feat: session garbage collection (#315)
Some checks failed
Forge CI / smoke-and-build (pull_request) Failing after 14s

Add garbage_collect() method to SessionDB that cleans up empty and
trivial sessions based on age:
- Empty sessions (0 messages) older than 24h
- Trivial sessions (1-5 messages) older than 7 days
- Sessions with >5 messages kept indefinitely

Add `hermes sessions gc` CLI command with:
- --empty-hours (default: 24)
- --trivial-days (default: 7)
- --trivial-max (default: 5)
- --source filter
- --dry-run preview mode
- --yes skip confirmation

The dry-run flow: preview what would be deleted, ask for confirmation,
then execute. Handles child session FK constraints properly.

7 tests covering: empty/trivial deletion, active session protection,
substantial session preservation, dry-run, source filtering, and child
session handling.

Closes #315
This commit is contained in:
Alexander Whitestone
2026-04-13 17:30:39 -04:00
parent 992498463e
commit 69e10967bd
3 changed files with 248 additions and 1 deletions

View File

@@ -665,6 +665,127 @@ class TestPruneSessions:
# =========================================================================
# =========================================================================
# Garbage Collect
# =========================================================================
class TestGarbageCollect:
def test_gc_deletes_empty_old_sessions(self, db):
"""Empty sessions (0 messages) older than 24h should be deleted."""
db.create_session(session_id="empty_old", source="cli")
db.end_session("empty_old", end_reason="done")
db._conn.execute(
"UPDATE sessions SET started_at = ? WHERE id = ?",
(time.time() - 48 * 3600, "empty_old"), # 48 hours ago
)
db._conn.commit()
# Recent empty session should be kept
db.create_session(session_id="empty_new", source="cli")
db.end_session("empty_new", end_reason="done")
result = db.garbage_collect()
assert result["empty"] == 1
assert result["trivial"] == 0
assert result["total"] == 1
assert db.get_session("empty_old") is None
assert db.get_session("empty_new") is not None
def test_gc_deletes_trivial_old_sessions(self, db):
"""Sessions with 1-5 messages older than 7 days should be deleted."""
db.create_session(session_id="trivial_old", source="cli")
for i in range(3):
db.append_message("trivial_old", role="user", content=f"msg {i}")
db.end_session("trivial_old", end_reason="done")
db._conn.execute(
"UPDATE sessions SET started_at = ? WHERE id = ?",
(time.time() - 10 * 86400, "trivial_old"), # 10 days ago
)
db._conn.commit()
result = db.garbage_collect()
assert result["trivial"] == 1
assert result["total"] == 1
assert db.get_session("trivial_old") is None
def test_gc_keeps_active_sessions(self, db):
"""Active (not ended) sessions should never be deleted."""
db.create_session(session_id="active_old", source="cli")
# Backdate but don't end
db._conn.execute(
"UPDATE sessions SET started_at = ? WHERE id = ?",
(time.time() - 48 * 3600, "active_old"),
)
db._conn.commit()
result = db.garbage_collect()
assert result["total"] == 0
assert db.get_session("active_old") is not None
def test_gc_keeps_substantial_sessions(self, db):
"""Sessions with >5 messages should never be deleted."""
db.create_session(session_id="big_old", source="cli")
for i in range(10):
db.append_message("big_old", role="user", content=f"msg {i}")
db.end_session("big_old", end_reason="done")
db._conn.execute(
"UPDATE sessions SET started_at = ? WHERE id = ?",
(time.time() - 365 * 86400, "big_old"), # 1 year ago
)
db._conn.commit()
result = db.garbage_collect()
assert result["total"] == 0
assert db.get_session("big_old") is not None
def test_gc_dry_run_does_not_delete(self, db):
"""dry_run=True should return counts but not delete anything."""
db.create_session(session_id="empty_old", source="cli")
db.end_session("empty_old", end_reason="done")
db._conn.execute(
"UPDATE sessions SET started_at = ? WHERE id = ?",
(time.time() - 48 * 3600, "empty_old"),
)
db._conn.commit()
result = db.garbage_collect(dry_run=True)
assert result["total"] == 1
assert db.get_session("empty_old") is not None # Still exists
def test_gc_with_source_filter(self, db):
"""--source should only GC sessions from that source."""
for sid, src in [("old_cli", "cli"), ("old_tg", "telegram")]:
db.create_session(session_id=sid, source=src)
db.end_session(sid, end_reason="done")
db._conn.execute(
"UPDATE sessions SET started_at = ? WHERE id = ?",
(time.time() - 48 * 3600, sid),
)
db._conn.commit()
result = db.garbage_collect(source="cli")
assert result["total"] == 1
assert db.get_session("old_cli") is None
assert db.get_session("old_tg") is not None
def test_gc_handles_child_sessions(self, db):
"""Child sessions should be deleted when parent is GC'd."""
db.create_session(session_id="parent_old", source="cli")
db.end_session("parent_old", end_reason="done")
db._conn.execute(
"UPDATE sessions SET started_at = ? WHERE id = ?",
(time.time() - 48 * 3600, "parent_old"),
)
# Create child session
db.create_session(session_id="child", source="cli", parent_session_id="parent_old")
db.end_session("child", end_reason="done")
db._conn.commit()
result = db.garbage_collect()
assert result["total"] == 1
assert db.get_session("parent_old") is None
assert db.get_session("child") is None
# Schema and WAL mode
# =========================================================================