fix: resolve import errors and restore auto-refresh functionality

- Remove unused duplicate_detection module imports and functionality
- Create missing qualified_names.py module with normalize_file_path and generate_qualified_name functions
- Fix all module import errors that were preventing server startup
- Restore auto-refresh mechanism - file watcher now properly detects new files
- Update response_formatter.py to remove legacy duplicate detection code
- All MCP tools now working: find_files, get_file_summary, search_code_advanced
- Comprehensive testing confirms all functionality restored

Author: johnhuang316

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "code-index-mcp"
-version = "2.0.0"
+version = "2.0.1"
 description = "Code indexing and analysis tools for LLMs using MCP"
 readme = "README.md"
 requires-python = ">=3.10"

src/code_index_mcp/indexing/__init__.py

@@ -6,31 +6,16 @@
 """
 
 # Import utility functions that are still used
-from .duplicate_detection import (
-    detect_duplicate_functions,
-    detect_duplicate_classes,
-    get_duplicate_statistics,
-    format_duplicate_report
-)
-
 from .qualified_names import (
     generate_qualified_name,
     normalize_file_path
 )
 
-# Simple models for backward compatibility
-from .simple_models import CodeIndex
-
 # SCIP builder is still used by the new architecture
 from .scip_builder import SCIPIndexBuilder
 
 __all__ = [
-    'detect_duplicate_functions',
-    'detect_duplicate_classes', 
-    'get_duplicate_statistics',
-    'format_duplicate_report',
     'generate_qualified_name',
     'normalize_file_path',
-    'SCIPIndexBuilder',
-    'CodeIndex'
+    'SCIPIndexBuilder'
 ]

src/code_index_mcp/indexing/qualified_names.py

@@ -0,0 +1,49 @@
+"""
+Qualified name generation utilities.
+"""
+import os
+from typing import Optional
+
+
+def normalize_file_path(file_path: str) -> str:
+    """
+    Normalize a file path to use forward slashes and relative paths.
+    
+    Args:
+        file_path: The file path to normalize
+        
+    Returns:
+        Normalized file path
+    """
+    # Convert to forward slashes and make relative
+    normalized = file_path.replace('\\', '/')
+    
+    # Remove leading slash if present
+    if normalized.startswith('/'):
+        normalized = normalized[1:]
+    
+    return normalized
+
+
+def generate_qualified_name(file_path: str, symbol_name: str, namespace: Optional[str] = None) -> str:
+    """
+    Generate a qualified name for a symbol.
+    
+    Args:
+        file_path: Path to the file containing the symbol
+        symbol_name: Name of the symbol
+        namespace: Optional namespace/module context
+        
+    Returns:
+        Qualified name for the symbol
+    """
+    normalized_path = normalize_file_path(file_path)
+    
+    # Remove file extension for module-like name
+    base_name = os.path.splitext(normalized_path)[0]
+    module_path = base_name.replace('/', '.')
+    
+    if namespace:
+        return f"{module_path}.{namespace}.{symbol_name}"
+    else:
+        return f"{module_path}.{symbol_name}"

src/code_index_mcp/utils/response_formatter.py

@@ -9,7 +9,6 @@
 from typing import Any, Dict, List, Optional, Union
 
 from ..indexing.qualified_names import generate_qualified_name
-from ..indexing.duplicate_detection import detect_duplicate_functions, detect_duplicate_classes
 
 
 class ResponseFormatter:
@@ -76,37 +75,8 @@ def _get_duplicate_names_from_index(index_cache: Optional[Dict[str, Any]] = None
         if not index_cache:
             return duplicates
 
-        try:
-            # Create a temporary CodeIndex-like object for duplicate detection
-            from ..indexing.simple_models import CodeIndex
-            
-            # Convert index_cache to CodeIndex format if needed
-            if isinstance(index_cache, dict) and 'lookups' in index_cache and index_cache['lookups'] is not None:
-                # Validate lookups structure before creating CodeIndex
-                lookups = index_cache.get('lookups', {})
-                if not isinstance(lookups, dict):
-                    return duplicates
-                
-                temp_index = CodeIndex(
-                    project_metadata=index_cache.get('project_metadata', {}),
-                    directory_tree=index_cache.get('directory_tree', {}),
-                    files=index_cache.get('files', []),
-                    lookups=lookups,
-                    reverse_lookups=index_cache.get('reverse_lookups', {}),
-                    special_files=index_cache.get('special_files', {}),
-                    index_metadata=index_cache.get('index_metadata', {})
-                )
-                
-                # Detect duplicates with additional error handling
-                duplicate_functions = detect_duplicate_functions(temp_index)
-                duplicate_classes = detect_duplicate_classes(temp_index)
-                
-                duplicates['functions'] = set(duplicate_functions.keys())
-                duplicates['classes'] = set(duplicate_classes.keys())
-                
-        except (ImportError, AttributeError, KeyError, TypeError):
-            # If we can't detect duplicates, return empty sets
-            pass
+        # Duplicate detection functionality removed - was legacy code
+        # Return empty duplicates as this feature is no longer used
 
         return duplicates