aiecs 1.5.1__py3-none-any.whl

aiecs/scripts/dependance_patch/fix_weasel/patch_weasel_library.sh

@@ -0,0 +1,188 @@
+#!/bin/bash
+
+# Comprehensive script to fix weasel library duplicate validator function error
+# This script provides multiple approaches to patch the issue
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_DIR="$(dirname "$SCRIPT_DIR")"
+
+echo "🔧 Weasel Library Patcher"
+echo "========================="
+echo "Project directory: $PROJECT_DIR"
+echo ""
+
+# Function to check if we're in the right directory
+check_project_structure() {
+    if [ ! -f "$PROJECT_DIR/pyproject.toml" ]; then
+        echo "❌ Error: pyproject.toml not found. Please run this script from the python-middleware directory"
+        exit 1
+    fi
+}
+
+# Function to get poetry virtual environment path
+get_venv_path() {
+    cd "$PROJECT_DIR"
+    local venv_path
+    venv_path=$(poetry env info --path 2>/dev/null || echo "")
+
+    if [ -z "$venv_path" ]; then
+        echo "❌ Error: Could not find poetry virtual environment"
+        echo "Please make sure poetry is installed and the virtual environment is created"
+        echo "Try running: poetry install"
+        exit 1
+    fi
+
+    echo "$venv_path"
+}
+
+# Function to apply the patch
+apply_patch() {
+    local venv_path="$1"
+    local schemas_file="$venv_path/lib/python3.10/site-packages/weasel/schemas.py"
+
+    echo "📁 Target file: $schemas_file"
+
+    if [ ! -f "$schemas_file" ]; then
+        echo "❌ Error: weasel schemas.py file not found"
+        echo "The weasel package might not be installed or in a different location"
+        exit 1
+    fi
+
+    # Create backup
+    local backup_file="${schemas_file}.backup.$(date +%Y%m%d_%H%M%S)"
+    cp "$schemas_file" "$backup_file"
+    echo "💾 Backup created: $backup_file"
+
+    # Check if already patched
+    if grep -q "allow_reuse=True" "$schemas_file"; then
+        echo "✅ File already contains allow_reuse=True - may already be patched"
+        echo "Checking if the specific issue is resolved..."
+    fi
+
+    # Show current problematic content
+    echo ""
+    echo "📖 Current content around the problematic area:"
+    echo "------------------------------------------------"
+    sed -n '85,95p' "$schemas_file" | nl -ba -v85
+    echo "------------------------------------------------"
+    echo ""
+
+    # Apply the patch using Python for more precise control
+    python3 << EOF
+import re
+import sys
+
+schemas_file = "$schemas_file"
+
+try:
+    with open(schemas_file, 'r') as f:
+        content = f.read()
+
+    # Pattern to find @validator and @root_validator decorators that need allow_reuse=True
+    # Look for the specific problematic validator
+    pattern = r'(@(?:root_)?validator\([^)]*\))\s*\n(\s*def\s+check_legacy_keys)'
+
+    def fix_validator(match):
+        decorator = match.group(1)
+        func_def = match.group(2)
+
+        # Add allow_reuse=True if not present
+        if 'allow_reuse' not in decorator:
+            # Remove the closing parenthesis and add allow_reuse=True
+            fixed_decorator = decorator[:-1] + ', allow_reuse=True)'
+            return fixed_decorator + '\n' + func_def
+        return match.group(0)
+
+    # Apply the fix
+    fixed_content = re.sub(pattern, fix_validator, content)
+
+    # Also fix any other @validator or @root_validator decorators that might have the same issue
+    general_pattern = r'(@(?:root_)?validator\([^)]*)\)(?=\s*\n\s*def)'
+
+    def fix_general_validator(match):
+        decorator = match.group(1)
+        if 'allow_reuse' not in decorator:
+            return decorator + ', allow_reuse=True)'
+        return match.group(0)
+
+    fixed_content = re.sub(general_pattern, fix_general_validator, fixed_content)
+
+    # Write back the fixed content
+    with open(schemas_file, 'w') as f:
+        f.write(fixed_content)
+
+    print("✅ Patch applied successfully")
+
+except Exception as e:
+    print(f"❌ Error applying patch: {e}")
+    sys.exit(1)
+EOF
+
+    # Show the patched content
+    echo ""
+    echo "📖 Patched content:"
+    echo "-------------------"
+    sed -n '85,95p' "$schemas_file" | nl -ba -v85
+    echo "-------------------"
+    echo ""
+
+    # Verify the patch
+    if grep -q "allow_reuse=True" "$schemas_file"; then
+        echo "✅ Verification: allow_reuse=True found in the file"
+    else
+        echo "⚠️  Warning: allow_reuse=True not found after patching"
+    fi
+
+    echo "💾 Original file backed up to: $backup_file"
+}
+
+# Function to test the fix
+test_fix() {
+    echo ""
+    echo "🧪 Testing the fix..."
