Whenever a message is sent to a local backend, the request fails immediately with the following error message:
Engine protocol ngPredictTokens request returned 400: {"error":{"code":400,"message":"Failed to initialize samplers: failed to parse grammar","type":"invalid_request_error"}}
This occurs regardless of the selected local model (tested with both Qwen 3.5 9B and Nemotron Nano 3 4B.
To Reproduce:
Launch Bionic Omni Session with the local engine connected.
Load any local model (e.g., Qwen 3.5 9B or Nemotron Nano 3B).
Type any basic prompt in the chat box (e.g., "why any local ai model not working" or "anything ").
Submit the prompt. The engine immediately returns a 400 grammar parsing error.
Whenever a message is sent to a local backend, the request fails immediately with the following error message:
Engine protocol ngPredictTokens request returned 400: {"error":{"code":400,"message":"Failed to initialize samplers: failed to parse grammar","type":"invalid_request_error"}}
This occurs regardless of the selected local model (tested with both Qwen 3.5 9B and Nemotron Nano 3 4B.
To Reproduce:
Launch Bionic Omni Session with the local engine connected.
Load any local model (e.g., Qwen 3.5 9B or Nemotron Nano 3B).
Type any basic prompt in the chat box (e.g., "why any local ai model not working" or "anything ").
Submit the prompt. The engine immediately returns a 400 grammar parsing error.
