1 files changed, 44 insertions, 3 deletions
diff --git a/packages/meshbay-hub/src/meshbay_hub/tasks/cleanup.py b/packages/meshbay-hub/src/meshbay_hub/tasks/cleanup.py
index 7674c6e..c387100 100644
--- a/packages/meshbay-hub/src/meshbay_hub/tasks/cleanup.py
+++ b/packages/meshbay-hub/src/meshbay_hub/tasks/cleanup.py
@@ -1,13 +1,13 @@
-"""Scheduled cleanup tasks — IP log purge (1-year retention)."""
+"""Scheduled cleanup tasks — IP log purge, and unhosted group collection."""
 
 import asyncio
 import logging
 from datetime import datetime, timedelta, timezone
 
-from sqlalchemy import delete
+from sqlalchemy import delete, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from meshbay_hub.db.models import IPLog
+from meshbay_hub.db.models import Group, GroupMember, IPLog
 
 log = logging.getLogger(__name__)
 
@@ -38,3 +38,44 @@ async def cleanup_loop(get_session):
             await asyncio.sleep(CLEANUP_INTERVAL_HOURS * 3600)
     except asyncio.CancelledError:
         return
+
+
+# ── Groups that never got a node ──────────────────────────────────────────────
+
+UNHOSTED_GRACE_DAYS = 7
+
+
+async def find_unhosted_groups(db: AsyncSession, grace_days: int = UNHOSTED_GRACE_DAYS):
+    """Groups created more than `grace_days` ago that no node has ever announced.
+
+    `hosted_at` is set the first time a node registers claiming the group and is
+    never cleared, so this finds groups that were created and then abandoned —
+    not ones whose node happens to be offline today. That distinction is the
+    whole reason the column exists rather than a check against the live socket
+    registry, which would delete every group during a hub restart.
+    """
+    cutoff = datetime.now(timezone.utc) - timedelta(days=grace_days)
+    result = await db.execute(
+        select(Group).where(Group.hosted_at.is_(None), Group.created_at < cutoff))
+    return list(result.scalars().all())
+
+
+async def prune_unhosted_groups(db: AsyncSession, grace_days: int = UNHOSTED_GRACE_DAYS,
+                                dry_run: bool = False) -> list[tuple[str, str]]:
+    """Delete abandoned groups. Returns [(id, name)] of what was (or would be) removed.
+
+    Memberships go with the group — there is no cascade configured, and leaving
+    orphan rows behind would keep the group in everyone's /mine query through the
+    join. Nothing on a node is touched: the hub does not command those machines,
+    and by definition no node ever claimed this group anyway.
+    """
+    doomed = await find_unhosted_groups(db, grace_days)
+    if not doomed or dry_run:
+        return [(g.id, g.name) for g in doomed]
+
+    ids = [g.id for g in doomed]
+    await db.execute(delete(GroupMember).where(GroupMember.group_id.in_(ids)))
+    await db.execute(delete(Group).where(Group.id.in_(ids)))
+    await db.commit()
+    log.info("Pruned %d group(s) that no node ever hosted", len(doomed))
+    return [(g.id, g.name) for g in doomed]