Implement LRU cache for project queries and remove unused files

Co-authored-by: Mte90 <403283+Mte90@users.noreply.github.com>

Author: Copilot

OPTIMIZATION_NOTES.md

@@ -2,29 +2,25 @@
 
 ## Actionable Optimizations
 
-### 1. **main.py** - Cache Management
-- Replace `_ANALYSES_CACHE` global variable with `functools.lru_cache` decorator
-- This provides automatic cache size limits and thread-safety
-
-### 2. **db.py** - Database Performance
+### 1. **db.py** - Database Performance
 - Add connection pooling for high-load scenarios using SQLite connection pool
 - Implement prepared statements for frequently used queries to reduce parsing overhead
 
-### 3. **analyzer.py** - Batch Processing
+### 2. **analyzer.py** - Batch Processing
 - Improve embedding batch processing by implementing parallel batch requests
 - Add configurable batch size tuning based on API rate limits
 
-### 4. **external_api.py** - API Reliability
+### 3. **external_api.py** - API Reliability
 - Add rate limiting to prevent API quota exhaustion (consider using `ratelimit` library)
 - Implement retry logic with exponential backoff for failed API calls
 - Add circuit breaker pattern for cascading failure prevention
 
-### 5. **config.py** - Configuration Validation
+### 4. **config.py** - Configuration Validation
 - Add Pydantic-based validation for critical config values
 - Implement type checking for environment variables at startup
 - Add sensible defaults for all optional configuration
 
-### 6. **logger.py** - Production Logging
+### 5. **logger.py** - Production Logging
 - Add log rotation using `logging.handlers.RotatingFileHandler`
 - Configure separate log levels for development vs production
 - Add structured logging (JSON format) for better log aggregation

REQUIREMENTS_VERIFICATION.md

@@ -1,6 +1,7 @@
 import os
 import sqlite3
 from typing import Any, Dict, List, Optional
+from functools import lru_cache
 
 from config import CFG  # config (keeps chunk_size etc if needed)
 import atexit
@@ -533,7 +534,10 @@ def _create():
             conn.close()
 
     try:
-        return _retry_on_db_locked(_create)
+        result = _retry_on_db_locked(_create)
+        # Invalidate cache after creating a new project
+        _get_project_by_id_cached.cache_clear()
+        return result
     except Exception as e:
         _LOG.error(f"Failed to create project: {e}")
         raise
@@ -559,25 +563,36 @@ def _get():
     return _retry_on_db_locked(_get)
 
 
-def get_project_by_id(project_id: str) -> Optional[Dict[str, Any]]:
-    """Get project metadata by ID."""
-    _init_registry_db()
-    
-    registry_path = _get_projects_registry_path()
-    
+@lru_cache(maxsize=128)
+def _get_project_by_id_cached(project_id: str, registry_path: str) -> Optional[tuple]:
+    """Internal cached function that returns immutable tuple."""
     def _get():
         conn = _get_connection(registry_path)
         try:
             cur = conn.cursor()
             cur.execute("SELECT * FROM projects WHERE id = ?", (project_id,))
             row = cur.fetchone()
-            return dict(row) if row else None
+            if row:
+                # Convert row to tuple of key-value pairs for immutability
+                return tuple(dict(row).items())
+            return None
         finally:
             conn.close()
 
     return _retry_on_db_locked(_get)
 
 
+def get_project_by_id(project_id: str) -> Optional[Dict[str, Any]]:
+    """Get project metadata by ID with caching."""
+    _init_registry_db()
+    
+    registry_path = _get_projects_registry_path()
+    cached_result = _get_project_by_id_cached(project_id, registry_path)
+    
+    # Convert tuple back to dict
+    return dict(cached_result) if cached_result else None
+
+
 def list_projects() -> List[Dict[str, Any]]:
     """List all registered projects."""
     _init_registry_db()
@@ -598,7 +613,7 @@ def _list():
 
 
 def update_project_status(project_id: str, status: str, last_indexed_at: Optional[str] = None):
-    """Update project indexing status."""
+    """Update project indexing status and invalidate cache."""
     _init_registry_db()
 
     registry_path = _get_projects_registry_path()
@@ -622,10 +637,12 @@ def _update():
             conn.close()
 
     _retry_on_db_locked(_update)
+    # Invalidate cache after update
+    _get_project_by_id_cached.cache_clear()
 
 
 def update_project_settings(project_id: str, settings: Dict[str, Any]):
-    """Update project settings (stored as JSON)."""
+    """Update project settings (stored as JSON) and invalidate cache."""
     import json
     _init_registry_db()
 
@@ -644,10 +661,12 @@ def _update():
             conn.close()
 
     _retry_on_db_locked(_update)
+    # Invalidate cache after update
+    _get_project_by_id_cached.cache_clear()
 
 
 def delete_project(project_id: str):
-    """Delete a project and its database."""
+    """Delete a project and its database, invalidating cache."""
     _init_registry_db()
 
     project = get_project_by_id(project_id)
@@ -673,6 +692,8 @@ def _delete():
             conn.close()
 
     _retry_on_db_locked(_delete)
+    # Invalidate cache after deletion
+    _get_project_by_id_cached.cache_clear()
 
 
 def get_or_create_project(project_path: str, name: Optional[str] = None) -> Dict[str, Any]: