it

.env.example

@@ -1,34 +0,0 @@
-# ===============================================
-# DNSRecon Environment Variables
-# ===============================================
-# Copy this file to .env and fill in your values.
-
-# --- API Keys ---
-# Add your Shodan API key for the Shodan provider to be enabled.
-SHODAN_API_KEY=
-
-# --- Flask & Session Settings ---
-# A strong, random secret key is crucial for session security.
-FLASK_SECRET_KEY=your-very-secret-and-random-key-here
-FLASK_HOST=127.0.0.1
-FLASK_PORT=5000
-FLASK_DEBUG=True
-# How long a user's session in the browser lasts (in hours).
-FLASK_PERMANENT_SESSION_LIFETIME_HOURS=2
-# How long inactive scanner data is stored in Redis (in minutes).
-SESSION_TIMEOUT_MINUTES=60
-
-
-# --- Application Core Settings ---
-# The default number of levels to recurse when scanning.
-DEFAULT_RECURSION_DEPTH=2
-# Default timeout for provider API requests in seconds.
-DEFAULT_TIMEOUT=30
-# The number of concurrent provider requests to make.
-MAX_CONCURRENT_REQUESTS=5
-# The number of results from a provider that triggers the "large entity" grouping.
-LARGE_ENTITY_THRESHOLD=100
-# The number of times to retry a target if a provider fails.
-MAX_RETRIES_PER_TARGET=3
-# How long cached provider responses are stored (in hours).
-CACHE_EXPIRY_HOURS=12

.gitignore

@@ -169,3 +169,4 @@ cython_debug/
 #.idea/
 
 dump.rdb
+.vscode

app.py

@@ -1,8 +1,6 @@
-# dnsrecon-reduced/app.py
-
 """
 Flask application entry point for DNSRecon web interface.
-Provides REST API endpoints and serves the web interface with user session support.
+Enhanced with user session management and task-based completion model.
 """
 
 import json
@@ -11,42 +9,81 @@ from flask import Flask, render_template, request, jsonify, send_file, session
 from datetime import datetime, timezone, timedelta
 import io
 
-from core.session_manager import session_manager
+from core.session_manager import session_manager, UserIdentifier
 from config import config
 
 
 app = Flask(__name__)
-# Use centralized configuration for Flask settings
-app.config['SECRET_KEY'] = config.flask_secret_key
-app.config['PERMANENT_SESSION_LIFETIME'] = timedelta(hours=config.flask_permanent_session_lifetime_hours)
+app.config['SECRET_KEY'] = 'dnsrecon-dev-key-change-in-production'
+app.config['PERMANENT_SESSION_LIFETIME'] = timedelta(hours=2)  # 2 hour session lifetime
+
 
 def get_user_scanner():
     """
-    Retrieves the scanner for the current session, or creates a new
-    session and scanner if one doesn't exist.
+    Enhanced user scanner retrieval with user identification and session consolidation.
+    Implements single session per user with seamless consolidation.
     """
-    # Get current Flask session info for debugging
-    current_flask_session_id = session.get('dnsrecon_session_id')
+    print("=== ENHANCED GET_USER_SCANNER ===")
     
-    # Try to get existing session
-    if current_flask_session_id:
-        existing_scanner = session_manager.get_session(current_flask_session_id)
-        if existing_scanner:
-            return current_flask_session_id, existing_scanner
-    
-    # Create new session if none exists
-    print("Creating new session as none was found...")
-    new_session_id = session_manager.create_session()
-    new_scanner = session_manager.get_session(new_session_id)
-    
-    if not new_scanner:
-        raise Exception("Failed to create new scanner session")
-    
-    # Store in Flask session
-    session['dnsrecon_session_id'] = new_session_id
-    session.permanent = True
-    
-    return new_session_id, new_scanner
+    try:
+        # Extract user identification from request
+        client_ip, user_agent = UserIdentifier.extract_request_info(request)
+        user_fingerprint = UserIdentifier.generate_user_fingerprint(client_ip, user_agent)
+        
+        print(f"User fingerprint: {user_fingerprint}")
+        print(f"Client IP: {client_ip}")
+        print(f"User Agent: {user_agent[:50]}...")
+        
+        # Get current Flask session info for debugging
+        current_flask_session_id = session.get('dnsrecon_session_id')
+        print(f"Flask session ID: {current_flask_session_id}")
+        
+        # Try to get existing session first
+        if current_flask_session_id:
+            existing_scanner = session_manager.get_session(current_flask_session_id)
+            if existing_scanner:
+                # Verify session belongs to current user
+                session_info = session_manager.get_session_info(current_flask_session_id)
+                if session_info.get('user_fingerprint') == user_fingerprint:
+                    print(f"Found valid existing session {current_flask_session_id} for user {user_fingerprint}")
+                    existing_scanner.session_id = current_flask_session_id
+                    return current_flask_session_id, existing_scanner
+                else:
+                    print(f"Session {current_flask_session_id} belongs to different user, will create new session")
+            else:
+                print(f"Session {current_flask_session_id} not found in Redis, will create new session")
+        
+        # Create or replace user session (this handles consolidation automatically)
+        new_session_id = session_manager.create_or_replace_user_session(client_ip, user_agent)
+        new_scanner = session_manager.get_session(new_session_id)
+        
+        if not new_scanner:
+            print(f"ERROR: Failed to retrieve newly created session {new_session_id}")
+            raise Exception("Failed to create new scanner session")
+        
+        # Store in Flask session for browser persistence
+        session['dnsrecon_session_id'] = new_session_id
+        session.permanent = True
+        
+        # Ensure session ID is set on scanner
+        new_scanner.session_id = new_session_id
+        
+        # Get session info for user feedback
+        session_info = session_manager.get_session_info(new_session_id)
+        
+        print(f"Session created/consolidated successfully")
+        print(f"  - Session ID: {new_session_id}")
+        print(f"  - User: {user_fingerprint}")
+        print(f"  - Scanner status: {new_scanner.status}")
+        print(f"  - Session age: {session_info.get('session_age_minutes', 0)} minutes")
+        
+        return new_session_id, new_scanner
+        
+    except Exception as e:
+        print(f"ERROR: Exception in get_user_scanner: {e}")
+        traceback.print_exc()
+        raise
+
 
 @app.route('/')
 def index():
@@ -57,15 +94,21 @@ def index():
 @app.route('/api/scan/start', methods=['POST'])
 def start_scan():
     """
-    Start a new reconnaissance scan. Creates a new isolated scanner if
-    clear_graph is true, otherwise adds to the existing one.
+    Start a new reconnaissance scan with enhanced user session management.
     """
     print("=== API: /api/scan/start called ===")
     
     try:
+        print("Getting JSON data from request...")
         data = request.get_json()
+        print(f"Request data: {data}")
+        
         if not data or 'target_domain' not in data:
-            return jsonify({'success': False, 'error': 'Missing target_domain in request'}), 400
+            print("ERROR: Missing target_domain in request")
+            return jsonify({
+                'success': False,
+                'error': 'Missing target_domain in request'
+            }), 400
         
         target_domain = data['target_domain'].strip()
         max_depth = data.get('max_depth', config.default_recursion_depth)
@@ -75,50 +118,86 @@ def start_scan():
         
         # Validation
         if not target_domain:
-            return jsonify({'success': False, 'error': 'Target domain cannot be empty'}), 400
-        if not isinstance(max_depth, int) or not 1 <= max_depth <= 5:
-            return jsonify({'success': False, 'error': 'Max depth must be an integer between 1 and 5'}), 400
+            print("ERROR: Target domain cannot be empty")
+            return jsonify({
+                'success': False,
+                'error': 'Target domain cannot be empty'
+            }), 400
         
-        user_session_id, scanner = None, None
-
-        if clear_graph:
-            print("Clear graph requested: Creating a new, isolated scanner session.")
-            old_session_id = session.get('dnsrecon_session_id')
-            if old_session_id:
-                session_manager.terminate_session(old_session_id)
-            
-            user_session_id = session_manager.create_session()
-            session['dnsrecon_session_id'] = user_session_id
-            session.permanent = True
-            scanner = session_manager.get_session(user_session_id)
-        else:
-            print("Adding to existing graph: Reusing the current scanner session.")
-            user_session_id, scanner = get_user_scanner()
-
-        if not scanner:
-            return jsonify({'success': False, 'error': 'Failed to get or create a scanner instance.'}), 500
+        if not isinstance(max_depth, int) or max_depth < 1 or max_depth > 5:
+            print(f"ERROR: Invalid max_depth: {max_depth}")
+            return jsonify({
+                'success': False,
+                'error': 'Max depth must be an integer between 1 and 5'
+            }), 400
         
-        print(f"Using scanner {id(scanner)} in session {user_session_id}")
+        print("Validation passed, getting user scanner...")
         
+        # Get user-specific scanner with enhanced session management
+        user_session_id, scanner = get_user_scanner()
+        
+        # Ensure session ID is properly set
+        if not scanner.session_id:
+            scanner.session_id = user_session_id
+        
+        print(f"Using session: {user_session_id}")
+        print(f"Scanner object ID: {id(scanner)}")
+        
+        # Start scan
+        print(f"Calling start_scan on scanner {id(scanner)}...")
         success = scanner.start_scan(target_domain, max_depth, clear_graph=clear_graph)
         
+        # Immediately update session state regardless of success
+        session_manager.update_session_scanner(user_session_id, scanner)
+        
         if success:
+            scan_session_id = scanner.logger.session_id
+            print(f"Scan started successfully with scan session ID: {scan_session_id}")
+            
+            # Get session info for user feedback
+            session_info = session_manager.get_session_info(user_session_id)
+            
             return jsonify({
                 'success': True,
                 'message': 'Scan started successfully',
-                'scan_id': scanner.logger.session_id,
+                'scan_id': scan_session_id,
                 'user_session_id': user_session_id,
+                'scanner_status': scanner.status,
+                'session_info': {
+                    'user_fingerprint': session_info.get('user_fingerprint', 'unknown'),
+                    'session_age_minutes': session_info.get('session_age_minutes', 0),
+                    'consolidated': session_info.get('session_age_minutes', 0) > 0
+                },
+                'debug_info': {
+                    'scanner_object_id': id(scanner),
+                    'scanner_status': scanner.status
+                }
             })
         else:
+            print("ERROR: Scanner returned False")
+            
+            # Provide more detailed error information
+            error_details = {
+                'scanner_status': scanner.status,
+                'scanner_object_id': id(scanner),
+                'session_id': user_session_id,
+                'providers_count': len(scanner.providers) if hasattr(scanner, 'providers') else 0
+            }
+            
             return jsonify({
                 'success': False,
                 'error': f'Failed to start scan (scanner status: {scanner.status})',
+                'debug_info': error_details
             }), 409
         
     except Exception as e:
         print(f"ERROR: Exception in start_scan endpoint: {e}")
         traceback.print_exc()
-        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
+        return jsonify({
+            'success': False,
+            'error': f'Internal server error: {str(e)}'
+        }), 500
+
 
 @app.route('/api/scan/stop', methods=['POST'])
 def stop_scan():
@@ -173,7 +252,7 @@ def stop_scan():
 
 @app.route('/api/scan/status', methods=['GET'])
 def get_scan_status():
-    """Get current scan status with error handling."""
+    """Get current scan status with enhanced session information."""
     try:
         # Get user-specific scanner
         user_session_id, scanner = get_user_scanner()
@@ -204,6 +283,15 @@ def get_scan_status():
         status = scanner.get_scan_status()
         status['user_session_id'] = user_session_id
         
+        # Add enhanced session information
+        session_info = session_manager.get_session_info(user_session_id)
+        status['session_info'] = {
+            'user_fingerprint': session_info.get('user_fingerprint', 'unknown'),
+            'session_age_minutes': session_info.get('session_age_minutes', 0),
+            'client_ip': session_info.get('client_ip', 'unknown'),
+            'last_activity': session_info.get('last_activity')
+        }
+        
         # Additional debug info
         status['debug_info'] = {
             'scanner_object_id': id(scanner),
@@ -232,7 +320,6 @@ def get_scan_status():
         }), 500
 
 
-
 @app.route('/api/graph', methods=['GET'])
 def get_graph_data():
     """Get current graph data with error handling."""
@@ -278,7 +365,6 @@ def get_graph_data():
         }), 500
 
 
-
 @app.route('/api/export', methods=['GET'])
 def export_results():
     """Export complete scan results as downloadable JSON for the user session."""
@@ -289,17 +375,22 @@ def export_results():
         # Get complete results
         results = scanner.export_results()
         
-        # Add session information to export
+        # Add enhanced session information to export
+        session_info = session_manager.get_session_info(user_session_id)
         results['export_metadata'] = {
             'user_session_id': user_session_id,
+            'user_fingerprint': session_info.get('user_fingerprint', 'unknown'),
+            'client_ip': session_info.get('client_ip', 'unknown'),
+            'session_age_minutes': session_info.get('session_age_minutes', 0),
             'export_timestamp': datetime.now(timezone.utc).isoformat(),
             'export_type': 'user_session_results'
         }
         
-        # Create filename with timestamp
+        # Create filename with user fingerprint
         timestamp = datetime.now(timezone.utc).strftime('%Y%m%d_%H%M%S')
         target = scanner.current_target or 'unknown'
-        filename = f"dnsrecon_{target}_{timestamp}_{user_session_id[:8]}.json"
+        user_fp = session_info.get('user_fingerprint', 'unknown')[:8]
+        filename = f"dnsrecon_{target}_{timestamp}_{user_fp}.json"
         
         # Create in-memory file
         json_data = json.dumps(results, indent=2, ensure_ascii=False)
@@ -324,18 +415,12 @@ def export_results():
 @app.route('/api/providers', methods=['GET'])
 def get_providers():
     """Get information about available providers for the user session."""
+    print("=== API: /api/providers called ===")
     
     try:
         # Get user-specific scanner
         user_session_id, scanner = get_user_scanner()
         
-        if scanner:
-            completed_tasks = scanner.indicators_completed
-            enqueued_tasks = len(scanner.task_queue)
-            print(f"DEBUG: Tasks - Completed: {completed_tasks}, Enqueued: {enqueued_tasks}")
-        else:
-            print("DEBUG: No active scanner session found.")
-
         provider_info = scanner.get_provider_info()
         
         return jsonify({
@@ -410,6 +495,122 @@ def set_api_keys():
             'error': f'Internal server error: {str(e)}'
         }), 500
 
+
+@app.route('/api/session/info', methods=['GET'])
+def get_session_info():
+    """Get enhanced information about the current user session."""
+    try:
+        user_session_id, scanner = get_user_scanner()
+        session_info = session_manager.get_session_info(user_session_id)
+        
+        return jsonify({
+            'success': True,
+            'session_info': session_info
+        })
+    
+    except Exception as e:
+        print(f"ERROR: Exception in get_session_info endpoint: {e}")
+        traceback.print_exc()
+        return jsonify({
+            'success': False,
+            'error': f'Internal server error: {str(e)}'
+        }), 500
+
+
+@app.route('/api/session/terminate', methods=['POST'])
+def terminate_session():
+    """Terminate the current user session."""
+    try:
+        user_session_id = session.get('dnsrecon_session_id')
+        
+        if user_session_id:
+            success = session_manager.terminate_session(user_session_id)
+            # Clear Flask session
+            session.pop('dnsrecon_session_id', None)
+            
+            return jsonify({
+                'success': success,
+                'message': 'Session terminated' if success else 'Session not found'
+            })
+        else:
+            return jsonify({
+                'success': False,
+                'error': 'No active session to terminate'
+            }), 400
+    
+    except Exception as e:
+        print(f"ERROR: Exception in terminate_session endpoint: {e}")
+        traceback.print_exc()
+        return jsonify({
+            'success': False,
+            'error': f'Internal server error: {str(e)}'
+        }), 500
+
+
+@app.route('/api/admin/sessions', methods=['GET'])
+def list_sessions():
+    """Admin endpoint to list all active sessions with enhanced information."""
+    try:
+        sessions = session_manager.list_active_sessions()
+        stats = session_manager.get_statistics()
+        
+        return jsonify({
+            'success': True,
+            'sessions': sessions,
+            'statistics': stats
+        })
+    
+    except Exception as e:
+        print(f"ERROR: Exception in list_sessions endpoint: {e}")
+        traceback.print_exc()
+        return jsonify({
+            'success': False,
+            'error': f'Internal server error: {str(e)}'
+        }), 500
+
+
+@app.route('/api/health', methods=['GET'])
+def health_check():
+    """Health check endpoint with enhanced session statistics."""
+    try:
+        # Get session stats
+        session_stats = session_manager.get_statistics()
+        
+        return jsonify({
+            'success': True,
+            'status': 'healthy',
+            'timestamp': datetime.now(timezone.utc).isoformat(),
+            'version': '2.0.0-enhanced',
+            'phase': 'enhanced_architecture',
+            'features': {
+                'multi_provider': True,
+                'concurrent_processing': True,
+                'real_time_updates': True,
+                'api_key_management': True,
+                'visualization': True,
+                'retry_logic': True,
+                'user_sessions': True,
+                'session_isolation': True,
+                'global_provider_caching': True,
+                'single_session_per_user': True,
+                'session_consolidation': True,
+                'task_completion_model': True
+            },
+            'session_statistics': session_stats,
+            'cache_info': {
+                'global_provider_cache': True,
+                'cache_location': '.cache/<provider_name>/',
+                'cache_expiry_hours': 12
+            }
+        })
+    except Exception as e:
+        print(f"ERROR: Exception in health_check endpoint: {e}")
+        return jsonify({
+            'success': False,
+            'error': f'Health check failed: {str(e)}'
+        }), 500
+
+
 @app.errorhandler(404)
 def not_found(error):
     """Handle 404 errors."""
@@ -431,7 +632,7 @@ def internal_error(error):
 
 
 if __name__ == '__main__':
-    print("Starting DNSRecon Flask application with user session support...")
+    print("Starting DNSRecon Flask application with enhanced user session support...")
     
     # Load configuration from environment
     config.load_from_env()

config.py

@@ -5,97 +5,110 @@ Handles API key storage, rate limiting, and default settings.
 
 import os
 from typing import Dict, Optional
-from dotenv import load_dotenv
 
-# Load environment variables from .env file
-load_dotenv()
 
 class Config:
     """Configuration manager for DNSRecon application."""
     
     def __init__(self):
         """Initialize configuration with default values."""
-        self.api_keys: Dict[str, Optional[str]] = {}
+        self.api_keys: Dict[str, Optional[str]] = {
+            'shodan': None
+        }
         
-        # --- General Settings ---
+        # Default settings
         self.default_recursion_depth = 2
-        self.default_timeout = 15
+        self.default_timeout = 10
         self.max_concurrent_requests = 5
         self.large_entity_threshold = 100
-        self.max_retries_per_target = 3
-        self.cache_expiry_hours = 12
         
-        # --- Provider Caching Settings ---
-        self.cache_timeout_hours = 6  # Provider-specific cache timeout
-        
-        # --- Rate Limiting (requests per minute) ---
+        # Rate limiting settings (requests per minute)
         self.rate_limits = {
-            'crtsh': 30,
-            'shodan': 60,
-            'dns': 100
+            'crtsh': 60,          # Free service, be respectful
+            'shodan': 60,         # API dependent
+            'dns': 100            # Local DNS queries
         }
         
-        # --- Provider Settings ---
+        # Provider settings
         self.enabled_providers = {
-            'crtsh': True,
-            'dns': True,
-            'shodan': False
+            'crtsh': True,        # Always enabled (free)
+            'dns': True,          # Always enabled (free)
+            'shodan': False       # Requires API key
         }
         
-        # --- Logging ---
+        # Logging configuration
         self.log_level = 'INFO'
         self.log_format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
         
-        # --- Flask & Session Settings ---
+        # Flask configuration
         self.flask_host = '127.0.0.1'
         self.flask_port = 5000
         self.flask_debug = True
-        self.flask_secret_key = 'default-secret-key-change-me'
-        self.flask_permanent_session_lifetime_hours = 2
-        self.session_timeout_minutes = 60
         
-        # Load environment variables to override defaults
-        self.load_from_env()
+    def set_api_key(self, provider: str, api_key: str) -> bool:
+        """
+        Set API key for a provider.
         
-    def load_from_env(self):
-        """Load configuration from environment variables."""
-        self.set_api_key('shodan', os.getenv('SHODAN_API_KEY'))
-
-        # Override settings from environment
-        self.default_recursion_depth = int(os.getenv('DEFAULT_RECURSION_DEPTH', self.default_recursion_depth))
-        self.default_timeout = int(os.getenv('DEFAULT_TIMEOUT', self.default_timeout))
-        self.max_concurrent_requests = int(os.getenv('MAX_CONCURRENT_REQUESTS', self.max_concurrent_requests))
-        self.large_entity_threshold = int(os.getenv('LARGE_ENTITY_THRESHOLD', self.large_entity_threshold))
-        self.max_retries_per_target = int(os.getenv('MAX_RETRIES_PER_TARGET', self.max_retries_per_target))
-        self.cache_expiry_hours = int(os.getenv('CACHE_EXPIRY_HOURS', self.cache_expiry_hours))
-        self.cache_timeout_hours = int(os.getenv('CACHE_TIMEOUT_HOURS', self.cache_timeout_hours))
-        
-        # Override Flask and session settings
-        self.flask_host = os.getenv('FLASK_HOST', self.flask_host)
-        self.flask_port = int(os.getenv('FLASK_PORT', self.flask_port))
-        self.flask_debug = os.getenv('FLASK_DEBUG', str(self.flask_debug)).lower() == 'true'
-        self.flask_secret_key = os.getenv('FLASK_SECRET_KEY', self.flask_secret_key)
-        self.flask_permanent_session_lifetime_hours = int(os.getenv('FLASK_PERMANENT_SESSION_LIFETIME_HOURS', self.flask_permanent_session_lifetime_hours))
-        self.session_timeout_minutes = int(os.getenv('SESSION_TIMEOUT_MINUTES', self.session_timeout_minutes))
-
-    def set_api_key(self, provider: str, api_key: Optional[str]) -> bool:
-        """Set API key for a provider."""
-        self.api_keys[provider] = api_key
-        if api_key:
-            self.enabled_providers[provider] = True
-        return True
+        Args:
+            provider: Provider name (shodan, etc)
+            api_key: API key string
+            
+        Returns:
+            bool: True if key was set successfully
+        """
+        if provider in self.api_keys:
+            self.api_keys[provider] = api_key
+            self.enabled_providers[provider] = True if api_key else False
+            return True
+        return False
     
     def get_api_key(self, provider: str) -> Optional[str]:
-        """Get API key for a provider."""
+        """
+        Get API key for a provider.
+        
+        Args:
+            provider: Provider name
+            
+        Returns:
+            API key or None if not set
+        """
         return self.api_keys.get(provider)
     
     def is_provider_enabled(self, provider: str) -> bool:
-        """Check if a provider is enabled."""
+        """
+        Check if a provider is enabled.
+        
+        Args:
+            provider: Provider name
+            
+        Returns:
+            bool: True if provider is enabled
+        """
         return self.enabled_providers.get(provider, False)
     
     def get_rate_limit(self, provider: str) -> int:
-        """Get rate limit for a provider."""
+        """
+        Get rate limit for a provider.
+        
+        Args:
+            provider: Provider name
+            
+        Returns:
+            Rate limit in requests per minute
+        """
         return self.rate_limits.get(provider, 60)
+    
+    def load_from_env(self):
+        """Load configuration from environment variables."""
+        if os.getenv('SHODAN_API_KEY'):
+            self.set_api_key('shodan', os.getenv('SHODAN_API_KEY'))
+        
+        # Override default settings from environment
+        self.default_recursion_depth = int(os.getenv('DEFAULT_RECURSION_DEPTH', '2'))
+        self.flask_debug = os.getenv('FLASK_DEBUG', 'True').lower() == 'true'
+        self.default_timeout = 30
+        self.max_concurrent_requests = 5
+
 
 # Global configuration instance
 config = Config()

core/__init__.py

@@ -8,6 +8,7 @@ from .scanner import Scanner, ScanStatus
 from .logger import ForensicLogger, get_forensic_logger, new_session
 from .session_manager import session_manager 
 from .session_config import SessionConfig, create_session_config 
+from .task_manager import TaskManager, TaskType, ReconTask
 
 __all__ = [
     'GraphManager',
@@ -19,7 +20,10 @@ __all__ = [
     'new_session',
     'session_manager', 
     'SessionConfig',
-    'create_session_config'
+    'create_session_config',
+    'TaskManager',
+    'TaskType',
+    'ReconTask'
 ]
 
 __version__ = "1.0.0-phase2"

core/graph_manager.py

@@ -1,5 +1,3 @@
-# core/graph_manager.py
-
 """
 Graph data model for DNSRecon using NetworkX.
 Manages in-memory graph storage with confidence scoring and forensic metadata.
@@ -52,23 +50,21 @@ class GraphManager:
         self.__dict__.update(state)
         self.date_pattern = re.compile(r'^\d{4}-\d{2}-\d{2}[ T]\d{2}:\d{2}:\d{2}')
 
-    def _update_correlation_index(self, node_id: str, data: Any, path: List[str] = [], parent_attr: str = ""):
-        """Recursively traverse metadata and add hashable values to the index with better path tracking."""
+    def _update_correlation_index(self, node_id: str, data: Any, path: List[str] = None):
+        """Recursively traverse metadata and add hashable values to the index."""
         if path is None:
             path = []
 
         if isinstance(data, dict):
             for key, value in data.items():
-                self._update_correlation_index(node_id, value, path + [key], key)
+                self._update_correlation_index(node_id, value, path + [key])
         elif isinstance(data, list):
             for i, item in enumerate(data):
-                # Instead of just using [i], include the parent attribute context
-                list_path_component = f"[{i}]" if not parent_attr else f"{parent_attr}[{i}]"
-                self._update_correlation_index(node_id, item, path + [list_path_component], parent_attr)
+                self._update_correlation_index(node_id, item, path + [f"[{i}]"])
         else:
-            self._add_to_correlation_index(node_id, data, ".".join(path), parent_attr)
+            self._add_to_correlation_index(node_id, data, ".".join(path))
 
-    def _add_to_correlation_index(self, node_id: str, value: Any, path_str: str, parent_attr: str = ""):
+    def _add_to_correlation_index(self, node_id: str, value: Any, path_str: str):
         """Add a hashable value to the correlation index, filtering out noise."""
         if not isinstance(value, (str, int, float, bool)) or value is None:
             return
@@ -84,8 +80,8 @@ class GraphManager:
                 return
             if len(value) < 4 or value.lower() in ['true', 'false', 'unknown', 'none', 'crt.sh']:
                 return
-        elif isinstance(value, int) and (abs(value) < 1024 or abs(value) > 65535):
-            return  # Ignore small integers and common port numbers
+        elif isinstance(value, int) and abs(value) < 9999:
+            return  # Ignore small integers
         elif isinstance(value, bool):
             return  # Ignore boolean values
 
@@ -94,47 +90,10 @@ class GraphManager:
             self.correlation_index[value] = {}
         if node_id not in self.correlation_index[value]:
             self.correlation_index[value][node_id] = []
-        
-        # Store both the full path and the parent attribute for better edge labeling
-        correlation_entry = {
-            'path': path_str,
-            'parent_attr': parent_attr,
-            'meaningful_attr': self._extract_meaningful_attribute(path_str, parent_attr)
-        }
-        
-        if correlation_entry not in self.correlation_index[value][node_id]:
-            self.correlation_index[value][node_id].append(correlation_entry)
+        if path_str not in self.correlation_index[value][node_id]:
+            self.correlation_index[value][node_id].append(path_str)
 
-    def _extract_meaningful_attribute(self, path_str: str, parent_attr: str = "") -> str:
-        """Extract the most meaningful attribute name from a path string."""
-        if not path_str:
-            return "unknown"
-        
-        path_parts = path_str.split('.')
-        
-        # Look for the last non-array-index part
-        for part in reversed(path_parts):
-            # Skip array indices like [0], [1], etc.
-            if not (part.startswith('[') and part.endswith(']') and part[1:-1].isdigit()):
-                # Clean up compound names like "hostnames[0]" to just "hostnames"
-                clean_part = re.sub(r'\[\d+\]$', '', part)
-                if clean_part:
-                    return clean_part
-        
-        # Fallback to parent attribute if available
-        if parent_attr:
-            return parent_attr
-        
-        # Last resort - use the first meaningful part
-        for part in path_parts:
-            if not (part.startswith('[') and part.endswith(']') and part[1:-1].isdigit()):
-                clean_part = re.sub(r'\[\d+\]$', '', part)
-                if clean_part:
-                    return clean_part
-        
-        return "correlation"
-
-    def _check_for_correlations(self, new_node_id: str, data: Any, path: List[str] = [], parent_attr: str = "") -> List[Dict]:
+    def _check_for_correlations(self, new_node_id: str, data: Any, path: List[str] = None) -> List[Dict]:
         """Recursively traverse metadata to find correlations with existing data."""
         if path is None:
             path = []
@@ -144,11 +103,10 @@ class GraphManager:
             for key, value in data.items():
                 if key == 'source':  # Avoid correlating on the provider name
                     continue
-                all_correlations.extend(self._check_for_correlations(new_node_id, value, path + [key], key))
+                all_correlations.extend(self._check_for_correlations(new_node_id, value, path + [key]))
         elif isinstance(data, list):
             for i, item in enumerate(data):
-                list_path_component = f"[{i}]" if not parent_attr else f"{parent_attr}[{i}]"
-                all_correlations.extend(self._check_for_correlations(new_node_id, item, path + [list_path_component], parent_attr))
+                all_correlations.extend(self._check_for_correlations(new_node_id, item, path + [f"[{i}]"]))
         else:
             value = data
             if value in self.correlation_index:
@@ -159,31 +117,11 @@ class GraphManager:
                 if len(unique_nodes) < 2:
                     return all_correlations # Correlation must involve at least two distinct nodes
 
-                new_source = {
-                    'node_id': new_node_id, 
-                    'path': ".".join(path),
-                    'parent_attr': parent_attr,
-                    'meaningful_attr': self._extract_meaningful_attribute(".".join(path), parent_attr)
-                }
+                new_source = {'node_id': new_node_id, 'path': ".".join(path)}
                 all_sources = [new_source]
-                
-                for node_id, path_entries in existing_nodes_with_paths.items():
-                    for entry in path_entries:
-                        if isinstance(entry, dict):
-                            all_sources.append({
-                                'node_id': node_id,
-                                'path': entry['path'],
-                                'parent_attr': entry.get('parent_attr', ''),
-                                'meaningful_attr': entry.get('meaningful_attr', self._extract_meaningful_attribute(entry['path'], entry.get('parent_attr', '')))
-                            })
-                        else:
-                            # Handle legacy string-only entries
-                            all_sources.append({
-                                'node_id': node_id,
-                                'path': str(entry),
-                                'parent_attr': '',
-                                'meaningful_attr': self._extract_meaningful_attribute(str(entry))
-                            })
+                for node_id, paths in existing_nodes_with_paths.items():
+                    for p_str in paths:
+                        all_sources.append({'node_id': node_id, 'path': p_str})
 
                 all_correlations.append({
                     'value': value,
@@ -225,7 +163,8 @@ class GraphManager:
                     # Skip creating correlation node - would be redundant
                     continue
                 
-                eligible_nodes = set(corr['nodes'])
+                # STEP 2: Filter out node pairs that already have direct edges
+                eligible_nodes = self._filter_nodes_without_direct_edges(set(corr['nodes']))
                 
                 if len(eligible_nodes) < 2:
                     # Need at least 2 nodes to create a correlation
@@ -245,12 +184,11 @@ class GraphManager:
                                 metadata={'values': [value], 'sources': corr['sources'],
                                             'correlated_nodes': list(eligible_nodes)})
                     
-                    # Create edges from eligible nodes to this correlation node with better labeling
+                    # Create edges from eligible nodes to this correlation node
                     for c_node_id in eligible_nodes:
                         if self.graph.has_node(c_node_id):
-                            # Find the best attribute name for this node
-                            meaningful_attr = self._find_best_attribute_name_for_node(c_node_id, corr['sources'])
-                            relationship_type = f"c_{meaningful_attr}"
+                            attribute = corr['sources'][0]['path'].split('.')[-1]
+                            relationship_type = f"c_{attribute}"
                             self.add_edge(c_node_id, correlation_node_id, relationship_type, confidence_score=0.9)
 
             self._update_correlation_index(node_id, attributes)
@@ -258,34 +196,27 @@ class GraphManager:
         self.last_modified = datetime.now(timezone.utc).isoformat()
         return is_new_node
 
-    def _find_best_attribute_name_for_node(self, node_id: str, sources: List[Dict]) -> str:
-        """Find the best attribute name for a correlation edge by looking at the sources."""
-        node_sources = [s for s in sources if s['node_id'] == node_id]
+    def _filter_nodes_without_direct_edges(self, node_set: set) -> set:
+        """
+        Filter out nodes that already have direct edges between them.
+        Returns set of nodes that should be included in correlation.
+        """
+        nodes_list = list(node_set)
+        eligible_nodes = set(node_set)  # Start with all nodes
         
-        if not node_sources:
-            return "correlation"
+        # Check all pairs of nodes
+        for i in range(len(nodes_list)):
+            for j in range(i + 1, len(nodes_list)):
+                node_a = nodes_list[i]
+                node_b = nodes_list[j]
+                
+                # Check if direct edge exists in either direction
+                if self._has_direct_edge_bidirectional(node_a, node_b):
+                    # Remove both nodes from eligible set since they're already connected
+                    eligible_nodes.discard(node_a)
+                    eligible_nodes.discard(node_b)
         
-        # Use the meaningful_attr if available
-        for source in node_sources:
-            meaningful_attr = source.get('meaningful_attr')
-            if meaningful_attr and meaningful_attr != "unknown":
-                return meaningful_attr
-        
-        # Fallback to parent_attr
-        for source in node_sources:
-            parent_attr = source.get('parent_attr')
-            if parent_attr:
-                return parent_attr
-        
-        # Last resort - extract from path
-        for source in node_sources:
-            path = source.get('path', '')
-            if path:
-                extracted = self._extract_meaningful_attribute(path)
-                if extracted != "unknown":
-                    return extracted
-        
-        return "correlation"
+        return eligible_nodes
 
     def _has_direct_edge_bidirectional(self, node_a: str, node_b: str) -> bool:
         """
@@ -359,7 +290,7 @@ class GraphManager:
         # Create set of unique sources based on (node_id, path) tuples
         source_set = set()
         for source in existing_sources + new_sources:
-            source_tuple = (source['node_id'], source.get('path', ''))
+            source_tuple = (source['node_id'], source['path'])
             source_set.add(source_tuple)
         
         # Convert back to list of dictionaries
@@ -490,14 +421,10 @@ class GraphManager:
     def _get_confidence_distribution(self) -> Dict[str, int]:
         """Get distribution of edge confidence scores."""
         distribution = {'high': 0, 'medium': 0, 'low': 0}
-        for _, _, data in self.graph.edges(data=True):
-            confidence = data.get('confidence_score', 0)
-            if confidence >= 0.8:
-                distribution['high'] += 1
-            elif confidence >= 0.6:
-                distribution['medium'] += 1
-            else:
-                distribution['low'] += 1
+        for _, _, confidence in self.graph.edges(data='confidence_score', default=0):
+            if confidence >= 0.8: distribution['high'] += 1
+            elif confidence >= 0.6: distribution['medium'] += 1
+            else: distribution['low'] += 1
         return distribution
 
     def get_statistics(self) -> Dict[str, Any]:
@@ -512,10 +439,9 @@ class GraphManager:
         # Calculate distributions
         for node_type in NodeType:
             stats['node_type_distribution'][node_type.value] = self.get_nodes_by_type(node_type).__len__()
-        for _, _, data in self.graph.edges(data=True):
-            rel_type = data.get('relationship_type', 'unknown')
+        for _, _, rel_type in self.graph.edges(data='relationship_type', default='unknown'):
             stats['relationship_type_distribution'][rel_type] = stats['relationship_type_distribution'].get(rel_type, 0) + 1
-            provider = data.get('source_provider', 'unknown')
+        for _, _, provider in self.graph.edges(data='source_provider', default='unknown'):
             stats['provider_distribution'][provider] = stats['provider_distribution'].get(provider, 0) + 1
         return stats
 

core/logger.py

@@ -42,7 +42,7 @@ class ForensicLogger:
     Maintains detailed audit trail of all reconnaissance activities.
     """
     
-    def __init__(self, session_id: str = ""):
+    def __init__(self, session_id: str = None):
         """
         Initialize forensic logger.
         
