claude-mpm 4.13.2__py3-none-any.whl → 4.18.2__py3-none-any.whl

claude_mpm/services/core/models/stability.py

@@ -0,0 +1,264 @@
+"""
+Stability Monitoring Data Models for Claude MPM Framework
+===========================================================
+
+WHY: This module defines data structures for stability monitoring operations,
+including memory leak detection, log pattern matching, and resource usage tracking.
+
+DESIGN DECISION: Uses dataclasses for immutability and type safety. Provides
+clear data structures for proactive monitoring and crash prevention.
+
+ARCHITECTURE:
+- MemoryTrend: Memory usage trend analysis with leak detection
+- LogPatternMatch: Log pattern match with severity and context
+- ResourceUsage: Comprehensive resource usage snapshot
+"""
+
+from dataclasses import asdict, dataclass, field
+from datetime import datetime
+from typing import Any, Dict, List
+
+
+@dataclass
+class MemoryTrend:
+    """
+    Memory usage trend analysis result.
+
+    WHY: Provides structured data for memory leak detection, including
+    historical measurements, slope calculation, and leak detection status.
+
+    Attributes:
+        deployment_id: Unique deployment identifier
+        timestamps: List of measurement timestamps
+        memory_mb: List of memory measurements in megabytes
+        slope_mb_per_minute: Calculated memory growth rate (MB/minute)
+        is_leaking: Whether a memory leak was detected
+        window_size: Number of measurements in the analysis window
+        threshold_mb_per_minute: Leak detection threshold used
+    """
+
+    deployment_id: str
+    timestamps: List[datetime] = field(default_factory=list)
+    memory_mb: List[float] = field(default_factory=list)
+    slope_mb_per_minute: float = 0.0
+    is_leaking: bool = False
+    window_size: int = 0
+    threshold_mb_per_minute: float = 10.0
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Convert to dictionary for JSON serialization.
+
+        Returns:
+            Dictionary representation with datetimes converted to ISO format
+        """
+        data = asdict(self)
+        data["timestamps"] = [ts.isoformat() for ts in self.timestamps]
+        return data
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "MemoryTrend":
+        """
+        Create MemoryTrend from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            MemoryTrend instance
+        """
+        # Convert ISO strings to datetime
+        if isinstance(data.get("timestamps"), list):
+            data["timestamps"] = [
+                datetime.fromisoformat(ts) if isinstance(ts, str) else ts
+                for ts in data["timestamps"]
+            ]
+
+        return cls(**data)
+
+    @property
+    def latest_memory_mb(self) -> float:
+        """Get the most recent memory measurement."""
+        return self.memory_mb[-1] if self.memory_mb else 0.0
+
+    @property
+    def oldest_memory_mb(self) -> float:
+        """Get the oldest memory measurement in the window."""
+        return self.memory_mb[0] if self.memory_mb else 0.0
+
+    @property
+    def time_span_minutes(self) -> float:
+        """Get the time span covered by the measurements in minutes."""
+        if len(self.timestamps) < 2:
+            return 0.0
+        delta = self.timestamps[-1] - self.timestamps[0]
+        return delta.total_seconds() / 60.0
+
+
+@dataclass
+class LogPatternMatch:
+    """
+    Result of a log pattern match.
+
+    WHY: Contains all information about a detected error pattern in logs,
+    enabling analysis, alerting, and debugging of issues before they cause crashes.
+
+    Attributes:
+        deployment_id: Unique deployment identifier
+        pattern: Regex pattern that matched
+        line: The log line that matched
+        timestamp: When the match was detected
+        severity: Error severity level (ERROR, CRITICAL, WARNING)
+        line_number: Line number in log file (if available)
+        context: Additional context lines (before/after)
+    """
+
+    deployment_id: str
+    pattern: str
+    line: str
+    timestamp: datetime = field(default_factory=datetime.now)
+    severity: str = "ERROR"
+    line_number: int = 0
+    context: List[str] = field(default_factory=list)
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Convert to dictionary for JSON serialization.
+
+        Returns:
