refactor: half way to process per session

core/processes/__init__.py

@@ -0,0 +1,3 @@
+"""
+Session Process Management Module
+"""

core/processes/communication.py

@@ -0,0 +1,317 @@
+"""
+Inter-Process Communication (IPC) system for session processes.
+Defines message types and protocols for main ↔ session communication.
+"""
+
+import time
+from enum import Enum
+from typing import Dict, Any, Optional, Union
+from dataclasses import dataclass, field
+import numpy as np
+
+
+class MessageType(Enum):
+    """Message types for IPC communication."""
+
+    # Commands: Main → Session
+    INITIALIZE = "initialize"
+    PROCESS_FRAME = "process_frame"
+    SET_SESSION_ID = "set_session_id"
+    SHUTDOWN = "shutdown"
+    HEALTH_CHECK = "health_check"
+
+    # Responses: Session → Main
+    INITIALIZED = "initialized"
+    DETECTION_RESULT = "detection_result"
+    SESSION_SET = "session_set"
+    SHUTDOWN_COMPLETE = "shutdown_complete"
+    HEALTH_RESPONSE = "health_response"
+    ERROR = "error"
+
+
+@dataclass
+class IPCMessage:
+    """Base class for all IPC messages."""
+    type: MessageType
+    session_id: str
+    timestamp: float = field(default_factory=time.time)
+    message_id: str = field(default_factory=lambda: str(int(time.time() * 1000000)))
+
+
+@dataclass
+class InitializeCommand(IPCMessage):
+    """Initialize session process with configuration."""
+    subscription_config: Dict[str, Any] = field(default_factory=dict)
+    model_config: Dict[str, Any] = field(default_factory=dict)
+
+
+
+@dataclass
+class ProcessFrameCommand(IPCMessage):
+    """Process a frame through the detection pipeline."""
+    frame: Optional[np.ndarray] = None
+    display_id: str = ""
+    subscription_identifier: str = ""
+    frame_timestamp: float = 0.0
+
+
+
+@dataclass
+class SetSessionIdCommand(IPCMessage):
+    """Set the session ID for the current session."""
+    backend_session_id: str = ""
+    display_id: str = ""
+
+
+
+@dataclass
+class ShutdownCommand(IPCMessage):
+    """Shutdown the session process gracefully."""
+
+
+
+@dataclass
+class HealthCheckCommand(IPCMessage):
+    """Check health status of session process."""
+
+
+
+@dataclass
+class InitializedResponse(IPCMessage):
+    """Response indicating successful initialization."""
+    success: bool = False
+    error_message: Optional[str] = None
+
+
+
+@dataclass
+class DetectionResultResponse(IPCMessage):
+    """Detection results from session process."""
+    detections: Dict[str, Any] = field(default_factory=dict)
+    processing_time: float = 0.0
+    phase: str = ""  # "detection" or "processing"
+
+
+
+@dataclass
+class SessionSetResponse(IPCMessage):
+    """Response confirming session ID was set."""
+    success: bool = False
+    backend_session_id: str = ""
+
+
+
+@dataclass
+class ShutdownCompleteResponse(IPCMessage):
+    """Response confirming graceful shutdown."""
+
+
+
+@dataclass
+class HealthResponse(IPCMessage):
+    """Health status response."""
+    status: str = "unknown"  # "healthy", "degraded", "unhealthy"
+    memory_usage_mb: float = 0.0
+    cpu_percent: float = 0.0
+    gpu_memory_mb: Optional[float] = None
+    uptime_seconds: float = 0.0
+    processed_frames: int = 0
+
+
+
+@dataclass
+class ErrorResponse(IPCMessage):
+    """Error message from session process."""
+    error_type: str = ""
+    error_message: str = ""
+    traceback: Optional[str] = None
+
+
+
+# Type aliases for message unions
+CommandMessage = Union[
+    InitializeCommand,
+    ProcessFrameCommand,
+    SetSessionIdCommand,
+    ShutdownCommand,
+    HealthCheckCommand
+]
+
+ResponseMessage = Union[
+    InitializedResponse,
+    DetectionResultResponse,
+    SessionSetResponse,
+    ShutdownCompleteResponse,
+    HealthResponse,
+    ErrorResponse
+]
+
+IPCMessageUnion = Union[CommandMessage, ResponseMessage]
+
+
+class MessageSerializer:
+    """Handles serialization/deserialization of IPC messages."""
+
+    @staticmethod
+    def serialize_message(message: IPCMessageUnion) -> Dict[str, Any]:
+        """
+        Serialize message to dictionary for queue transport.
+
+        Args:
+            message: Message to serialize
+
+        Returns:
+            Dictionary representation of message
+        """
+        result = {
+            'type': message.type.value,
+            'session_id': message.session_id,
+            'timestamp': message.timestamp,
+            'message_id': message.message_id,
+        }
+
+        # Add specific fields based on message type
+        if isinstance(message, InitializeCommand):
+            result.update({
+                'subscription_config': message.subscription_config,
+                'model_config': message.model_config
+            })
+        elif isinstance(message, ProcessFrameCommand):
+            result.update({
+                'frame': message.frame,
+                'display_id': message.display_id,
+                'subscription_identifier': message.subscription_identifier,
+                'frame_timestamp': message.frame_timestamp
+            })
+        elif isinstance(message, SetSessionIdCommand):
+            result.update({
+                'backend_session_id': message.backend_session_id,
+                'display_id': message.display_id
+            })
+        elif isinstance(message, InitializedResponse):
+            result.update({
+                'success': message.success,
+                'error_message': message.error_message
+            })
+        elif isinstance(message, DetectionResultResponse):
+            result.update({
+                'detections': message.detections,
+                'processing_time': message.processing_time,
+                'phase': message.phase
+            })
+        elif isinstance(message, SessionSetResponse):
+            result.update({
+                'success': message.success,
+                'backend_session_id': message.backend_session_id
+            })
+        elif isinstance(message, HealthResponse):
+            result.update({
+                'status': message.status,
+                'memory_usage_mb': message.memory_usage_mb,
+                'cpu_percent': message.cpu_percent,
+                'gpu_memory_mb': message.gpu_memory_mb,
+                'uptime_seconds': message.uptime_seconds,
+                'processed_frames': message.processed_frames
+            })
+        elif isinstance(message, ErrorResponse):
+            result.update({
+                'error_type': message.error_type,
+                'error_message': message.error_message,
+                'traceback': message.traceback
+            })
+
+        return result
+
+    @staticmethod
+    def deserialize_message(data: Dict[str, Any]) -> IPCMessageUnion:
+        """
+        Deserialize dictionary back to message object.