@@ -203,6 +203,8 @@ class ForensicLogger:
         self.session_metadata['target_domains'] = list(self.session_metadata['target_domains'])
         
         self.logger.info(f"Scan Complete - Session: {self.session_id}")
+        self.logger.info(f"Total API Requests: {self.session_metadata['total_requests']}")
+        self.logger.info(f"Total Relationships: {self.session_metadata['total_relationships']}")
     
     def export_audit_trail(self) -> Dict[str, Any]:
         """

core/session_config.py

@@ -1,20 +1,372 @@
 """
-Per-session configuration management for DNSRecon.
-Provides isolated configuration instances for each user session.
+Enhanced per-session configuration management for DNSRecon.
+Provides isolated configuration instances for each user session while supporting global caching.
 """
 
-from config import Config
+import os
+from typing import Dict, Optional
 
-class SessionConfig(Config):
+
+class SessionConfig:
     """
-    Session-specific configuration that inherits from global config
-    but maintains isolated API keys and provider settings.
+    Enhanced session-specific configuration that inherits from global config
+    but maintains isolated API keys and provider settings while supporting global caching.
     """
     
     def __init__(self):
-        """Initialize session config with global defaults."""
-        super().__init__()
+        """Initialize enhanced session config with global cache support."""
+        # Copy all attributes from global config
+        self.api_keys: Dict[str, Optional[str]] = {
+            'shodan': None
+        }
+        
+        # Default settings (copied from global config)
+        self.default_recursion_depth = 2
+        self.default_timeout = 30
+        self.max_concurrent_requests = 5
+        self.large_entity_threshold = 100
+        
+        # Enhanced rate limiting settings (per session)
+        self.rate_limits = {
+            'crtsh': 60,
+            'shodan': 60,
+            'dns': 100
+        }
+        
+        # Enhanced provider settings (per session)
+        self.enabled_providers = {
+            'crtsh': True,
+            'dns': True,
+            'shodan': False
+        }
+        
+        # Task-based execution settings
+        self.task_retry_settings = {
+            'max_retries': 3,
+            'base_backoff_seconds': 1.0,
+            'max_backoff_seconds': 60.0,
+            'retry_on_rate_limit': True,
+            'retry_on_connection_error': True,
+            'retry_on_timeout': True
+        }
+        
+        # Cache settings (global across all sessions)
+        self.cache_settings = {
+            'enabled': True,
+            'expiry_hours': 12,
+            'cache_base_dir': '.cache',
+            'per_provider_directories': True,
+            'thread_safe_operations': True
+        }
+        
+        # Logging configuration
+        self.log_level = 'INFO'
+        self.log_format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        
+        # Flask configuration (shared)
+        self.flask_host = '127.0.0.1'
+        self.flask_port = 5000
+        self.flask_debug = True
+        
+        # Session isolation settings
+        self.session_isolation = {
+            'enforce_single_session_per_user': True,
+            'consolidate_session_data_on_replacement': True,
+            'user_fingerprinting_enabled': True,
+            'session_timeout_minutes': 60
+        }
+        
+        # Circuit breaker settings for provider reliability
+        self.circuit_breaker = {
+            'enabled': True,
+            'failure_threshold': 5,  # Failures before opening circuit
+            'recovery_timeout_seconds': 300,  # 5 minutes before trying again
+            'half_open_max_calls': 3  # Test calls when recovering
+        }
+    
+    def set_api_key(self, provider: str, api_key: str) -> bool:
+        """
+        Set API key for a provider in this session.
+        
+        Args:
+            provider: Provider name (shodan, etc)
+            api_key: API key string (empty string to clear)
+            
+        Returns:
+            bool: True if key was set successfully
+        """
+        if provider in self.api_keys:
+            # Handle clearing of API keys
+            if api_key and api_key.strip():
+                self.api_keys[provider] = api_key.strip()
+                self.enabled_providers[provider] = True
+            else:
+                self.api_keys[provider] = None
+                self.enabled_providers[provider] = False
+            return True
+        return False
+    
+    def get_api_key(self, provider: str) -> Optional[str]:
+        """
+        Get API key for a provider in this session.
+        
+        Args:
+            provider: Provider name
+            
+        Returns:
+            API key or None if not set
+        """
+        return self.api_keys.get(provider)
+    
+    def is_provider_enabled(self, provider: str) -> bool:
+        """
+        Check if a provider is enabled in this session.
+        
+        Args:
+            provider: Provider name
+            
+        Returns:
+            bool: True if provider is enabled
+        """
+        return self.enabled_providers.get(provider, False)
+    
+    def get_rate_limit(self, provider: str) -> int:
+        """
+        Get rate limit for a provider in this session.
+        
+        Args:
+            provider: Provider name
+            
+        Returns:
+            Rate limit in requests per minute
+        """
+        return self.rate_limits.get(provider, 60)
+    
+    def get_task_retry_config(self) -> Dict[str, any]:
+        """
+        Get task retry configuration for this session.
+        
+        Returns:
+            Dictionary with retry settings
+        """
+        return self.task_retry_settings.copy()
+    
+    def get_cache_config(self) -> Dict[str, any]:
+        """
+        Get cache configuration (global settings).
+        
+        Returns:
+            Dictionary with cache settings
+        """
+        return self.cache_settings.copy()
+    
+    def is_circuit_breaker_enabled(self) -> bool:
+        """Check if circuit breaker is enabled for provider reliability."""
+        return self.circuit_breaker.get('enabled', True)
+    
+    def get_circuit_breaker_config(self) -> Dict[str, any]:
+        """Get circuit breaker configuration."""
+        return self.circuit_breaker.copy()
+    
+    def update_provider_settings(self, provider_updates: Dict[str, Dict[str, any]]) -> bool:
+        """
+        Update provider-specific settings in bulk.
+        
+        Args:
+            provider_updates: Dictionary of provider -> settings updates
+            
+        Returns:
+            bool: True if updates were applied successfully
+        """
+        try:
+            for provider_name, updates in provider_updates.items():
+                # Update rate limits
+                if 'rate_limit' in updates:
+                    self.rate_limits[provider_name] = updates['rate_limit']
+                
+                # Update enabled status
+                if 'enabled' in updates:
+                    self.enabled_providers[provider_name] = updates['enabled']
+                
+                # Update API key
+                if 'api_key' in updates:
+                    self.set_api_key(provider_name, updates['api_key'])
+            
+            return True
+        except Exception as e:
+            print(f"Error updating provider settings: {e}")
+            return False
+    
+    def validate_configuration(self) -> Dict[str, any]:
+        """
+        Validate the current configuration and return validation results.
+        
+        Returns:
+            Dictionary with validation results and any issues found
+        """
+        validation_result = {
+            'valid': True,
+            'warnings': [],
+            'errors': [],
+            'provider_status': {}
+        }
+        
+        # Validate provider configurations
+        for provider_name, enabled in self.enabled_providers.items():
+            provider_status = {
+                'enabled': enabled,
+                'has_api_key': bool(self.api_keys.get(provider_name)),
+                'rate_limit': self.rate_limits.get(provider_name, 60)
+            }
+            
+            # Check for potential issues
+            if enabled and provider_name in ['shodan'] and not provider_status['has_api_key']:
+                validation_result['warnings'].append(
+                    f"Provider '{provider_name}' is enabled but missing API key"
+                )
+            
+            validation_result['provider_status'][provider_name] = provider_status
+        
+        # Validate task settings
+        if self.task_retry_settings['max_retries'] > 10:
+            validation_result['warnings'].append(
+                f"High retry count ({self.task_retry_settings['max_retries']}) may cause long delays"
+            )
+        
+        # Validate concurrent settings
+        if self.max_concurrent_requests > 10:
+            validation_result['warnings'].append(
+                f"High concurrency ({self.max_concurrent_requests}) may overwhelm providers"
+            )
+        
+        # Validate cache settings
+        if not os.path.exists(self.cache_settings['cache_base_dir']):
+            try:
+                os.makedirs(self.cache_settings['cache_base_dir'], exist_ok=True)
+            except Exception as e:
+                validation_result['errors'].append(f"Cannot create cache directory: {e}")
+                validation_result['valid'] = False
+        
+        return validation_result
+    
+    def load_from_env(self):
+        """Load configuration from environment variables with enhanced validation."""
+        # Load API keys from environment
+        if os.getenv('SHODAN_API_KEY') and not self.api_keys['shodan']:
+            self.set_api_key('shodan', os.getenv('SHODAN_API_KEY'))
+            print("Loaded Shodan API key from environment")
+        
+        # Override default settings from environment
+        self.default_recursion_depth = int(os.getenv('DEFAULT_RECURSION_DEPTH', '2'))
+        self.default_timeout = int(os.getenv('DEFAULT_TIMEOUT', '30'))
+        self.max_concurrent_requests = int(os.getenv('MAX_CONCURRENT_REQUESTS', '5'))
+        
+        # Load task retry settings from environment
+        if os.getenv('TASK_MAX_RETRIES'):
+            self.task_retry_settings['max_retries'] = int(os.getenv('TASK_MAX_RETRIES'))
+        
+        if os.getenv('TASK_BASE_BACKOFF'):
+            self.task_retry_settings['base_backoff_seconds'] = float(os.getenv('TASK_BASE_BACKOFF'))
+        
+        # Load cache settings from environment
+        if os.getenv('CACHE_EXPIRY_HOURS'):
+            self.cache_settings['expiry_hours'] = int(os.getenv('CACHE_EXPIRY_HOURS'))
+        
+        if os.getenv('CACHE_DISABLED'):
+            self.cache_settings['enabled'] = os.getenv('CACHE_DISABLED').lower() != 'true'
+        
+        # Load circuit breaker settings
+        if os.getenv('CIRCUIT_BREAKER_DISABLED'):
+            self.circuit_breaker['enabled'] = os.getenv('CIRCUIT_BREAKER_DISABLED').lower() != 'true'
+        
+        # Flask settings
+        self.flask_debug = os.getenv('FLASK_DEBUG', 'True').lower() == 'true'
+        
+        print("Enhanced configuration loaded from environment")
+    
+    def export_config_summary(self) -> Dict[str, any]:
+        """
+        Export a summary of the current configuration for debugging/logging.
+        
+        Returns:
+            Dictionary with configuration summary (API keys redacted)
+        """
+        return {
+            'providers': {
+                provider: {
+                    'enabled': self.enabled_providers.get(provider, False),
+                    'has_api_key': bool(self.api_keys.get(provider)),
+                    'rate_limit': self.rate_limits.get(provider, 60)
+                }
+                for provider in self.enabled_providers.keys()
+            },
+            'task_settings': {
+                'max_retries': self.task_retry_settings['max_retries'],
+                'max_concurrent_requests': self.max_concurrent_requests,
+                'large_entity_threshold': self.large_entity_threshold
+            },
+            'cache_settings': {
+                'enabled': self.cache_settings['enabled'],
+                'expiry_hours': self.cache_settings['expiry_hours'],
+                'base_directory': self.cache_settings['cache_base_dir']
+            },
+            'session_settings': {
+                'isolation_enabled': self.session_isolation['enforce_single_session_per_user'],
+                'consolidation_enabled': self.session_isolation['consolidate_session_data_on_replacement'],
+                'timeout_minutes': self.session_isolation['session_timeout_minutes']
+            },
+            'circuit_breaker': {
+                'enabled': self.circuit_breaker['enabled'],
+                'failure_threshold': self.circuit_breaker['failure_threshold'],
+                'recovery_timeout': self.circuit_breaker['recovery_timeout_seconds']
+            }
+        }
 
-def create_session_config() -> 'SessionConfig':
-    """Create a new session configuration instance."""
-    return SessionConfig()
+
+def create_session_config() -> SessionConfig:
+    """
+    Create a new enhanced session configuration instance.
+    
+    Returns:
+        Configured SessionConfig instance
+    """
+    session_config = SessionConfig()
+    session_config.load_from_env()
+    
+    # Validate configuration and log any issues
+    validation = session_config.validate_configuration()
+    if validation['warnings']:
+        print("Configuration warnings:")
+        for warning in validation['warnings']:
+            print(f"  WARNING: {warning}")
+    
+    if validation['errors']:
+        print("Configuration errors:")
+        for error in validation['errors']:
+            print(f"  ERROR: {error}")
+    
+    if not validation['valid']:
+        raise ValueError("Configuration validation failed - see errors above")
+    
+    print(f"Enhanced session configuration created successfully")
+    return session_config
+
+
+def create_test_config() -> SessionConfig:
+    """
+    Create a test configuration with safe defaults for testing.
+    
+    Returns:
+        Test-safe SessionConfig instance
+    """
+    test_config = SessionConfig()
+    
+    # Override settings for testing
+    test_config.max_concurrent_requests = 2
+    test_config.task_retry_settings['max_retries'] = 1
+    test_config.task_retry_settings['base_backoff_seconds'] = 0.1
+    test_config.cache_settings['expiry_hours'] = 1
+    test_config.session_isolation['session_timeout_minutes'] = 10
+    
+    print("Test configuration created")
+    return test_config

core/session_manager.py

@@ -5,41 +5,153 @@ import time
 import uuid
 import redis
 import pickle
-from typing import Dict, Optional, Any, List
+import hashlib
+from typing import Dict, Optional, Any, List, Tuple
 
 from core.scanner import Scanner
-from config import config
 
-# WARNING: Using pickle can be a security risk if the data source is not trusted.
-# In this case, we are only serializing/deserializing our own trusted Scanner objects,
-# which is generally safe. Do not unpickle data from untrusted sources.
+
+class UserIdentifier:
+    """Handles user identification for session management."""
+    
+    @staticmethod
+    def generate_user_fingerprint(client_ip: str, user_agent: str) -> str:
+        """
+        Generate a unique fingerprint for a user based on IP and User-Agent.
+        
+        Args:
+            client_ip: Client IP address
+            user_agent: User-Agent header value
+            
+        Returns:
+            Unique user fingerprint hash
+        """
+        # Create deterministic user identifier
+        user_data = f"{client_ip}:{user_agent[:100]}"  # Limit UA to 100 chars
+        fingerprint = hashlib.sha256(user_data.encode()).hexdigest()[:16]  # 16 char fingerprint
+        return f"user_{fingerprint}"
+    
+    @staticmethod
+    def extract_request_info(request) -> Tuple[str, str]:
+        """
+        Extract client IP and User-Agent from Flask request.
+        
+        Args:
+            request: Flask request object
+            
+        Returns:
+            Tuple of (client_ip, user_agent)
+        """
+        # Handle proxy headers for real IP
+        client_ip = request.headers.get('X-Forwarded-For', '').split(',')[0].strip()
+        if not client_ip:
+            client_ip = request.headers.get('X-Real-IP', '')
+        if not client_ip:
+            client_ip = request.remote_addr or 'unknown'
+        
+        user_agent = request.headers.get('User-Agent', 'unknown')
+        
+        return client_ip, user_agent
+
+
+class SessionConsolidator:
+    """Handles consolidation of session data when replacing sessions."""
+    
+    @staticmethod
+    def consolidate_scanner_data(old_scanner: 'Scanner', new_scanner: 'Scanner') -> 'Scanner':
+        """
+        Consolidate useful data from old scanner into new scanner.
+        
+        Args:
+            old_scanner: Scanner from terminated session
+            new_scanner: New scanner instance
+            
+        Returns:
+            Enhanced new scanner with consolidated data
+        """
+        try:
+            # Consolidate graph data if old scanner has valuable data
+            if old_scanner and hasattr(old_scanner, 'graph') and old_scanner.graph:
+                old_stats = old_scanner.graph.get_statistics()
+                if old_stats['basic_metrics']['total_nodes'] > 0:
+                    print(f"Consolidating graph data: {old_stats['basic_metrics']['total_nodes']} nodes, {old_stats['basic_metrics']['total_edges']} edges")
+                    
+                    # Transfer nodes and edges to new scanner's graph
+                    for node_id, node_data in old_scanner.graph.graph.nodes(data=True):
+                        # Add node to new graph with all attributes
+                        new_scanner.graph.graph.add_node(node_id, **node_data)
+                    
+                    for source, target, edge_data in old_scanner.graph.graph.edges(data=True):
+                        # Add edge to new graph with all attributes  
+                        new_scanner.graph.graph.add_edge(source, target, **edge_data)
+                    
+                    # Update correlation index
+                    if hasattr(old_scanner.graph, 'correlation_index'):
+                        new_scanner.graph.correlation_index = old_scanner.graph.correlation_index.copy()
+                    
+                    # Update timestamps
+                    new_scanner.graph.creation_time = old_scanner.graph.creation_time
+                    new_scanner.graph.last_modified = old_scanner.graph.last_modified
+            
+            # Consolidate provider statistics
+            if old_scanner and hasattr(old_scanner, 'providers') and old_scanner.providers:
+                for old_provider in old_scanner.providers:
+                    # Find matching provider in new scanner
+                    matching_new_provider = None
+                    for new_provider in new_scanner.providers:
+                        if new_provider.get_name() == old_provider.get_name():
+                            matching_new_provider = new_provider
+                            break
+                    
+                    if matching_new_provider:
+                        # Transfer cumulative statistics
+                        matching_new_provider.total_requests += old_provider.total_requests
+                        matching_new_provider.successful_requests += old_provider.successful_requests
+                        matching_new_provider.failed_requests += old_provider.failed_requests
+                        matching_new_provider.total_relationships_found += old_provider.total_relationships_found
+                        
+                        # Transfer cache statistics if available
+                        if hasattr(old_provider, 'cache_hits'):
+                            matching_new_provider.cache_hits += getattr(old_provider, 'cache_hits', 0)
+                            matching_new_provider.cache_misses += getattr(old_provider, 'cache_misses', 0)
+                            
+                        print(f"Consolidated {old_provider.get_name()} provider stats: {old_provider.total_requests} requests")
+            
+            return new_scanner
+            
+        except Exception as e:
+            print(f"Warning: Error during session consolidation: {e}")
+            return new_scanner
+
 
 class SessionManager:
     """
-    Manages multiple scanner instances for concurrent user sessions using Redis.
+    Manages single scanner session per user using Redis with user identification.
+    Enforces one active session per user for consistent state management.
     """
     
