fix(gateway): persist memory flush state to prevent redundant re-flushes on restart

The _session_expiry_watcher tracked flushed sessions in an in-memory set
(_pre_flushed_sessions) that was lost on gateway restart. Expired sessions
remained in sessions.json and were re-discovered every restart, causing
redundant AIAgent runs that burned API credits and blocked the event loop.

Fix: Add a memory_flushed boolean field to SessionEntry, persisted in
sessions.json. The watcher sets it after a successful flush. On restart,
the flag survives and the watcher skips already-flushed sessions.

- Add memory_flushed field to SessionEntry with to_dict/from_dict support
- Old sessions.json entries without the field default to False (backward compat)
- Remove the ephemeral _pre_flushed_sessions set from SessionStore
- Update tests: save/load roundtrip, legacy entry compat, auto-reset behavior
This commit is contained in:
Teknium 2026-04-01 11:55:22 -07:00
parent a39891b33c
commit 31fd50d808
No known key found for this signature in database
3 changed files with 111 additions and 32 deletions

View file

@ -1280,8 +1280,8 @@ class GatewayRunner:
try:
self.session_store._ensure_loaded()
for key, entry in list(self.session_store._entries.items()):
if entry.session_id in self.session_store._pre_flushed_sessions:
continue # already flushed this session
if entry.memory_flushed:
continue # already flushed this session (persisted to disk)
if not self.session_store._is_session_expired(entry):
continue # session still active
# Session has expired — flush memories in the background
@ -1292,7 +1292,15 @@ class GatewayRunner:
try:
await self._async_flush_memories(entry.session_id, key)
self._shutdown_gateway_honcho(key)
self.session_store._pre_flushed_sessions.add(entry.session_id)
# Mark as flushed and persist to disk so the flag
# survives gateway restarts.
with self.session_store._lock:
entry.memory_flushed = True
self.session_store._save()
logger.info(
"Pre-reset memory flush completed for session %s",
entry.session_id,
)
except Exception as e:
logger.debug("Proactive memory flush failed for %s: %s", entry.session_id, e)
except Exception as e:

View file

@ -364,6 +364,12 @@ class SessionEntry:
auto_reset_reason: Optional[str] = None # "idle" or "daily"
reset_had_activity: bool = False # whether the expired session had any messages
# Set by the background expiry watcher after it successfully flushes
# memories for this session. Persisted to sessions.json so the flag
# survives gateway restarts (the old in-memory _pre_flushed_sessions
# set was lost on restart, causing redundant re-flushes).
memory_flushed: bool = False
def to_dict(self) -> Dict[str, Any]:
result = {
"session_key": self.session_key,
@ -381,6 +387,7 @@ class SessionEntry:
"last_prompt_tokens": self.last_prompt_tokens,
"estimated_cost_usd": self.estimated_cost_usd,
"cost_status": self.cost_status,
"memory_flushed": self.memory_flushed,
}
if self.origin:
result["origin"] = self.origin.to_dict()
@ -416,6 +423,7 @@ class SessionEntry:
last_prompt_tokens=data.get("last_prompt_tokens", 0),
estimated_cost_usd=data.get("estimated_cost_usd", 0.0),
cost_status=data.get("cost_status", "unknown"),
memory_flushed=data.get("memory_flushed", False),
)
@ -479,9 +487,6 @@ class SessionStore:
self._loaded = False
self._lock = threading.Lock()
self._has_active_processes_fn = has_active_processes_fn
# on_auto_reset is deprecated — memory flush now runs proactively
# via the background session expiry watcher in GatewayRunner.
self._pre_flushed_sessions: set = set() # session_ids already flushed by watcher
# Initialize SQLite session database
self._db = None
@ -684,15 +689,12 @@ class SessionStore:
self._save()
return entry
else:
# Session is being auto-reset. The background expiry watcher
# should have already flushed memories proactively; discard
# the marker so it doesn't accumulate.
# Session is being auto-reset.
was_auto_reset = True
auto_reset_reason = reset_reason
# Track whether the expired session had any real conversation
reset_had_activity = entry.total_tokens > 0
db_end_session_id = entry.session_id
self._pre_flushed_sessions.discard(entry.session_id)
else:
was_auto_reset = False
auto_reset_reason = None