+            Dictionary representation with datetime converted to ISO format
+        """
+        data = asdict(self)
+        data["timestamp"] = self.timestamp.isoformat()
+        return data
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "LogPatternMatch":
+        """
+        Create LogPatternMatch from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            LogPatternMatch instance
+        """
+        # Convert ISO string to datetime
+        if isinstance(data.get("timestamp"), str):
+            data["timestamp"] = datetime.fromisoformat(data["timestamp"])
+
+        return cls(**data)
+
+    @property
+    def is_critical(self) -> bool:
+        """Check if this match represents a critical error."""
+        return self.severity == "CRITICAL"
+
+
+@dataclass
+class ResourceUsage:
+    """
+    Comprehensive resource usage snapshot.
+
+    WHY: Provides detailed resource consumption metrics across multiple
+    resource types to enable preemptive action before exhaustion.
+
+    Attributes:
+        deployment_id: Unique deployment identifier
+        file_descriptors: Current file descriptor count
+        max_file_descriptors: Maximum file descriptors allowed (ulimit -n)
+        threads: Current thread count
+        connections: Current network connection count
+        disk_free_mb: Free disk space in working directory (MB)
+        is_critical: Whether any resource exceeds 80% threshold
+        timestamp: When the measurement was taken
+        details: Additional resource-specific details
+    """
+
+    deployment_id: str
+    file_descriptors: int = 0
+    max_file_descriptors: int = 0
+    threads: int = 0
+    connections: int = 0
+    disk_free_mb: float = 0.0
+    is_critical: bool = False
+    timestamp: datetime = field(default_factory=datetime.now)
+    details: Dict[str, Any] = field(default_factory=dict)
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Convert to dictionary for JSON serialization.
+
+        Returns:
+            Dictionary representation with datetime converted to ISO format
+        """
+        data = asdict(self)
+        data["timestamp"] = self.timestamp.isoformat()
+        return data
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "ResourceUsage":
+        """
+        Create ResourceUsage from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            ResourceUsage instance
+        """
+        # Convert ISO string to datetime
+        if isinstance(data.get("timestamp"), str):
+            data["timestamp"] = datetime.fromisoformat(data["timestamp"])
+
+        return cls(**data)
+
+    @property
+    def fd_usage_percent(self) -> float:
+        """Calculate file descriptor usage percentage."""
+        if self.max_file_descriptors == 0:
+            return 0.0
+        return (self.file_descriptors / self.max_file_descriptors) * 100.0
+
+    @property
+    def is_fd_critical(self) -> bool:
+        """Check if file descriptor usage is critical (>80%)."""
+        return self.fd_usage_percent >= 80.0  # >= instead of > for 80% exactly
+
+    def get_critical_resources(self) -> List[str]:
+        """
+        Get list of resources at critical levels.
+
+        Returns:
+            List of resource names exceeding 80% threshold
+        """
+        critical = []
+
+        if self.is_fd_critical:
+            critical.append(
+                f"file_descriptors ({self.file_descriptors}/{self.max_file_descriptors})"
+            )
+
+        # Check thread count (threshold from details if available)
+        thread_threshold = self.details.get("thread_threshold", 1000)
+        if self.threads > thread_threshold * 0.8:
+            critical.append(f"threads ({self.threads})")
+
+        # Check connection count (threshold from details if available)
+        connection_threshold = self.details.get("connection_threshold", 500)
+        if self.connections > connection_threshold * 0.8:
+            critical.append(f"connections ({self.connections})")
+
+        # Check disk space (threshold from details if available)
+        disk_threshold_mb = self.details.get("disk_threshold_mb", 100)
+        if self.disk_free_mb < disk_threshold_mb:
+            critical.append(f"disk_space ({self.disk_free_mb:.1f}MB free)")
+
+        return critical
+
+
+__all__ = [
+    "LogPatternMatch",
+    "MemoryTrend",
+    "ResourceUsage",
+]