+
+        Args:
+            data: Dictionary representation
+
+        Returns:
+            Deserialized message object
+        """
+        msg_type = MessageType(data['type'])
+        session_id = data['session_id']
+        timestamp = data['timestamp']
+        message_id = data['message_id']
+
+        base_kwargs = {
+            'session_id': session_id,
+            'timestamp': timestamp,
+            'message_id': message_id
+        }
+
+        if msg_type == MessageType.INITIALIZE:
+            return InitializeCommand(
+                type=msg_type,
+                subscription_config=data['subscription_config'],
+                model_config=data['model_config'],
+                **base_kwargs
+            )
+        elif msg_type == MessageType.PROCESS_FRAME:
+            return ProcessFrameCommand(
+                type=msg_type,
+                frame=data['frame'],
+                display_id=data['display_id'],
+                subscription_identifier=data['subscription_identifier'],
+                frame_timestamp=data['frame_timestamp'],
+                **base_kwargs
+            )
+        elif msg_type == MessageType.SET_SESSION_ID:
+            return SetSessionIdCommand(
+                backend_session_id=data['backend_session_id'],
+                display_id=data['display_id'],
+                **base_kwargs
+            )
+        elif msg_type == MessageType.SHUTDOWN:
+            return ShutdownCommand(**base_kwargs)
+        elif msg_type == MessageType.HEALTH_CHECK:
+            return HealthCheckCommand(**base_kwargs)
+        elif msg_type == MessageType.INITIALIZED:
+            return InitializedResponse(
+                type=msg_type,
+                success=data['success'],
+                error_message=data.get('error_message'),
+                **base_kwargs
+            )
+        elif msg_type == MessageType.DETECTION_RESULT:
+            return DetectionResultResponse(
+                type=msg_type,
+                detections=data['detections'],
+                processing_time=data['processing_time'],
+                phase=data['phase'],
+                **base_kwargs
+            )
+        elif msg_type == MessageType.SESSION_SET:
+            return SessionSetResponse(
+                type=msg_type,
+                success=data['success'],
+                backend_session_id=data['backend_session_id'],
+                **base_kwargs
+            )
+        elif msg_type == MessageType.SHUTDOWN_COMPLETE:
+            return ShutdownCompleteResponse(type=msg_type, **base_kwargs)
+        elif msg_type == MessageType.HEALTH_RESPONSE:
+            return HealthResponse(
+                type=msg_type,
+                status=data['status'],
+                memory_usage_mb=data['memory_usage_mb'],
+                cpu_percent=data['cpu_percent'],
+                gpu_memory_mb=data.get('gpu_memory_mb'),
+                uptime_seconds=data.get('uptime_seconds', 0.0),
+                processed_frames=data.get('processed_frames', 0),
+                **base_kwargs
+            )
+        elif msg_type == MessageType.ERROR:
+            return ErrorResponse(
+                type=msg_type,
+                error_type=data['error_type'],
+                error_message=data['error_message'],
+                traceback=data.get('traceback'),
+                **base_kwargs
+            )
+        else:
+            raise ValueError(f"Unknown message type: {msg_type}")

core/processes/session_manager.py

@@ -0,0 +1,464 @@
+"""
+Session Process Manager - Manages lifecycle of session processes.
+Handles process spawning, monitoring, cleanup, and health checks.
+"""
+
+import time
+import logging
+import asyncio
+import multiprocessing as mp
+from typing import Dict, Optional, Any, Callable
+from dataclasses import dataclass
+from concurrent.futures import ThreadPoolExecutor
+import threading
+
+from .communication import (
+    MessageSerializer, MessageType,
+    InitializeCommand, ProcessFrameCommand, SetSessionIdCommand,
+    ShutdownCommand, HealthCheckCommand,
+    InitializedResponse, DetectionResultResponse, SessionSetResponse,
+    ShutdownCompleteResponse, HealthResponse, ErrorResponse
+)
+from .session_worker import session_worker_main
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class SessionProcessInfo:
+    """Information about a running session process."""
+    session_id: str
+    subscription_identifier: str
+    process: mp.Process
+    command_queue: mp.Queue
+    response_queue: mp.Queue
+    created_at: float
+    last_health_check: float = 0.0
+    is_initialized: bool = False
+    processed_frames: int = 0
+
+
+class SessionProcessManager:
+    """
+    Manages lifecycle of session processes.
+    Each session gets its own dedicated process for complete isolation.
+    """
+
+    def __init__(self, max_concurrent_sessions: int = 20, health_check_interval: int = 30):
+        """
+        Initialize session process manager.
+
+        Args:
+            max_concurrent_sessions: Maximum number of concurrent session processes
+            health_check_interval: Interval in seconds between health checks
+        """
+        self.max_concurrent_sessions = max_concurrent_sessions
+        self.health_check_interval = health_check_interval
+
+        # Active session processes
+        self.sessions: Dict[str, SessionProcessInfo] = {}
+        self.subscription_to_session: Dict[str, str] = {}
+
+        # Thread pool for response processing
+        self.response_executor = ThreadPoolExecutor(max_workers=4, thread_name_prefix="ResponseProcessor")
+
+        # Health check task
+        self.health_check_task = None
+        self.is_running = False
+
+        # Message callbacks
+        self.detection_result_callback: Optional[Callable] = None
+        self.error_callback: Optional[Callable] = None
+
+        # Store main event loop for async operations from threads
+        self.main_event_loop = None
+
+        logger.info(f"SessionProcessManager initialized (max_sessions={max_concurrent_sessions})")
+
+    async def start(self):
+        """Start the session process manager."""
+        if self.is_running:
+            return
+
+        self.is_running = True
+
+        # Store the main event loop for use in threads
+        self.main_event_loop = asyncio.get_running_loop()
+
+        logger.info("Starting session process manager")
+
+        # Start health check task
+        self.health_check_task = asyncio.create_task(self._health_check_loop())
+
+        # Start response processing for existing sessions
+        for session_info in self.sessions.values():
+            self._start_response_processing(session_info)
+
+    async def stop(self):
+        """Stop the session process manager and cleanup all sessions."""
