interactive_feedback
Gather user feedback during AI workflows to adjust actions and confirm next steps. Supports quick selection options and conversation tracking for iterative task completion.
Instructions
Interactive feedback collection tool for LLM agents.
USAGE RULES:
During any process, task, or conversation, whether asking, replying, or completing phased tasks, you must call this tool to ask for feedback.
Unless receiving termination instructions, all steps must repeatedly call this tool.
Whenever user feedback is received, if the feedback content is not empty, you must call this tool again and adjust behavior based on the feedback content.
Only when the user explicitly indicates "end" or "no more interaction needed" can you stop calling this tool, and the process is considered complete.
You should summarize what have done, and provide project directory through args to let user know what you have done to provide feedback for next step.
CONVERSATION_ID USAGE:
IMPORTANT: Always provide a consistent conversation_id for the same chat window or conversation thread
If your IDE or client provides a conversation/thread/chat ID, use it as the conversation_id
Using the same conversation_id will replace the previous feedback session for that conversation
This allows multiple AI conversations to have independent feedback sessions without interfering with each other
Examples:
Cursor: Use the conversation UUID from the chat window
VS Code: Use the conversation/thread identifier
If no ID is available: Generate a UUID once per conversation and reuse it
If conversation_id is not provided, a new one will be auto-generated (may cause session conflicts in multi-conversation scenarios)
QUICK OPTIONS FEATURE: You can provide quick selection options in the summary using XML format. Users can click checkboxes to select options.
Basic Format:
Format with Attributes (optional title, key, description):
Multiple option groups are supported:
User selections will be returned in the feedback with group numbers like "[1] A. First option".
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| summary | No | AI 工作完成的摘要說明 | 我已完成了您請求的任務。 |
| timeout | No | 等待用戶回饋的超時時間（秒） | |
| conversation_id | No | 會話唯一標識符，用於區分不同的對話窗口。為同一個對話使用一致的 ID 以保持會話連續性。如果未提供，將自動生成新 ID。 | |
| project_directory | No | 專案目錄路徑 | . |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |