aigroup-econ-mcp 0.4.1__py3-none-any.whl → 0.5.0__py3-none-any.whl

aigroup_econ_mcp/tools/tool_descriptions.py

@@ -0,0 +1,416 @@
+"""
+工具描述模块
+统一管理所有MCP工具的描述信息，便于维护和复用
+"""
+
+from typing import Dict, Any, List
+from pydantic import Field
+
+
+class ToolDescription:
+    """工具描述类"""
+    
+    def __init__(self, name: str, description: str, field_descriptions: Dict[str, str] = None):
+        self.name = name
+        self.description = description
+        self.field_descriptions = field_descriptions or {}
+    
+    def get_field_description(self, field_name: str, default: str = "") -> str:
+        """获取字段描述"""
+        return self.field_descriptions.get(field_name, default)
+
+
+# ============================================================================
+# 基础统计工具描述 (5个)
+# ============================================================================
+
+DESCRIPTIVE_STATISTICS = ToolDescription(
+    name="descriptive_statistics",
+    description="计算描述性统计量\n\n支持三种输入方式（按优先级）：\n1. file_path: 文件路径 (如 \"data.csv\")\n2. file_content: 文件内容字符串\n3. data: 直接传入数据字典",
+    field_descriptions={
+        "file_path": "CSV/JSON文件路径",
+        "file_content": "CSV/JSON文件内容",
+        "file_format": "文件格式(csv/json/auto)",
+        "data": "数据字典(直接数据输入)"
+    }
+)
+
+OLS_REGRESSION = ToolDescription(
+    name="ols_regression",
+    description="OLS回归分析\n\n支持文件输入或直接数据输入。文件格式示例：\nCSV: 最后一列为因变量，其余列为自变量",
+    field_descriptions={
+        "file_path": "CSV/JSON文件路径",
+        "file_content": "CSV/JSON文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量(直接输入)",
+        "x_data": "自变量(直接输入)",
+        "feature_names": "特征名称"
+    }
+)
+
+HYPOTHESIS_TESTING = ToolDescription(
+    name="hypothesis_testing",
+    description="假设检验 - 支持文件或直接数据输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "第一组数据",
+        "data2": "第二组数据",
+        "test_type": "检验类型(t_test/adf)"
+    }
+)
+
+TIME_SERIES_ANALYSIS = ToolDescription(
+    name="time_series_analysis",
+    description="时间序列分析 - 支持文件或直接数据输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "时间序列数据"
+    }
+)
+
+CORRELATION_ANALYSIS = ToolDescription(
+    name="correlation_analysis",
+    description="相关性分析 - 支持文件或直接数据输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "多变量数据",
+        "method": "相关系数类型"
+    }
+)
+
+
+# ============================================================================
+# 面板数据工具描述 (4个)
+# ============================================================================
+
+PANEL_FIXED_EFFECTS = ToolDescription(
+    name="panel_fixed_effects",
+    description="固定效应模型 - 支持文件输入",
+    field_descriptions={
+        "file_path": "CSV文件路径。CSV格式要求：必须包含实体ID列(列名含entity_id/id/entity/firm/company/country/region之一)和时间列(列名含time_period/time/date/year/month/period/quarter之一)",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "entity_ids": "实体ID列表",
+        "time_periods": "时间周期列表",
+        "feature_names": "特征名称",
+        "entity_effects": "是否包含实体效应",
+        "time_effects": "是否包含时间效应"
+    }
+)
+
+PANEL_RANDOM_EFFECTS = ToolDescription(
+    name="panel_random_effects",
+    description="随机效应模型 - 支持文件输入",
+    field_descriptions={
+        "file_path": "CSV文件路径。CSV格式要求：必须包含实体ID列(列名含entity_id/id/entity/firm/company/country/region之一)和时间列(列名含time_period/time/date/year/month/period/quarter之一)",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "entity_ids": "实体ID列表",
+        "time_periods": "时间周期列表",
+        "feature_names": "特征名称",
+        "entity_effects": "是否包含实体效应",
+        "time_effects": "是否包含时间效应"
+    }
+)
+
+PANEL_HAUSMAN_TEST = ToolDescription(
+    name="panel_hausman_test",
+    description="Hausman检验 - 支持文件输入",
+    field_descriptions={
+        "file_path": "CSV文件路径。CSV格式要求：必须包含实体ID列(列名含entity_id/id/entity/firm/company/country/region之一)和时间列(列名含time_period/time/date/year/month/period/quarter之一)",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "entity_ids": "实体ID列表",
+        "time_periods": "时间周期列表",
+        "feature_names": "特征名称"
+    }
+)
+
+PANEL_UNIT_ROOT_TEST = ToolDescription(
+    name="panel_unit_root_test",
+    description="面板单位根检验 - 支持文件输入",
+    field_descriptions={
+        "file_path": "CSV文件路径。CSV格式要求：必须包含实体ID列(列名含entity_id/id/entity/firm/company/country/region之一)和时间列(列名含time_period/time/date/year/month/period/quarter之一)。数据量要求：至少3个实体，每个实体至少5个时间点",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "时间序列数据",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "entity_ids": "实体ID列表",
+        "time_periods": "时间周期列表",
+        "feature_names": "特征名称",
+        "test_type": "检验类型"
+    }
+)
+
+
+# ============================================================================
+# 高级时间序列工具描述 (5个)
+# ============================================================================
+
+VAR_MODEL_ANALYSIS = ToolDescription(
+    name="var_model_analysis",
+    description="VAR模型分析 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "多变量时间序列数据",
+        "max_lags": "最大滞后阶数",
+        "ic": "信息准则类型"
+    }
+)
+
+VECM_MODEL_ANALYSIS = ToolDescription(
+    name="vecm_model_analysis",
+    description="VECM模型分析 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "多变量时间序列数据",
+        "coint_rank": "协整秩",
+        "deterministic": "确定性项类型",
+        "max_lags": "最大滞后阶数"
+    }
+)
+
+GARCH_MODEL_ANALYSIS = ToolDescription(
+    name="garch_model_analysis",
+    description="GARCH模型分析 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "时间序列数据",
+        "order": "GARCH模型阶数",
+        "dist": "误差分布类型"
+    }
+)
+
+STATE_SPACE_MODEL_ANALYSIS = ToolDescription(
+    name="state_space_model_analysis",
+    description="状态空间模型分析 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "时间序列数据",
+        "state_dim": "状态维度",
+        "observation_dim": "观测维度",
+        "trend": "是否包含趋势项",
+        "seasonal": "是否包含季节项",
+        "period": "季节周期"
+    }
+)
+
+VARIANCE_DECOMPOSITION_ANALYSIS = ToolDescription(
+    name="variance_decomposition_analysis",
+    description="方差分解分析 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "data": "多变量时间序列数据",
+        "periods": "分解期数",
+        "max_lags": "最大滞后阶数"
+    }
+)
+
+
+# ============================================================================
+# 机器学习工具描述 (6个)
+# ============================================================================
+
+RANDOM_FOREST_REGRESSION_ANALYSIS = ToolDescription(
+    name="random_forest_regression_analysis",
+    description="随机森林回归 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "feature_names": "特征名称",
+        "n_estimators": "树的数量",
+        "max_depth": "最大深度"
+    }
+)
+
+GRADIENT_BOOSTING_REGRESSION_ANALYSIS = ToolDescription(
+    name="gradient_boosting_regression_analysis",
+    description="梯度提升树回归 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "feature_names": "特征名称",
+        "n_estimators": "树的数量",
+        "learning_rate": "学习率",
+        "max_depth": "最大深度"
+    }
+)
+
+LASSO_REGRESSION_ANALYSIS = ToolDescription(
+    name="lasso_regression_analysis",
+    description="Lasso回归 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "feature_names": "特征名称",
+        "alpha": "正则化参数"
+    }
+)
+
+RIDGE_REGRESSION_ANALYSIS = ToolDescription(
+    name="ridge_regression_analysis",
+    description="Ridge回归 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "feature_names": "特征名称",
