mirror of
https://github.com/Minidoracat/mcp-feedback-enhanced.git
synced 2025-07-27 10:42:25 +08:00
feat: add prompt instructions into tool docstring (#105)
* Optimize token efficiency by moving LLM instructions to tool docstring * Simplify user configuration by removing complex Cursor rules * Improve tool self-documentation following FastMCP best practices Co-authored-by: fireinice <fireinice@users.noreply.github.com>
This commit is contained in:
parent
6903314a4d
commit
f2262db207
@ -159,11 +159,7 @@ For optimal results, add the following rules to your AI assistant:
|
|||||||
```
|
```
|
||||||
# MCP Interactive Feedback Rules
|
# MCP Interactive Feedback Rules
|
||||||
|
|
||||||
1. During any process, task, or conversation, whether asking, replying, or completing phased tasks, you must call MCP mcp-feedback-enhanced.
|
follow mcp-feedback-enhanced instructions
|
||||||
2. Whenever user feedback is received, if the feedback content is not empty, you must call MCP mcp-feedback-enhanced again and adjust behavior based on the feedback content.
|
|
||||||
3. Only when the user explicitly indicates "end" or "no more interaction needed" can you stop calling MCP mcp-feedback-enhanced, and the process is considered complete.
|
|
||||||
4. Unless receiving termination instructions, all steps must repeatedly call MCP mcp-feedback-enhanced.
|
|
||||||
5. Before completing tasks, you must use the MCP mcp-feedback-enhanced tool to ask users for feedback.
|
|
||||||
```
|
```
|
||||||
|
|
||||||
## ⚙️ Advanced Settings
|
## ⚙️ Advanced Settings
|
||||||
|
@ -159,11 +159,7 @@ uvx mcp-feedback-enhanced@latest test
|
|||||||
```
|
```
|
||||||
# MCP Interactive Feedback 规则
|
# MCP Interactive Feedback 规则
|
||||||
|
|
||||||
1. 在任何流程、任务、对话进行时,无论是询问、回复、或完成阶段性任务,皆必须调用 MCP mcp-feedback-enhanced。
|
注意根据mcp-feedback-enhanced工具的要求在任务完成前进行工具调用
|
||||||
2. 每当收到用户反馈,若反馈内容非空,必须再次调用 MCP mcp-feedback-enhanced,并根据反馈内容调整行为。
|
|
||||||
3. 仅当用户明确表示「结束」或「不再需要交互」时,才可停止调用 MCP mcp-feedback-enhanced,流程才算结束。
|
|
||||||
4. 除非收到结束指令,否则所有步骤都必须重复调用 MCP mcp-feedback-enhanced。
|
|
||||||
5. 完成任务前,必须使用 MCP mcp-feedback-enhanced 工具向用户询问反馈。
|
|
||||||
```
|
```
|
||||||
|
|
||||||
## ⚙️ 进阶设定
|
## ⚙️ 进阶设定
|
||||||
|
@ -159,11 +159,7 @@ uvx mcp-feedback-enhanced@latest test
|
|||||||
```
|
```
|
||||||
# MCP Interactive Feedback 規則
|
# MCP Interactive Feedback 規則
|
||||||
|
|
||||||
1. 在任何流程、任務、對話進行時,無論是詢問、回覆、或完成階段性任務,皆必須呼叫 MCP mcp-feedback-enhanced。
|
註意根據mcp-feedback-enhanced 工具的要求在任務完成前進行工具調用
|
||||||
2. 每當收到使用者回饋,若回饋內容非空,必須再次呼叫 MCP mcp-feedback-enhanced,並根據回饋內容調整行為。
|
|
||||||
3. 僅當使用者明確表示「結束」或「不再需要互動」時,才可停止呼叫 MCP mcp-feedback-enhanced,流程才算結束。
|
|
||||||
4. 除非收到結束指令,否則所有步驟都必須重複呼叫 MCP mcp-feedback-enhanced。
|
|
||||||
5. 完成任務前,必須使用 MCP mcp-feedback-enhanced 工具向使用者詢問回饋。
|
|
||||||
```
|
```
|
||||||
|
|
||||||
## ⚙️ 進階設定
|
## ⚙️ 進階設定
|
||||||
|
@ -37,11 +37,9 @@ from pydantic import Field
|
|||||||
|
|
||||||