claude_mpm/services/core/path_resolver.py

@@ -13,6 +13,7 @@ that was previously embedded in FrameworkLoader. It manages:
 The service consolidates path management logic while maintaining backward compatibility.
 """
 
+import os
 import subprocess
 from enum import Enum
 from pathlib import Path
@@ -74,10 +75,25 @@ class PathResolver(IPathResolver):
             return path_obj
 
         if base_dir is None:
-            base_dir = Path.cwd()
+            base_dir = self._get_working_dir()
 
         return (base_dir / path_obj).resolve()
 
+    def _get_working_dir(self) -> Path:
+        """Get working directory respecting CLAUDE_MPM_USER_PWD.
+
+        When Claude MPM runs from a global installation, CLAUDE_MPM_USER_PWD
+        contains the user's actual working directory. This ensures project-local
+        paths are resolved correctly.
+
+        Returns:
+            Path: The user's working directory
+        """
+        user_pwd = os.environ.get("CLAUDE_MPM_USER_PWD")
+        if user_pwd:
+            return Path(user_pwd)
+        return Path.cwd()
+
     def validate_path(self, path: Path, must_exist: bool = False) -> bool:
         """
         Validate a path for security and existence.
@@ -129,7 +145,7 @@ class PathResolver(IPathResolver):
             Project root path or None if not found
         """
         if start_path is None:
-            start_path = Path.cwd()
+            start_path = self._get_working_dir()
 
         start_path = start_path.resolve()
 
@@ -265,7 +281,7 @@ class PathResolver(IPathResolver):
 
         if agents_dir and agents_dir.exists():
             discovered_agents_dir = agents_dir
-            self.logger.info(f"Using custom agents directory: {discovered_agents_dir}")
+            self.logger.debug(f"Using custom agents directory: {discovered_agents_dir}")
         elif framework_path and framework_path != Path("__PACKAGED__"):
             # Prioritize templates directory over main agents directory
             templates_dir = (
@@ -299,7 +315,7 @@ class PathResolver(IPathResolver):
         paths = {"project": None, "user": None, "system": None}
 
         # Project-specific instructions
-        project_path = Path.cwd() / ".claude-mpm" / "INSTRUCTIONS.md"
+        project_path = self._get_working_dir() / ".claude-mpm" / "INSTRUCTIONS.md"
         if project_path.exists():
             paths["project"] = project_path
 
@@ -423,11 +439,11 @@ class PathResolver(IPathResolver):
         """Check common locations for claude-mpm."""
         candidates = [
             # Current directory (if we're already in claude-mpm)
-            Path.cwd(),
+            self._get_working_dir(),
             # Development location
             Path.home() / "Projects" / "claude-mpm",
             # Current directory subdirectory
-            Path.cwd() / "claude-mpm",
+            self._get_working_dir() / "claude-mpm",
         ]
 
         for candidate in candidates:
@@ -487,7 +503,7 @@ class PathResolver(IPathResolver):
             pass
 
         # Check if we're in development
-        if (Path.cwd() / "pyproject.toml").exists():
+        if (self._get_working_dir() / "pyproject.toml").exists():
             return DeploymentContext.DEVELOPMENT
 
         return DeploymentContext.UNKNOWN

claude_mpm/services/diagnostics/__init__.py

@@ -13,6 +13,6 @@ DESIGN DECISIONS:
 
 from .diagnostic_runner import DiagnosticRunner
 from .doctor_reporter import DoctorReporter
-from .models import DiagnosticResult, DiagnosticStatus
+from .models import DiagnosticResult
 
-__all__ = ["DiagnosticResult", "DiagnosticRunner", "DiagnosticStatus", "DoctorReporter"]
+__all__ = ["DiagnosticResult", "DiagnosticRunner", "DoctorReporter"]

claude_mpm/services/diagnostics/checks/agent_check.py

@@ -6,7 +6,8 @@ WHY: Verify that agents are properly deployed, up-to-date, and functioning corre
 
 from pathlib import Path
 
-from ..models import DiagnosticResult, DiagnosticStatus
+from ....core.enums import OperationResult, ValidationSeverity
+from ..models import DiagnosticResult
 from .base_check import BaseDiagnosticCheck
 