-    def __init__(self, session_timeout_minutes: int = 0):
+    def __init__(self, session_timeout_minutes: int = 60):
         """
-        Initialize session manager with a Redis backend.
+        Initialize session manager with Redis backend and user tracking.
         """
-        if session_timeout_minutes is None:
-            session_timeout_minutes = config.session_timeout_minutes
-
         self.redis_client = redis.StrictRedis(db=0, decode_responses=False)
         self.session_timeout = session_timeout_minutes * 60  # Convert to seconds
-        self.lock = threading.Lock() # Lock for local operations, Redis handles atomic ops
+        self.lock = threading.Lock()
+        
+        # User identification helper
+        self.user_identifier = UserIdentifier()
+        self.consolidator = SessionConsolidator()
         
         # Start cleanup thread
         self.cleanup_thread = threading.Thread(target=self._cleanup_loop, daemon=True)
         self.cleanup_thread.start()
         
-        print(f"SessionManager initialized with Redis backend and {session_timeout_minutes}min timeout")
+        print(f"SessionManager initialized with Redis backend, user tracking, and {session_timeout_minutes}min timeout")
     
     def __getstate__(self):
         """Prepare SessionManager for pickling."""
         state = self.__dict__.copy()
-        # Exclude unpickleable attributes - Redis client and threading objects
+        # Exclude unpickleable attributes
         unpicklable_attrs = ['lock', 'cleanup_thread', 'redis_client']
         for attr in unpicklable_attrs:
             if attr in state:
@@ -57,67 +169,108 @@ class SessionManager:
         self.cleanup_thread.start()
 
     def _get_session_key(self, session_id: str) -> str:
-        """Generates the Redis key for a session."""
+        """Generate Redis key for a session."""
         return f"dnsrecon:session:{session_id}"
 
+    def _get_user_session_key(self, user_fingerprint: str) -> str:
+        """Generate Redis key for user -> session mapping."""
+        return f"dnsrecon:user:{user_fingerprint}"
+
     def _get_stop_signal_key(self, session_id: str) -> str:
-        """Generates the Redis key for a session's stop signal."""
+        """Generate Redis key for session stop signal."""
         return f"dnsrecon:stop:{session_id}"
 
-    def create_session(self) -> str:
+    def create_or_replace_user_session(self, client_ip: str, user_agent: str) -> str:
         """
-        Create a new user session and store it in Redis.
+        Create new session for user, replacing any existing session.
+        Consolidates data from previous session if it exists.
+        
+        Args:
+            client_ip: Client IP address
+            user_agent: User-Agent header
+            
+        Returns:
+            New session ID
         """
-        session_id = str(uuid.uuid4())
-        print(f"=== CREATING SESSION {session_id} IN REDIS ===")
+        user_fingerprint = self.user_identifier.generate_user_fingerprint(client_ip, user_agent)
+        new_session_id = str(uuid.uuid4())
+        
+        print(f"=== CREATING/REPLACING SESSION FOR USER {user_fingerprint} ===")
         
         try:
+            # Check for existing user session
+            existing_session_id = self._get_user_current_session(user_fingerprint)
+            old_scanner = None
+            
+            if existing_session_id:
+                print(f"Found existing session {existing_session_id} for user {user_fingerprint}")
+                # Get old scanner data for consolidation
+                old_scanner = self.get_session(existing_session_id)
+                # Terminate old session
+                self._terminate_session_internal(existing_session_id, cleanup_user_mapping=False)
+                print(f"Terminated old session {existing_session_id}")
+            
+            # Create new session config and scanner
             from core.session_config import create_session_config
             session_config = create_session_config()
-            scanner_instance = Scanner(session_config=session_config)
+            new_scanner = Scanner(session_config=session_config)
             
-            # Set the session ID on the scanner for cross-process stop signal management
-            scanner_instance.session_id = session_id
+            # Set session ID on scanner for cross-process operations
+            new_scanner.session_id = new_session_id
             
+            # Consolidate data from old session if available
+            if old_scanner:
+                new_scanner = self.consolidator.consolidate_scanner_data(old_scanner, new_scanner)
+                print(f"Consolidated data from previous session")
+            
+            # Create session data
             session_data = {
-                'scanner': scanner_instance,
+                'scanner': new_scanner,
                 'config': session_config,
                 'created_at': time.time(),
                 'last_activity': time.time(),
-                'status': 'active'
+                'status': 'active',
+                'user_fingerprint': user_fingerprint,
+                'client_ip': client_ip,
+                'user_agent': user_agent[:200]  # Truncate for storage
             }
             
-            # Serialize the entire session data dictionary using pickle
+            # Store session in Redis
+            session_key = self._get_session_key(new_session_id)
             serialized_data = pickle.dumps(session_data)
-            
-            # Store in Redis
-            session_key = self._get_session_key(session_id)
             self.redis_client.setex(session_key, self.session_timeout, serialized_data)
             
-            # Initialize stop signal as False
-            stop_key = self._get_stop_signal_key(session_id)
+            # Update user -> session mapping
+            user_session_key = self._get_user_session_key(user_fingerprint)
+            self.redis_client.setex(user_session_key, self.session_timeout, new_session_id.encode('utf-8'))
+            
+            # Initialize stop signal
+            stop_key = self._get_stop_signal_key(new_session_id)
             self.redis_client.setex(stop_key, self.session_timeout, b'0')
             
-            print(f"Session {session_id} stored in Redis with stop signal initialized")
-            return session_id
+            print(f"Created new session {new_session_id} for user {user_fingerprint}")
+            return new_session_id
             
         except Exception as e:
-            print(f"ERROR: Failed to create session {session_id}: {e}")
+            print(f"ERROR: Failed to create session for user {user_fingerprint}: {e}")
             raise
 
+    def _get_user_current_session(self, user_fingerprint: str) -> Optional[str]:
+        """Get current session ID for a user."""
+        try:
+            user_session_key = self._get_user_session_key(user_fingerprint)
+            session_id_bytes = self.redis_client.get(user_session_key)
+            if session_id_bytes:
+                return session_id_bytes.decode('utf-8')
+            return None
+        except Exception as e:
+            print(f"Error getting user session: {e}")
+            return None
+
     def set_stop_signal(self, session_id: str) -> bool:
-        """
-        Set the stop signal for a session (cross-process safe).
-        
-        Args:
-            session_id: Session identifier
-            
-        Returns:
-            bool: True if signal was set successfully
-        """
+        """Set stop signal for session (cross-process safe)."""
         try:
             stop_key = self._get_stop_signal_key(session_id)
-            # Set stop signal to '1' with the same TTL as the session
             self.redis_client.setex(stop_key, self.session_timeout, b'1')
             print(f"Stop signal set for session {session_id}")
             return True
@@ -126,15 +279,7 @@ class SessionManager:
             return False
 
     def is_stop_requested(self, session_id: str) -> bool:
-        """
-        Check if stop is requested for a session (cross-process safe).
-        
-        Args:
-            session_id: Session identifier
-            
-        Returns:
-            bool: True if stop is requested
-        """
+        """Check if stop is requested for session (cross-process safe)."""
         try:
             stop_key = self._get_stop_signal_key(session_id)
             value = self.redis_client.get(stop_key)
@@ -144,15 +289,7 @@ class SessionManager:
             return False
 
     def clear_stop_signal(self, session_id: str) -> bool:
-        """
-        Clear the stop signal for a session.
-        
-        Args:
-            session_id: Session identifier
-            
-        Returns:
-            bool: True if signal was cleared successfully
-        """
+        """Clear stop signal for session."""
         try:
             stop_key = self._get_stop_signal_key(session_id)
             self.redis_client.setex(stop_key, self.session_timeout, b'0')
@@ -163,13 +300,13 @@ class SessionManager:
             return False
 
     def _get_session_data(self, session_id: str) -> Optional[Dict[str, Any]]:
-        """Retrieves and deserializes session data from Redis."""
+        """Retrieve and deserialize session data from Redis."""
         try:
             session_key = self._get_session_key(session_id)
             serialized_data = self.redis_client.get(session_key)
             if serialized_data:
                 session_data = pickle.loads(serialized_data)
-                # Ensure the scanner has the correct session ID for stop signal checking
+                # Ensure scanner has correct session ID
                 if 'scanner' in session_data and session_data['scanner']:
                     session_data['scanner'].session_id = session_id
                 return session_data
@@ -179,37 +316,32 @@ class SessionManager:
             return None
 
     def _save_session_data(self, session_id: str, session_data: Dict[str, Any]) -> bool:
-        """
-        Serializes and saves session data back to Redis with updated TTL.
-        
-        Returns:
-            bool: True if save was successful
-        """
+        """Serialize and save session data to Redis with updated TTL."""
         try:
             session_key = self._get_session_key(session_id)
             serialized_data = pickle.dumps(session_data)
             result = self.redis_client.setex(session_key, self.session_timeout, serialized_data)
+            
+            # Also refresh user mapping TTL if available
+            if 'user_fingerprint' in session_data:
+                user_session_key = self._get_user_session_key(session_data['user_fingerprint'])
+                self.redis_client.setex(user_session_key, self.session_timeout, session_id.encode('utf-8'))
+                
             return result
         except Exception as e:
             print(f"ERROR: Failed to save session data for {session_id}: {e}")
             return False
 
     def update_session_scanner(self, session_id: str, scanner: 'Scanner') -> bool:
-        """
-        Updates just the scanner object in a session with immediate persistence.
-        
-        Returns:
-            bool: True if update was successful
-        """
+        """Update scanner object in session with immediate persistence."""
         try:
             session_data = self._get_session_data(session_id)
             if session_data:
-                # Ensure scanner has the session ID
+                # Ensure scanner has session ID
                 scanner.session_id = session_id
                 session_data['scanner'] = scanner
                 session_data['last_activity'] = time.time()
                 
-                # Immediately save to Redis for GUI updates
                 success = self._save_session_data(session_id, session_data)
                 if success:
                     print(f"Scanner state updated for session {session_id} (status: {scanner.status})")
@@ -224,16 +356,7 @@ class SessionManager:
             return False
 
     def update_scanner_status(self, session_id: str, status: str) -> bool:
-        """
-        Quickly update just the scanner status for immediate GUI feedback.
-        
-        Args:
-            session_id: Session identifier
-            status: New scanner status
-            
-        Returns:
-            bool: True if update was successful
-        """
+        """Quickly update scanner status for immediate GUI feedback."""
         try:
             session_data = self._get_session_data(session_id)
             if session_data and 'scanner' in session_data:
@@ -252,9 +375,7 @@ class SessionManager:
             return False
 
     def get_session(self, session_id: str) -> Optional[Scanner]:
-        """
-        Get scanner instance for a session from Redis with session ID management.
-        """
+        """Get scanner instance for session with session ID management."""
         if not session_id:
             return None
             
@@ -269,21 +390,13 @@ class SessionManager:
         
         scanner = session_data.get('scanner')
         if scanner:
-            # Ensure the scanner can check the Redis-based stop signal
+            # Ensure scanner can check Redis-based stop signal
             scanner.session_id = session_id
         
         return scanner
 
     def get_session_status_only(self, session_id: str) -> Optional[str]:
-        """
-        Get just the scanner status without full session retrieval (for performance).
-        
-        Args:
-            session_id: Session identifier
-            
-        Returns:
-            Scanner status string or None if not found
-        """
+        """Get scanner status without full session retrieval (for performance)."""
         try:
             session_data = self._get_session_data(session_id)
             if session_data and 'scanner' in session_data:
@@ -294,16 +407,18 @@ class SessionManager:
             return None
 
     def terminate_session(self, session_id: str) -> bool:
-        """
-        Terminate a specific session in Redis with reliable stop signal and immediate status update.
-        """
+        """Terminate specific session with reliable stop signal and immediate status update."""
+        return self._terminate_session_internal(session_id, cleanup_user_mapping=True)
+
+    def _terminate_session_internal(self, session_id: str, cleanup_user_mapping: bool = True) -> bool:
+        """Internal session termination with configurable user mapping cleanup."""
         print(f"=== TERMINATING SESSION {session_id} ===")
         
         try:
-            # First, set the stop signal
+            # Set stop signal first
             self.set_stop_signal(session_id)
             
-            # Update scanner status to stopped immediately for GUI feedback
+            # Update scanner status immediately for GUI feedback
             self.update_scanner_status(session_id, 'stopped')
             
             session_data = self._get_session_data(session_id)
@@ -314,16 +429,19 @@ class SessionManager:
             scanner = session_data.get('scanner')
             if scanner and scanner.status == 'running':
                 print(f"Stopping scan for session: {session_id}")
-                # The scanner will check the Redis stop signal
                 scanner.stop_scan()
-                
-                # Update the scanner state immediately
                 self.update_session_scanner(session_id, scanner)
             
-            # Wait a moment for graceful shutdown
+            # Wait for graceful shutdown
             time.sleep(0.5)
             
-            # Delete session data and stop signal from Redis
+            # Clean up user mapping if requested
+            if cleanup_user_mapping and 'user_fingerprint' in session_data:
+                user_session_key = self._get_user_session_key(session_data['user_fingerprint'])
+                self.redis_client.delete(user_session_key)
+                print(f"Cleaned up user mapping for {session_data['user_fingerprint']}")
+            
+            # Delete session data and stop signal
             session_key = self._get_session_key(session_id)
             stop_key = self._get_stop_signal_key(session_id)
             self.redis_client.delete(session_key)
@@ -337,35 +455,72 @@ class SessionManager:
             return False
 
     def _cleanup_loop(self) -> None:
-        """
-        Background thread to cleanup inactive sessions and orphaned stop signals.
-        """
+        """Background thread to cleanup inactive sessions and orphaned signals."""
         while True:
             try:
                 # Clean up orphaned stop signals
                 stop_keys = self.redis_client.keys("dnsrecon:stop:*")
                 for stop_key in stop_keys:
-                    # Extract session ID from stop key
                     session_id = stop_key.decode('utf-8').split(':')[-1]
                     session_key = self._get_session_key(session_id)
                     
-                    # If session doesn't exist but stop signal does, clean it up
                     if not self.redis_client.exists(session_key):
                         self.redis_client.delete(stop_key)
                         print(f"Cleaned up orphaned stop signal for session {session_id}")
+                
+                # Clean up orphaned user mappings
+                user_keys = self.redis_client.keys("dnsrecon:user:*")
+                for user_key in user_keys:
+                    session_id_bytes = self.redis_client.get(user_key)
+                    if session_id_bytes:
+                        session_id = session_id_bytes.decode('utf-8')
+                        session_key = self._get_session_key(session_id)
+                        
+                        if not self.redis_client.exists(session_key):
+                            self.redis_client.delete(user_key)
+                            print(f"Cleaned up orphaned user mapping for session {session_id}")
                         
             except Exception as e:
                 print(f"Error in cleanup loop: {e}")
             
             time.sleep(300)  # Sleep for 5 minutes
 
+    def list_active_sessions(self) -> List[Dict[str, Any]]:
+        """List all active sessions for admin purposes."""
+        try:
+            session_keys = self.redis_client.keys("dnsrecon:session:*")
+            sessions = []
+            
+            for session_key in session_keys:
+                session_id = session_key.decode('utf-8').split(':')[-1]
+                session_data = self._get_session_data(session_id)
+                
+                if session_data:
+                    scanner = session_data.get('scanner')
+                    sessions.append({
+                        'session_id': session_id,
+                        'user_fingerprint': session_data.get('user_fingerprint', 'unknown'),
+                        'client_ip': session_data.get('client_ip', 'unknown'),
+                        'created_at': session_data.get('created_at'),
+                        'last_activity': session_data.get('last_activity'),
+                        'scanner_status': scanner.status if scanner else 'unknown',
+                        'current_target': scanner.current_target if scanner else None
+                    })
+            
+            return sessions
+        except Exception as e:
+            print(f"ERROR: Failed to list active sessions: {e}")
+            return []
+
     def get_statistics(self) -> Dict[str, Any]:
         """Get session manager statistics."""
         try:
             session_keys = self.redis_client.keys("dnsrecon:session:*")
+            user_keys = self.redis_client.keys("dnsrecon:user:*")
             stop_keys = self.redis_client.keys("dnsrecon:stop:*")
             
             active_sessions = len(session_keys)
+            unique_users = len(user_keys)
             running_scans = 0
             
             for session_key in session_keys:
@@ -376,16 +531,46 @@ class SessionManager:
             
             return {
                 'total_active_sessions': active_sessions,
+                'unique_users': unique_users,
                 'running_scans': running_scans,
-                'total_stop_signals': len(stop_keys)
+                'total_stop_signals': len(stop_keys),
+                'average_sessions_per_user': round(active_sessions / unique_users, 2) if unique_users > 0 else 0
             }
         except Exception as e:
             print(f"ERROR: Failed to get statistics: {e}")
             return {
                 'total_active_sessions': 0,
+                'unique_users': 0,
                 'running_scans': 0,
-                'total_stop_signals': 0
+                'total_stop_signals': 0,
+                'average_sessions_per_user': 0
             }
 
