ops: consistent rotated db backups + cron, consecutive-api-error staff alert

deploy/backup_db.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+"""Consistent, rotated bot.db backups (SPEC-012 OPS-13).
+
+Run from cron on each host. Uses the sqlite3 online-backup API so the
+snapshot is consistent even while the bot writes (WAL-safe), gzips it,
+and keeps the newest N. Stdlib only.
+
+Usage: python3 backup_db.py <bot.db> <backup-dir> [keep]
+"""
+
+import gzip
+import os
+import shutil
+import sqlite3
+import sys
+import tempfile
+import time
+from pathlib import Path
+
+DEFAULT_KEEP = 14
+BACKUP_GLOB = "bot-*.db.gz"
+
+
+def snapshot(src: Path, dest_gz: Path) -> None:
+    """Write a consistent gzipped snapshot of src to dest_gz (OPS-13)."""
+    fd, tmp_path = tempfile.mkstemp(suffix=".db", dir=str(dest_gz.parent))
+    os.close(fd)
+    tmp = Path(tmp_path)
+    try:
+        source = sqlite3.connect(str(src))
+        try:
+            target = sqlite3.connect(str(tmp))
+            try:
+                source.backup(target)  # atomic, WAL-safe online backup
+            finally:
+                target.close()
+        finally:
+            source.close()
+        with open(tmp, "rb") as raw, gzip.open(str(dest_gz), "wb") as gz:
+            shutil.copyfileobj(raw, gz)
+        os.chmod(dest_gz, 0o600)  # conversation data
+    finally:
+        tmp.unlink(missing_ok=True)
+
+
+def victims(existing: list, keep: int) -> list:
+    """Given backup paths (any order), return the ones to delete, oldest first (OPS-14)."""
+    ordered = sorted(existing)  # timestamped names sort chronologically
+    return ordered[: max(0, len(ordered) - keep)]
+
+
+def rotate(backup_dir: Path, keep: int) -> int:
+    removed = 0
+    for path in victims(list(backup_dir.glob(BACKUP_GLOB)), keep):
+        Path(path).unlink(missing_ok=True)
+        removed += 1
+    return removed
+
+
+def main() -> int:
+    if len(sys.argv) < 3:
+        print("usage: backup_db.py <bot.db> <backup-dir> [keep]", file=sys.stderr)
+        return 2
+    src = Path(sys.argv[1]).expanduser()
+    backup_dir = Path(sys.argv[2]).expanduser()
+    keep = int(sys.argv[3]) if len(sys.argv) > 3 else DEFAULT_KEEP
+    if not src.exists():
+        print(f"backup: source {src} missing", file=sys.stderr)
+        return 1
+    backup_dir.mkdir(parents=True, exist_ok=True)
+    stamp = time.strftime("%Y%m%d-%H%M%S", time.gmtime())
+    dest = backup_dir / f"bot-{stamp}.db.gz"
+    snapshot(src, dest)
+    removed = rotate(backup_dir, keep)
+    print(f"backup: wrote {dest.name} ({dest.stat().st_size} bytes), rotated {removed} old")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())