+        if not self.is_running:
+            return
+
+        logger.info("Stopping session process manager")
+        self.is_running = False
+
+        # Cancel health check task
+        if self.health_check_task:
+            self.health_check_task.cancel()
+            try:
+                await self.health_check_task
+            except asyncio.CancelledError:
+                pass
+
+        # Shutdown all sessions
+        shutdown_tasks = []
+        for session_id in list(self.sessions.keys()):
+            task = asyncio.create_task(self.remove_session(session_id))
+            shutdown_tasks.append(task)
+
+        if shutdown_tasks:
+            await asyncio.gather(*shutdown_tasks, return_exceptions=True)
+
+        # Cleanup thread pool
+        self.response_executor.shutdown(wait=True)
+
+        logger.info("Session process manager stopped")
+
+    async def create_session(self, subscription_identifier: str, subscription_config: Dict[str, Any]) -> bool:
+        """
+        Create a new session process for a subscription.
+
+        Args:
+            subscription_identifier: Unique subscription identifier
+            subscription_config: Subscription configuration
+
+        Returns:
+            True if session was created successfully
+        """
+        try:
+            # Check if we're at capacity
+            if len(self.sessions) >= self.max_concurrent_sessions:
+                logger.warning(f"Cannot create session: at max capacity ({self.max_concurrent_sessions})")
+                return False
+
+            # Check if subscription already has a session
+            if subscription_identifier in self.subscription_to_session:
+                existing_session_id = self.subscription_to_session[subscription_identifier]
+                logger.info(f"Subscription {subscription_identifier} already has session {existing_session_id}")
+                return True
+
+            # Generate unique session ID
+            session_id = f"session_{int(time.time() * 1000)}_{subscription_identifier.replace(';', '_')}"
+
+            logger.info(f"Creating session process for subscription {subscription_identifier}")
+            logger.info(f"Session ID: {session_id}")
+
+            # Create communication queues
+            command_queue = mp.Queue()
+            response_queue = mp.Queue()
+
+            # Create and start process
+            process = mp.Process(
+                target=session_worker_main,
+                args=(session_id, command_queue, response_queue),
+                name=f"SessionWorker-{session_id}"
+            )
+            process.start()
+
+            # Store session information
+            session_info = SessionProcessInfo(
+                session_id=session_id,
+                subscription_identifier=subscription_identifier,
+                process=process,
+                command_queue=command_queue,
+                response_queue=response_queue,
+                created_at=time.time()
+            )
+
+            self.sessions[session_id] = session_info
+            self.subscription_to_session[subscription_identifier] = session_id
+
+            # Start response processing for this session
+            self._start_response_processing(session_info)
+
+            logger.info(f"Session process created: {session_id} (PID: {process.pid})")
+
+            # Initialize the session with configuration
+            model_config = {
+                'modelId': subscription_config.get('modelId'),
+                'modelUrl': subscription_config.get('modelUrl'),
+                'modelName': subscription_config.get('modelName')
+            }
+
+            init_command = InitializeCommand(
+                type=MessageType.INITIALIZE,
+                session_id=session_id,
+                subscription_config=subscription_config,
+                model_config=model_config
+            )
+
+            await self._send_command(session_id, init_command)
+
+            return True
+
+        except Exception as e:
+            logger.error(f"Failed to create session for {subscription_identifier}: {e}", exc_info=True)
+            # Cleanup on failure
+            if session_id in self.sessions:
+                await self._cleanup_session(session_id)
+            return False
+
+    async def remove_session(self, subscription_identifier: str) -> bool:
+        """
+        Remove a session process for a subscription.
+
+        Args:
+            subscription_identifier: Subscription identifier to remove
+
+        Returns:
+            True if session was removed successfully
+        """
+        try:
+            session_id = self.subscription_to_session.get(subscription_identifier)
+            if not session_id:
+                logger.warning(f"No session found for subscription {subscription_identifier}")
+                return False
+
+            logger.info(f"Removing session {session_id} for subscription {subscription_identifier}")
+
+            session_info = self.sessions.get(session_id)
+            if session_info:
+                # Send shutdown command
+                shutdown_command = ShutdownCommand(session_id=session_id)
+                await self._send_command(session_id, shutdown_command)
+
+                # Wait for graceful shutdown (with timeout)
+                try:
+                    await asyncio.wait_for(self._wait_for_shutdown(session_info), timeout=10.0)
+                except asyncio.TimeoutError:
+                    logger.warning(f"Session {session_id} did not shutdown gracefully, terminating")
+
+            # Cleanup session
+            await self._cleanup_session(session_id)
+
+            return True
+
+        except Exception as e:
+            logger.error(f"Failed to remove session for {subscription_identifier}: {e}", exc_info=True)
+            return False
+
+    async def process_frame(self, subscription_identifier: str, frame: Any, display_id: str, frame_timestamp: float) -> bool:
+        """
+        Send a frame to the session process for processing.
+
+        Args:
+            subscription_identifier: Subscription identifier
+            frame: Frame to process
+            display_id: Display identifier
+            frame_timestamp: Timestamp of the frame
+
+        Returns:
+            True if frame was sent successfully
+        """
+        try:
+            session_id = self.subscription_to_session.get(subscription_identifier)
+            if not session_id:
+                logger.warning(f"No session found for subscription {subscription_identifier}")
+                return False
+
+            session_info = self.sessions.get(session_id)
+            if not session_info or not session_info.is_initialized:
+                logger.warning(f"Session {session_id} not initialized")
+                return False
+
+            # Create process frame command
+            process_command = ProcessFrameCommand(
+                session_id=session_id,
+                frame=frame,
+                display_id=display_id,
+                subscription_identifier=subscription_identifier,
+                frame_timestamp=frame_timestamp
+            )
+
+            await self._send_command(session_id, process_command)
+            return True
+
+        except Exception as e:
+            logger.error(f"Failed to process frame for {subscription_identifier}: {e}", exc_info=True)
+            return False
+
+    async def set_session_id(self, subscription_identifier: str, backend_session_id: str, display_id: str) -> bool:
+        """
+        Set the backend session ID for a session.
