tool parameters parsing not compatible with the response of glm4 model in xinference provider when function tool call integerated

[cyflhn]

Self Checks

• This is only for bug report, if you would like to ask a question, please head to Discussions.
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

Dify version

0.10.0

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

1. add a glm4-chat-1m model in xinference model provider
2. create agent with function tool integrated.
3. start a chat in this agent

✔️ Expected Behavior

get a normal response from agent

❌ Actual Behavior

got an error of "tool_parameters should be a dict, but got a string"

[dosubot]

The error "tool_parameters should be a dict, but got a string" typically occurs when the tool_parameters are incorrectly handled or assigned as a string instead of a dictionary. In the Dify platform, the _generate_parameters method in the ToolNode class is responsible for generating a dictionary of parameters. If node_data.tool_parameters is set as a string, this error will occur because the code expects a dictionary format ^[1].

To resolve this issue, ensure that the tool_parameters are correctly formatted as a dictionary when integrating the glm4 model with the xinference provider. Check the part of your code where tool_parameters are being set or passed to ensure they are structured as a dictionary. This should help in aligning the parameter parsing with the expected format.

To continue talking to Dosu, mention @dosu.