fix(rtc): auto-reconnect signaling WebSocket on unexpected loss

`WebSocketClient` had no reconnect logic of its own — `_on_close`,
`_on_error`, and the health-check timeout in `_ping_loop` only logged
and stopped the connection. When the signaling WS dropped (transient
TCP reset, missed health check, server-side close without an SFU error
event), the session sat hanging until the frontend's own timeout fired
a DELETE.

Under concurrent load this is the dominant remaining cause of "the
agent disconnected randomly" reports: even with the late-offer fix in
place, a single brief WS blip is fatal because nothing kicks
reconnection.

- `signaling.py`: emit a `connection_lost` event with a reason string
  on (a) unexpected `_on_close`, (b) `_on_error` after the initial
  handshake completed, and (c) `_ping_loop` health-check timeout
  (notify *before* `self.close()` so the user-initiated guard does not
  suppress it). Idempotent via `_connection_lost_sent`.
- `connection_manager.py`: subscribe to `connection_lost` on the WS
  client and route it into the existing `ReconnectionManager`
  (`ReconnectionStrategy.FAST`). The manager already handles strategy
  escalation, locking, and the disconnection-timeout deadline.

Author: aliev

getstream/video/rtc/connection_manager.py

@@ -36,7 +36,7 @@
 from getstream.video.rtc.recording import RecordingManager
 from getstream.video.rtc.participants import ParticipantsState
 from getstream.video.rtc.tracks import SubscriptionConfig, SubscriptionManager
-from getstream.video.rtc.reconnection import ReconnectionManager
+from getstream.video.rtc.reconnection import ReconnectionManager, ReconnectionStrategy
 from getstream.video.rtc.peer_connection import PeerConnectionManager
 from getstream.video.rtc.models import JoinCallResponse
 from getstream.video.rtc.tracer import Tracer
@@ -277,6 +277,25 @@ async def _on_subscriber_offer(self, event: events_pb2.SubscriberOffer):
             finally:
                 self.subscriber_negotiation_lock.release()
 
+    async def _on_signaling_connection_lost(self, reason):
+        """Reconnect when the signaling WebSocket drops unexpectedly.
+
+        The WebSocketClient itself only logs the error and stops; it has
+        no reconnect of its own. This handler bridges that gap by routing
+        the loss into the existing `ReconnectionManager`, so a transient
+        TCP reset or a missed health check no longer means a dead session.
+        """
+        if not self.running:
+            return
+        logger.warning(f"Signaling WS lost; triggering reconnect: {reason}")
+        try:
+            await self._reconnector.reconnect(
+                strategy=ReconnectionStrategy.FAST,
+                reason=f"signaling ws lost: {reason}",
+            )
+        except Exception:
+            logger.exception("Reconnect after signaling WS loss failed")
+
     async def _connect_coordinator_ws(self):
         """
         Connects to the coordinator websocket and subscribes to events.
@@ -414,6 +433,15 @@ async def _connect_internal(
             # Connect subscriber offer event to handle SDP negotiation
             self._ws_client.on_event("subscriber_offer", self._on_subscriber_offer)
 
+            # Drive reconnection when the signaling WS drops outside of an
+            # SFU-level error event (raw socket close, health-check timeout,
+            # transport-level exceptions). Without this handler the
+            # WebSocketClient just logs and stops; the session sits hanging
+            # until the frontend times out and tears it down.
+            self._ws_client.on_event(
+                "connection_lost", self._on_signaling_connection_lost
+            )
+
             # Re-emit the events so they can be subscribed to on the ConnectionManager
             self._ws_client.on_wildcard("*", self.emit)
 

getstream/video/rtc/signaling.py

@@ -67,6 +67,7 @@ def __init__(
         self.thread = None
         self.running = False
         self.closed = False
+        self._connection_lost_sent = False
 