View file

@ -3,7 +3,7 @@
Verifies that:
1. _is_session_expired() works from a SessionEntry alone (no source needed)
2. The sync callback is no longer called in get_or_create_session
3. _pre_flushed_sessions tracking works correctly
3. memory_flushed flag persists across save/load cycles (prevents restart re-flush)
4. The background watcher can detect expired sessions
"""
@ -115,8 +115,8 @@ class TestIsSessionExpired:
class TestGetOrCreateSessionNoCallback:
"""get_or_create_session should NOT call a sync flush callback."""
def test_auto_reset_cleans_pre_flushed_marker(self, idle_store):
"""When a session auto-resets, the pre_flushed marker should be discarded."""
def test_auto_reset_creates_new_session_after_flush(self, idle_store):
"""When a flushed session auto-resets, a new session_id is created."""
source = SessionSource(
platform=Platform.TELEGRAM,
chat_id="123",
@ -127,7 +127,7 @@ class TestGetOrCreateSessionNoCallback:
old_sid = entry1.session_id
# Simulate the watcher having flushed it
idle_store._pre_flushed_sessions.add(old_sid)
entry1.memory_flushed = True
# Simulate the session going idle
entry1.updated_at = datetime.now() - timedelta(minutes=120)
@ -137,9 +137,8 @@ class TestGetOrCreateSessionNoCallback:
entry2 = idle_store.get_or_create_session(source)
assert entry2.session_id != old_sid
assert entry2.was_auto_reset is True
# The old session_id should be removed from pre_flushed
assert old_sid not in idle_store._pre_flushed_sessions
# New session starts with memory_flushed=False
assert entry2.memory_flushed is False
def test_no_sync_callback_invoked(self, idle_store):
"""No synchronous callback should block during auto-reset."""
@ -160,21 +159,91 @@ class TestGetOrCreateSessionNoCallback:
assert entry2.was_auto_reset is True
class TestPreFlushedSessionsTracking:
"""The _pre_flushed_sessions set should prevent double-flushing."""
class TestMemoryFlushedFlag:
"""The memory_flushed flag on SessionEntry prevents double-flushing."""
def test_starts_empty(self, idle_store):
assert len(idle_store._pre_flushed_sessions) == 0
def test_defaults_to_false(self):
entry = SessionEntry(
session_key="agent:main:telegram:dm:123",
session_id="sid_new",
created_at=datetime.now(),
updated_at=datetime.now(),
platform=Platform.TELEGRAM,
chat_type="dm",
)
assert entry.memory_flushed is False
def test_add_and_check(self, idle_store):
idle_store._pre_flushed_sessions.add("sid_old")
assert "sid_old" in idle_store._pre_flushed_sessions
assert "sid_other" not in idle_store._pre_flushed_sessions
def test_persists_through_save_load(self, idle_store):
"""memory_flushed=True must survive a save/load cycle (simulates restart)."""
key = "agent:main:discord:thread:789"
entry = SessionEntry(
session_key=key,
session_id="sid_flushed",
created_at=datetime.now() - timedelta(hours=5),
updated_at=datetime.now() - timedelta(hours=5),
platform=Platform.DISCORD,
chat_type="thread",
memory_flushed=True,
)
idle_store._entries[key] = entry
idle_store._save()
def test_discard_on_reset(self, idle_store):
"""discard should remove without raising if not present."""
idle_store._pre_flushed_sessions.add("sid_a")
idle_store._pre_flushed_sessions.discard("sid_a")
assert "sid_a" not in idle_store._pre_flushed_sessions
# discard on non-existent should not raise
idle_store._pre_flushed_sessions.discard("sid_nonexistent")
# Simulate restart: clear in-memory state, reload from disk
idle_store._entries.clear()
idle_store._loaded = False
idle_store._ensure_loaded()
reloaded = idle_store._entries[key]
assert reloaded.memory_flushed is True
def test_unflushed_entry_survives_restart_as_unflushed(self, idle_store):
"""An entry without memory_flushed stays False after reload."""
key = "agent:main:telegram:dm:456"
entry = SessionEntry(
session_key=key,
session_id="sid_not_flushed",
created_at=datetime.now() - timedelta(hours=2),
updated_at=datetime.now() - timedelta(hours=2),
platform=Platform.TELEGRAM,
chat_type="dm",
)
idle_store._entries[key] = entry
idle_store._save()
idle_store._entries.clear()
idle_store._loaded = False
idle_store._ensure_loaded()
reloaded = idle_store._entries[key]
assert reloaded.memory_flushed is False
def test_roundtrip_to_dict_from_dict(self):
"""to_dict/from_dict must preserve memory_flushed."""
entry = SessionEntry(
session_key="agent:main:telegram:dm:999",
session_id="sid_rt",
created_at=datetime.now(),
updated_at=datetime.now(),
platform=Platform.TELEGRAM,
chat_type="dm",
memory_flushed=True,
)
d = entry.to_dict()
assert d["memory_flushed"] is True
restored = SessionEntry.from_dict(d)
assert restored.memory_flushed is True
def test_legacy_entry_without_field_defaults_false(self):
"""Old sessions.json entries missing memory_flushed should default to False."""
data = {
"session_key": "agent:main:telegram:dm:legacy",
"session_id": "sid_legacy",
"created_at": datetime.now().isoformat(),
"updated_at": datetime.now().isoformat(),
"platform": "telegram",
"chat_type": "dm",
# no memory_flushed key
}
entry = SessionEntry.from_dict(data)
assert entry.memory_flushed is False