fix(gateway): defer background review notifications until after main reply

Background review notifications ("💾 Skill created", "💾 Memory updated")
could race ahead of the main assistant reply in chat, making it look like
the agent stopped after creating a skill.

Gate bg-review notifications behind a threading.Event + pending queue.
Register a release callback on the adapter's _post_delivery_callbacks dict
so base.py's finally block fires it after the main response is delivered.

The queued-message path in _run_agent pops and calls the callback directly
to prevent double-fire.

Co-authored-by: Hermes Agent <hermes@nousresearch.com>
Closes #10541
This commit is contained in:
Greer Guthrie 2026-04-15 16:40:38 -07:00 committed by Teknium
parent 44941f0ed1
commit 33ff29dfae
3 changed files with 130 additions and 2 deletions

View file

@ -839,6 +839,11 @@ class BasePlatformAdapter(ABC):
# Gateway shutdown cancels these so an old gateway instance doesn't keep
# working on a task after --replace or manual restarts.
self._background_tasks: set[asyncio.Task] = set()
# One-shot callbacks to fire after the main response is delivered.
# Keyed by session_key. GatewayRunner uses this to defer
# background-review notifications ("💾 Skill created") until the
# primary reply has been sent.
self._post_delivery_callbacks: Dict[str, Callable] = {}
self._expected_cancelled_tasks: set[asyncio.Task] = set()
self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
# Chats where auto-TTS on voice input is disabled (set by /voice off)
@ -1894,6 +1899,14 @@ class BasePlatformAdapter(ABC):
except Exception:
pass # Last resort — don't let error reporting crash the handler
finally:
# Fire any one-shot post-delivery callback registered for this
# session (e.g. deferred background-review notifications).
_post_cb = getattr(self, "_post_delivery_callbacks", {}).pop(session_key, None)
if callable(_post_cb):
try:
_post_cb()
except Exception:
pass
# Stop typing indicator
typing_task.cancel()
try: