claude-mpm 4.1.26__py3-none-any.whl → 4.24.0__py3-none-any.whl

claude_mpm/services/infrastructure/daemon_manager.py

@@ -16,7 +16,6 @@ This service handles:
 - Status monitoring and health checks
 """
 
-import logging
 import os
 import signal
 import subprocess
@@ -32,9 +31,10 @@ except ImportError:
     import psutil
 
 # from claude_mpm.core.base_service import BaseService
+from claude_mpm.core.logging_utils import get_logger
 from claude_mpm.services.socketio.server.main import SocketIOServer
 
-logger = logging.getLogger(__name__)
+logger = get_logger(__name__)
 
 
 class SocketIODaemonManager:
@@ -80,7 +80,7 @@ class SocketIODaemonManager:
             return False
 
         try:
-            with open(self.pid_file) as f:
+            with self.pid_file.open() as f:
                 pid = int(f.read().strip())
 
             # Check if process exists and is running
@@ -107,7 +107,7 @@ class SocketIODaemonManager:
             )
             if response.status_code == 200:
                 return response.json()
-        except:
+        except Exception:
             pass
         return None
 
@@ -135,7 +135,7 @@ class SocketIODaemonManager:
             pid = os.fork()
             if pid > 0:
                 # Parent process - save PID and exit
-                with open(self.pid_file, "w") as f:
+                with self.pid_file.open("w") as f:
                     f.write(str(pid))
                 logger.info(f"Socket.IO server started as daemon (PID: {pid})")
                 return True
@@ -155,7 +155,7 @@ class SocketIODaemonManager:
         os.umask(0)
 
         # Redirect stdout/stderr to log file
-        with open(self.log_file, "a") as log:
+        with self.log_file.open("a") as log:
             os.dup2(log.fileno(), sys.stdout.fileno())
             os.dup2(log.fileno(), sys.stderr.fileno())
 
@@ -199,7 +199,7 @@ class SocketIODaemonManager:
             return False
 
         try:
-            with open(self.pid_file) as f:
+            with self.pid_file.open() as f:
                 pid = int(f.read().strip())
 
             logger.info(f"Stopping Socket.IO server (PID: {pid})")
@@ -254,7 +254,7 @@ class SocketIODaemonManager:
         }
 
         if status_info["running"]:
-            with open(self.pid_file) as f:
+            with self.pid_file.open() as f:
                 status_info["pid"] = int(f.read().strip())
 
             # Check port accessibility
@@ -265,7 +265,7 @@ class SocketIODaemonManager:
                 result = sock.connect_ex((self.host, self.port))
                 sock.close()
                 status_info["port_accessible"] = result == 0
-            except:
+            except Exception:
                 status_info["port_accessible"] = False
 
             # Check for conflicts

claude_mpm/services/infrastructure/logging.py

@@ -11,7 +11,7 @@ Part of TSK-0046: Service Layer Architecture Reorganization
 
 import json
 import logging
-from datetime import datetime
+from datetime import datetime, timezone
 from typing import Any, Dict, List, Optional
 
 from claude_mpm.core.logger import get_logger
@@ -92,7 +92,7 @@ class LoggingService(SyncBaseService, IStructuredLogger):
 
         if self.structured_logging:
             log_entry = {
-                "timestamp": datetime.utcnow().isoformat(),
+                "timestamp": datetime.now(timezone.utc).isoformat(),
                 "level": level,
                 "message": message,
                 "context": context,

claude_mpm/services/infrastructure/monitoring/__init__.py

@@ -3,12 +3,12 @@
 Exports main monitoring components for backward compatibility.
 """
 
+from ....core.enums import HealthStatus
 from .aggregator import MonitoringAggregatorService
 from .base import (
     HealthChecker,
     HealthCheckResult,
     HealthMetric,
-    HealthStatus,
 )
 
 # Legacy exports for backward compatibility

claude_mpm/services/infrastructure/monitoring/aggregator.py

@@ -9,12 +9,12 @@ import time
 from collections import deque
 from typing import Any, Callable, Dict, List, Optional
 
+from ....core.enums import HealthStatus
 from .base import (
     BaseMonitoringService,
     HealthChecker,
     HealthCheckResult,
     HealthMetric,
-    HealthStatus,
 )
 
 
@@ -212,14 +212,14 @@ class MonitoringAggregatorService(BaseMonitoringService):
 
         total_metrics = len(metrics)
 
-        # Critical if any critical metrics
-        if status_counts[HealthStatus.CRITICAL] > 0:
-            return HealthStatus.CRITICAL
+        # Unhealthy if any unhealthy metrics
+        if status_counts[HealthStatus.UNHEALTHY] > 0:
+            return HealthStatus.UNHEALTHY
 
-        # Warning if >30% warning metrics
-        warning_ratio = status_counts[HealthStatus.WARNING] / total_metrics
-        if warning_ratio > 0.3:
-            return HealthStatus.WARNING
+        # Degraded if >30% degraded metrics
+        degraded_ratio = status_counts[HealthStatus.DEGRADED] / total_metrics
+        if degraded_ratio > 0.3:
+            return HealthStatus.DEGRADED
 
         # Unknown if >50% unknown metrics
         unknown_ratio = status_counts[HealthStatus.UNKNOWN] / total_metrics
@@ -375,10 +375,10 @@ class MonitoringAggregatorService(BaseMonitoringService):
         checks_count = len(recent_results)
 
         # Determine aggregated status
-        if status_counts[HealthStatus.CRITICAL] > 0:
-            aggregated_status = HealthStatus.CRITICAL
-        elif status_counts[HealthStatus.WARNING] > checks_count * 0.3:
-            aggregated_status = HealthStatus.WARNING
+        if status_counts[HealthStatus.UNHEALTHY] > 0:
+            aggregated_status = HealthStatus.UNHEALTHY
+        elif status_counts[HealthStatus.DEGRADED] > checks_count * 0.3:
+            aggregated_status = HealthStatus.DEGRADED
         elif status_counts[HealthStatus.UNKNOWN] > checks_count * 0.5:
             aggregated_status = HealthStatus.UNKNOWN
         else:

claude_mpm/services/infrastructure/monitoring/base.py

@@ -7,17 +7,9 @@ import time
 from abc import ABC, abstractmethod
 from dataclasses import asdict, dataclass
 from datetime import datetime, timezone
-from enum import Enum
 from typing import Any, Dict, List, Optional, Union
 
-
-class HealthStatus(Enum):
-    """Health status levels for monitoring."""
-
-    HEALTHY = "healthy"
-    WARNING = "warning"
-    CRITICAL = "critical"
-    UNKNOWN = "unknown"
+from ....core.enums import HealthStatus
 
 
 @dataclass
@@ -75,11 +67,11 @@ class HealthCheckResult:
             "healthy_metrics": len(
                 [m for m in self.metrics if m.status == HealthStatus.HEALTHY]
             ),
-            "warning_metrics": len(
-                [m for m in self.metrics if m.status == HealthStatus.WARNING]
+            "degraded_metrics": len(
+                [m for m in self.metrics if m.status == HealthStatus.DEGRADED]
             ),
-            "critical_metrics": len(
-                [m for m in self.metrics if m.status == HealthStatus.CRITICAL]
+            "unhealthy_metrics": len(
+                [m for m in self.metrics if m.status == HealthStatus.UNHEALTHY]
             ),
         }
 

claude_mpm/services/infrastructure/monitoring/network.py

@@ -6,7 +6,8 @@ Monitors network connectivity, port availability, and socket health.
 import socket
 from typing import Dict, List, Optional
 
-from .base import BaseMonitoringService, HealthMetric, HealthStatus
+from ....core.enums import HealthStatus
+from .base import BaseMonitoringService, HealthMetric
 
 
 class NetworkHealthService(BaseMonitoringService):
@@ -98,7 +99,7 @@ class NetworkHealthService(BaseMonitoringService):
                 HealthMetric(
                     name="socket_creation",
                     value=False,
-                    status=HealthStatus.CRITICAL,
+                    status=HealthStatus.UNHEALTHY,
                     message=f"Failed to create socket: {e}",
                 )
             )
@@ -142,11 +143,11 @@ class NetworkHealthService(BaseMonitoringService):
                     )
                 )
             else:
-                # Determine if this is critical or warning based on endpoint type
+                # Determine if this is unhealthy or degraded based on endpoint type
                 status = (
-                    HealthStatus.WARNING
+                    HealthStatus.DEGRADED
                     if "optional" in name.lower()
-                    else HealthStatus.CRITICAL
+                    else HealthStatus.UNHEALTHY
                 )
                 metrics.append(
                     HealthMetric(
@@ -161,7 +162,7 @@ class NetworkHealthService(BaseMonitoringService):
                 HealthMetric(
                     name=metric_name,
                     value=False,
-                    status=HealthStatus.WARNING,
+                    status=HealthStatus.DEGRADED,
                     message=f"Connection to {host}:{port} timed out after {timeout}s",
                 )
             )

claude_mpm/services/infrastructure/monitoring/process.py

@@ -6,8 +6,9 @@ Monitors individual process health including CPU, memory, file descriptors, and
 from typing import List
 
 from claude_mpm.core.constants import ResourceLimits, TimeoutConfig
+from claude_mpm.core.enums import HealthStatus
 