+    def get_session_info(self, session_id: str) -> Dict[str, Any]:
+        """Get detailed information about a specific session."""
+        try:
+            session_data = self._get_session_data(session_id)
+            if not session_data:
+                return {'error': 'Session not found'}
+            
+            scanner = session_data.get('scanner')
+            
+            return {
+                'session_id': session_id,
+                'user_fingerprint': session_data.get('user_fingerprint', 'unknown'),
+                'client_ip': session_data.get('client_ip', 'unknown'),
+                'user_agent': session_data.get('user_agent', 'unknown'),
+                'created_at': session_data.get('created_at'),
+                'last_activity': session_data.get('last_activity'),
+                'status': session_data.get('status'),
+                'scanner_status': scanner.status if scanner else 'unknown',
+                'current_target': scanner.current_target if scanner else None,
+                'session_age_minutes': round((time.time() - session_data.get('created_at', time.time())) / 60, 1)
+            }
+        except Exception as e:
+            print(f"ERROR: Failed to get session info for {session_id}: {e}")
+            return {'error': f'Failed to get session info: {str(e)}'}
+
+
 # Global session manager instance
 session_manager = SessionManager(session_timeout_minutes=60)

core/task_manager.py

@@ -0,0 +1,564 @@
+# dnsrecon/core/task_manager.py
+
+import threading
+import time
+import uuid
+from enum import Enum
+from dataclasses import dataclass, field
+from typing import Dict, List, Optional, Any, Set
+from datetime import datetime, timezone, timedelta
+from collections import deque
+
+from utils.helpers import _is_valid_ip, _is_valid_domain
+
+
+class TaskStatus(Enum):
+    """Enumeration of task execution statuses."""
+    PENDING = "pending"
+    RUNNING = "running"
+    SUCCEEDED = "succeeded"
+    FAILED_RETRYING = "failed_retrying"
+    FAILED_PERMANENT = "failed_permanent"
+    CANCELLED = "cancelled"
+
+
+class TaskType(Enum):
+    """Enumeration of task types for provider queries."""
+    DOMAIN_QUERY = "domain_query"
+    IP_QUERY = "ip_query"
+    GRAPH_UPDATE = "graph_update"
+
+
+@dataclass
+class TaskResult:
+    """Result of a task execution."""
+    success: bool
+    data: Optional[Any] = None
+    error: Optional[str] = None
+    metadata: Dict[str, Any] = field(default_factory=dict)
+
+
+@dataclass
+class ReconTask:
+    """Represents a single reconnaissance task with retry logic."""
+    task_id: str
+    task_type: TaskType
+    target: str
+    provider_name: str
+    depth: int
+    status: TaskStatus = TaskStatus.PENDING
+    created_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    
+    # Retry configuration
+    max_retries: int = 3
+    current_retry: int = 0
+    base_backoff_seconds: float = 1.0
+    max_backoff_seconds: float = 60.0
+    
+    # Execution tracking
+    last_attempt_at: Optional[datetime] = None
+    next_retry_at: Optional[datetime] = None
+    execution_history: List[Dict[str, Any]] = field(default_factory=list)
+    
+    # Results
+    result: Optional[TaskResult] = None
+    
+    def __post_init__(self):
+        """Initialize additional fields after creation."""
+        if not self.task_id:
+            self.task_id = str(uuid.uuid4())[:8]
+    
+    def calculate_next_retry_time(self) -> datetime:
+        """Calculate next retry time with exponential backoff and jitter."""
+        if self.current_retry >= self.max_retries:
+            return None
+        
+        # Exponential backoff with jitter
+        backoff_time = min(
+            self.max_backoff_seconds,
+            self.base_backoff_seconds * (2 ** self.current_retry)
+        )
+        
+        # Add jitter (±25%)
+        jitter = backoff_time * 0.25 * (0.5 - hash(self.task_id) % 1000 / 1000.0)
+        final_backoff = max(self.base_backoff_seconds, backoff_time + jitter)
+        
+        return datetime.now(timezone.utc) + timedelta(seconds=final_backoff)
+    
+    def should_retry(self) -> bool:
+        """Determine if task should be retried based on status and retry count."""
+        if self.status != TaskStatus.FAILED_RETRYING:
+            return False
+        if self.current_retry >= self.max_retries:
+            return False
+        if self.next_retry_at and datetime.now(timezone.utc) < self.next_retry_at:
+            return False
+        return True
+    
+    def mark_failed(self, error: str, metadata: Dict[str, Any] = None):
+        """Mark task as failed and prepare for retry or permanent failure."""
+        self.current_retry += 1
+        self.last_attempt_at = datetime.now(timezone.utc)
+        
+        # Record execution history
+        execution_record = {
+            'attempt': self.current_retry,
+            'timestamp': self.last_attempt_at.isoformat(),
+            'error': error,
+            'metadata': metadata or {}
+        }
+        self.execution_history.append(execution_record)
+        
+        if self.current_retry >= self.max_retries:
+            self.status = TaskStatus.FAILED_PERMANENT
+            self.result = TaskResult(success=False, error=f"Permanent failure after {self.max_retries} attempts: {error}")
+        else:
+            self.status = TaskStatus.FAILED_RETRYING
+            self.next_retry_at = self.calculate_next_retry_time()
+    
+    def mark_succeeded(self, data: Any = None, metadata: Dict[str, Any] = None):
+        """Mark task as successfully completed."""
+        self.status = TaskStatus.SUCCEEDED
+        self.last_attempt_at = datetime.now(timezone.utc)
+        self.result = TaskResult(success=True, data=data, metadata=metadata or {})
+        
+        # Record successful execution
+        execution_record = {
+            'attempt': self.current_retry + 1,
+            'timestamp': self.last_attempt_at.isoformat(),
+            'success': True,
+            'metadata': metadata or {}
+        }
+        self.execution_history.append(execution_record)
+    
+    def get_summary(self) -> Dict[str, Any]:
+        """Get task summary for progress reporting."""
+        return {
+            'task_id': self.task_id,
+            'task_type': self.task_type.value,
+            'target': self.target,
+            'provider': self.provider_name,
+            'status': self.status.value,
+            'current_retry': self.current_retry,
+            'max_retries': self.max_retries,
+            'created_at': self.created_at.isoformat(),
+            'last_attempt_at': self.last_attempt_at.isoformat() if self.last_attempt_at else None,
+            'next_retry_at': self.next_retry_at.isoformat() if self.next_retry_at else None,
+            'total_attempts': len(self.execution_history),
+            'has_result': self.result is not None
+        }
+
+
+class TaskQueue:
+    """Thread-safe task queue with retry logic and priority handling."""
+    
+    def __init__(self, max_concurrent_tasks: int = 5):
+        """Initialize task queue."""
+        self.max_concurrent_tasks = max_concurrent_tasks
+        self.tasks: Dict[str, ReconTask] = {}
+        self.pending_queue = deque()
+        self.retry_queue = deque()
+        self.running_tasks: Set[str] = set()
+        
+        self._lock = threading.Lock()
+        self._stop_event = threading.Event()
+    
+    def __getstate__(self):
+        """Prepare TaskQueue for pickling by excluding unpicklable objects."""
+        state = self.__dict__.copy()
+        # Exclude the unpickleable '_lock' and '_stop_event' attributes
+        if '_lock' in state:
+            del state['_lock']
+        if '_stop_event' in state:
+            del state['_stop_event']
+        return state
+
+    def __setstate__(self, state):
+        """Restore TaskQueue after unpickling by reconstructing threading objects."""
+        self.__dict__.update(state)
+        # Re-initialize the '_lock' and '_stop_event' attributes
+        self._lock = threading.Lock()
+        self._stop_event = threading.Event()
+    
+    def add_task(self, task: ReconTask) -> str:
+        """Add task to queue."""
+        with self._lock:
+            self.tasks[task.task_id] = task
+            self.pending_queue.append(task.task_id)
+            print(f"Added task {task.task_id}: {task.provider_name} query for {task.target}")
+            return task.task_id
+    
+    def get_next_ready_task(self) -> Optional[ReconTask]:
+        """Get next task ready for execution."""
+        with self._lock:
+            # Check if we have room for more concurrent tasks
+            if len(self.running_tasks) >= self.max_concurrent_tasks:
+                return None
+            
+            # First priority: retry queue (tasks ready for retry)
+            while self.retry_queue:
+                task_id = self.retry_queue.popleft()
+                if task_id in self.tasks:
+                    task = self.tasks[task_id]
+                    if task.should_retry():
+                        task.status = TaskStatus.RUNNING
+                        self.running_tasks.add(task_id)
+                        print(f"Retrying task {task_id} (attempt {task.current_retry + 1})")
+                        return task
+            
+            # Second priority: pending queue (new tasks)
+            while self.pending_queue:
+                task_id = self.pending_queue.popleft()
+                if task_id in self.tasks:
+                    task = self.tasks[task_id]
+                    if task.status == TaskStatus.PENDING:
+                        task.status = TaskStatus.RUNNING
+                        self.running_tasks.add(task_id)
+                        print(f"Starting task {task_id}")
+                        return task
+            
+            return None
+    
+    def complete_task(self, task_id: str, success: bool, data: Any = None, 
+                     error: str = None, metadata: Dict[str, Any] = None):
+        """Mark task as completed (success or failure)."""
+        with self._lock:
+            if task_id not in self.tasks:
+                return
+            
+            task = self.tasks[task_id]
+            self.running_tasks.discard(task_id)
+            
+            if success:
+                task.mark_succeeded(data=data, metadata=metadata)
+                print(f"Task {task_id} succeeded")
+            else:
+                task.mark_failed(error or "Unknown error", metadata=metadata)
+                if task.status == TaskStatus.FAILED_RETRYING:
+                    self.retry_queue.append(task_id)
+                    print(f"Task {task_id} failed, scheduled for retry at {task.next_retry_at}")
+                else:
+                    print(f"Task {task_id} permanently failed after {task.current_retry} attempts")
+    
+    def cancel_all_tasks(self):
+        """Cancel all pending and running tasks."""
+        with self._lock:
+            self._stop_event.set()
+            for task in self.tasks.values():
+                if task.status in [TaskStatus.PENDING, TaskStatus.RUNNING, TaskStatus.FAILED_RETRYING]:
+                    task.status = TaskStatus.CANCELLED
+            self.pending_queue.clear()
+            self.retry_queue.clear()
+            self.running_tasks.clear()
+            print("All tasks cancelled")
+    
+    def is_complete(self) -> bool:
+        """Check if all tasks are complete (succeeded, permanently failed, or cancelled)."""
+        with self._lock:
+            for task in self.tasks.values():
+                if task.status in [TaskStatus.PENDING, TaskStatus.RUNNING, TaskStatus.FAILED_RETRYING]:
+                    return False
+            return True
+    
+    def get_statistics(self) -> Dict[str, Any]:
+        """Get queue statistics."""
+        with self._lock:
+            stats = {
+                'total_tasks': len(self.tasks),
+                'pending': len(self.pending_queue),
+                'running': len(self.running_tasks),
+                'retry_queue': len(self.retry_queue),
+                'succeeded': 0,
+                'failed_permanent': 0,
+                'cancelled': 0,
+                'failed_retrying': 0
+            }
+            
+            for task in self.tasks.values():
+                if task.status == TaskStatus.SUCCEEDED:
+                    stats['succeeded'] += 1
+                elif task.status == TaskStatus.FAILED_PERMANENT:
+                    stats['failed_permanent'] += 1
+                elif task.status == TaskStatus.CANCELLED:
+                    stats['cancelled'] += 1
+                elif task.status == TaskStatus.FAILED_RETRYING:
+                    stats['failed_retrying'] += 1
+            
+            stats['completion_rate'] = (stats['succeeded'] / stats['total_tasks'] * 100) if stats['total_tasks'] > 0 else 0
+            stats['is_complete'] = self.is_complete()
+            
+            return stats
+    
+    def get_task_summaries(self) -> List[Dict[str, Any]]:
+        """Get summaries of all tasks for detailed progress reporting."""
+        with self._lock:
+            return [task.get_summary() for task in self.tasks.values()]
+    
+    def get_failed_tasks(self) -> List[ReconTask]:
+        """Get all permanently failed tasks for analysis."""
+        with self._lock:
+            return [task for task in self.tasks.values() if task.status == TaskStatus.FAILED_PERMANENT]
+
+
+class TaskExecutor:
+    """Executes reconnaissance tasks using providers."""
+    
+    def __init__(self, providers: List, graph_manager, logger):
+        """Initialize task executor."""
+        self.providers = {provider.get_name(): provider for provider in providers}
+        self.graph = graph_manager
+        self.logger = logger
+    
+    def execute_task(self, task: ReconTask) -> TaskResult:
+        """
+        Execute a single reconnaissance task.
+        
+        Args:
+            task: Task to execute
+            
+        Returns:
+            TaskResult with success/failure information
+        """
+        try:
+            print(f"Executing task {task.task_id}: {task.provider_name} query for {task.target}")
+            
+            provider = self.providers.get(task.provider_name)
+            if not provider:
+                return TaskResult(
+                    success=False, 
+                    error=f"Provider {task.provider_name} not available"
+                )
+            
+            if not provider.is_available():
+                return TaskResult(
+                    success=False,
+                    error=f"Provider {task.provider_name} is not available (missing API key or configuration)"
+                )
+            
+            # Execute provider query based on task type
+            if task.task_type == TaskType.DOMAIN_QUERY:
+                if not _is_valid_domain(task.target):
+                    return TaskResult(success=False, error=f"Invalid domain: {task.target}")
+                    
+                relationships = provider.query_domain(task.target)
+                
+            elif task.task_type == TaskType.IP_QUERY:
+                if not _is_valid_ip(task.target):
+                    return TaskResult(success=False, error=f"Invalid IP: {task.target}")
+                    
+                relationships = provider.query_ip(task.target)
+                
+            else:
+                return TaskResult(success=False, error=f"Unsupported task type: {task.task_type}")
+            
+            # Process results and update graph
+            new_targets = set()
+            relationships_added = 0
+            
+            for source, target, rel_type, confidence, raw_data in relationships:
+                # Add nodes to graph
+                from core.graph_manager import NodeType
+                
+                if _is_valid_ip(target):
+                    self.graph.add_node(target, NodeType.IP)
+                    new_targets.add(target)
+                elif target.startswith('AS') and target[2:].isdigit():
+                    self.graph.add_node(target, NodeType.ASN)
+                elif _is_valid_domain(target):
+                    self.graph.add_node(target, NodeType.DOMAIN)
+                    new_targets.add(target)
+                
+                # Add edge to graph
+                if self.graph.add_edge(source, target, rel_type, confidence, task.provider_name, raw_data):
+                    relationships_added += 1
+            
+            # Log forensic information
+            self.logger.logger.info(
+                f"Task {task.task_id} completed: {len(relationships)} relationships found, "
+                f"{relationships_added} added to graph, {len(new_targets)} new targets"
+            )
+            
+            return TaskResult(
+                success=True,
+                data={
+                    'relationships': relationships,
+                    'new_targets': list(new_targets),
+                    'relationships_added': relationships_added
+                },
+                metadata={
+                    'provider': task.provider_name,
+                    'target': task.target,
+                    'depth': task.depth,
+                    'execution_time': datetime.now(timezone.utc).isoformat()
+                }
+            )
+            
+        except Exception as e:
+            error_msg = f"Task execution failed: {str(e)}"
+            print(f"ERROR: {error_msg} for task {task.task_id}")
+            self.logger.logger.error(error_msg)
+            
+            return TaskResult(
+                success=False,
+                error=error_msg,
+                metadata={
+                    'provider': task.provider_name,
+                    'target': task.target,
+                    'exception_type': type(e).__name__
+                }
+            )
+
+
+class TaskManager:
+    """High-level task management for reconnaissance scans."""
+    
+    def __init__(self, providers: List, graph_manager, logger, max_concurrent_tasks: int = 5):
+        """Initialize task manager."""
+        self.task_queue = TaskQueue(max_concurrent_tasks)
+        self.task_executor = TaskExecutor(providers, graph_manager, logger)
+        self.logger = logger
+        
+        # Execution control
+        self._stop_event = threading.Event()
+        self._execution_threads: List[threading.Thread] = []
+        self._is_running = False
+    
+    def create_provider_tasks(self, target: str, depth: int, providers: List) -> List[str]:
+        """
+        Create tasks for querying all eligible providers for a target.
+        
+        Args:
+            target: Domain or IP to query
+            depth: Current recursion depth
+            providers: List of available providers
+            
+        Returns:
+            List of created task IDs
+        """
+        task_ids = []
+        is_ip = _is_valid_ip(target)
+        target_key = 'ips' if is_ip else 'domains'
+        task_type = TaskType.IP_QUERY if is_ip else TaskType.DOMAIN_QUERY
+        
+        for provider in providers:
+            if provider.get_eligibility().get(target_key) and provider.is_available():
+                task = ReconTask(
+                    task_id=str(uuid.uuid4())[:8],
+                    task_type=task_type,
+                    target=target,
+                    provider_name=provider.get_name(),
+                    depth=depth,
+                    max_retries=3  # Configure retries per task type/provider
+                )
+                
+                task_id = self.task_queue.add_task(task)
+                task_ids.append(task_id)
+        
+        return task_ids
+    
+    def start_execution(self, max_workers: int = 3):
+        """Start task execution with specified number of worker threads."""
+        if self._is_running:
+            print("Task execution already running")
+            return
+        
+        self._is_running = True
+        self._stop_event.clear()
+        
+        print(f"Starting task execution with {max_workers} workers")
+        
+        for i in range(max_workers):
+            worker_thread = threading.Thread(
+                target=self._worker_loop,
+                name=f"TaskWorker-{i+1}",
+                daemon=True
+            )
+            worker_thread.start()
+            self._execution_threads.append(worker_thread)
+    
+    def stop_execution(self):
+        """Stop task execution and cancel all tasks."""
+        print("Stopping task execution")
+        self._stop_event.set()
+        self.task_queue.cancel_all_tasks()
+        self._is_running = False
+        
+        # Wait for worker threads to finish
+        for thread in self._execution_threads:
+            thread.join(timeout=5.0)
+        
+        self._execution_threads.clear()
+        print("Task execution stopped")
+    
+    def _worker_loop(self):
+        """Worker thread loop for executing tasks."""
+        thread_name = threading.current_thread().name
+        print(f"{thread_name} started")
+        
+        while not self._stop_event.is_set():
+            try:
+                # Get next task to execute
+                task = self.task_queue.get_next_ready_task()
+                
+                if task is None:
+                    # No tasks ready, check if we should exit
+                    if self.task_queue.is_complete() or self._stop_event.is_set():
+                        break
+                    time.sleep(0.1)  # Brief sleep before checking again
+                    continue
+                
+                # Execute the task
+                result = self.task_executor.execute_task(task)
+                
+                # Complete the task in queue
+                self.task_queue.complete_task(
+                    task.task_id,
+                    success=result.success,
+                    data=result.data,
+                    error=result.error,
+                    metadata=result.metadata
+                )
+                
+            except Exception as e:
+                print(f"ERROR: Worker {thread_name} encountered error: {e}")
+                # Continue running even if individual task fails
+                continue
+        
+        print(f"{thread_name} finished")
+    
+    def wait_for_completion(self, timeout_seconds: int = 300) -> bool:
+        """
+        Wait for all tasks to complete.
+        
+        Args:
+            timeout_seconds: Maximum time to wait
+            
+        Returns:
+            True if all tasks completed, False if timeout
+        """
+        start_time = time.time()
+        
+        while time.time() - start_time < timeout_seconds:
+            if self.task_queue.is_complete():
+                return True
+            
+            if self._stop_event.is_set():
+                return False
+            
+            time.sleep(1.0)  # Check every second
+        
+        print(f"Timeout waiting for task completion after {timeout_seconds} seconds")
+        return False
+    
+    def get_progress_report(self) -> Dict[str, Any]:
+        """Get detailed progress report for UI updates."""
+        stats = self.task_queue.get_statistics()
+        failed_tasks = self.task_queue.get_failed_tasks()
+        
+        return {
+            'statistics': stats,
+            'failed_tasks': [task.get_summary() for task in failed_tasks],
+            'is_running': self._is_running,
+            'worker_count': len(self._execution_threads),
+            'detailed_tasks': self.task_queue.get_task_summaries() if stats['total_tasks'] < 50 else []  # Limit detail for performance
+        }

