#!/usr/bin/env bash
#
# Qdrant snapshot + off-host rotation.
#
# Snapshots both collections (mem0_v3 + mem0_v3_entities) back-to-back via the
# Qdrant REST API, downloads them to a date-stamped local directory, uploads to
# the configured rclone remote, prunes local copies older than 14 days, and
# emits a Prometheus textfile metric for future scrape.
#
# Env vars (override defaults):
#   QDRANT_CONTAINER       container name (default: mem0-qdrant)
#   COLLECTIONS            space-separated collection names
#                          (default: "mem0_v3 mem0_v3_entities")
#   BACKUP_DIR             local backup root
#                          (default: ~/aistuff/mem0/backups/qdrant)
#   RCLONE_REMOTE          rclone remote path (e.g. b2:mem0-backups/qdrant).
#                          If unset, off-host upload is skipped.
#   LOCAL_RETENTION_DAYS   how long to keep local copies (default: 14)
#   TEXTFILE_DIR           Prometheus node_exporter textfile collector dir
#                          (default: /var/lib/node_exporter/textfile_collector,
#                          skipped if the dir does not exist)
#
# Suggested cron (daily at 03:00 UTC):
#   0 3 * * *  RCLONE_REMOTE=b2:mem0-backups/qdrant /home/ubuntu/aistuff/mem0/scripts/backup_qdrant.sh >> /home/ubuntu/aistuff/mem0/backups/backup.log 2>&1
#
# Exit codes:
#   0 success
#   1 snapshot/download failure
#   2 rclone failure (after local download succeeded)

set -euo pipefail

QDRANT_CONTAINER="${QDRANT_CONTAINER:-mem0-qdrant}"
COLLECTIONS="${COLLECTIONS:-mem0_v3 mem0_v3_entities}"
BACKUP_DIR="${BACKUP_DIR:-$HOME/aistuff/mem0/backups/qdrant}"
RCLONE_REMOTE="${RCLONE_REMOTE:-}"
LOCAL_RETENTION_DAYS="${LOCAL_RETENTION_DAYS:-14}"
TEXTFILE_DIR="${TEXTFILE_DIR:-/var/lib/node_exporter/textfile_collector}"

TS="$(date -u +%Y%m%dT%H%M%SZ)"
DAY="$(date -u +%Y-%m-%d)"
TARGET_DIR="$BACKUP_DIR/$DAY"
mkdir -p "$TARGET_DIR"

log() { printf '[%s] %s\n' "$(date -u +%FT%TZ)" "$*"; }

log "starting backup ts=$TS dir=$TARGET_DIR collections=$COLLECTIONS"

total_bytes=0
for col in $COLLECTIONS; do
  log "snapshot create: $col"
  resp=$(docker exec "$QDRANT_CONTAINER" curl -fsS -X POST \
    "http://localhost:6333/collections/$col/snapshots?wait=true")
  snap_name=$(printf '%s' "$resp" \
    | python3 -c 'import sys,json; print(json.load(sys.stdin)["result"]["name"])')

  out_file="$TARGET_DIR/${col}_${TS}_${snap_name}"
  log "snapshot download: $col/$snap_name -> $out_file"
  docker cp "$QDRANT_CONTAINER:/qdrant/storage/collections/$col/snapshots/$snap_name" "$out_file"

  # Remove the in-container snapshot to avoid disk bloat on the volume.
  docker exec "$QDRANT_CONTAINER" curl -fsS -X DELETE \
    "http://localhost:6333/collections/$col/snapshots/$snap_name" >/dev/null

  size=$(stat -c %s "$out_file" 2>/dev/null || stat -f %z "$out_file")
  total_bytes=$((total_bytes + size))
  log "downloaded: $out_file ($size bytes)"
done

if [ -n "$RCLONE_REMOTE" ]; then
  log "rclone copy: $TARGET_DIR -> $RCLONE_REMOTE/$DAY"
  if ! rclone copy "$TARGET_DIR" "$RCLONE_REMOTE/$DAY"; then
    log "rclone failed (local copies retained)"
    exit 2
  fi
else
  log "RCLONE_REMOTE unset; skipping off-host upload"
fi

log "pruning local copies older than $LOCAL_RETENTION_DAYS days"
find "$BACKUP_DIR" -mindepth 1 -maxdepth 1 -type d -mtime "+$LOCAL_RETENTION_DAYS" -exec rm -rf {} +

if [ -d "$TEXTFILE_DIR" ]; then
  tmp="$(mktemp)"
  {
    echo "# HELP qdrant_last_backup_timestamp_seconds Unix timestamp of last successful Qdrant backup."
    echo "# TYPE qdrant_last_backup_timestamp_seconds gauge"
    echo "qdrant_last_backup_timestamp_seconds $(date -u +%s)"
    echo "# HELP qdrant_last_backup_bytes Total bytes of last successful Qdrant backup."
    echo "# TYPE qdrant_last_backup_bytes gauge"
    echo "qdrant_last_backup_bytes $total_bytes"
  } > "$tmp"
  mv "$tmp" "$TEXTFILE_DIR/qdrant_backup.prom"
  log "textfile metric written: $TEXTFILE_DIR/qdrant_backup.prom"
fi

log "backup complete: $total_bytes bytes across $(echo "$COLLECTIONS" | wc -w) collection(s)"