+        "alpha": "正则化参数"
+    }
+)
+
+CROSS_VALIDATION_ANALYSIS = ToolDescription(
+    name="cross_validation_analysis",
+    description="交叉验证 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "feature_names": "特征名称",
+        "model_type": "模型类型",
+        "cv_folds": "交叉验证折数",
+        "scoring": "评分指标"
+    }
+)
+
+FEATURE_IMPORTANCE_ANALYSIS_TOOL = ToolDescription(
+    name="feature_importance_analysis_tool",
+    description="特征重要性分析 - 支持文件输入",
+    field_descriptions={
+        "file_path": "文件路径",
+        "file_content": "文件内容",
+        "file_format": "文件格式",
+        "y_data": "因变量数据",
+        "x_data": "自变量数据",
+        "feature_names": "特征名称",
+        "method": "分析方法",
+        "top_k": "显示前K个重要特征"
+    }
+)
+
+
+# ============================================================================
+# 工具描述映射
+# ============================================================================
+
+TOOL_DESCRIPTIONS: Dict[str, ToolDescription] = {
+    # 基础统计工具
+    "descriptive_statistics": DESCRIPTIVE_STATISTICS,
+    "ols_regression": OLS_REGRESSION,
+    "hypothesis_testing": HYPOTHESIS_TESTING,
+    "time_series_analysis": TIME_SERIES_ANALYSIS,
+    "correlation_analysis": CORRELATION_ANALYSIS,
+    
+    # 面板数据工具
+    "panel_fixed_effects": PANEL_FIXED_EFFECTS,
+    "panel_random_effects": PANEL_RANDOM_EFFECTS,
+    "panel_hausman_test": PANEL_HAUSMAN_TEST,
+    "panel_unit_root_test": PANEL_UNIT_ROOT_TEST,
+    
+    # 高级时间序列工具
+    "var_model_analysis": VAR_MODEL_ANALYSIS,
+    "vecm_model_analysis": VECM_MODEL_ANALYSIS,
+    "garch_model_analysis": GARCH_MODEL_ANALYSIS,
+    "state_space_model_analysis": STATE_SPACE_MODEL_ANALYSIS,
+    "variance_decomposition_analysis": VARIANCE_DECOMPOSITION_ANALYSIS,
+    
+    # 机器学习工具
+    "random_forest_regression_analysis": RANDOM_FOREST_REGRESSION_ANALYSIS,
+    "gradient_boosting_regression_analysis": GRADIENT_BOOSTING_REGRESSION_ANALYSIS,
+    "lasso_regression_analysis": LASSO_REGRESSION_ANALYSIS,
+    "ridge_regression_analysis": RIDGE_REGRESSION_ANALYSIS,
+    "cross_validation_analysis": CROSS_VALIDATION_ANALYSIS,
+    "feature_importance_analysis_tool": FEATURE_IMPORTANCE_ANALYSIS_TOOL,
+}
+
+
+def get_tool_description(tool_name: str) -> ToolDescription:
+    """获取工具描述"""
+    if tool_name not in TOOL_DESCRIPTIONS:
+        raise ValueError(f"未知的工具名称: {tool_name}")
+    return TOOL_DESCRIPTIONS[tool_name]
+
+
+def get_all_tool_names() -> List[str]:
+    """获取所有工具名称"""
+    return list(TOOL_DESCRIPTIONS.keys())
+
+
+def get_field_description(tool_name: str, field_name: str, default: str = "") -> str:
+    """获取指定工具的字段描述"""
+    tool_desc = get_tool_description(tool_name)
+    return tool_desc.get_field_description(field_name, default)
+
+
+# 导出主要类和函数
+__all__ = [
+    "ToolDescription",
+    "TOOL_DESCRIPTIONS",
+    "get_tool_description",
+    "get_all_tool_names",
+    "get_field_description",
+    
+    # 基础统计工具
+    "DESCRIPTIVE_STATISTICS",
+    "OLS_REGRESSION",
+    "HYPOTHESIS_TESTING",
+    "TIME_SERIES_ANALYSIS",
+    "CORRELATION_ANALYSIS",
+    
+    # 面板数据工具
+    "PANEL_FIXED_EFFECTS",
+    "PANEL_RANDOM_EFFECTS",
+    "PANEL_HAUSMAN_TEST",
+    "PANEL_UNIT_ROOT_TEST",
+    
+    # 高级时间序列工具
+    "VAR_MODEL_ANALYSIS",
+    "VECM_MODEL_ANALYSIS",
+    "GARCH_MODEL_ANALYSIS",
+    "STATE_SPACE_MODEL_ANALYSIS",
+    "VARIANCE_DECOMPOSITION_ANALYSIS",
+    
+    # 机器学习工具
+    "RANDOM_FOREST_REGRESSION_ANALYSIS",
+    "GRADIENT_BOOSTING_REGRESSION_ANALYSIS",
+    "LASSO_REGRESSION_ANALYSIS",
+    "RIDGE_REGRESSION_ANALYSIS",
+    "CROSS_VALIDATION_ANALYSIS",
+    "FEATURE_IMPORTANCE_ANALYSIS_TOOL",
+]