+
+        Args:
+            subscription_identifier: Subscription identifier
+            backend_session_id: Backend session ID
+            display_id: Display identifier
+
+        Returns:
+            True if session ID was set successfully
+        """
+        try:
+            session_id = self.subscription_to_session.get(subscription_identifier)
+            if not session_id:
+                logger.warning(f"No session found for subscription {subscription_identifier}")
+                return False
+
+            # Create set session ID command
+            set_command = SetSessionIdCommand(
+                session_id=session_id,
+                backend_session_id=backend_session_id,
+                display_id=display_id
+            )
+
+            await self._send_command(session_id, set_command)
+            return True
+
+        except Exception as e:
+            logger.error(f"Failed to set session ID for {subscription_identifier}: {e}", exc_info=True)
+            return False
+
+    def set_detection_result_callback(self, callback: Callable):
+        """Set callback for handling detection results."""
+        self.detection_result_callback = callback
+
+    def set_error_callback(self, callback: Callable):
+        """Set callback for handling errors."""
+        self.error_callback = callback
+
+    def get_session_count(self) -> int:
+        """Get the number of active sessions."""
+        return len(self.sessions)
+
+    def get_session_info(self, subscription_identifier: str) -> Optional[Dict[str, Any]]:
+        """Get information about a session."""
+        session_id = self.subscription_to_session.get(subscription_identifier)
+        if not session_id:
+            return None
+
+        session_info = self.sessions.get(session_id)
+        if not session_info:
+            return None
+
+        return {
+            'session_id': session_id,
+            'subscription_identifier': subscription_identifier,
+            'created_at': session_info.created_at,
+            'is_initialized': session_info.is_initialized,
+            'processed_frames': session_info.processed_frames,
+            'process_pid': session_info.process.pid if session_info.process.is_alive() else None,
+            'is_alive': session_info.process.is_alive()
+        }
+
+    async def _send_command(self, session_id: str, command):
+        """Send command to session process."""
+        session_info = self.sessions.get(session_id)
+        if not session_info:
+            raise ValueError(f"Session {session_id} not found")
+
+        serialized = MessageSerializer.serialize_message(command)
+        session_info.command_queue.put(serialized)
+
+    def _start_response_processing(self, session_info: SessionProcessInfo):
+        """Start processing responses from a session process."""
+        def process_responses():
+            while session_info.session_id in self.sessions and session_info.process.is_alive():
+                try:
+                    if not session_info.response_queue.empty():
+                        response_data = session_info.response_queue.get(timeout=1.0)
+                        response = MessageSerializer.deserialize_message(response_data)
+                        if self.main_event_loop:
+                            asyncio.run_coroutine_threadsafe(
+                                self._handle_response(session_info.session_id, response),
+                                self.main_event_loop
+                            )
+                    else:
+                        time.sleep(0.01)
+                except Exception as e:
+                    logger.error(f"Error processing response from {session_info.session_id}: {e}")
+
+        self.response_executor.submit(process_responses)
+
+    async def _handle_response(self, session_id: str, response):
+        """Handle response from session process."""
+        try:
+            session_info = self.sessions.get(session_id)
+            if not session_info:
+                return
+
+            if response.type == MessageType.INITIALIZED:
+                session_info.is_initialized = response.success
+                if response.success:
+                    logger.info(f"Session {session_id} initialized successfully")
+                else:
+                    logger.error(f"Session {session_id} initialization failed: {response.error_message}")
+
+            elif response.type == MessageType.DETECTION_RESULT:
+                session_info.processed_frames += 1
+                if self.detection_result_callback:
+                    await self.detection_result_callback(session_info.subscription_identifier, response)
+
+            elif response.type == MessageType.SESSION_SET:
+                logger.info(f"Session ID set for {session_id}: {response.backend_session_id}")
+
+            elif response.type == MessageType.HEALTH_RESPONSE:
+                session_info.last_health_check = time.time()
+                logger.debug(f"Health check for {session_id}: {response.status}")
+
+            elif response.type == MessageType.ERROR:
+                logger.error(f"Error from session {session_id}: {response.error_message}")
+                if self.error_callback:
+                    await self.error_callback(session_info.subscription_identifier, response)
+
+        except Exception as e:
+            logger.error(f"Error handling response from {session_id}: {e}", exc_info=True)
+
+    async def _wait_for_shutdown(self, session_info: SessionProcessInfo):
+        """Wait for session process to shutdown gracefully."""
+        while session_info.process.is_alive():
+            await asyncio.sleep(0.1)
+
+    async def _cleanup_session(self, session_id: str):
+        """Cleanup session process and resources."""
+        try:
+            session_info = self.sessions.get(session_id)
+            if not session_info:
+                return
+
+            # Terminate process if still alive
+            if session_info.process.is_alive():
+                session_info.process.terminate()
+                # Wait a bit for graceful termination
+                await asyncio.sleep(1.0)
+                if session_info.process.is_alive():
+                    session_info.process.kill()
+
+            # Remove from tracking
+            del self.sessions[session_id]
+            if session_info.subscription_identifier in self.subscription_to_session:
+                del self.subscription_to_session[session_info.subscription_identifier]
+
+            logger.info(f"Session {session_id} cleaned up")
+
+        except Exception as e:
+            logger.error(f"Error cleaning up session {session_id}: {e}", exc_info=True)
+
+    async def _health_check_loop(self):
+        """Periodic health check of all session processes."""
+        while self.is_running:
+            try:
+                for session_id in list(self.sessions.keys()):
+                    session_info = self.sessions.get(session_id)
+                    if session_info and session_info.is_initialized:
+                        # Send health check
+                        health_command = HealthCheckCommand(session_id=session_id)
+                        await self._send_command(session_id, health_command)
+
+                await asyncio.sleep(self.health_check_interval)
+
+            except asyncio.CancelledError:
+                break
+            except Exception as e:
+                logger.error(f"Error in health check loop: {e}", exc_info=True)
+                await asyncio.sleep(5.0)  # Brief pause before retrying

core/processes/session_worker.py

@@ -0,0 +1,813 @@
+"""
+Session Worker Process - Individual process that handles one session completely.
+Each camera/session gets its own dedicated worker process for complete isolation.
