
[Timer]
|
||||
OnCalendar=*-*-* 03:30:00
|
||||
Persistent=true
|
||||
RandomizedDelaySec=300
|
||||
|
||||
[Install]
|
||||
WantedBy=timers.target
|
||||
@@ -0,0 +1,83 @@
|
||||
#!/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
|
||||
# bash restore.sh --dry-run <datei|latest> # nur anzeigen, was passieren würde
|
||||
# bash restore.sh [--yes] <datei|latest> # wiederherstellen (--yes = ohne Rückfrage)
|
||||
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"
|
||||
|
||||
usage() { echo "Nutzung: restore.sh --list | restore.sh [--dry-run] [--yes] <datei|latest>"; }
|
||||
list_backups() {
|
||||
echo "Verfügbare Backups in $DEST_DIR:"
|
||||
ls -1t "$DEST_DIR"/mc2-state-*.tar.gz 2>/dev/null | while read -r f; do
|
||||
printf " %s (%s)\n" "$(basename "$f")" "$(du -h "$f" | cut -f1)"
|
||||
done
|
||||
[ -n "$(ls -A "$DEST_DIR"/mc2-state-*.tar.gz 2>/dev/null || true)" ] || echo " (keine)"
|
||||
}
|
||||
|
||||
[ $# -eq 0 ] && { usage; exit 1; }
|
||||
DRY=0; YES=0; TARGET=""
|
||||
for a in "$@"; do
|
||||
case "$a" in
|
||||
--list) list_backups; exit 0 ;;
|
||||
--dry-run) DRY=1 ;;
|
||||
--yes) YES=1 ;;
|
||||
-*) usage; exit 1 ;;
|
||||
*) TARGET="$a" ;;
|
||||
esac
|
||||
done
|
||||
[ -z "$TARGET" ] && { usage; exit 1; }
|
||||
[ "$TARGET" = "latest" ] && TARGET="$(ls -1t "$DEST_DIR"/mc2-state-*.tar.gz 2>/dev/null | head -1 || true)"
|
||||
[ -f "$TARGET" ] || TARGET="$DEST_DIR/$(basename "${TARGET:-}")"
|
||||
[ -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."
|
||||
Reference in New Issue
Block a user