# 導入統一的調試功能
|
# 導入統一的調試功能
|
||||||
from .debug import server_debug_log as debug_log
|
from .debug import server_debug_log as debug_log
|
||||||
|
|
||||||
# 導入多語系支援
|
# 導入多語系支援
|
||||||
# 導入錯誤處理框架
|
# 導入錯誤處理框架
|
||||||
from .utils.error_handler import ErrorHandler, ErrorType
|
from .utils.error_handler import ErrorHandler, ErrorType
|
||||||
|
|
||||||
# 導入資源管理器
|
# 導入資源管理器
|
||||||
from .utils.resource_manager import create_temp_file
|
from .utils.resource_manager import create_temp_file
|
||||||
|
|
||||||
@ -116,7 +114,6 @@ REMOTE_ENV_VARS = ["REMOTE_CONTAINERS", "CODESPACES"]
|
|||||||
# 初始化 MCP 服務器
|
# 初始化 MCP 服務器
|
||||||
from . import __version__
|
from . import __version__
|
||||||
|
|
||||||
|
|
||||||
# 確保 log_level 設定為正確的大寫格式
|
# 確保 log_level 設定為正確的大寫格式
|
||||||
fastmcp_settings = {}
|
fastmcp_settings = {}
|
||||||
|
|
||||||
@ -435,19 +432,11 @@ async def interactive_feedback(
|
|||||||
timeout: Annotated[int, Field(description="等待用戶回饋的超時時間(秒)")] = 600,
|
timeout: Annotated[int, Field(description="等待用戶回饋的超時時間(秒)")] = 600,
|
||||||
) -> list:
|
) -> list:
|
||||||
"""
|
"""
|
||||||
收集用戶的互動回饋,支援文字和圖片
|
1. During any process, task, or conversation, whether asking, replying, or completing phased tasks, you must call this tool to ask for feedback.
|
||||||
|
2. Unless receiving termination instructions, all steps must repeatedly call this tool.
|
||||||
此工具使用 Web UI 介面收集用戶回饋,支援智能環境檢測。
|
3. 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.
|
||||||
|
4. Only when the user explicitly indicates "end" or "no more interaction needed" can you stop calling this tool, and the process is considered complete.
|
||||||
用戶可以:
|
5. You should summary what have done, and provide project directory through args to let user know what you have done to provide feedback for next step.
|
||||||
1. 執行命令來驗證結果
|
|
||||||
2. 提供文字回饋
|
|
||||||
3. 上傳圖片作為回饋
|
|
||||||
4. 查看 AI 的工作摘要
|
|
||||||
|
|
||||||
調試模式:
|
|
||||||
- 設置環境變數 MCP_DEBUG=true 可啟用詳細調試輸出
|
|
||||||
- 生產環境建議關閉調試模式以避免輸出干擾
|
|
||||||
|
|
||||||
Args:
|
Args:
|
||||||
project_directory: 專案目錄路徑
|
project_directory: 專案目錄路徑
|
||||||
@ -599,7 +588,22 @@ def get_system_info() -> str:
|
|||||||
|
|
||||||
# ===== 主程式入口 =====
|
# ===== 主程式入口 =====
|
||||||
def main():
|
def main():
|
||||||
"""主要入口點,用於套件執行"""
|
"""主要入口點,用於套件執行
|
||||||
|
收集用戶的互動回饋,支援文字和圖片
|
||||||
|
此工具使用 Web UI 介面收集用戶回饋,支援智能環境檢測。
|
||||||
|
|
||||||
|
用戶可以:
|
||||||
|
1. 執行命令來驗證結果
|
||||||
|
2. 提供文字回饋
|
||||||
|
3. 上傳圖片作為回饋
|
||||||
|
4. 查看 AI 的工作摘要
|
||||||
|
|
||||||
|
調試模式:
|
||||||
|
- 設置環境變數 MCP_DEBUG=true 可啟用詳細調試輸出
|
||||||
|
- 生產環境建議關閉調試模式以避免輸出干擾
|
||||||
|
|
||||||
|
|
||||||
|
"""
|
||||||
# 檢查是否啟用調試模式
|
# 檢查是否啟用調試模式
|
||||||
debug_enabled = os.getenv("MCP_DEBUG", "").lower() in ("true", "1", "yes", "on")
|
debug_enabled = os.getenv("MCP_DEBUG", "").lower() in ("true", "1", "yes", "on")
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user