+"""
+
+import asyncio
+import multiprocessing as mp
+import time
+import logging
+import sys
+import os
+import traceback
+import psutil
+import threading
+import cv2
+import requests
+from typing import Dict, Any, Optional, Tuple
+from pathlib import Path
+import numpy as np
+from queue import Queue, Empty
+
+# Import core modules
+from ..models.manager import ModelManager
+from ..detection.pipeline import DetectionPipeline
+from ..models.pipeline import PipelineParser
+from ..logging.session_logger import PerSessionLogger
+from .communication import (
+    MessageSerializer, MessageType, IPCMessageUnion,
+    InitializeCommand, ProcessFrameCommand, SetSessionIdCommand,
+    ShutdownCommand, HealthCheckCommand,
+    InitializedResponse, DetectionResultResponse, SessionSetResponse,
+    ShutdownCompleteResponse, HealthResponse, ErrorResponse
+)
+
+
+class IntegratedStreamReader:
+    """
+    Integrated RTSP/HTTP stream reader for session worker processes.
+    Handles both RTSP streams and HTTP snapshots with automatic failover.
+    """
+
+    def __init__(self, session_id: str, subscription_config: Dict[str, Any], logger: logging.Logger):
+        self.session_id = session_id
+        self.subscription_config = subscription_config
+        self.logger = logger
+
+        # Stream configuration
+        self.rtsp_url = subscription_config.get('rtspUrl')
+        self.snapshot_url = subscription_config.get('snapshotUrl')
+        self.snapshot_interval = subscription_config.get('snapshotInterval', 2000) / 1000.0  # Convert to seconds
+
+        # Stream state
+        self.is_running = False
+        self.rtsp_cap = None
+        self.stream_thread = None
+        self.stop_event = threading.Event()
+
+        # Frame buffer - single latest frame only
+        self.frame_queue = Queue(maxsize=1)
+        self.last_frame_time = 0
+
+        # Stream health monitoring
+        self.consecutive_errors = 0
+        self.max_consecutive_errors = 30
+        self.reconnect_delay = 5.0
+        self.frame_timeout = 10.0  # Seconds without frame before considered dead
+
+        # Crop coordinates if present
+        self.crop_coords = None
+        if subscription_config.get('cropX1') is not None:
+            self.crop_coords = (
+                subscription_config['cropX1'],
+                subscription_config['cropY1'],
+                subscription_config['cropX2'],
+                subscription_config['cropY2']
+            )
+
+    def start(self) -> bool:
+        """Start the stream reading in background thread."""
+        if self.is_running:
+            return True
+
+        try:
+            self.is_running = True
+            self.stop_event.clear()
+
+            # Start background thread for stream reading
+            self.stream_thread = threading.Thread(
+                target=self._stream_loop,
+                name=f"StreamReader-{self.session_id}",
+                daemon=True
+            )
+            self.stream_thread.start()
+
+            self.logger.info(f"Stream reader started for {self.session_id}")
+            return True
+
+        except Exception as e:
+            self.logger.error(f"Failed to start stream reader: {e}")
+            self.is_running = False
+            return False
+
+    def stop(self):
+        """Stop the stream reading."""
+        if not self.is_running:
+            return
+
+        self.logger.info(f"Stopping stream reader for {self.session_id}")
+        self.is_running = False
+        self.stop_event.set()
+
+        # Close RTSP connection
+        if self.rtsp_cap:
+            try:
+                self.rtsp_cap.release()
+            except:
+                pass
+            self.rtsp_cap = None
+
+        # Wait for thread to finish
+        if self.stream_thread and self.stream_thread.is_alive():
+            self.stream_thread.join(timeout=3.0)
+
+    def get_latest_frame(self) -> Optional[Tuple[np.ndarray, str, float]]:
+        """Get the latest frame if available. Returns (frame, display_id, timestamp) or None."""
+        try:
+            # Non-blocking get - return None if no frame available
+            frame_data = self.frame_queue.get_nowait()
+            return frame_data
+        except Empty:
+            return None
+
+    def _stream_loop(self):
+        """Main stream reading loop - runs in background thread."""
+        self.logger.info(f"Stream loop started for {self.session_id}")
+
+        while self.is_running and not self.stop_event.is_set():
+            try:
+                if self.rtsp_url:
+                    # Try RTSP first
+                    self._read_rtsp_stream()
+                elif self.snapshot_url:
+                    # Fallback to HTTP snapshots
+                    self._read_http_snapshots()
+                else:
+                    self.logger.error("No stream URL configured")
+                    break
+
+            except Exception as e:
+                self.logger.error(f"Error in stream loop: {e}")
+                self._handle_stream_error()
+
+        self.logger.info(f"Stream loop ended for {self.session_id}")
+
+    def _read_rtsp_stream(self):
+        """Read frames from RTSP stream."""
+        if not self.rtsp_cap:
+            self._connect_rtsp()
+
+        if not self.rtsp_cap:
+            return
+
+        try:
+            ret, frame = self.rtsp_cap.read()
+
+            if ret and frame is not None:
+                # Process the frame
+                processed_frame = self._process_frame(frame)
+                if processed_frame is not None:
+                    # Extract display ID from subscription identifier
+                    display_id = self.subscription_config['subscriptionIdentifier'].split(';')[-1]
+                    timestamp = time.time()
+
+                    # Put frame in queue (replace if full)
+                    try:
+                        # Clear queue and put new frame
+                        try:
+                            self.frame_queue.get_nowait()
+                        except Empty:
+                            pass
+                        self.frame_queue.put((processed_frame, display_id, timestamp), timeout=0.1)
+                        self.last_frame_time = timestamp
+                        self.consecutive_errors = 0
+                    except:
+                        pass  # Queue full, skip frame
+            else:
+                self._handle_stream_error()
+
+        except Exception as e:
+            self.logger.error(f"Error reading RTSP frame: {e}")
+            self._handle_stream_error()
+
+    def _read_http_snapshots(self):
+        """Read frames from HTTP snapshot URL."""
+        try:
+            response = requests.get(self.snapshot_url, timeout=10)
+            response.raise_for_status()
+
+            # Convert response to numpy array
+            img_array = np.asarray(bytearray(response.content), dtype=np.uint8)
+            frame = cv2.imdecode(img_array, cv2.IMREAD_COLOR)
+
+            if frame is not None:
+                # Process the frame
+                processed_frame = self._process_frame(frame)
+                if processed_frame is not None:
+                    # Extract display ID from subscription identifier
+                    display_id = self.subscription_config['subscriptionIdentifier'].split(';')[-1]
+                    timestamp = time.time()
+
+                    # Put frame in queue (replace if full)
+                    try:
+                        # Clear queue and put new frame
+                        try:
+                            self.frame_queue.get_nowait()
+                        except Empty:
+                            pass
+                        self.frame_queue.put((processed_frame, display_id, timestamp), timeout=0.1)
+                        self.last_frame_time = timestamp
+                        self.consecutive_errors = 0
+                    except:
+                        pass  # Queue full, skip frame
+
+            # Wait for next snapshot interval
+            time.sleep(self.snapshot_interval)
+
+        except Exception as e:
+            self.logger.error(f"Error reading HTTP snapshot: {e}")
+            self._handle_stream_error()
+
+    def _connect_rtsp(self):
+        """Connect to RTSP stream."""