+    cd "$PROJECT_DIR"
+
+    # Try to import the problematic module
+    if python3 -c "
+import sys
+sys.path.insert(0, '.')
+try:
+    from aiecs.tools.task_tools.research_tool import *
+    print('✅ Import successful - fix appears to work!')
+except Exception as e:
+    print(f'❌ Import still fails: {e}')
+    sys.exit(1)
+" 2>/dev/null; then
+        echo "✅ Fix verification successful!"
+    else
+        echo "⚠️  Fix verification failed - you may need to restart your Python environment"
+    fi
+}
+
+# Main execution
+main() {
+    echo "Starting patch process..."
+
+    check_project_structure
+
+    local venv_path
+    venv_path=$(get_venv_path)
+    echo "📍 Virtual environment: $venv_path"
+
+    apply_patch "$venv_path"
+
+    test_fix
+
+    echo ""
+    echo "🎉 Weasel library patch completed!"
+    echo ""
+    echo "Next steps:"
+    echo "1. Try running your tests again"
+    echo "2. If the issue persists, you may need to restart your Python environment"
+    echo "3. To revert changes, restore from the backup file shown above"
+}
+
+# Run the main function
+main "$@"

aiecs/scripts/dependance_patch/fix_weasel/run_weasel_patch.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+
+# Script to run the weasel library patch using poetry
+# This ensures we're working within the correct virtual environment
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_DIR="$(dirname "$SCRIPT_DIR")"
+
+echo "🔧 Running Weasel Library Patch via Poetry"
+echo "=========================================="
+echo "Project directory: $PROJECT_DIR"
+echo ""
+
+# Change to project directory
+cd "$PROJECT_DIR"
+
+# Check if pyproject.toml exists
+if [ ! -f "pyproject.toml" ]; then
+    echo "❌ Error: pyproject.toml not found. Please run this script from the python-middleware directory"
+    exit 1
+fi
+
+# Check if poetry is available
+if ! command -v poetry &> /dev/null; then
+    echo "❌ Error: Poetry is not installed or not in PATH"
+    echo "Please install poetry first: https://python-poetry.org/docs/#installation"
+    exit 1
+fi
+
+# Run the Python patch script using poetry
+echo "🚀 Running patch script with poetry..."
+poetry run python3 scripts/fix_weasel_validator.py
+
+echo ""
+echo "🎉 Patch execution completed!"