-from .base import BaseMonitoringService, HealthMetric, HealthStatus
+from .base import BaseMonitoringService, HealthMetric
 
 try:
     import psutil
@@ -66,7 +67,7 @@ class ProcessHealthService(BaseMonitoringService):
                 HealthMetric(
                     name="psutil_availability",
                     value=False,
-                    status=HealthStatus.WARNING,
+                    status=HealthStatus.DEGRADED,
                     message="psutil not available for process monitoring",
                 )
             )
@@ -77,7 +78,7 @@ class ProcessHealthService(BaseMonitoringService):
                 HealthMetric(
                     name="process_exists",
                     value=False,
-                    status=HealthStatus.CRITICAL,
+                    status=HealthStatus.UNHEALTHY,
                     message=f"Process {self.pid} not found",
                 )
             )
@@ -90,7 +91,7 @@ class ProcessHealthService(BaseMonitoringService):
                     HealthMetric(
                         name="process_exists",
                         value=False,
-                        status=HealthStatus.CRITICAL,
+                        status=HealthStatus.UNHEALTHY,
                         message=f"Process {self.pid} is no longer running",
                     )
                 )
@@ -119,7 +120,7 @@ class ProcessHealthService(BaseMonitoringService):
                 HealthMetric(
                     name="process_exists",
                     value=False,
-                    status=HealthStatus.CRITICAL,
+                    status=HealthStatus.UNHEALTHY,
                     message=f"Process {self.pid} no longer exists",
                 )
             )
@@ -153,7 +154,7 @@ class ProcessHealthService(BaseMonitoringService):
                     status=(
                         HealthStatus.HEALTHY
                         if process_healthy
-                        else HealthStatus.CRITICAL
+                        else HealthStatus.UNHEALTHY
                     ),
                     message=f"Process status: {status}",
                 )
@@ -179,9 +180,9 @@ class ProcessHealthService(BaseMonitoringService):
             cpu_status = HealthStatus.HEALTHY
             if cpu_percent > self.cpu_threshold:
                 cpu_status = (
-                    HealthStatus.WARNING
+                    HealthStatus.DEGRADED
                     if cpu_percent < self.cpu_threshold * 1.2
-                    else HealthStatus.CRITICAL
+                    else HealthStatus.UNHEALTHY
                 )
 
             metrics.append(
@@ -213,9 +214,9 @@ class ProcessHealthService(BaseMonitoringService):
             memory_status = HealthStatus.HEALTHY
             if memory_mb > self.memory_threshold_mb:
                 memory_status = (
-                    HealthStatus.WARNING
+                    HealthStatus.DEGRADED
                     if memory_mb < self.memory_threshold_mb * 1.2
-                    else HealthStatus.CRITICAL
+                    else HealthStatus.UNHEALTHY
                 )
 
             metrics.append(
@@ -256,9 +257,9 @@ class ProcessHealthService(BaseMonitoringService):
                 fd_status = HealthStatus.HEALTHY
                 if fd_count > self.fd_threshold:
                     fd_status = (
-                        HealthStatus.WARNING
+                        HealthStatus.DEGRADED
                         if fd_count < self.fd_threshold * 1.2
-                        else HealthStatus.CRITICAL
+                        else HealthStatus.UNHEALTHY
                     )
 
                 metrics.append(

claude_mpm/services/infrastructure/monitoring/resources.py

@@ -5,7 +5,8 @@ Monitors system-wide resource usage including CPU, memory, and disk utilization.
 
 from typing import Dict, List, Optional
 
-from .base import BaseMonitoringService, HealthMetric, HealthStatus
+from ....core.enums import HealthStatus
+from .base import BaseMonitoringService, HealthMetric
 
 try:
     import psutil
@@ -53,7 +54,7 @@ class ResourceMonitorService(BaseMonitoringService):
                 HealthMetric(
                     name="psutil_availability",
                     value=False,
-                    status=HealthStatus.WARNING,
+                    status=HealthStatus.DEGRADED,
                     message="psutil not available for resource monitoring",
                 )
             )
@@ -176,15 +177,15 @@ class ResourceMonitorService(BaseMonitoringService):
         # Load average (Unix only)
         try:
             if hasattr(psutil, "getloadavg"):
-                load1, load5, load15 = psutil.getloadavg()
+                load1, load5, _load15 = psutil.getloadavg()
                 cpu_count = psutil.cpu_count()
 
                 # Load is concerning if > cpu_count
                 load_status = HealthStatus.HEALTHY
                 if load1 > cpu_count:
-                    load_status = HealthStatus.WARNING
+                    load_status = HealthStatus.DEGRADED
                 if load1 > cpu_count * 1.5:
-                    load_status = HealthStatus.CRITICAL
+                    load_status = HealthStatus.UNHEALTHY
 
                 metrics.append(
                     HealthMetric(
@@ -220,8 +221,8 @@ class ResourceMonitorService(BaseMonitoringService):
         if value < threshold:
             return HealthStatus.HEALTHY
         if value < threshold * 1.1:  # 10% above threshold
-            return HealthStatus.WARNING
-        return HealthStatus.CRITICAL
+            return HealthStatus.DEGRADED
+        return HealthStatus.UNHEALTHY
 
     def get_resource_summary(self) -> Optional[Dict[str, float]]:
         """Get quick resource summary without full health check.

