diff options
Diffstat (limited to 'packages/meshbay-node/src/meshbay_node')
| -rw-r--r-- | packages/meshbay-node/src/meshbay_node/hub_client.py | 17 |
1 files changed, 14 insertions, 3 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/hub_client.py b/packages/meshbay-node/src/meshbay_node/hub_client.py index 691ac7c..334107d 100644 --- a/packages/meshbay-node/src/meshbay_node/hub_client.py +++ b/packages/meshbay-node/src/meshbay_node/hub_client.py @@ -241,6 +241,7 @@ class HubClient: # working one until someone notices the node has vanished. async with websockets.connect( ws_url, ping_interval=20, ping_timeout=20, close_timeout=5, + open_timeout=15, ) as ws: auth_msg = { "type": "auth", @@ -250,10 +251,20 @@ class HubClient: if group_ids: auth_msg["group_ids"] = group_ids await ws.send(json.dumps(auth_msg)) - auth_resp = json.loads(await ws.recv()) + # Bounded: a hub that accepts the socket and then says nothing + # — which is what it does for a few seconds while restarting — + # would otherwise park this task here forever, with the node + # running, silent, and invisible to everyone. + auth_resp = json.loads( + await asyncio.wait_for(ws.recv(), timeout=15)) if auth_resp.get("type") != "auth_ok": - log.error("WS auth failed: %s", auth_resp) - return + # Not fatal: the token may simply have expired while we + # were disconnected. Refresh on the next pass rather than + # ending the task, which used to strand the node for good. + log.warning("WS auth refused: %s — retrying in 5s", auth_resp) + await asyncio.sleep(5) + await self.ensure_fresh_token() + continue self._ws = ws log.info("Hub WS connected") |