+echo ""
+echo "Next steps:"
+echo "1. Try running your tests again with: poetry run pytest"
+echo "2. If the issue persists, you may need to restart your development environment"

aiecs/scripts/tools_develop/README.md

@@ -0,0 +1,449 @@
+# 工具开发辅助脚本
+
+本目录包含用于 AIECS 工具开发和维护的验证脚本，帮助开发者确保工具质量和 Schema 自动生成的有效性。
+
+## 📋 脚本列表
+
+### 1. 工具验证器 (`verify_tools.py`)
+
+快速验证和展示 aiecs.tools 注册的所有工具和功能，帮助开发者了解工具注册情况。
+
+**用途**：
+- 列出所有注册的工具及其状态
+- 显示每个工具的描述和功能方法
+- 提供工具使用示例
+- 分析工具注册表信息
+- 展示工具继承关系和模块分布
+
+**命令**：
+```bash
+# 从项目根目录运行（推荐）
+python -m aiecs.scripts.tools_develop.verify_tools
+
+# 直接运行脚本
+python aiecs/scripts/tools_develop/verify_tools.py
+```
+
+**输出示例**：
+```
+================================================================================
+AIECS Tools 注册工具验证
+================================================================================
+
+发现 26 个注册的工具
+
+================================================================================
+📁 任务工具 (10 个)
+================================================================================
+
+[1] chart
+    描述: Chart and visualization operations
+    状态: loaded
+
+[2] pandas
+    描述: Data analysis and manipulation
+    状态: loaded
+
+... (更多工具)
+
+================================================================================
+📁 文档工具 (7 个)
+================================================================================
+
+[11] document_parser
+    描述: Document parsing and content extraction
+    状态: loaded
+
+... (更多工具)
+
+================================================================================
+📁 数据统计工具 (9 个)
+================================================================================
+
+[18] data_loader
+    描述: Universal data loading from multiple formats
+    状态: loaded
+
+... (更多工具)
+
+================================================================================
+✅ 工具列表显示完成! 共 26 个工具
+================================================================================
+
+================================================================================
+🎮 交互模式
+================================================================================
+
+提示:
+  - 输入工具序号 (1-26) 查看详细功能
+  - 输入工具名称查看详细功能
+  - 输入 'list' 重新显示工具列表
+  - 输入 'q' 或 'quit' 退出
+
+👉 请选择工具 > pandas
+
+================================================================================
+🔍 加载工具: pandas
+================================================================================
+
+⏳ 正在加载...
+    已触发 task_tools.pandas_tool 模块加载
+
+✅ 工具已成功加载
+    类名: PandasTool
+    模块: aiecs.tools.task_tools.pandas_tool
+
+📋 原子功能列表 (共 41 个方法):
+--------------------------------------------------------------------------------
+
+  [1] apply(records: List, func: str, columns: List, axis: int = 0) -> List
+      Apply a function to specified columns or rows.
+
+  [2] astype(records: List, dtypes: Dict) -> List
+      Convert column types in DataFrame.
+
+  [3] concat(records_list: List, axis: int = 0) -> List
+      Concatenate multiple DataFrames.
+
+  ... (更多方法)
+
+  [41] write_file(records: List, file_path: str, file_type: str = 'csv') -> Dict
+      Write DataFrame to a file.
+
+--------------------------------------------------------------------------------
+```
+
+### 2. 类型注解检查器 (`check_type_annotations.py`)
+
+检查工具方法的类型注解完整性，确保所有方法都有完整的类型注解（参数类型 + 返回类型）。
+
+**用途**：
+- 验证新开发的工具是否有完整的类型注解
+- 检查现有工具的类型注解覆盖率
+- 为自动 Schema 生成提供基础保障
+
+**命令**：
+```bash
+# 检查所有工具
+aiecs-tools-check-annotations
+
+# 检查特定工具
+aiecs-tools-check-annotations pandas
+
+# 检查多个工具
+aiecs-tools-check-annotations pandas chart image
+
+# 显示详细的改进建议
+aiecs-tools-check-annotations pandas --verbose
+```
+
+**输出示例**：
+```
+====================================================================================================
+工具类型注解检查器
+====================================================================================================
+
+✅ pandas: 38/38 方法有完整类型注解 (100.0%)
+
+⚠️ my_tool: 5/10 方法有完整类型注解 (50.0%)
+
+  需要改进的方法:
+    ✗ process_data: 无类型注解
+    ⚠ filter_records: 部分类型注解
+      → 为参数 'condition' 添加类型注解
