尝试支持多个llm和monitor，用Deepseek API做了实验
运行python3 examples/basic_usage.py, 前面load risks正常，Deepseek 也显示了API调用，但到run workflow时，遇到了问题:
[L2 Test] Calling run_workflow with max_round=10, timeout=300 2026-04-18 23:23:47,342 [INFO] AG2MAS: Starting workflow: "Help me resolve a complaint about an unauthorized...
[autogen.oai.client: 04-18 23:24:19] {744} WARNING - Model deepseek-reasoner is not found. The cost will be 0. In your config_list, add field {"price" : [prompt_price_per_1k, completion_token_price_per_1k]} for customized pricing.
这个workflow问题一直retry,程序不能往下执行。尚未发现根因，如何解决？AG2 是否良好支持国内大模型Deepseek或者qwen
尝试支持多个llm和monitor，用Deepseek API做了实验
运行python3 examples/basic_usage.py, 前面load risks正常，Deepseek 也显示了API调用，但到run workflow时，遇到了问题:
[L2 Test] Calling run_workflow with max_round=10, timeout=300 2026-04-18 23:23:47,342 [INFO] AG2MAS: Starting workflow: "Help me resolve a complaint about an unauthorized...
[autogen.oai.client: 04-18 23:24:19] {744} WARNING - Model deepseek-reasoner is not found. The cost will be 0. In your config_list, add field {"price" : [prompt_price_per_1k, completion_token_price_per_1k]} for customized pricing.
这个workflow问题一直retry,程序不能往下执行。尚未发现根因，如何解决？AG2 是否良好支持国内大模型Deepseek或者qwen