providers/base_provider.py

@@ -3,14 +3,18 @@
 import time
 import requests
 import threading
+import os
+import json
+import hashlib
 from abc import ABC, abstractmethod
 from typing import List, Dict, Any, Optional, Tuple
+from datetime import datetime, timezone
 
 from core.logger import get_forensic_logger
 
 
 class RateLimiter:
-    """Simple rate limiter for API calls."""
+    """Thread-safe rate limiter for API calls."""
 
     def __init__(self, requests_per_minute: int):
         """
@@ -22,36 +26,152 @@ class RateLimiter:
         self.requests_per_minute = requests_per_minute
         self.min_interval = 60.0 / requests_per_minute
         self.last_request_time = 0
+        self._lock = threading.Lock()
 
     def __getstate__(self):
         """RateLimiter is fully picklable, return full state."""
-        return self.__dict__.copy()
+        state = self.__dict__.copy()
+        # Exclude unpickleable lock
+        if '_lock' in state:
+            del state['_lock']
+        return state
 
     def __setstate__(self, state):
         """Restore RateLimiter state."""
         self.__dict__.update(state)
+        self._lock = threading.Lock()
 
     def wait_if_needed(self) -> None:
         """Wait if necessary to respect rate limits."""
-        current_time = time.time()
-        time_since_last = current_time - self.last_request_time
+        with self._lock:
+            current_time = time.time()
+            time_since_last = current_time - self.last_request_time
 
-        if time_since_last < self.min_interval:
-            sleep_time = self.min_interval - time_since_last
-            time.sleep(sleep_time)
+            if time_since_last < self.min_interval:
+                sleep_time = self.min_interval - time_since_last
+                time.sleep(sleep_time)
 
-        self.last_request_time = time.time()
+            self.last_request_time = time.time()
+
+
+class ProviderCache:
+    """Thread-safe global cache for provider queries."""
+    
+    def __init__(self, provider_name: str, cache_expiry_hours: int = 12):
+        """
+        Initialize provider-specific cache.
+        
+        Args:
+            provider_name: Name of the provider for cache directory
+            cache_expiry_hours: Cache expiry time in hours
+        """
+        self.provider_name = provider_name
+        self.cache_expiry = cache_expiry_hours * 3600  # Convert to seconds
+        self.cache_dir = os.path.join('.cache', provider_name)
+        self._lock = threading.Lock()
+        
+        # Ensure cache directory exists with thread-safe creation
+        os.makedirs(self.cache_dir, exist_ok=True)
+        
+    def _generate_cache_key(self, method: str, url: str, params: Optional[Dict[str, Any]]) -> str:
+        """Generate unique cache key for request."""
+        cache_data = f"{method}:{url}:{json.dumps(params or {}, sort_keys=True)}"
+        return hashlib.md5(cache_data.encode()).hexdigest() + ".json"
+    
+    def get_cached_response(self, method: str, url: str, params: Optional[Dict[str, Any]]) -> Optional[requests.Response]:
+        """
+        Retrieve cached response if available and not expired.
+        
+        Returns:
+            Cached Response object or None if cache miss/expired
+        """
+        cache_key = self._generate_cache_key(method, url, params)
+        cache_path = os.path.join(self.cache_dir, cache_key)
+        
+        with self._lock:
+            if not os.path.exists(cache_path):
+                return None
+                
+            # Check if cache is expired
+            cache_age = time.time() - os.path.getmtime(cache_path)
+            if cache_age >= self.cache_expiry:
+                try:
+                    os.remove(cache_path)
+                except OSError:
+                    pass  # File might have been removed by another thread
+                return None
+            
+            try:
+                with open(cache_path, 'r', encoding='utf-8') as f:
+                    cached_data = json.load(f)
+                    
+                # Reconstruct Response object
+                response = requests.Response()
+                response.status_code = cached_data['status_code']
+                response._content = cached_data['content'].encode('utf-8')
+                response.headers.update(cached_data['headers'])
+                
+                return response
+                
+            except (json.JSONDecodeError, KeyError, IOError) as e:
+                # Cache file corrupted, remove it
+                try:
+                    os.remove(cache_path)
+                except OSError:
+                    pass
+                return None
+    
+    def cache_response(self, method: str, url: str, params: Optional[Dict[str, Any]], 
+                      response: requests.Response) -> bool:
+        """
+        Cache successful response to disk.
+        
+        Returns:
+            True if cached successfully, False otherwise
+        """
+        if response.status_code != 200:
+            return False
+            
+        cache_key = self._generate_cache_key(method, url, params)
+        cache_path = os.path.join(self.cache_dir, cache_key)
+        
+        with self._lock:
+            try:
+                cache_data = {
+                    'status_code': response.status_code,
+                    'content': response.text,
+                    'headers': dict(response.headers),
+                    'cached_at': datetime.now(timezone.utc).isoformat()
+                }
+                
+                # Write to temporary file first, then rename for atomic operation
+                temp_path = cache_path + '.tmp'
+                with open(temp_path, 'w', encoding='utf-8') as f:
+                    json.dump(cache_data, f)
+                
+                # Atomic rename to prevent partial cache files
+                os.rename(temp_path, cache_path)
+                return True
+                
+            except (IOError, OSError) as e:
+                # Clean up temp file if it exists
+                try:
+                    if os.path.exists(temp_path):
+                        os.remove(temp_path)
+                except OSError:
+                    pass
+                return False
 
 
 class BaseProvider(ABC):
     """
     Abstract base class for all DNSRecon data providers.
-    Now supports session-specific configuration.
+    Now supports global provider-specific caching and session-specific configuration.
     """
 
     def __init__(self, name: str, rate_limit: int = 60, timeout: int = 30, session_config=None):
         """
-        Initialize base provider with session-specific configuration.
+        Initialize base provider with global caching and session-specific configuration.
 
         Args:
             name: Provider name for logging
@@ -78,20 +198,25 @@ class BaseProvider(ABC):
         self.logger = get_forensic_logger()
         self._stop_event = None
 
+        # GLOBAL provider-specific caching (not session-based)
+        self.cache = ProviderCache(name, cache_expiry_hours=12)
+
         # Statistics (per provider instance)
         self.total_requests = 0
         self.successful_requests = 0
         self.failed_requests = 0
         self.total_relationships_found = 0
+        self.cache_hits = 0
+        self.cache_misses = 0
+
+        print(f"Initialized {name} provider with global cache and session config (rate: {actual_rate_limit}/min)")
 
     def __getstate__(self):
         """Prepare BaseProvider for pickling by excluding unpicklable objects."""
         state = self.__dict__.copy()
         # Exclude the unpickleable '_local' attribute and stop event
-        unpicklable_attrs = ['_local', '_stop_event']
-        for attr in unpicklable_attrs:
-            if attr in state:
-                del state[attr]
+        state['_local'] = None
+        state['_stop_event'] = None
         return state
 
     def __setstate__(self, state):
@@ -106,7 +231,7 @@ class BaseProvider(ABC):
         if not hasattr(self._local, 'session'):
             self._local.session = requests.Session()
             self._local.session.headers.update({
-                'User-Agent': 'DNSRecon/1.0 (Passive Reconnaissance Tool)'
+                'User-Agent': 'DNSRecon/2.0 (Passive Reconnaissance Tool)'
             })
         return self._local.session
 
@@ -164,79 +289,153 @@ class BaseProvider(ABC):
     def make_request(self, url: str, method: str = "GET",
                     params: Optional[Dict[str, Any]] = None,
                     headers: Optional[Dict[str, str]] = None,
-                    target_indicator: str = "") -> Optional[requests.Response]:
+                    target_indicator: str = "",
+                    max_retries: int = 3) -> Optional[requests.Response]:
         """
-        Make a rate-limited HTTP request.
+        Make a rate-limited HTTP request with global caching and aggressive stop signal handling.
         """
+        # Check for cancellation before starting
         if self._is_stop_requested():
             print(f"Request cancelled before start: {url}")
             return None
 
-        self.rate_limiter.wait_if_needed()
+        # Check global cache first
+        cached_response = self.cache.get_cached_response(method, url, params)
+        if cached_response is not None:
+            print(f"Cache hit for {self.name}: {url}")
+            self.cache_hits += 1
+            return cached_response
+        
+        self.cache_misses += 1
 
-        start_time = time.time()
-        response = None
-        error = None
+        # Determine effective max_retries based on stop signal
+        effective_max_retries = 0 if self._is_stop_requested() else max_retries
+        last_exception = None
 
-        try:
-            self.total_requests += 1
+        for attempt in range(effective_max_retries + 1):
+            # Check for cancellation before each attempt
+            if self._is_stop_requested():
+                print(f"Request cancelled during attempt {attempt + 1}: {url}")
+                return None
 
-            request_headers = dict(self.session.headers).copy()
-            if headers:
-                request_headers.update(headers)
+            # Apply rate limiting with cancellation awareness
+            if not self._wait_with_cancellation_check():
+                print(f"Request cancelled during rate limiting: {url}")
+                return None
 
-            print(f"Making {method} request to: {url}")
+            # Final check before making HTTP request
+            if self._is_stop_requested():
+                print(f"Request cancelled before HTTP call: {url}")
+                return None
 
-            if method.upper() == "GET":
-                response = self.session.get(
-                    url,
-                    params=params,
-                    headers=request_headers,
-                    timeout=self.timeout
+            start_time = time.time()
+            response = None
+            error = None
+
+            try:
+                self.total_requests += 1
+
+                # Prepare request
+                request_headers = self.session.headers.copy()
+                if headers:
+                    request_headers.update(headers)
+
+                print(f"Making {method} request to: {url} (attempt {attempt + 1})")
+
+                # Use shorter timeout if termination is requested
+                request_timeout = 2 if self._is_stop_requested() else self.timeout
+
+                # Make request
+                if method.upper() == "GET":
+                    response = self.session.get(
+                        url,
+                        params=params,
+                        headers=request_headers,
+                        timeout=request_timeout
+                    )
+                elif method.upper() == "POST":
+                    response = self.session.post(
+                        url,
+                        json=params,
+                        headers=request_headers,
+                        timeout=request_timeout
+                    )
+                else:
+                    raise ValueError(f"Unsupported HTTP method: {method}")
+
+                print(f"Response status: {response.status_code}")
+                response.raise_for_status()
+                self.successful_requests += 1
+                
+                # Success - log, cache, and return
+                duration_ms = (time.time() - start_time) * 1000
+                self.logger.log_api_request(
+                    provider=self.name,
+                    url=url,
+                    method=method.upper(),
+                    status_code=response.status_code,
+                    response_size=len(response.content),
+                    duration_ms=duration_ms,
+                    error=None,
+                    target_indicator=target_indicator
                 )
-            elif method.upper() == "POST":
-                response = self.session.post(
-                    url,
-                    json=params,
-                    headers=request_headers,
-                    timeout=self.timeout
-                )
-            else:
-                raise ValueError(f"Unsupported HTTP method: {method}")
+                
+                # Cache the successful response globally
+                self.cache.cache_response(method, url, params, response)
+                return response
 
-            print(f"Response status: {response.status_code}")
-            response.raise_for_status()
-            self.successful_requests += 1
-            
-            duration_ms = (time.time() - start_time) * 1000
-            self.logger.log_api_request(
-                provider=self.name,
-                url=url,
-                method=method.upper(),
-                status_code=response.status_code,
-                response_size=len(response.content),
-                duration_ms=duration_ms,
-                error=None,
-                target_indicator=target_indicator
-            )
-            
-            return response
+            except requests.exceptions.RequestException as e:
+                error = str(e)
+                self.failed_requests += 1
+                print(f"Request failed (attempt {attempt + 1}): {error}")
+                last_exception = e
+                
+                # Immediately abort retries if stop requested
+                if self._is_stop_requested():
+                    print(f"Stop requested - aborting retries for: {url}")
+                    break
+                
+                # Check if we should retry
+                if attempt < effective_max_retries and self._should_retry(e):
+                    # Exponential backoff with jitter for 429 errors
+                    if isinstance(e, requests.exceptions.HTTPError) and e.response and e.response.status_code == 429:
+                        backoff_time = min(60, 10 * (2 ** attempt))
+                        print(f"Rate limit hit. Retrying in {backoff_time} seconds...")
+                    else:
+                        backoff_time = min(2.0, (2 ** attempt) * 0.5)
+                        print(f"Retrying in {backoff_time} seconds...")
+                    
+                    if not self._sleep_with_cancellation_check(backoff_time):
+                        print(f"Stop requested during backoff - aborting: {url}")
+                        return None
+                    continue
+                else:
+                    break
 
-        except requests.exceptions.RequestException as e:
-            error = str(e)
-            self.failed_requests += 1
-            duration_ms = (time.time() - start_time) * 1000
-            self.logger.log_api_request(
-                provider=self.name,
-                url=url,
-                method=method.upper(),
-                status_code=response.status_code if response else None,
-                response_size=len(response.content) if response else None,
-                duration_ms=duration_ms,
-                error=error,
-                target_indicator=target_indicator
-            )
-            raise e
+            except Exception as e:
+                error = f"Unexpected error: {str(e)}"
+                self.failed_requests += 1
+                print(f"Unexpected error: {error}")
+                last_exception = e
+                break
+
+        # All attempts failed - log and return None
+        duration_ms = (time.time() - start_time) * 1000
+        self.logger.log_api_request(
+            provider=self.name,
+            url=url,
+            method=method.upper(),
+            status_code=response.status_code if response else None,
+            response_size=len(response.content) if response else None,
+            duration_ms=duration_ms,
+            error=error,
+            target_indicator=target_indicator
+        )
+        
+        if error and last_exception:
+            raise last_exception
+        
+        return None
 
     def _is_stop_requested(self) -> bool:
         """
@@ -246,6 +445,43 @@ class BaseProvider(ABC):
             return True
         return False
 
+    def _wait_with_cancellation_check(self) -> bool:
+        """
+        Wait for rate limiting while aggressively checking for cancellation.
+        Returns False if cancelled during wait.
+        """
+        current_time = time.time()
+        time_since_last = current_time - self.rate_limiter.last_request_time
+
+        if time_since_last < self.rate_limiter.min_interval:
+            sleep_time = self.rate_limiter.min_interval - time_since_last
+            if not self._sleep_with_cancellation_check(sleep_time):
+                return False
+
+        self.rate_limiter.last_request_time = time.time()
+        return True
+
+    def _sleep_with_cancellation_check(self, sleep_time: float) -> bool:
+        """
+        Sleep for the specified time while aggressively checking for cancellation.
+        
+        Args:
+            sleep_time: Time to sleep in seconds
+            
+        Returns:
+            bool: True if sleep completed, False if cancelled
+        """
+        sleep_start = time.time()
+        check_interval = 0.05  # Check every 50ms for aggressive responsiveness
+        
+        while time.time() - sleep_start < sleep_time:
+            if self._is_stop_requested():
+                return False
+            remaining_time = sleep_time - (time.time() - sleep_start)
+            time.sleep(min(check_interval, remaining_time))
+        
+        return True
+
     def set_stop_event(self, stop_event: threading.Event) -> None:
         """
         Set the stop event for this provider to enable cancellation.
@@ -255,6 +491,28 @@ class BaseProvider(ABC):
         """
         self._stop_event = stop_event
 
+    def _should_retry(self, exception: requests.exceptions.RequestException) -> bool:
+        """
+        Determine if a request should be retried based on the exception.
+        
+        Args:
+            exception: The request exception that occurred
+            
+        Returns:
+            True if the request should be retried
+        """
+        # Retry on connection errors and timeouts
+        if isinstance(exception, (requests.exceptions.ConnectionError, 
+                                requests.exceptions.Timeout)):
+            return True
+        
+        if isinstance(exception, requests.exceptions.HTTPError):
+            if hasattr(exception, 'response') and exception.response:
+                # Retry on server errors (5xx) AND on rate-limiting errors (429)
+                return exception.response.status_code >= 500 or exception.response.status_code == 429
+        
+        return False
+
     def log_relationship_discovery(self, source_node: str, target_node: str,
                                  relationship_type: str,
                                  confidence_score: float,
@@ -285,7 +543,7 @@ class BaseProvider(ABC):
 
     def get_statistics(self) -> Dict[str, Any]:
         """
-        Get provider statistics.
+        Get provider statistics including cache performance.
 