+      → 添加返回类型注解
+
+====================================================================================================
+总体统计: 43/48 方法有完整类型注解 (89.6%)
+====================================================================================================
+```
+
+### 3. Schema 质量验证器 (`validate_tool_schemas.py`)
+
+验证自动生成的 Schema 质量，识别需要改进的文档字符串。
+
+**用途**：
+- 验证 Schema 自动生成是否成功
+- 评估生成的 Schema 描述质量
+- 指导开发者改进文档字符串
+
+**命令**：
+```bash
+# 验证所有工具
+aiecs-tools-validate-schemas
+
+# 验证特定工具
+aiecs-tools-validate-schemas pandas
+
+# 显示详细的改进建议
+aiecs-tools-validate-schemas pandas --verbose
+
+# 显示示例 Schema
+aiecs-tools-validate-schemas pandas --show-examples
+```
+
+**输出示例**：
+```
+====================================================================================================
+工具 Schema 质量验证器
+====================================================================================================
+
+✅ chart
+  方法数: 3
+  成功生成 Schema: 3 (100.0%)
+  描述质量: 100.0%
+  综合评分: 100.0% (A (优秀))
+
+❌ pandas
+  方法数: 38
+  成功生成 Schema: 38 (100.0%)
+  描述质量: 0.0%
+  综合评分: 66.7% (D (需改进))
+
+  需要改进的方法 (38 个):
+
+    filter:
+      💡 在文档字符串的 Args 部分为参数 'records' 添加描述
+      💡 在文档字符串的 Args 部分为参数 'condition' 添加描述
+
+====================================================================================================
+总体统计:
+  方法数: 41
+  Schema 生成率: 41/41 (100.0%)
+  描述质量: 7.3%
+====================================================================================================
+```
+
+## 🚀 工具开发工作流
+
+### 新工具开发流程
+
+1. **编写工具类**
+   ```python
+   from aiecs.tools.base_tool import BaseTool
+   from typing import List, Dict
+   
+   class MyTool(BaseTool):
+       """My custom tool"""
+       
+       def process(self, data: List[Dict], threshold: float = 0.5) -> Dict:
+           """
+           Process data with threshold.
+           
+           Args:
+               data: Input data to process
+               threshold: Processing threshold (0.0 to 1.0)
+           
+           Returns:
+               Processing results
+           """
+           pass
+   ```
+
+2. **检查类型注解**
+   ```bash
+   aiecs-tools-check-annotations my_tool --verbose
+   ```
+   
+   确保所有方法都有 ✅ 标记。
+
+3. **验证 Schema 质量**
+   ```bash
+   aiecs-tools-validate-schemas my_tool --show-examples
+   ```
+   
+   目标：综合评分 ≥ 80% (B 良好)
+
+4. **改进文档字符串**
+   
+   根据验证器的建议，改进文档字符串：
+   ```python
+   def process(self, data: List[Dict], threshold: float = 0.5) -> Dict:
+       """
+       Process data with threshold filtering.
+       
+       Args:
+           data: List of data records to process (each record is a dict)
+           threshold: Minimum confidence threshold for filtering (0.0 to 1.0, default: 0.5)
+       
+       Returns:
+           Dictionary containing processed results and statistics
+       """
+       pass
+   ```
+
+5. **重新验证**
+   ```bash
+   aiecs-tools-validate-schemas my_tool
+   ```
+
+### 现有工具维护流程
+
+1. **定期检查**
+   ```bash
+   # 每次修改工具后运行
+   aiecs-tools-check-annotations my_tool
+   aiecs-tools-validate-schemas my_tool
+   ```
+
+2. **批量检查**
+   ```bash
+   # 检查所有工具
+   aiecs-tools-check-annotations
+   aiecs-tools-validate-schemas
+   ```
+
+3. **持续改进**
+   - 优先改进评分 < 80% 的工具
+   - 为通用描述（如 "Parameter xxx"）添加有意义的说明
+
+## 📊 质量标准
+
+### 类型注解标准
+
+- ✅ **优秀 (100%)**：所有方法都有完整类型注解
+- ⚠️ **良好 (80-99%)**：大部分方法有完整类型注解
+- ❌ **需改进 (<80%)**：缺少大量类型注解
+
+### Schema 质量标准
+
+- ✅ **A (优秀) ≥90%**：Schema 生成成功，描述质量高
+- ⚠️ **B (良好) 80-89%**：Schema 生成成功，描述质量中等
+- ⚠️ **C (中等) 70-79%**：Schema 生成成功，描述质量较低
+- ❌ **D (需改进) <70%**：Schema 生成失败或描述质量差
+
+## 💡 最佳实践
+
+### 1. 完整的类型注解
+
+```python
+# ✅ 好的示例
+def filter(self, records: List[Dict], condition: str) -> List[Dict]:
+    pass
+
+# ❌ 不好的示例
+def filter(self, records, condition):  # 缺少类型注解
+    pass
+
+def filter(self, records: List[Dict], condition):  # 部分缺失
+    pass
+```
+
+### 2. 详细的文档字符串
+
+使用 Google 或 NumPy 风格：
+
+```python
+# ✅ Google 风格（推荐）
+def filter(self, records: List[Dict], condition: str) -> List[Dict]:
+    """
+    Filter DataFrame based on a condition.