+        try:
+            self.logger.info(f"Connecting to RTSP: {self.rtsp_url}")
+
+            # Create VideoCapture with optimized settings
+            self.rtsp_cap = cv2.VideoCapture(self.rtsp_url)
+
+            # Set buffer size to 1 to reduce latency
+            self.rtsp_cap.set(cv2.CAP_PROP_BUFFERSIZE, 1)
+
+            # Check if connection successful
+            if self.rtsp_cap.isOpened():
+                # Test read a frame
+                ret, frame = self.rtsp_cap.read()
+                if ret and frame is not None:
+                    self.logger.info(f"RTSP connection successful for {self.session_id}")
+                    self.consecutive_errors = 0
+                    return True
+
+            # Connection failed
+            if self.rtsp_cap:
+                self.rtsp_cap.release()
+                self.rtsp_cap = None
+
+        except Exception as e:
+            self.logger.error(f"Failed to connect RTSP: {e}")
+
+        return False
+
+    def _process_frame(self, frame: np.ndarray) -> Optional[np.ndarray]:
+        """Process frame - apply cropping if configured."""
+        if frame is None:
+            return None
+
+        try:
+            # Apply crop if configured
+            if self.crop_coords:
+                x1, y1, x2, y2 = self.crop_coords
+                if x1 < x2 and y1 < y2:
+                    frame = frame[y1:y2, x1:x2]
+
+            return frame
+
+        except Exception as e:
+            self.logger.error(f"Error processing frame: {e}")
+            return None
+
+    def _handle_stream_error(self):
+        """Handle stream errors with reconnection logic."""
+        self.consecutive_errors += 1
+
+        if self.consecutive_errors >= self.max_consecutive_errors:
+            self.logger.error(f"Too many consecutive errors ({self.consecutive_errors}), stopping stream")
+            self.stop()
+            return
+
+        # Close current connection
+        if self.rtsp_cap:
+            try:
+                self.rtsp_cap.release()
+            except:
+                pass
+            self.rtsp_cap = None
+
+        # Wait before reconnecting
+        self.logger.warning(f"Stream error #{self.consecutive_errors}, reconnecting in {self.reconnect_delay}s")
+        time.sleep(self.reconnect_delay)
+
+    def is_healthy(self) -> bool:
+        """Check if stream is healthy (receiving frames)."""
+        if not self.is_running:
+            return False
+
+        # Check if we've received a frame recently
+        if self.last_frame_time > 0:
+            time_since_frame = time.time() - self.last_frame_time
+            return time_since_frame < self.frame_timeout
+
+        return False
+
+
+class SessionWorkerProcess:
+    """
+    Individual session worker process that handles one camera/session completely.
+    Runs in its own process with isolated memory, models, and state.
+    """
+
+    def __init__(self, session_id: str, command_queue: mp.Queue, response_queue: mp.Queue):
+        """
+        Initialize session worker process.
+
+        Args:
+            session_id: Unique session identifier
+            command_queue: Queue to receive commands from main process
+            response_queue: Queue to send responses back to main process
+        """
+        self.session_id = session_id
+        self.command_queue = command_queue
+        self.response_queue = response_queue
+
+        # Process information
+        self.process = None
+        self.start_time = time.time()
+        self.processed_frames = 0
+
+        # Session components (will be initialized in process)
+        self.model_manager = None
+        self.detection_pipeline = None
+        self.pipeline_parser = None
+        self.logger = None
+        self.session_logger = None
+        self.stream_reader = None
+
+        # Session state
+        self.subscription_config = None
+        self.model_config = None
+        self.backend_session_id = None
+        self.display_id = None
+        self.is_initialized = False
+        self.should_shutdown = False
+
+        # Frame processing
+        self.frame_processing_enabled = False
+
+    async def run(self):
+        """
+        Main entry point for the worker process.
+        This method runs in the separate process.
+        """
+        try:
+            # Set process name for debugging
+            mp.current_process().name = f"SessionWorker-{self.session_id}"
+
+            # Setup basic logging first (enhanced after we get subscription config)
+            self._setup_basic_logging()
+
+            self.logger.info(f"Session worker process started for session {self.session_id}")
+            self.logger.info(f"Process ID: {os.getpid()}")
+
+            # Main message processing loop with integrated frame processing
+            while not self.should_shutdown:
+                try:
+                    # Process pending messages
+                    await self._process_pending_messages()
+
+                    # Process frames if enabled and initialized
+                    if self.frame_processing_enabled and self.is_initialized and self.stream_reader:
+                        await self._process_stream_frames()
+
+                    # Brief sleep to prevent busy waiting
+                    await asyncio.sleep(0.01)
+
+                except Exception as e:
+                    self.logger.error(f"Error in main processing loop: {e}", exc_info=True)
+                    self._send_error_response("main_loop_error", str(e), traceback.format_exc())
+
+        except Exception as e:
+            # Critical error in main run loop
+            if self.logger:
+                self.logger.error(f"Critical error in session worker: {e}", exc_info=True)
+            else:
+                print(f"Critical error in session worker {self.session_id}: {e}")
+
+        finally:
+            # Cleanup stream reader
+            if self.stream_reader:
+                self.stream_reader.stop()
+
+            if self.session_logger:
+                self.session_logger.log_session_end()
+            if self.session_logger:
+                self.session_logger.cleanup()
+            if self.logger:
+                self.logger.info(f"Session worker process {self.session_id} shutting down")
+
+    async def _handle_message(self, message: IPCMessageUnion):
+        """
+        Handle incoming messages from main process.