aigroup_econ_mcp/tools/tool_registry.py

@@ -7,7 +7,7 @@ from typing import Dict, Any, Optional, List, Callable
 from pydantic import Field
 from typing import Annotated
 
-from .decorators import econometric_tool
+from .base import with_file_support_decorator as econometric_tool
 
 
 # 标准文件输入参数定义

{aigroup_econ_mcp-0.4.1.dist-info → aigroup_econ_mcp-0.5.0.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: aigroup-econ-mcp
-Version: 0.4.1
-Summary: 专业计量经济学MCP工具 - 让大模型直接进行数据分析
+Version: 0.5.0
+Summary: 专业计量经济学MCP工具 - 让大模型直接进行数据分析（重构版：工具描述模块化）
 Project-URL: Homepage, https://github.com/aigroup/aigroup-econ-mcp
 Project-URL: Repository, https://github.com/aigroup/aigroup-econ-mcp.git
 Project-URL: Issues, https://github.com/aigroup/aigroup-econ-mcp/issues

aigroup_econ_mcp-0.5.0.dist-info/RECORD

@@ -0,0 +1,30 @@
+aigroup_econ_mcp/__init__.py,sha256=PdZxvF3Zn-a5rHMnRTZ8JgtNcmmtJ0IKJc6Clz4QCL4,511
+aigroup_econ_mcp/cli.py,sha256=7yeNXWNwMdpUswAO4LsqAvb0EmCO3S6Bs6sl483uSXI,3363
+aigroup_econ_mcp/config.py,sha256=ab5X4-H8isIe2nma0c0AOqlyYgwhf5kfe9Zx5XRrzIo,18876
+aigroup_econ_mcp/server.py,sha256=Nqgu5bkAChdBH23Z8KmR14FO5ZDD7T6Hbug3m51ujHU,30899
+aigroup_econ_mcp/tools/__init__.py,sha256=WYrsZX3Emv09c8QikvtG2BouUFZCguYkQ7eDjuwarAg,396
+aigroup_econ_mcp/tools/base.py,sha256=Mv_mcKVTIg9A2dsqBBiU74_Ai2nb5sn2S3U4CNOxLKw,15218
+aigroup_econ_mcp/tools/cache.py,sha256=Urv2zuycp5dS7Qh-XQWEMrwszq9RZ-il8cz_-WniGgc,15311
+aigroup_econ_mcp/tools/data_loader.py,sha256=BVYvP04bQpsk3dZVFy-Y8EK3dnY4Pm0JSBYrthnHf74,5619
+aigroup_econ_mcp/tools/file_parser.py,sha256=0isfNaUOz1SjlNLwy4T5J8OidWP2tEdm2KZEtyE-KRg,28203
+aigroup_econ_mcp/tools/machine_learning.py,sha256=PpxrJVJw4eND95Wl0uGPEqUHXrIwTUSCd0QB1B4o4wY,1459
+aigroup_econ_mcp/tools/ml_ensemble.py,sha256=XOL0PzCsx9LY_pFbKCAxjYdGny-HqEhlZyov2r1l3ww,6475
