1 files changed, 92 insertions, 0 deletions
diff --git a/scripts/newos4-prune-debug.py b/scripts/newos4-prune-debug.py
new file mode 100755
index 0000000..7fe0fcb
--- /dev/null
+++ b/scripts/newos4-prune-debug.py
@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+"""Prune self-referential / stale debug rows from newOS4 telemetry.
+
+Read-only unless --apply. Coordinates with PHP via the SAME flock on errors.json
+(ingest.php opens it 'c' + LOCK_EX), and always archives before rewriting.
+"""
+import argparse, fcntl, json, os, re, time
+
+ROOT = '/var/www/webx11.duckdns.org/spaces/newos4'
+DEBUG = os.path.join(ROOT, 'data', 'debug')
+ERRORS = os.path.join(DEBUG, 'errors.json')
+ARCHIVE = os.path.join(DEBUG, 'archive')
+SELF = re.compile(r'/api/debug/(ingest|report)\.php', re.I)
+
+
+def iso_to_epoch(s):
+    """Parse '2026-10-20T16:57:31.589Z' or '...+00:00'. Returns None when unparseable."""
+    if not s:
+        return None
+    t = str(s).strip().replace('Z', '+00:00')
+    if '.' in t:
+        head, rest = t.split('.', 1)
+        frac = rest[:6].ljust(6, '0')
+        tail = rest[6:]
+        t = f'{head}.{frac}{tail}'
+    try:
+        import datetime
+        d = datetime.datetime.fromisoformat(t)
+        if d.tzinfo is None:
+            d = d.replace(tzinfo=datetime.timezone.utc)
+        return d.timestamp()
+    except Exception:
+        return None
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument('--apply', action='store_true')
+    ap.add_argument('--max-age-days', type=int, default=30)
+    a = ap.parse_args()
+    cutoff = time.time() - a.max_age_days * 86400
+
+    fp = open(ERRORS, 'r+', encoding='utf-8')
+    fcntl.flock(fp, fcntl.LOCK_EX)
+    try:
+        errors = json.load(fp) or []
+        keep, drop = [], []
+        for e in errors:
+            msg = str(e.get('message', ''))
+            age_ref = iso_to_epoch(e.get('last_seen')) or iso_to_epoch(e.get('ingested_at'))
+            if SELF.search(msg):
+                drop.append((e, 'self-referential'))
+            elif age_ref is not None and age_ref < cutoff:
+                drop.append((e, f'older than {a.max_age_days}d'))
+            else:
+                keep.append(e)
+
+        print(f'records={len(errors)} keep={len(keep)} drop={len(drop)}')
+        reasons = {}
+        for e, why in drop:
+            reasons[why] = reasons.get(why, 0) + 1
+        for why, n in sorted(reasons.items()):
+            print(f'  drop {n:>2} reason={why}')
+        for e, why in drop[:8]:
+            print(f"    count={e.get('count')} {why}: {str(e.get('message'))[:80]}")
+        print(f"occurrences before={sum(int(e.get('count') or 1) for e in errors)} "
+              f"after={sum(int(e.get('count') or 1) for e in keep)}")
+
+        if not a.apply:
+            print('dry-run; re-run with --apply to write')
+            return
+
+        os.makedirs(ARCHIVE, exist_ok=True)
+        archive = os.path.join(ARCHIVE, f'errors-{time.strftime("%Y%m%d_%H%M%S")}.json')
+        with open(archive, 'w', encoding='utf-8') as af:
+            json.dump(errors, af, indent=2)
+        os.chmod(archive, 0o644)
+
+        fp.seek(0)
+        fp.truncate()
+        json.dump(keep, fp, indent=2)
+        fp.flush()
+        os.fsync(fp.fileno())
+        open(os.path.join(DEBUG, '.rebuild_clusters'), 'w').write(str(int(time.time())))
+        print(f'applied: {archive} written, errors.json rewritten, cluster rebuild flagged')
+    finally:
+        fcntl.flock(fp, fcntl.LOCK_UN)
+        fp.close()
+
+
+if __name__ == '__main__':
+    main()