+
+        Args:
+            message: Deserialized message object
+        """
+        try:
+            if message.type == MessageType.INITIALIZE:
+                await self._handle_initialize(message)
+            elif message.type == MessageType.PROCESS_FRAME:
+                await self._handle_process_frame(message)
+            elif message.type == MessageType.SET_SESSION_ID:
+                await self._handle_set_session_id(message)
+            elif message.type == MessageType.SHUTDOWN:
+                await self._handle_shutdown(message)
+            elif message.type == MessageType.HEALTH_CHECK:
+                await self._handle_health_check(message)
+            else:
+                self.logger.warning(f"Unknown message type: {message.type}")
+
+        except Exception as e:
+            self.logger.error(f"Error handling message {message.type}: {e}", exc_info=True)
+            self._send_error_response(f"handle_{message.type.value}_error", str(e), traceback.format_exc())
+
+    async def _handle_initialize(self, message: InitializeCommand):
+        """
+        Initialize the session with models and pipeline.
+
+        Args:
+            message: Initialize command message
+        """
+        try:
+            self.logger.info(f"Initializing session {self.session_id}")
+            self.logger.info(f"Subscription config: {message.subscription_config}")
+            self.logger.info(f"Model config: {message.model_config}")
+
+            # Store configuration
+            self.subscription_config = message.subscription_config
+            self.model_config = message.model_config
+
+            # Setup enhanced logging now that we have subscription config
+            self._setup_enhanced_logging()
+
+            # Initialize model manager (isolated for this process)
+            self.model_manager = ModelManager("models")
+            self.logger.info("Model manager initialized")
+
+            # Download and prepare model if needed
+            model_id = self.model_config.get('modelId')
+            model_url = self.model_config.get('modelUrl')
+            model_name = self.model_config.get('modelName', f'Model-{model_id}')
+
+            if model_id and model_url:
+                model_path = self.model_manager.ensure_model(model_id, model_url, model_name)
+                if not model_path:
+                    raise RuntimeError(f"Failed to download/prepare model {model_id}")
+
+                self.logger.info(f"Model {model_id} prepared at {model_path}")
+
+                # Log model loading
+                if self.session_logger:
+                    self.session_logger.log_model_loading(model_id, model_name, str(model_path))
+
+                # Load pipeline configuration
+                self.pipeline_parser = self.model_manager.get_pipeline_config(model_id)
+                if not self.pipeline_parser:
+                    raise RuntimeError(f"Failed to load pipeline config for model {model_id}")
+
+                self.logger.info(f"Pipeline configuration loaded for model {model_id}")
+
+                # Initialize detection pipeline (isolated for this session)
+                self.detection_pipeline = DetectionPipeline(
+                    pipeline_parser=self.pipeline_parser,
+                    model_manager=self.model_manager,
+                    model_id=model_id,
+                    message_sender=None  # Will be set to send via IPC
+                )
+
+                # Initialize pipeline components
+                if not await self.detection_pipeline.initialize():
+                    raise RuntimeError("Failed to initialize detection pipeline")
+
+                self.logger.info("Detection pipeline initialized successfully")
+
+                # Initialize integrated stream reader
+                self.logger.info("Initializing integrated stream reader")
+                self.stream_reader = IntegratedStreamReader(
+                    self.session_id,
+                    self.subscription_config,
+                    self.logger
+                )
+
+                # Start stream reading
+                if self.stream_reader.start():
+                    self.logger.info("Stream reader started successfully")
+                    self.frame_processing_enabled = True
+                else:
+                    self.logger.error("Failed to start stream reader")
+
+                self.is_initialized = True
+
+                # Send success response
+                response = InitializedResponse(
+                    type=MessageType.INITIALIZED,
+                    session_id=self.session_id,
+                    success=True
+                )
+                self._send_response(response)
+
+            else:
+                raise ValueError("Missing required model configuration (modelId, modelUrl)")
+
+        except Exception as e:
+            self.logger.error(f"Failed to initialize session: {e}", exc_info=True)
+            response = InitializedResponse(
+                type=MessageType.INITIALIZED,
+                session_id=self.session_id,
+                success=False,
+                error_message=str(e)
+            )
+            self._send_response(response)
+
+    async def _handle_process_frame(self, message: ProcessFrameCommand):
+        """
+        Process a frame through the detection pipeline.
+
+        Args:
+            message: Process frame command message
+        """
+        if not self.is_initialized:
+            self._send_error_response("not_initialized", "Session not initialized", None)
+            return
+
+        try:
+            self.logger.debug(f"Processing frame for display {message.display_id}")
+
+            # Process frame through detection pipeline
+            if self.backend_session_id:
+                # Processing phase (after session ID is set)
+                result = await self.detection_pipeline.execute_processing_phase(
+                    frame=message.frame,
+                    display_id=message.display_id,
+                    session_id=self.backend_session_id,
+                    subscription_id=message.subscription_identifier
+                )
+                phase = "processing"
+            else:
+                # Detection phase (before session ID is set)
+                result = await self.detection_pipeline.execute_detection_phase(
+                    frame=message.frame,
+                    display_id=message.display_id,
+                    subscription_id=message.subscription_identifier
+                )
+                phase = "detection"
+
+            self.processed_frames += 1
+
+            # Send result back to main process
+            response = DetectionResultResponse(
+                session_id=self.session_id,
+                detections=result,
+                processing_time=result.get('processing_time', 0.0),
+                phase=phase
+            )
+            self._send_response(response)
+
+        except Exception as e:
+            self.logger.error(f"Error processing frame: {e}", exc_info=True)
+            self._send_error_response("frame_processing_error", str(e), traceback.format_exc())
+
+    async def _handle_set_session_id(self, message: SetSessionIdCommand):
+        """
+        Set the backend session ID for this session.
+
+        Args:
+            message: Set session ID command message
+        """
+        try:
+            self.logger.info(f"Setting backend session ID: {message.backend_session_id}")
+            self.backend_session_id = message.backend_session_id
+            self.display_id = message.display_id
+
+            response = SessionSetResponse(
+                session_id=self.session_id,
+                success=True,
+                backend_session_id=message.backend_session_id
+            )
+            self._send_response(response)
+
+        except Exception as e:
+            self.logger.error(f"Error setting session ID: {e}", exc_info=True)
+            self._send_error_response("set_session_id_error", str(e), traceback.format_exc())
+
+    async def _handle_shutdown(self, message: ShutdownCommand):
+        """
+        Handle graceful shutdown request.