+    
+    Args:
+        records: List of records to filter (each record is a dict)
+        condition: Filter condition using pandas query syntax (e.g., 'age > 30')
+    
+    Returns:
+        Filtered list of records
+    """
+    pass
+
+# ✅ NumPy 风格
+def filter(self, records: List[Dict], condition: str) -> List[Dict]:
+    """
+    Filter DataFrame based on a condition.
+    
+    Parameters
+    ----------
+    records : List[Dict]
+        List of records to filter (each record is a dict)
+    condition : str
+        Filter condition using pandas query syntax (e.g., 'age > 30')
+    
+    Returns
+    -------
+    List[Dict]
+        Filtered list of records
+    """
+    pass
+```
+
+### 3. 有意义的描述
+
+```python
+# ❌ 不好的描述
+"""
+Args:
+    records: Parameter records
+    condition: Parameter condition
+"""
+
+# ✅ 好的描述
+"""
+Args:
+    records: List of data records to filter (each record contains fields like 'name', 'age', etc.)
+    condition: Filter condition using pandas query syntax (e.g., 'age > 30 and status == "active"')
+"""
+```
+
+### 4. 处理复杂类型
+
+```python
+from typing import List, Dict, Optional, Union
+import pandas as pd
+
+# ✅ 使用标准类型
+def process(self, data: List[Dict]) -> Dict:
+    pass
+
+# ✅ pandas 类型会自动映射为 Any
+def process(self, df: pd.DataFrame) -> pd.DataFrame:
+    pass
+
+# ✅ 可选参数
+def process(self, data: List[Dict], config: Optional[Dict] = None) -> Dict:
+    pass
+```
+
+## 🔧 故障排查
+
+### 问题：类型注解检查失败
+
+**原因**：缺少类型注解或使用了不支持的类型
+
+**解决**：
+1. 为所有参数添加类型注解
+2. 添加返回类型注解
+3. 使用标准类型（List, Dict, str, int, float, bool 等）
+
+### 问题：Schema 生成失败
+
+**原因**：
+- 方法没有参数（除了 self）→ 这是正常的，无需 Schema
+- 类型注解不完整 → 运行类型注解检查器
+- 使用了不支持的类型 → 会自动映射为 Any
+
+### 问题：描述质量低
+
+**原因**：文档字符串缺少 Args 部分或描述不详细
+
+**解决**：
+1. 添加文档字符串的 Args 部分
+2. 为每个参数添加详细描述
+3. 使用 Google 或 NumPy 风格
+
+## 📚 相关文档
+
+- [Schema Generator 技术文档](../../../docs/TOOLS/TOOLS_SCHEMA_GENERATOR.md)
+- [LangChain Adapter 技术文档](../../../docs/TOOLS/TOOLS_LANGCHAIN_ADAPTER.md)
+- [BaseTool 开发指南](../../../docs/TOOLS/TOOLS_BASE_TOOL.md)
+
+## 🤝 贡献
+
+如果你发现这些工具有改进空间，欢迎提交 PR 或 Issue！
+
+---
+
+**维护者**: AIECS Tools Team  
+**最后更新**: 2025-10-02
+