+aigroup_econ_mcp/tools/ml_evaluation.py,sha256=hiwVW3-N0hnSAJfZW4luOCXt3sTh1W9Hj3CwZLRVaJk,8900
+aigroup_econ_mcp/tools/ml_models.py,sha256=hJEUgARxkqYgJqu6_7eRc1WnD2HcTGxtXf8Jre_XO1U,2137
+aigroup_econ_mcp/tools/ml_regularization.py,sha256=p81UXlb9ebyRuA_hSA4phmbFvORF-MaINMlYJkWKTbo,5070
+aigroup_econ_mcp/tools/monitoring.py,sha256=-hcw5nu5Q91FmDz39mRBsKavrTmEqXsKfGzlXr_5f0c,16708
+aigroup_econ_mcp/tools/optimized_example.py,sha256=tZVQ2jTzHY_zixTynm4Sq8gj5hz6eWg7MKqNwsxrPoQ,6784
+aigroup_econ_mcp/tools/panel_data.py,sha256=uzbgcDLXACfdi9KaMRmZdRTkhMtEyWb7p3vS3mUJ-co,19254
+aigroup_econ_mcp/tools/regression.py,sha256=uMGRGUQo4mU1sb8fwpP2FpkCqt_e9AtqEtUpInACtJo,6443
+aigroup_econ_mcp/tools/statistics.py,sha256=2cHgNSUXwPYPLxntVOEOL8yF-x92mrgjK-R8kkxDihg,4239
+aigroup_econ_mcp/tools/time_series.py,sha256=LNCO0bYXLPilQ2kSVXA3woNp8ERVq7n3jaoQhWgTCJQ,21763
+aigroup_econ_mcp/tools/timeout.py,sha256=vNnGsR0sXW1xvIbKCF-qPUU3QNDAn_MaQgSxbGxkfW4,8404
+aigroup_econ_mcp/tools/tool_descriptions.py,sha256=nTr373CgBPESbX9cbrRPMTTN-O8fc2d1PZ_XVIIqzBY,14710
+aigroup_econ_mcp/tools/tool_handlers.py,sha256=cqv7FU95b_kjEJcZSAIGuGjUqbcCCKT0MXrmflnnelo,15028
+aigroup_econ_mcp/tools/tool_registry.py,sha256=4SFpMnReZyGfEHCCDnojwHIUEpuQICS9M2u_9xuoUck,4413
+aigroup_econ_mcp/tools/validation.py,sha256=F7LHwog5xtFIMjD9D48kd8jAF5MsZb7wjdrgaOg8EKo,16657
+aigroup_econ_mcp-0.5.0.dist-info/METADATA,sha256=EoTmsI3tVHr48fYsWc0DkfaaXh5tcsrRBqT1tpZ-sSE,10839
+aigroup_econ_mcp-0.5.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+aigroup_econ_mcp-0.5.0.dist-info/entry_points.txt,sha256=j5ZJYOc4lAZV-X3XkAuGhzHtIRcJtZ6Gz8ZKPY_QTrM,62
+aigroup_econ_mcp-0.5.0.dist-info/licenses/LICENSE,sha256=DoyCJUWlDzKbqc5KRbFpsGYLwLh-XJRHKQDoITjb1yc,1083
+aigroup_econ_mcp-0.5.0.dist-info/RECORD,,

