Unhandled exception on req_str

[snapo]

Running the latest workbee 0.2.2 (latest from today)

Got the following exception:

2023-10-27 22:19:13,397 - httpx - INFO - HTTP Request: POST http://test/v1/chat/completions "HTTP/1.1 200 OK"
2023-10-27 22:19:13,398 - ai_worker.main - INFO - done TheBloke/vicuna-7B-v1.5-GGUF:Q4_K_M (5.875 secs)
Traceback (most recent call last):
  File "ai_worker\main.py", line 357, in run_one
  File "ai_worker\main.py", line 338, in ws_recv
  File "websockets\legacy\protocol.py", line 568, in recv
  File "websockets\legacy\protocol.py", line 944, in ensure_open
websockets.exceptions.ConnectionClosedError: received 1012 (service restart); then sent 1012 (service restart)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "ai_worker\__main__.py", line 4, in <module>
  File "ai_worker\main.py", line 504, in main
  File "asyncio\runners.py", line 190, in run
  File "asyncio\runners.py", line 118, in run
  File "asyncio\base_events.py", line 653, in run_until_complete
  File "ai_worker\main.py", line 201, in run
  File "ai_worker\main.py", line 347, in run_ws
  File "ai_worker\main.py", line 382, in run_one
UnboundLocalError: cannot access local variable 'req_str' where it is not associated with a value
[14004] Failed to execute script '__main__' due to unhandled exception!

Hope this helps.... After a restart everything works fine again... seems to happen when possibly the websocket connection is lost.

I had when i wrote a bot for the deribit exchange also always issues with asyncio handling it. After very long struggles i switched to the python library lomond since then i never had a issue again.... (https://github.com/wildfoundry/dataplicity-lomond) (automatic reconnect, handling of different tcp / ip protocol errors, disconnect handling)

[snapo]

seems to be fixed, received a task today, little later had a disconnect and it reconnected