+
+        Args:
+            message: Shutdown command message
+        """
+        try:
+            self.logger.info("Received shutdown request")
+            self.should_shutdown = True
+
+            # Cleanup resources
+            if self.detection_pipeline:
+                # Add cleanup method to pipeline if needed
+                pass
+
+            response = ShutdownCompleteResponse(session_id=self.session_id)
+            self._send_response(response)
+
+        except Exception as e:
+            self.logger.error(f"Error during shutdown: {e}", exc_info=True)
+
+    async def _handle_health_check(self, message: HealthCheckCommand):
+        """
+        Handle health check request.
+
+        Args:
+            message: Health check command message
+        """
+        try:
+            # Get process metrics
+            process = psutil.Process()
+            memory_info = process.memory_info()
+            memory_mb = memory_info.rss / (1024 * 1024)  # Convert to MB
+            cpu_percent = process.cpu_percent()
+
+            # GPU memory (if available)
+            gpu_memory_mb = None
+            try:
+                import torch
+                if torch.cuda.is_available():
+                    gpu_memory_mb = torch.cuda.memory_allocated() / (1024 * 1024)
+            except ImportError:
+                pass
+
+            # Determine health status
+            status = "healthy"
+            if memory_mb > 2048:  # More than 2GB
+                status = "degraded"
+            if memory_mb > 4096:  # More than 4GB
+                status = "unhealthy"
+
+            response = HealthResponse(
+                session_id=self.session_id,
+                status=status,
+                memory_usage_mb=memory_mb,
+                cpu_percent=cpu_percent,
+                gpu_memory_mb=gpu_memory_mb,
+                uptime_seconds=time.time() - self.start_time,
+                processed_frames=self.processed_frames
+            )
+            self._send_response(response)
+
+        except Exception as e:
+            self.logger.error(f"Error checking health: {e}", exc_info=True)
+            self._send_error_response("health_check_error", str(e), traceback.format_exc())
+
+    def _send_response(self, response: IPCMessageUnion):
+        """
+        Send response message to main process.
+
+        Args:
+            response: Response message to send
+        """
+        try:
+            serialized = MessageSerializer.serialize_message(response)
+            self.response_queue.put(serialized)
+        except Exception as e:
+            if self.logger:
+                self.logger.error(f"Failed to send response: {e}")
+
+    def _send_error_response(self, error_type: str, error_message: str, traceback_str: Optional[str]):
+        """
+        Send error response to main process.
+
+        Args:
+            error_type: Type of error
+            error_message: Error message
+            traceback_str: Optional traceback string
+        """
+        error_response = ErrorResponse(
+            type=MessageType.ERROR,
+            session_id=self.session_id,
+            error_type=error_type,
+            error_message=error_message,
+            traceback=traceback_str
+        )
+        self._send_response(error_response)
+
+    def _setup_basic_logging(self):
+        """
+        Setup basic logging for this process before we have subscription config.
+        """
+        logging.basicConfig(
+            level=logging.INFO,
+            format=f"%(asctime)s [%(levelname)s] SessionWorker-{self.session_id}: %(message)s",
+            handlers=[
+                logging.StreamHandler(sys.stdout)
+            ]
+        )
+        self.logger = logging.getLogger(f"session_worker_{self.session_id}")
+
+    def _setup_enhanced_logging(self):
+        """
+        Setup per-session logging with dedicated log file after we have subscription config.
+        Phase 2: Enhanced logging with file rotation and session context.
+        """
+        if not self.subscription_config:
+            return
+
+        # Initialize per-session logger
+        subscription_id = self.subscription_config.get('subscriptionIdentifier', self.session_id)
+
+        self.session_logger = PerSessionLogger(
+            session_id=self.session_id,
+            subscription_identifier=subscription_id,
+            log_dir="logs",
+            max_size_mb=100,
+            backup_count=5
+        )
+
+        # Get the configured logger (replaces basic logger)
+        self.logger = self.session_logger.get_logger()
+
+        # Log session start
+        self.session_logger.log_session_start(os.getpid())
+
+    async def _process_pending_messages(self):
+        """Process pending IPC messages from main process."""
+        try:
+            # Process all pending messages
+            while not self.command_queue.empty():
+                message_data = self.command_queue.get_nowait()
+                message = MessageSerializer.deserialize_message(message_data)
+                await self._handle_message(message)
+        except Exception as e:
+            if not self.command_queue.empty():
+                # Only log error if there was actually a message to process
+                self.logger.error(f"Error processing messages: {e}", exc_info=True)
+
+    async def _process_stream_frames(self):
+        """Process frames from the integrated stream reader."""
+        try:
+            if not self.stream_reader or not self.stream_reader.is_running:
+                return
+
+            # Get latest frame from stream
+            frame_data = self.stream_reader.get_latest_frame()
+            if frame_data is None:
+                return
+
+            frame, display_id, timestamp = frame_data
+
+            # Process frame through detection pipeline
+            subscription_identifier = self.subscription_config['subscriptionIdentifier']
+
+            if self.backend_session_id:
+                # Processing phase (after session ID is set)
+                result = await self.detection_pipeline.execute_processing_phase(
+                    frame=frame,
+                    display_id=display_id,
+                    session_id=self.backend_session_id,
+                    subscription_id=subscription_identifier
+                )
+                phase = "processing"
+            else:
+                # Detection phase (before session ID is set)
+                result = await self.detection_pipeline.execute_detection_phase(
+                    frame=frame,
+                    display_id=display_id,
+                    subscription_id=subscription_identifier
+                )
+                phase = "detection"
+
+            self.processed_frames += 1
+
+            # Send result back to main process
+            response = DetectionResultResponse(
+                type=MessageType.DETECTION_RESULT,
+                session_id=self.session_id,
+                detections=result,
+                processing_time=result.get('processing_time', 0.0),
+                phase=phase
+            )
+            self._send_response(response)
+
+            # Log frame processing (debug level to avoid spam)
+            self.logger.debug(f"Processed frame #{self.processed_frames} from {display_id} (phase: {phase})")
+
+        except Exception as e:
+            self.logger.error(f"Error processing stream frame: {e}", exc_info=True)
+
+
+def session_worker_main(session_id: str, command_queue: mp.Queue, response_queue: mp.Queue):
+    """
+    Main entry point for session worker process.
+    This function is called when the process is spawned.
+    """
+    # Create worker instance
+    worker = SessionWorkerProcess(session_id, command_queue, response_queue)
+
+    # Run the worker
+    asyncio.run(worker.run())