#20 openai request error

[Anonymous]

Originally created by: purple8cloud
Originally owned by: Inky-Feather

Traceback (most recent call last):
File "backend\api.py", line 6331, in ai_chat
File "backend\ai\ai_service.py", line 1014, in test_chat
File "backend\ai\ai_gateway.py", line 1480, in completion
File "backend\ai\ai_gateway.py", line 1418, in _openai_compatible_completion
File "backend\ai\ai_gateway.py", line 870, in _run_openai_reasoning_fallback_sync
File "backend\ai\ai_gateway.py", line 853, in _run_openai_reasoning_fallback_sync
File "backend\ai\ai_gateway.py", line 1405, in runner
File "backend\ai\ai_gateway.py", line 996, in _run_openai_compatible_with_fallback_sync
File "backend\ai\ai_gateway.py", line 416, in _call_with_retries_sync
File "backend\ai\ai_gateway.py", line 1412, in <lambda>
File "backend\ai\ai_gateway.py", line 1335, in _call_openai_compatible_chat
File "openai_utils_utils.py", line 286, in wrapper
File "openai\resources\chat\completions\completions.py", line 1204, in create
File "openai_base_client.py", line 1297, in post
File "openai_base_client.py", line 1070, in request
openai.BadRequestError: Error code: 400 - {'error': {'message': "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.", 'type': 'invalid_request_error', 'param': 'max_tokens', 'code': 'unsupported_parameter'}}</lambda>

cant use gpt6

[Anonymous]

Originally posted by: Inky-Feather

I plan to reimplement the AI functionality later, so no further optimizations have actually been done.
이후 AI 기능 부분을 재구현할 계획이어서 사실 더 이상의 최적화는 진행하지 않았습니다.

[Anonymous]

• assigned_to: Inky-Feather