aigroup_econ_mcp/tools/decorators.py

@@ -1,178 +0,0 @@
-"""
-工具装饰器模块
-提供自动文件输入处理、错误处理等功能
-"""
-
-from typing import Callable, Optional, Dict, Any, List
-from functools import wraps
-from mcp.server.session import ServerSession
-from mcp.server.fastmcp import Context
-from mcp.types import CallToolResult, TextContent
-
-from .file_parser import FileParser
-
-
-def with_file_input(tool_type: str):
-    """
-    为工具函数添加文件输入支持的装饰器
-    
-    支持两种输入方式：
-    1. file_path: CSV/JSON文件路径
-    2. file_content: 文件内容字符串
-    
-    Args:
-        tool_type: 工具类型 ('single_var', 'multi_var_dict', 'regression', 'panel', 'time_series')
-    
-    使用示例:
-        @with_file_input('regression')
-        async def my_tool(ctx, y_data=None, x_data=None, file_path=None, file_content=None, file_format='auto', **kwargs):
-            # 如果提供了file_path或file_content，数据会被自动填充
-            pass
-    """
-    def decorator(func: Callable) -> Callable:
-        @wraps(func)
-        async def wrapper(*args, **kwargs):
-            # 提取上下文和文件参数
-            ctx = args[0] if args else kwargs.get('ctx')
-            file_path = kwargs.get('file_path')
-            file_content = kwargs.get('file_content')
-            file_format = kwargs.get('file_format', 'auto')
-            
-            # 优先处理file_path
-            if file_path:
-                try:
-                    await ctx.info(f"检测到文件路径输入: {file_path}")
-                    
-                    # 从文件路径解析
-                    parsed = FileParser.parse_file_path(file_path, file_format)
-                    
-                    await ctx.info(
-                        f"文件解析成功：{parsed['n_variables']}个变量，"
-                        f"{parsed['n_observations']}个观测"
-                    )
-                    
-                    # 转换为工具格式
-                    converted = FileParser.convert_to_tool_format(parsed, tool_type)
-                    
-                    # 更新kwargs
-                    kwargs.update(converted)
-                    
-                    await ctx.info(f"数据已转换为{tool_type}格式")
-                    
-                except Exception as e:
-                    await ctx.error(f"文件解析失败: {str(e)}")
-                    return CallToolResult(
-                        content=[TextContent(type="text", text=f"文件解析错误: {str(e)}")],
-                        isError=True
-                    )
-            
-            # 如果没有file_path但有file_content，处理文件内容
-            elif file_content:
-                try:
-                    await ctx.info("检测到文件内容输入，开始解析...")
-                    
-                    # 解析文件内容
-                    parsed = FileParser.parse_file_content(file_content, file_format)
-                    
-                    await ctx.info(
-                        f"文件解析成功：{parsed['n_variables']}个变量，"
-                        f"{parsed['n_observations']}个观测"
-                    )
-                    
-                    # 转换为工具格式
-                    converted = FileParser.convert_to_tool_format(parsed, tool_type)
-                    
-                    # 更新kwargs
-                    kwargs.update(converted)
-                    
-                    await ctx.info(f"数据已转换为{tool_type}格式")
-                    
-                except Exception as e:
-                    await ctx.error(f"文件解析失败: {str(e)}")
-                    return CallToolResult(
-                        content=[TextContent(type="text", text=f"文件解析错误: {str(e)}")],
-                        isError=True
-                    )
-            
-            # 调用原函数
-            return await func(*args, **kwargs)
-        
-        return wrapper
-    return decorator
-
-
-def with_error_handling(func: Callable) -> Callable:
-    """
-    为工具函数添加统一错误处理的装饰器
-    """
-    @wraps(func)
-    async def wrapper(*args, **kwargs):
-        ctx = args[0] if args else kwargs.get('ctx')
-        tool_name = func.__name__
-        
-        try:
-            return await func(*args, **kwargs)
-        except Exception as e:
-            await ctx.error(f"{tool_name}执行出错: {str(e)}")
-            return CallToolResult(
-                content=[TextContent(type="text", text=f"错误: {str(e)}")],
-                isError=True
-            )
-    
-    return wrapper
-
-
-def with_logging(func: Callable) -> Callable:
-    """
-    为工具函数添加日志记录的装饰器
-    """
-    @wraps(func)
-    async def wrapper(*args, **kwargs):
-        ctx = args[0] if args else kwargs.get('ctx')
-        tool_name = func.__name__
-        
-        await ctx.info(f"开始执行 {tool_name}")
-        result = await func(*args, **kwargs)
-        await ctx.info(f"{tool_name} 执行完成")
-        
-        return result
-    
-    return wrapper
-
-
-def econometric_tool(
-    tool_type: str,
-    with_file_support: bool = True,
-    with_error_handling: bool = True,
-    with_logging: bool = True
-):
-    """
-    组合装饰器：为计量经济学工具添加所有标准功能
-    
-    Args:
-        tool_type: 工具类型
-        with_file_support: 是否启用文件输入支持
-        with_error_handling: 是否启用错误处理
-        with_logging: 是否启用日志记录
-    
-    使用示例:
-        @econometric_tool('regression')
-        async def ols_regression(ctx, y_data=None, x_data=None, **kwargs):
-            # 只需要编写核心业务逻辑
-            pass
-    """
-    def decorator(func: Callable) -> Callable:
-        wrapped = func
-        
-        if with_error_handling:
-            wrapped = globals()['with_error_handling'](wrapped)
-        
-        if with_file_support:
-            wrapped = with_file_input(tool_type)(wrapped)
-        
-        if with_logging:
-            wrapped = globals()['with_logging'](wrapped)
-        
-        return wrapped
-    
-    return decorator