         # For ping/health check mechanism
         self.ping_thread = None
@@ -214,11 +215,42 @@ def _on_error(self, ws, error):
             error_event.error.error.message = str(error)
             self.first_message = error_event
             self.first_message_event.set()
+        elif not self.closed:
+            self._notify_connection_lost(f"error: {error}")
 
     def _on_close(self, ws, close_status_code, close_msg):
         """Handle WebSocket close event."""
         logger.debug(f"WebSocket connection closed: {close_status_code} {close_msg}")
+        was_unexpected = not self.closed
         self.running = False
+        if was_unexpected:
+            self._notify_connection_lost(
+                f"closed by remote (code={close_status_code} msg={close_msg})"
+            )
+
+    def _notify_connection_lost(self, reason: str) -> None:
+        """Emit ``connection_lost`` once, hopping onto the main loop.
+
+        Callers run on the WS worker thread or ``_ping_loop`` thread; pyee
+        schedules async listeners via ``loop.create_task``, which is not
+        thread-safe. Same hop pattern as ``_on_message`` for SFU events.
+        Idempotent so a chained ``_on_error`` → ``_on_close`` only fires
+        one event.
+        """
+        if self._connection_lost_sent:
+            return
+        self._connection_lost_sent = True
+        try:
+            asyncio.run_coroutine_threadsafe(
+                self._emit_connection_lost(reason),
+                self.main_loop,
+            )
+        except Exception:
+            logger.exception("Failed to schedule connection_lost emit")
+
+    async def _emit_connection_lost(self, reason: str) -> None:
+        with telemetry.attach_span(self.parent_span):
+            self.emit("connection_lost", reason)
 
     def _start_ping_handler(self):
         """Start the ping mechanism in a background thread."""
@@ -242,6 +274,10 @@ def _ping_loop(self):
             current_time = time.time()
             if current_time - self.last_health_check_time > self.ping_interval * 2:
                 logger.warning("Health check failed, closing connection")
+                # Notify before close() so the owner can reconnect; close()
+                # itself sets `self.closed=True` and would suppress the
+                # notification in `_on_close`.
+                self._notify_connection_lost("health check timeout")
                 self.close()
                 return
 

tests/test_signaling.py

@@ -295,6 +295,59 @@ async def test_thread_usage(self, join_request, mock_websocket):
             # Thread should be joined during close
             assert not client.running
 
+    @pytest.mark.asyncio
+    async def test_connection_lost_emitted_on_unexpected_close(
+        self, join_request, mock_websocket
+    ):
+        """An unexpected WS close after handshake emits a `connection_lost` event.
+
+        The owner (ConnectionManager) relies on this signal to drive
+        reconnection — without it, a transient socket drop leaves the
+        session hanging until the frontend times out.
+        """
+        client = WebSocketClient(
+            "wss://test.url", join_request, asyncio.get_running_loop()
+        )
+
+        received: list[str] = []
+
+        async def on_lost(reason):
+            received.append(reason)
+
+        client.on_event("connection_lost", on_lost)
+
+        # Complete handshake so we're past the initial connect phase.
+        join_response = events_pb2.SfuEvent()
+        join_response.join_response.reconnected = False
+
+        connect_task = asyncio.create_task(client.connect())
+        await asyncio.sleep(0.1)
+
+        on_open_callback = mock_websocket.call_args[1]["on_open"]
+        on_open_callback(mock_websocket.return_value)
+
+        on_message_callback = mock_websocket.call_args[1]["on_message"]
+        on_message_callback(
+            mock_websocket.return_value, join_response.SerializeToString()
+        )
+        await connect_task
+
+        # Simulate the remote dropping the connection (not user-initiated).
+        on_close_callback = mock_websocket.call_args[1]["on_close"]
+        on_close_callback(mock_websocket.return_value, 1006, "abnormal closure")
+
+        # Allow the threadsafe-scheduled emit to run on the loop.
+        await asyncio.sleep(0.1)
+
+        assert len(received) == 1, (
+            f"expected exactly one connection_lost event, got {received}"
+        )
+        assert "1006" in received[0], (
+            f"reason should mention the close code, got {received[0]!r}"
+        )
+
+        client.close()
+
     @pytest.mark.asyncio
     async def test_on_open_traces_ws_open_and_join_request(
         self, join_request, mock_websocket