使用openai时报错，目前测试当带附件请求时，或需要工具交互时会报错

[dongboboa]

2025-03-26 18:18:45,407 - camel.agents.chat_agent - INFO - Model gpt-4o, index 0, processed these messages: [{'role': 'system', 'content': '===== RULES OF USER =====\nNever forget you are a user and I am a assistant. Never flip roles! You will always instruct me.\nWe share a common interest in collaborating to successfully complete a task.\nI must help you to complete the task.\nHere is the task: I read a paper about multiwavelength observations of fast radio bursts back in March 2021 on Arxiv, and it had a fascinating diagram of an X-ray time profile. There was a similar burst-1 diagram in another paper from one of the same authors about fast radio bursts back in July 2020, but I can't recall what the difference in seconds in the measured time span was. How many more seconds did one measure than the other? Just give the number.. Never forget our task!\nYou must instruct me based on my expertise and your needs to solve the task ONLY in the following two ways:\n\n1. Instruct with a necessary input:\nInstruction: <YOUR_INSTRUCTION>\nInput: <YOUR_INPUT>\n\n2. Instruct without any input:\nInstruction: <YOUR_INSTRUCTION>\nInput: None\n\nThe "Instruction" describes a task or question. The paired "Input" provides further context or information for the requested "Instruction".\n\nYou must give me one instruction at a time.\nI must write a response that appropriately solves the requested instruction.\nI must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons.\nYou should instruct me not ask me questions.\nNow you must start to instruct me using the two ways described above.\nDo not add anything else other than your instruction and the optional corresponding input!\nKeep giving me instructions and necessary inputs until you think the task is completed.\nWhen the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.\nNever say <CAMEL_TASK_DONE> unless my responses have solved your task.'}, {'role': 'user', 'content': '\n Now please give me instructions to solve over overall task step by step. If the task requires some specific knowledge, please instruct me to use tools to complete the task.\n '}, {'role': 'assistant', 'content': 'Instruction: Identify the exact paper you referenced about multiwavelength observations of fast radio bursts from March 2021 on Arxiv. \nInput: None '}, {'role': 'user', 'content': 'Solution: The paper you referenced is titled "[2103.07786] Multiwavelength observations of Fast Radio Bursts" and was published on Arxiv in March 2021. You can access it here.\n\nNext request.'}]
2025-03-26 18:18:47,859 - camel.models.model_manager - ERROR - Error processing with model: <camel.models.openai_model.OpenAIModel object at 0x31ff734c0>
2025-03-26 18:18:47,859 - camel.agents.chat_agent - ERROR - An error occurred while running model gpt-4o, index: 0
Traceback (most recent call last):
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/camel/agents/chat_agent.py", line 777, in _get_model_response
response = self.model_backend.run(
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/camel/models/model_manager.py", line 226, in run
raise exc
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/camel/models/model_manager.py", line 216, in run
response = self.current_model.run(messages, response_format, tools)
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/camel/models/base_model.py", line 50, in wrapped_run
return original_run(self, messages, *args, **kwargs)
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/camel/models/base_model.py", line 191, in run
return self._run(messages, response_format, tools)
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/camel/models/openai_model.py", line 161, in _run
return self._request_chat_completion(messages, tools)
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/camel/models/openai_model.py", line 204, in _request_chat_completion
return self._client.chat.completions.create(
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/openai/_utils/_utils.py", line 279, in wrapper
return func(*args, **kwargs)
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/openai/resources/chat/completions/completions.py", line 914, in create
return self._post(
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1242, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 919, in request
return self._request(
File "/Users/xxx/Desktop/owl/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1023, in _request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "Invalid parameter: messages with role 'tool' must be a response to a preceeding message with 'tool_calls'. (request id: 20250326181845501162718rf0gFvDi)", 'type': 'invalid_request_error', 'param': 'messages.[3].role', 'code': None}}
2025-03-26 18:18:47,864 - root - ERROR - 运行社会模拟时发生错误: Unable to process messages: the only provided model did not run successfully. Error: Error code: 400 - {'error': {'message': "Invalid parameter: messages with role 'tool' must be a response to a preceeding message with 'tool_calls'. (request id: 20250326181845501162718rf0gFvDi)", 'type': 'invalid_request_error', 'param': 'messages.[3].role', 'code': None}}

[dongboboa]

请求query：
I read a paper about multiwavelength observations of fast radio bursts back in March 2021 on Arxiv, and it had a fascinating diagram of an X-ray time profile. There was a similar burst-1 diagram in another paper from one of the same authors about fast radio bursts back in July 2020, but I can't recall what the difference in seconds in the measured time span was. How many more seconds did one measure than the other? Just give the number.

[Wendong-Fan]

hey @dongboboa , we did some fix and this issue should be resolved, could you help testing from your side and let us know if it's works now, thanks in advance!