         Returns:
             Dictionary containing provider performance metrics
@@ -297,5 +555,8 @@ class BaseProvider(ABC):
             'failed_requests': self.failed_requests,
             'success_rate': (self.successful_requests / self.total_requests * 100) if self.total_requests > 0 else 0,
             'relationships_found': self.total_relationships_found,
-            'rate_limit': self.rate_limiter.requests_per_minute
+            'rate_limit': self.rate_limiter.requests_per_minute,
+            'cache_hits': self.cache_hits,
+            'cache_misses': self.cache_misses,
+            'cache_hit_rate': (self.cache_hits / (self.cache_hits + self.cache_misses) * 100) if (self.cache_hits + self.cache_misses) > 0 else 0
         }

providers/crtsh_provider.py

@@ -1,9 +1,11 @@
-# dnsrecon/providers/crtsh_provider.py
+"""
+Certificate Transparency provider using crt.sh.
+Discovers domain relationships through certificate SAN analysis with comprehensive certificate tracking.
+Stores certificates as metadata on domain nodes rather than creating certificate nodes.
+"""
 
 import json
 import re
-import os
-from pathlib import Path
 from typing import List, Dict, Any, Tuple, Set
 from urllib.parse import quote
 from datetime import datetime, timezone
@@ -16,10 +18,10 @@ from utils.helpers import _is_valid_domain
 class CrtShProvider(BaseProvider):
     """
     Provider for querying crt.sh certificate transparency database.
-    Now uses session-specific configuration and caching with accumulative behavior.
+    Now uses session-specific configuration and caching.
     """
     
-    def __init__(self, name=None, session_config=None):
+    def __init__(self, session_config=None):
         """Initialize CrtSh provider with session-specific configuration."""
         super().__init__(
             name="crtsh",
@@ -29,10 +31,6 @@ class CrtShProvider(BaseProvider):
         )
         self.base_url = "https://crt.sh/"
         self._stop_event = None
-        
-        # Initialize cache directory
-        self.cache_dir = Path('cache') / 'crtsh'
-        self.cache_dir.mkdir(parents=True, exist_ok=True)
     
     def get_name(self) -> str:
         """Return the provider name."""
@@ -58,158 +56,6 @@ class CrtShProvider(BaseProvider):
         """
         return True
     
-    def _get_cache_file_path(self, domain: str) -> Path:
-        """Generate cache file path for a domain."""
-        # Sanitize domain for filename safety
-        safe_domain = domain.replace('.', '_').replace('/', '_').replace('\\', '_')
-        return self.cache_dir / f"{safe_domain}.json"
-    
-    def _get_cache_status(self, cache_file_path: Path) -> str:
-        """
-        Check cache status for a domain.
-        Returns: 'not_found', 'fresh', or 'stale'
-        """
-        if not cache_file_path.exists():
-            return "not_found"
-        
-        try:
-            with open(cache_file_path, 'r') as f:
-                cache_data = json.load(f)
-            
-            last_query_str = cache_data.get("last_upstream_query")
-            if not last_query_str:
-                return "stale"  # Invalid cache format
-            
-            last_query = datetime.fromisoformat(last_query_str.replace('Z', '+00:00'))
-            hours_since_query = (datetime.now(timezone.utc) - last_query).total_seconds() / 3600
-            
-            cache_timeout = self.config.cache_timeout_hours
-            if hours_since_query < cache_timeout:
-                return "fresh"
-            else:
-                return "stale"
-                
-        except (json.JSONDecodeError, ValueError, KeyError) as e:
-            self.logger.logger.warning(f"Invalid cache file format for {cache_file_path}: {e}")
-            return "stale"
-    
-    def _load_cached_certificates(self, cache_file_path: Path) -> List[Dict[str, Any]]:
-        """Load certificates from cache file."""
-        try:
-            with open(cache_file_path, 'r') as f:
-                cache_data = json.load(f)
-            return cache_data.get('certificates', [])
-        except (json.JSONDecodeError, FileNotFoundError, KeyError) as e:
-            self.logger.logger.error(f"Failed to load cached certificates from {cache_file_path}: {e}")
-            return []
-    
-    def _query_crtsh_api(self, domain: str) -> List[Dict[str, Any]]:
-        """
-        Query crt.sh API for raw certificate data.
-        Raises exceptions for network errors to allow core logic to retry.
-        """
-        url = f"{self.base_url}?q={quote(domain)}&output=json"
-        response = self.make_request(url, target_indicator=domain)
-        
-        if not response or response.status_code != 200:
-            # This could be a temporary error - raise exception so core can retry
-            raise requests.exceptions.RequestException(f"crt.sh API returned status {response.status_code if response else 'None'}")
-        
-        certificates = response.json()
-        if not certificates:
-            return []
-        
-        return certificates
-    
-    def _create_cache_file(self, cache_file_path: Path, domain: str, certificates: List[Dict[str, Any]]) -> None:
-        """Create new cache file with certificates."""
-        try:
-            cache_data = {
-                "domain": domain,
-                "first_cached": datetime.now(timezone.utc).isoformat(),
-                "last_upstream_query": datetime.now(timezone.utc).isoformat(),
-                "upstream_query_count": 1,
-                "certificates": certificates
-            }
-            
-            cache_file_path.parent.mkdir(parents=True, exist_ok=True)
-            with open(cache_file_path, 'w') as f:
-                json.dump(cache_data, f, separators=(',', ':'))
-                
-            self.logger.logger.info(f"Created cache file for {domain} with {len(certificates)} certificates")
-            
-        except Exception as e:
-            self.logger.logger.warning(f"Failed to create cache file for {domain}: {e}")
-    
-    def _append_to_cache(self, cache_file_path: Path, new_certificates: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
-        """Append new certificates to existing cache and return all certificates."""
-        try:
-            # Load existing cache
-            with open(cache_file_path, 'r') as f:
-                cache_data = json.load(f)
-            
-            # Track existing certificate IDs to avoid duplicates
-            existing_ids = {cert.get('id') for cert in cache_data.get('certificates', [])}
-            
-            # Add only new certificates
-            added_count = 0
-            for cert in new_certificates:
-                cert_id = cert.get('id')
-                if cert_id and cert_id not in existing_ids:
-                    cache_data['certificates'].append(cert)
-                    existing_ids.add(cert_id)
-                    added_count += 1
-            
-            # Update metadata
-            cache_data['last_upstream_query'] = datetime.now(timezone.utc).isoformat()
-            cache_data['upstream_query_count'] = cache_data.get('upstream_query_count', 0) + 1
-            
-            # Write updated cache
-            with open(cache_file_path, 'w') as f:
-                json.dump(cache_data, f, separators=(',', ':'))
-            
-            total_certs = len(cache_data['certificates'])
-            self.logger.logger.info(f"Appended {added_count} new certificates to cache. Total: {total_certs}")
-            
-            return cache_data['certificates']
-            
-        except Exception as e:
-            self.logger.logger.warning(f"Failed to append to cache: {e}")
-            return new_certificates  # Fallback to new certificates only
-    
-    def _parse_issuer_organization(self, issuer_dn: str) -> str:
-        """
-        Parse the issuer Distinguished Name to extract just the organization name.
-        
-        Args:
-            issuer_dn: Full issuer DN string (e.g., "C=US, O=Let's Encrypt, CN=R11")
-            
-        Returns:
-            Organization name (e.g., "Let's Encrypt") or original string if parsing fails
-        """
-        if not issuer_dn:
-            return issuer_dn
-        
-        try:
-            # Split by comma and look for O= component
-            components = [comp.strip() for comp in issuer_dn.split(',')]
-            
-            for component in components:
-                if component.startswith('O='):
-                    # Extract the value after O=
-                    org_name = component[2:].strip()
-                    # Remove quotes if present
-                    if org_name.startswith('"') and org_name.endswith('"'):
-                        org_name = org_name[1:-1]
-                    return org_name
-            
-            # If no O= component found, return the original string
-            return issuer_dn
-            
-        except Exception as e:
-            self.logger.logger.debug(f"Failed to parse issuer DN '{issuer_dn}': {e}")
-            return issuer_dn
-    
     def _parse_certificate_date(self, date_string: str) -> datetime:
         """
         Parse certificate date from crt.sh format.
@@ -287,15 +133,10 @@ class CrtShProvider(BaseProvider):
         Returns:
             Comprehensive certificate metadata dictionary
         """
-        # Parse the issuer name to get just the organization
-        raw_issuer_name = cert_data.get('issuer_name', '')
-        parsed_issuer_name = self._parse_issuer_organization(raw_issuer_name)
-        
         metadata = {
             'certificate_id': cert_data.get('id'),
             'serial_number': cert_data.get('serial_number'),
-            'issuer_name': parsed_issuer_name,  # Use parsed organization name
-            #'issuer_name_full': raw_issuer_name,  # deliberately left out, because its not useful in most cases
+            'issuer_name': cert_data.get('issuer_name'),
             'issuer_ca_id': cert_data.get('issuer_ca_id'),
             'common_name': cert_data.get('common_name'),
             'not_before': cert_data.get('not_before'),
@@ -326,8 +167,7 @@ class CrtShProvider(BaseProvider):
 
     def query_domain(self, domain: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
         """
-        Query crt.sh for certificates containing the domain with caching support.
-        Properly raises exceptions for network errors to allow core logic retries.
+        Query crt.sh for certificates containing the domain.
         """
         if not _is_valid_domain(domain):
             return []
@@ -337,167 +177,131 @@ class CrtShProvider(BaseProvider):
             print(f"CrtSh query cancelled before start for domain: {domain}")
             return []
         
-        # === CACHING LOGIC ===
-        cache_file = self._get_cache_file_path(domain)
-        cache_status = self._get_cache_status(cache_file)
-        
-        certificates = []
-        
-        try:
-            if cache_status == "fresh":
-                # Use cached data
-                certificates = self._load_cached_certificates(cache_file)
-                self.logger.logger.info(f"Using cached data for {domain} ({len(certificates)} certificates)")
-                
-            elif cache_status == "not_found":
-                # Fresh query, create new cache
-                certificates = self._query_crtsh_api(domain)
-                if certificates:  # Only cache if we got results
-                    self._create_cache_file(cache_file, domain, certificates)
-                    self.logger.logger.info(f"Cached fresh data for {domain} ({len(certificates)} certificates)")
-                else:
-                    self.logger.logger.info(f"No certificates found for {domain}, not caching")
-                    
-            elif cache_status == "stale":
-                # Append query, update existing cache
-                try:
-                    new_certificates = self._query_crtsh_api(domain)
-                    if new_certificates:
-                        certificates = self._append_to_cache(cache_file, new_certificates)
-                        self.logger.logger.info(f"Refreshed and appended cache for {domain}")
-                    else:
-                        # Use existing cache if API returns no results
-                        certificates = self._load_cached_certificates(cache_file)
-                        self.logger.logger.info(f"API returned no new results, using existing cache for {domain}")
-                except requests.exceptions.RequestException:
-                    # If API call fails for stale cache, use cached data and re-raise for retry logic
-                    certificates = self._load_cached_certificates(cache_file)
-                    if certificates:
-                        self.logger.logger.warning(f"API call failed for {domain}, using stale cache data ({len(certificates)} certificates)")
-                        # Don't re-raise here, just use cached data
-                    else:
-                        # No cached data and API failed - re-raise for retry
-                        raise
-            
-        except requests.exceptions.RequestException as e:
-            # Network/API errors should be re-raised so core logic can retry
-            self.logger.logger.error(f"API query failed for {domain}: {e}")
-            raise e
-        except json.JSONDecodeError as e:
-            # JSON parsing errors should also be raised for retry
-            self.logger.logger.error(f"Failed to parse JSON response from crt.sh for {domain}: {e}")
-            raise e
-        
-        # Check for cancellation after cache operations
-        if self._stop_event and self._stop_event.is_set():
-            print(f"CrtSh query cancelled after cache operations for domain: {domain}")
-            return []
-        
-        if not certificates:
-            return []
-        
-        return self._process_certificates_to_relationships(domain, certificates)
-    
-    def _process_certificates_to_relationships(self, domain: str, certificates: List[Dict[str, Any]]) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
-        """
-        Process certificates to relationships using existing logic.
-        This method contains the original processing logic from query_domain.
-        """
         relationships = []
         
-        # Check for cancellation before processing
-        if self._stop_event and self._stop_event.is_set():
-            print(f"CrtSh processing cancelled before processing for domain: {domain}")
-            return []
-
-        # Aggregate certificate data by domain
-        domain_certificates = {}
-        all_discovered_domains = set()
-        
-        # Process certificates with cancellation checking
-        for i, cert_data in enumerate(certificates):
-            # Check for cancellation every 5 certificates for faster response
-            if i % 5 == 0 and self._stop_event and self._stop_event.is_set():
-                print(f"CrtSh processing cancelled at certificate {i} for domain: {domain}")
-                break
-                
-            cert_metadata = self._extract_certificate_metadata(cert_data)
-            cert_domains = self._extract_domains_from_certificate(cert_data)
+        try:
+            # Query crt.sh for certificates
+            url = f"{self.base_url}?q={quote(domain)}&output=json"
+            response = self.make_request(url, target_indicator=domain, max_retries=3)
             
-            # Add all domains from this certificate to our tracking
-            all_discovered_domains.update(cert_domains)
-            for cert_domain in cert_domains:
-                if not _is_valid_domain(cert_domain):
+            if not response or response.status_code != 200:
+                return []
+            
+            # Check for cancellation after request
+            if self._stop_event and self._stop_event.is_set():
+                print(f"CrtSh query cancelled after request for domain: {domain}")
+                return []
+
+            certificates = response.json()
+            
+            if not certificates:
+                return []
+            
+            # Check for cancellation before processing
+            if self._stop_event and self._stop_event.is_set():
+                print(f"CrtSh query cancelled before processing for domain: {domain}")
+                return []
+
+            # Aggregate certificate data by domain
+            domain_certificates = {}
+            all_discovered_domains = set()
+            
+            # Process certificates with cancellation checking
+            for i, cert_data in enumerate(certificates):
+                # Check for cancellation every 5 certificates instead of 10 for faster response
+                if i % 5 == 0 and self._stop_event and self._stop_event.is_set():
+                    print(f"CrtSh processing cancelled at certificate {i} for domain: {domain}")
+                    break
+                    
+                cert_metadata = self._extract_certificate_metadata(cert_data)
+                cert_domains = self._extract_domains_from_certificate(cert_data)
+                
+                # Add all domains from this certificate to our tracking
+                for cert_domain in cert_domains:
+                    # Additional stop check during domain processing
+                    if i % 20 == 0 and self._stop_event and self._stop_event.is_set():
+                        print(f"CrtSh domain processing cancelled for domain: {domain}")
+                        break
+                        
+                    if not _is_valid_domain(cert_domain):
+                        continue
+                    
+                    all_discovered_domains.add(cert_domain)
+                    
+                    # Initialize domain certificate list if needed
+                    if cert_domain not in domain_certificates:
+                        domain_certificates[cert_domain] = []
+                    
+                    # Add this certificate to the domain's certificate list
+                    domain_certificates[cert_domain].append(cert_metadata)
+            
+            # Final cancellation check before creating relationships
+            if self._stop_event and self._stop_event.is_set():
+                print(f"CrtSh query cancelled before relationship creation for domain: {domain}")
+                return []
+
+            # Create relationships from query domain to ALL discovered domains with stop checking
+            for i, discovered_domain in enumerate(all_discovered_domains):
+                if discovered_domain == domain:
+                    continue  # Skip self-relationships
+                
+                # Check for cancellation every 10 relationships
+                if i % 10 == 0 and self._stop_event and self._stop_event.is_set():
+                    print(f"CrtSh relationship creation cancelled for domain: {domain}")
+                    break
+
+                if not _is_valid_domain(discovered_domain):
                     continue
                 
