Error when ask the second question after the first function call with ZhiPu Model

Self Checks

[X] This is only for bug report, if you would like to ask a question, please head to Discussions.
[X] I have searched for existing issues search for existing issues, including closed ones.
[X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
[X] Please do not modify this template :) and fill in all the required fields.

Dify version

0.6.11

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

reproduce environment:

select chat model to ZhiPu GLM-4 model
Create a agent app with a tool published by a workflow
Ask a question to the agent and it MUST invoke a tool for the question and the answer is feedbacked by the agent.
In the save conversation, then you ask the second question, the UI will pop an error message like 'Got unknown type role=<PromptMessageRole.TOOL: 'tool'> content='...' name='getCompanyInfo' tool_call_id='47e36eb3-a484-4eb9-955c-3122655d9143'>

✔️ Expected Behavior

no any error message poping up when ask question with Zhipu model

❌ Actual Behavior

the web UI pop up error message "Got unknown type role=<PromptMessageRole.TOOL: 'tool'> content='{"company_info": "[]", "register_info": "{\"company_info\": \"[]\"}"}' name='getCompanyInfo' tool_call_id='47e36eb3-a484-4eb9-955c-3122655d9143"

Hi @vccler! I'm here to help you with your bug report. I can assist with bug fixes, answer questions, and support you as you wait for a human maintainer. Let's tackle this together!

To resolve the error message that pops up when asking a second question with the ZhiPu Model in Dify version 0.6.11, you can try the following steps:

Check for Rate Limits: Ensure that you have not reached the rate limit for the ZhiPu Model. If you have, you may need to wait before making another request.
Clear Cache: If you encounter an "Invalid token" error, try clearing your browser's cache (Cookies, Session Storage, and Local Storage). If you are using a mobile app, clear the app's cache and try again.
Update Model Parameters: Ensure that the parameters you are using for the ZhiPu Model are within the acceptable range for that model. Different models have different parameter ranges, and using out-of-range values can cause errors.
Check API Key Quota: Verify that your API key has not exceeded its quota. If it has, you may need to upgrade your plan or wait until the quota resets.
Reduce Max Tokens: If the error is related to the length of the query or prompt, try reducing the "max_tokens" value in the parameter settings.
Ensure Latest Version: Make sure that both the frontend and backend versions of Dify are up to date and consistent with each other.

Additionally, the ZhiPu Model SDK defines several specific errors that might help you diagnose the issue:

APIAuthenticationError: Indicates an authentication issue, possibly due to an invalid API key.
APIReachLimitError: Indicates that the API rate limit has been reached.
APIInternalError: Indicates an internal server error.
APIServerFlowExceedError: Indicates that the server flow has been exceeded.
APIResponseValidationError: Indicates that the data returned by the API is invalid for the expected schema.
APITimeoutError: Indicates that the request has timed out.

Here is a relevant excerpt from the document:

### 15. 用户在使用应用时遇到报错“Invalid token”，该怎么解决？

如果遇到报错为 “Invalid token”，你可尝试如下两种解决办法：

* 浏览器清除缓存（Cookies、Session Storage 和 Local Storage），如果是手机里使用则清除对应 APP 的缓存，重新访问；
* 二是重新生成一个 App 网址，重新网址进入即可.

If these steps do not resolve the issue, there may be additional context-specific factors at play, and further investigation would be required ^[1]^[2].

To continue talking to Dosu, mention @dosu.

langgenius / dify