claude_mpm/services/infrastructure/monitoring/service.py

@@ -6,7 +6,8 @@ Monitors service-specific metrics like client connections, event processing, and
 import time
 from typing import Any, Dict, List
 
-from .base import BaseMonitoringService, HealthMetric, HealthStatus
+from ....core.enums import HealthStatus
+from .base import BaseMonitoringService, HealthMetric
 
 
 class ServiceHealthService(BaseMonitoringService):
@@ -79,9 +80,9 @@ class ServiceHealthService(BaseMonitoringService):
 
             # Determine status based on thresholds
             if client_count > self.max_clients:
-                client_status = HealthStatus.CRITICAL
+                client_status = HealthStatus.UNHEALTHY
             elif client_count > self.max_clients * 0.8:
-                client_status = HealthStatus.WARNING
+                client_status = HealthStatus.DEGRADED
             else:
                 client_status = HealthStatus.HEALTHY
 
@@ -129,7 +130,7 @@ class ServiceHealthService(BaseMonitoringService):
                 # Determine status based on rate
                 rate_status = HealthStatus.HEALTHY
                 if event_rate == 0 and events_processed > 0:
-                    rate_status = HealthStatus.WARNING  # Processing stopped
+                    rate_status = HealthStatus.DEGRADED  # Processing stopped
 
                 metrics.append(
                     HealthMetric(
@@ -157,9 +158,9 @@ class ServiceHealthService(BaseMonitoringService):
                 queue_size = self.service_stats["event_queue_size"]
                 queue_status = HealthStatus.HEALTHY
                 if queue_size > 1000:
-                    queue_status = HealthStatus.WARNING
+                    queue_status = HealthStatus.DEGRADED
                 if queue_size > 5000:
-                    queue_status = HealthStatus.CRITICAL
+                    queue_status = HealthStatus.UNHEALTHY
 
                 metrics.append(
                     HealthMetric(
@@ -191,9 +192,9 @@ class ServiceHealthService(BaseMonitoringService):
 
             # Determine status based on rate
             if error_rate > self.max_error_rate:
-                error_status = HealthStatus.CRITICAL
+                error_status = HealthStatus.UNHEALTHY
             elif error_rate > self.max_error_rate * 0.5:
-                error_status = HealthStatus.WARNING
+                error_status = HealthStatus.DEGRADED
             else:
                 error_status = HealthStatus.HEALTHY
 
@@ -213,7 +214,7 @@ class ServiceHealthService(BaseMonitoringService):
                     name="total_errors",
                     value=errors,
                     status=(
-                        HealthStatus.HEALTHY if errors == 0 else HealthStatus.WARNING
+                        HealthStatus.HEALTHY if errors == 0 else HealthStatus.DEGRADED
                     ),
                 )
             )
@@ -228,7 +229,7 @@ class ServiceHealthService(BaseMonitoringService):
                         status=(
                             HealthStatus.HEALTHY
                             if recent_errors == 0
-                            else HealthStatus.WARNING
+                            else HealthStatus.DEGRADED
                         ),
                     )
                 )
@@ -263,9 +264,9 @@ class ServiceHealthService(BaseMonitoringService):
 
                 # Determine status based on staleness
                 if time_since_activity > self.stale_activity_seconds * 2:
-                    activity_status = HealthStatus.CRITICAL
+                    activity_status = HealthStatus.UNHEALTHY
                 elif time_since_activity > self.stale_activity_seconds:
-                    activity_status = HealthStatus.WARNING
+                    activity_status = HealthStatus.DEGRADED
                 else:
                     activity_status = HealthStatus.HEALTHY
 
@@ -282,7 +283,7 @@ class ServiceHealthService(BaseMonitoringService):
                     HealthMetric(
                         name="time_since_last_activity",
                         value=-1,
-                        status=HealthStatus.WARNING,
+                        status=HealthStatus.DEGRADED,
                         message="No last activity recorded",
                     )
                 )
@@ -307,9 +308,9 @@ class ServiceHealthService(BaseMonitoringService):
 
             # Determine status based on response time
             if avg_time > 1000:  # > 1 second
-                time_status = HealthStatus.CRITICAL
+                time_status = HealthStatus.UNHEALTHY
             elif avg_time > 500:  # > 500ms
-                time_status = HealthStatus.WARNING
+                time_status = HealthStatus.DEGRADED
             else:
                 time_status = HealthStatus.HEALTHY