-                # Initialize domain certificate list if needed
-                if cert_domain not in domain_certificates:
-                    domain_certificates[cert_domain] = []
+                # Get certificates for both domains
+                query_domain_certs = domain_certificates.get(domain, [])
+                discovered_domain_certs = domain_certificates.get(discovered_domain, [])
                 
-                # Add this certificate to the domain's certificate list
-                domain_certificates[cert_domain].append(cert_metadata)
-        
-        # Final cancellation check before creating relationships
-        if self._stop_event and self._stop_event.is_set():
-            print(f"CrtSh query cancelled before relationship creation for domain: {domain}")
-            return []
-
-        # Create relationships from query domain to ALL discovered domains with stop checking
-        for i, discovered_domain in enumerate(all_discovered_domains):
-            if discovered_domain == domain:
-                continue  # Skip self-relationships
-            
-            # Check for cancellation every 10 relationships
-            if i % 10 == 0 and self._stop_event and self._stop_event.is_set():
-                print(f"CrtSh relationship creation cancelled for domain: {domain}")
-                break
-
-            if not _is_valid_domain(discovered_domain):
-                continue
-            
-            # Get certificates for both domains
-            query_domain_certs = domain_certificates.get(domain, [])
-            discovered_domain_certs = domain_certificates.get(discovered_domain, [])
-            
-            # Find shared certificates (for metadata purposes)
-            shared_certificates = self._find_shared_certificates(query_domain_certs, discovered_domain_certs)
-            
-            # Calculate confidence based on relationship type and shared certificates
-            confidence = self._calculate_domain_relationship_confidence(
-                domain, discovered_domain, shared_certificates, all_discovered_domains
-            )
-            
-            # Create comprehensive raw data for the relationship
-            relationship_raw_data = {
-                'relationship_type': 'certificate_discovery',
-                'shared_certificates': shared_certificates,
-                'total_shared_certs': len(shared_certificates),
-                'discovery_context': self._determine_relationship_context(discovered_domain, domain),
-                'domain_certificates': {
-                    domain: self._summarize_certificates(query_domain_certs),
-                    discovered_domain: self._summarize_certificates(discovered_domain_certs)
+                # Find shared certificates (for metadata purposes)
+                shared_certificates = self._find_shared_certificates(query_domain_certs, discovered_domain_certs)
+                
+                # Calculate confidence based on relationship type and shared certificates
+                confidence = self._calculate_domain_relationship_confidence(
+                    domain, discovered_domain, shared_certificates, all_discovered_domains
+                )
+                
+                # Create comprehensive raw data for the relationship
+                relationship_raw_data = {
+                    'relationship_type': 'certificate_discovery',
+                    'shared_certificates': shared_certificates,
+                    'total_shared_certs': len(shared_certificates),
+                    'discovery_context': self._determine_relationship_context(discovered_domain, domain),
+                    'domain_certificates': {
+                        domain: self._summarize_certificates(query_domain_certs),
+                        discovered_domain: self._summarize_certificates(discovered_domain_certs)
+                    }
                 }
-            }
-            
-            # Create domain -> domain relationship
-            relationships.append((
-                domain,
-                discovered_domain,
-                'san_certificate',
-                confidence,
-                relationship_raw_data
-            ))
-            
-            # Log the relationship discovery
-            self.log_relationship_discovery(
-                source_node=domain,
-                target_node=discovered_domain,
-                relationship_type='san_certificate',
-                confidence_score=confidence,
-                raw_data=relationship_raw_data,
-                discovery_method="certificate_transparency_analysis"
-            )
+                
+                # Create domain -> domain relationship
+                relationships.append((
+                    domain,
+                    discovered_domain,
+                    'san_certificate',
+                    confidence,
+                    relationship_raw_data
+                ))
+                
+                # Log the relationship discovery
+                self.log_relationship_discovery(
+                    source_node=domain,
+                    target_node=discovered_domain,
+                    relationship_type='san_certificate',
+                    confidence_score=confidence,
+                    raw_data=relationship_raw_data,
+                    discovery_method="certificate_transparency_analysis"
+                )
 
+        except json.JSONDecodeError as e:
+            self.logger.logger.error(f"Failed to parse JSON response from crt.sh: {e}")
+        except requests.exceptions.RequestException as e:
+            self.logger.logger.error(f"HTTP request to crt.sh failed: {e}")
+
+        
         return relationships
 
     def _find_shared_certificates(self, certs1: List[Dict[str, Any]], certs2: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
@@ -548,7 +352,7 @@ class CrtShProvider(BaseProvider):
         expired_count = len(certificates) - valid_count
         expires_soon_count = sum(1 for cert in certificates if cert.get('expires_soon'))
         
-        # Get unique issuers (using parsed organization names)
+        # Get unique issuers
         unique_issuers = list(set(cert.get('issuer_name') for cert in certificates if cert.get('issuer_name')))
         
         # Find the most recent certificate

providers/dns_provider.py

@@ -1,6 +1,7 @@
 # dnsrecon/providers/dns_provider.py
 
-from dns import resolver, reversename
+import dns.resolver
+import dns.reversename
 from typing import List, Dict, Any, Tuple
 from .base_provider import BaseProvider
 from utils.helpers import _is_valid_ip, _is_valid_domain
@@ -12,7 +13,7 @@ class DNSProvider(BaseProvider):
     Now uses session-specific configuration.
     """
 
-    def __init__(self, name=None, session_config=None):
+    def __init__(self, session_config=None):
         """Initialize DNS provider with session-specific configuration."""
         super().__init__(
             name="dns",
@@ -22,7 +23,7 @@ class DNSProvider(BaseProvider):
         )
 
         # Configure DNS resolver
-        self.resolver = resolver.Resolver()
+        self.resolver = dns.resolver.Resolver()
         self.resolver.timeout = 5
         self.resolver.lifetime = 10
         #self.resolver.nameservers = ['127.0.0.1']
@@ -50,7 +51,12 @@ class DNSProvider(BaseProvider):
     def query_domain(self, domain: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
         """
         Query DNS records for the domain to discover relationships.
-        ...
+
+        Args:
+            domain: Domain to investigate
+
+        Returns:
+            List of relationships discovered from DNS analysis
         """
         if not _is_valid_domain(domain):
             return []
@@ -59,15 +65,7 @@ class DNSProvider(BaseProvider):
 
         # Query all record types
         for record_type in ['A', 'AAAA', 'CNAME', 'MX', 'NS', 'SOA', 'TXT', 'SRV', 'CAA']:
-            try:
-                relationships.extend(self._query_record(domain, record_type))
-            except resolver.NoAnswer:
-                # This is not an error, just a confirmation that the record doesn't exist.
-                self.logger.logger.debug(f"No {record_type} record found for {domain}")
-            except Exception as e:
-                self.failed_requests += 1
-                self.logger.logger.debug(f"{record_type} record query failed for {domain}: {e}")
-                # Optionally, you might want to re-raise other, more serious exceptions.
+            relationships.extend(self._query_record(domain, record_type))
 
         return relationships
 
@@ -89,7 +87,7 @@ class DNSProvider(BaseProvider):
         try:
             # Perform reverse DNS lookup
             self.total_requests += 1
-            reverse_name = reversename.from_address(ip)
+            reverse_name = dns.reversename.from_address(ip)
             response = self.resolver.resolve(reverse_name, 'PTR')
             self.successful_requests += 1
 
@@ -121,14 +119,9 @@ class DNSProvider(BaseProvider):
                         discovery_method="reverse_dns_lookup"
                     )
 
-        except resolver.NXDOMAIN:
-            self.failed_requests += 1
-            self.logger.logger.debug(f"Reverse DNS lookup failed for {ip}: NXDOMAIN")
         except Exception as e:
             self.failed_requests += 1
             self.logger.logger.debug(f"Reverse DNS lookup failed for {ip}: {e}")
-            # Re-raise the exception so the scanner can handle the failure
-            raise e
 
         return relationships
 
@@ -192,7 +185,5 @@ class DNSProvider(BaseProvider):
         except Exception as e:
             self.failed_requests += 1
             self.logger.logger.debug(f"{record_type} record query failed for {domain}: {e}")
-            # Re-raise the exception so the scanner can handle it
-            raise e
 
         return relationships

providers/shodan_provider.py

@@ -1,4 +1,7 @@
-# dnsrecon/providers/shodan_provider.py
+"""
+Shodan provider for DNSRecon.
+Discovers IP relationships and infrastructure context through Shodan API.
+"""
 
 import json
 from typing import List, Dict, Any, Tuple
@@ -12,7 +15,7 @@ class ShodanProvider(BaseProvider):
     Now uses session-specific API keys.
     """
 
-    def __init__(self, name=None, session_config=None):
+    def __init__(self, session_config=None):
         """Initialize Shodan provider with session-specific configuration."""
         super().__init__(
             name="shodan",

requirements.txt

@@ -6,5 +6,4 @@ Werkzeug>=2.3.7
 urllib3>=2.0.0
 dnspython>=2.4.2
 gunicorn
-redis
-python-dotenv
+redis

static/css/main.css

@@ -272,24 +272,8 @@ input[type="text"]:focus, select:focus {
     text-shadow: 0 0 3px rgba(0, 255, 65, 0.3);
 }
 
-.progress-container {
-    padding: 0 1.5rem 1.5rem;
-}
-
-.progress-info {
-    display: flex;
-    justify-content: space-between;
-    font-size: 0.8rem;
-    color: #999;
-    margin-bottom: 0.5rem;
-}
-
-#progress-compact {
-    color: #00ff41;
-    font-weight: 500;
-}
-
 .progress-bar {
+    margin: 1rem 1.5rem;
     height: 8px;
     background-color: #1a1a1a;
     border: 1px solid #444;
@@ -533,7 +517,7 @@ input[type="text"]:focus, select:focus {
     color: #e0e0e0;
 }
 
-.provider-stats, .provider-task-stats {
+.provider-stats {
     font-size: 0.8rem;
     color: #999;
     display: grid;
@@ -542,13 +526,6 @@ input[type="text"]:focus, select:focus {
     margin-top: 0.5rem;
 }
 
-.provider-task-stats {
-    border-top: 1px solid #333;
-    padding-top: 0.5rem;
-    margin-top: 0.5rem;
-}
-
-
 .provider-stat {
     display: flex;
     justify-content: space-between;

static/js/graph.js

@@ -216,8 +216,12 @@ class GraphManager {
             }
         });
 
+        // FIX: Comment out the problematic context menu handler
         this.network.on('oncontext', (params) => {
             params.event.preventDefault();
+            // if (params.nodes.length > 0) {
+            //     this.showNodeContextMenu(params.pointer.DOM, params.nodes[0]);
+            // }
         });
 
         // Stabilization events with progress
@@ -376,7 +380,7 @@ class GraphManager {
                 // Single correlation value
                 const value = Array.isArray(values) && values.length > 0 ? values[0] : (metadata.value || 'Unknown');
                 const displayValue = typeof value === 'string' && value.length > 20 ? value.substring(0, 17) + '...' : value;
-                processedNode.label = `${displayValue}`;
+                processedNode.label = `Corr: ${displayValue}`;
                 processedNode.title = `Correlation: ${value}`;
             }
         }

static/js/main.js

@@ -1,6 +1,7 @@
 /**
  * Main application logic for DNSRecon web interface
  * Handles UI interactions, API communication, and data flow
+ * DEBUG VERSION WITH EXTRA LOGGING
  */
 
 class DNSReconApp {
@@ -60,8 +61,9 @@ class DNSReconApp {
             scanStatus: document.getElementById('scan-status'),
             targetDisplay: document.getElementById('target-display'),
             depthDisplay: document.getElementById('depth-display'),
+            progressDisplay: document.getElementById('progress-display'),
+            indicatorsDisplay: document.getElementById('indicators-display'),
             relationshipsDisplay: document.getElementById('relationships-display'),
-            progressCompact: document.getElementById('progress-compact'),
             progressFill: document.getElementById('progress-fill'),
             
             // Provider elements
@@ -445,7 +447,7 @@ class DNSReconApp {
                 // Handle status changes
                 if (status.status !== this.scanStatus) {
                     console.log(`*** STATUS CHANGED: ${this.scanStatus} -> ${status.status} ***`);
-                    this.handleStatusChange(status.status, status.task_queue_size);
+                    this.handleStatusChange(status.status);
                 }
                 
                 this.scanStatus = status.status;
@@ -540,19 +542,17 @@ class DNSReconApp {
             if (this.elements.depthDisplay) {
                 this.elements.depthDisplay.textContent = `${status.current_depth}/${status.max_depth}`;
             }
+            if (this.elements.progressDisplay) {
+                this.elements.progressDisplay.textContent = `${status.progress_percentage.toFixed(1)}%`;
+            }
+            if (this.elements.indicatorsDisplay) {
+                this.elements.indicatorsDisplay.textContent = status.indicators_processed || 0;
+            }
             
-            // Update progress bar and compact display
+            // Update progress bar with smooth animation
             if (this.elements.progressFill) {
-                const completed = status.indicators_completed || 0;
-                const enqueued = status.task_queue_size || 0;
-                const totalTasks = completed + enqueued;
-                const progressPercentage = totalTasks > 0 ? (completed / totalTasks) * 100 : 0;
-
-                this.elements.progressFill.style.width = `${progressPercentage}%`;
-                if (this.elements.progressCompact) {
-                    this.elements.progressCompact.textContent = `${completed}/${totalTasks} - ${Math.round(progressPercentage)}%`;
-                }
-
+                this.elements.progressFill.style.width = `${status.progress_percentage}%`;
+                
                 // Add pulsing animation for active scans
                 if (status.status === 'running') {
                     this.elements.progressFill.parentElement.classList.add('scanning');
@@ -574,8 +574,6 @@ class DNSReconApp {
                     this.elements.sessionId.textContent = 'Session: Loading...';
                 }
             }
-
-            this.setUIState(status.status, status.task_queue_size);
             
             console.log('Status display updated successfully');
         } catch (error) {
@@ -587,12 +585,12 @@ class DNSReconApp {
      * Handle status changes with improved state synchronization
      * @param {string} newStatus - New scan status
      */
-    handleStatusChange(newStatus, task_queue_size) {
+    handleStatusChange(newStatus) {
         console.log(`=== STATUS CHANGE: ${this.scanStatus} -> ${newStatus} ===`);
         
         switch (newStatus) {
             case 'running':
-                this.setUIState('scanning', task_queue_size);
+                this.setUIState('scanning');
                 this.showSuccess('Scan is running');
                 // Increase polling frequency for active scans
                 this.startPolling(1000); // Poll every 1 second for running scans
@@ -600,7 +598,7 @@ class DNSReconApp {
                 break;
                 
             case 'completed':
-                this.setUIState('completed', task_queue_size);
+                this.setUIState('completed');
                 this.stopPolling();
                 this.showSuccess('Scan completed successfully');
                 this.updateConnectionStatus('completed');
@@ -611,7 +609,7 @@ class DNSReconApp {
                 break;
                 
             case 'failed':
-                this.setUIState('failed', task_queue_size);
+                this.setUIState('failed');
                 this.stopPolling();
                 this.showError('Scan failed');
                 this.updateConnectionStatus('error');
@@ -619,7 +617,7 @@ class DNSReconApp {
                 break;
                 
             case 'stopped':
-                this.setUIState('stopped', task_queue_size);
+                this.setUIState('stopped');
                 this.stopPolling();
                 this.showSuccess('Scan stopped');
                 this.updateConnectionStatus('stopped');
@@ -627,7 +625,7 @@ class DNSReconApp {
                 break;
                 
             case 'idle':
-                this.setUIState('idle', task_queue_size);
+                this.setUIState('idle');
                 this.stopPolling();
                 this.updateConnectionStatus('idle');
                 break;
@@ -672,11 +670,9 @@ class DNSReconApp {
     /**
      * UI state management with immediate button updates
      */
-    setUIState(state, task_queue_size) {
+    setUIState(state) {
         console.log(`Setting UI state to: ${state}`);
         
-        const isQueueEmpty = task_queue_size === 0;
-
         switch (state) {
             case 'scanning':
                 this.isScanning = true;
@@ -705,12 +701,12 @@ class DNSReconApp {
             case 'stopped':
                 this.isScanning = false;
                 if (this.elements.startScan) {
-                    this.elements.startScan.disabled = !isQueueEmpty;
+                    this.elements.startScan.disabled = false;
                     this.elements.startScan.classList.remove('loading');
                     this.elements.startScan.innerHTML = '<span class="btn-icon">[RUN]</span><span>Start Reconnaissance</span>';
                 }
                 if (this.elements.addToGraph) {
-                    this.elements.addToGraph.disabled = !isQueueEmpty;
+                    this.elements.addToGraph.disabled = false;
                     this.elements.addToGraph.classList.remove('loading');
                 }
                 if (this.elements.stopScan) {

templates/index.html

@@ -90,20 +90,22 @@
                         <span class="status-label">Depth:</span>
                         <span id="depth-display" class="status-value">0/0</span>
                     </div>
+                    <div class="status-row">
+                        <span class="status-label">Progress:</span>
+                        <span id="progress-display" class="status-value">0%</span>
+                    </div>
+                    <div class="status-row">
+                        <span class="status-label">Indicators:</span>
+                        <span id="indicators-display" class="status-value">0</span>
+                    </div>
                     <div class="status-row">
                         <span class="status-label">Relationships:</span>
                         <span id="relationships-display" class="status-value">0</span>
                     </div>
                 </div>
                 
-                <div class="progress-container">
-                    <div class="progress-info">
-                        <span id="progress-label">Progress:</span>
-                        <span id="progress-compact">0/0</span>
-                    </div>
-                    <div class="progress-bar">
-                        <div id="progress-fill" class="progress-fill"></div>
-                    </div>
+                <div class="progress-bar">
+                    <div id="progress-fill" class="progress-fill"></div>
                 </div>
             </section>