在roocode 中使用会报错Roo Code uses complex prompts and iterative task

[djhdj1]

在roocode 中使用会报错Roo Code uses complex prompts and iterative task execution that may be challenging for less capable models. For best results, it's recommended to use Claude 3.7 Sonnet for its advanced agentic coding capabilities。
求问大佬如何解决，以下是日志

(This is an automated message, so do not respond to it conversationally.)
<environment_details>
# VSCode Visible Files
# VSCode Open Tabs
# Current Time
5/22/2025, 10:52:20 AM (Asia/Shanghai, UTC+8:00)
# Current Context Size (Tokens)
�
12,919 (10%)
# Current Cost
$0.00
# Current Mode
<slug>code</slug>
<name>💻 Code</name>
<model>gemini-2.5-exp-advanced</model>
</environment_details>
Assistant: \<ask\_followup\_question\>
\<question\>Hello\! How can I help you today?\</question\>
\<follow\_up\>
\<suggest\>Help me write some code.\</suggest\>
\<suggest\>I have a question about a specific file.\</suggest\>
\<suggest\>I need to run a command.\</suggest\>
\<suggest\>Tell me about this project.\</suggest\>
\</follow\_up\>
\</ask\_followup\_question\>
Human: [ERROR] You did not use a tool in your previous response! Please retry with a tool use.
# Reminder: Instructions for Tool Use
Tool uses are formatted using XML-style tags. The tool name itself becomes the XML tag name. Each parameter is enclosed within its own set of tags. Here's the structure:
<actual_tool_name>
<parameter1_name>value1</parameter1_name>
<parameter2_name>value2</parameter2_name>
...
</actual_tool_name>
For example, to use the attempt_completion tool:
<attempt_completion>
<result>
I have completed the task...
�
>
</attempt_completion>
Always use the actual tool name as the XML tag name for proper parsing and execution.
�
# Next Steps
If you have completed the user's task, use the attempt_completion tool. 
If you require additional information from the user, use the ask_followup_question tool. 
Otherwise, if you have not completed the task and do not need additional information, then proceed with the next step of the task. 
(This is an automated message, so do not respond to it conversationally.)
<environment_details>
# VSCode Visible Files
# VSCode Open Tabs
# Current Time
5/22/2025, 10:52:31 AM (Asia/Shanghai, UTC+8:00)
# Current Context Size (Tokens)
�
13,369 (10%)
# Current Cost
$0.00
# Current Mode
<slug>code</slug>
<name>💻 Code</name>
<model>gemini-2.5-exp-advanced</model>
</environment_details>
Assistant: 
INFO:main:Temp files: []
INFO:main:Available models: ['unspecified', 'gemini-2.0-flash', 'gemini-2.0-flash-thinking', 'gemini-2.5-flash', 'gemini-2.5-pro', 'gemini-2.0-exp-advanced', 'gemini-2.5-exp-advanced']
INFO:main:Using model: Model.G_2_5_EXP_ADVANCED
INFO:main:Sending request to Gemini...
INFO:httpx:HTTP Request: POST https://gemini.google.com/_/BardChatUi/data/assistant.lamda.BardFrontendService/StreamGenerate "HTTP/2 200 OK"
INFO:main:Response: \<ask\_followup\_question\>
\<question\>Hello\! How can I help you today?\</question\>
\<follow\_up\>
\<suggest\>Help me write some code.\</suggest\>
\<suggest\>I have a question about a specific file.\</suggest\>
\<suggest\>I need to run a command.\</suggest\>
\<suggest\>Tell me about this project.\</suggest\>
\</follow\_up\>
\</ask\_followup\_question\>
INFO:     ****:*** - "POST /v1/chat/completions HTTP/1.1" 200 OK
INFO:httpx:HTTP Request: POST https://accounts.google.com/RotateCookies "HTTP/2 200 OK"

[oiflippy]

我也报这个了，是不是降智了