 
@@ -64,29 +65,29 @@ class AgentCheck(BaseDiagnosticCheck):
             available_count = details["available_count"]
 
             if deployed_count == 0:
-                status = DiagnosticStatus.ERROR
+                status = ValidationSeverity.ERROR
                 message = f"No agents deployed (0/{available_count} available)"
                 fix_command = "claude-mpm agents deploy"
                 fix_description = "Deploy all available agents"
             elif deployed_count < available_count:
-                status = DiagnosticStatus.WARNING
+                status = ValidationSeverity.WARNING
                 message = f"{deployed_count}/{available_count} agents deployed"
                 fix_command = "claude-mpm agents deploy"
                 fix_description = (
                     f"Deploy remaining {available_count - deployed_count} agents"
                 )
-            elif any(r.status == DiagnosticStatus.ERROR for r in sub_results):
-                status = DiagnosticStatus.ERROR
+            elif any(r.status == ValidationSeverity.ERROR for r in sub_results):
+                status = ValidationSeverity.ERROR
                 message = "Agents have critical issues"
                 fix_command = None
                 fix_description = None
-            elif any(r.status == DiagnosticStatus.WARNING for r in sub_results):
-                status = DiagnosticStatus.WARNING
+            elif any(r.status == ValidationSeverity.WARNING for r in sub_results):
+                status = ValidationSeverity.WARNING
                 message = "Agents have minor issues"
                 fix_command = None
                 fix_description = None
             else:
-                status = DiagnosticStatus.OK
+                status = OperationResult.SUCCESS
                 message = f"All {deployed_count} agents properly deployed"
                 fix_command = None
                 fix_description = None
@@ -104,7 +105,7 @@ class AgentCheck(BaseDiagnosticCheck):
         except Exception as e:
             return DiagnosticResult(
                 category=self.category,
-                status=DiagnosticStatus.ERROR,
+                status=ValidationSeverity.ERROR,
                 message=f"Agent check failed: {e!s}",
                 details={"error": str(e)},
             )
@@ -127,7 +128,7 @@ class AgentCheck(BaseDiagnosticCheck):
             # Neither exists, default to user directory for error message
             return DiagnosticResult(
                 category="Deployed Agents",
-                status=DiagnosticStatus.ERROR,
+                status=ValidationSeverity.ERROR,
                 message="No agents directory found (checked project and user)",
                 details={
                     "project_path": str(project_agents_dir),
@@ -144,7 +145,7 @@ class AgentCheck(BaseDiagnosticCheck):
         if not agent_files:
             return DiagnosticResult(
                 category="Deployed Agents",
-                status=DiagnosticStatus.ERROR,
+                status=ValidationSeverity.ERROR,
                 message=f"No agents deployed in {location} directory",
                 details={"path": str(agents_dir), "location": location, "count": 0},
                 fix_command="claude-mpm agents deploy",
@@ -159,7 +160,7 @@ class AgentCheck(BaseDiagnosticCheck):
         if missing_core:
             return DiagnosticResult(
                 category="Deployed Agents",
-                status=DiagnosticStatus.WARNING,
+                status=ValidationSeverity.WARNING,
                 message=f"Missing core agents in {location}: {', '.join(missing_core)}",
                 details={
                     "path": str(agents_dir),
@@ -174,7 +175,7 @@ class AgentCheck(BaseDiagnosticCheck):
 
         return DiagnosticResult(
             category="Deployed Agents",
-            status=DiagnosticStatus.OK,
+            status=OperationResult.SUCCESS,
             message=f"{len(agent_files)} agents deployed ({location} level)",
             details={
                 "path": str(agents_dir),
@@ -205,7 +206,7 @@ class AgentCheck(BaseDiagnosticCheck):
             else:
                 return DiagnosticResult(
                     category="Agent Versions",
-                    status=DiagnosticStatus.SKIPPED,
+                    status=OperationResult.SKIPPED,
                     message="No agents to check",
                     details={},
                 )
@@ -224,7 +225,7 @@ class AgentCheck(BaseDiagnosticCheck):
             if outdated:
                 return DiagnosticResult(
                     category="Agent Versions",
-                    status=DiagnosticStatus.WARNING,
+                    status=ValidationSeverity.WARNING,
                     message=f"{len(outdated)} agent(s) outdated",
                     details={"outdated": outdated, "checked": checked},
                     fix_command="claude-mpm agents update",
@@ -234,14 +235,14 @@ class AgentCheck(BaseDiagnosticCheck):
             if checked == 0:
                 return DiagnosticResult(
                     category="Agent Versions",
-                    status=DiagnosticStatus.WARNING,
+                    status=ValidationSeverity.WARNING,
                     message="No agents to check",
                     details={"checked": 0},
                 )
 
             return DiagnosticResult(
                 category="Agent Versions",
-                status=DiagnosticStatus.OK,
+                status=OperationResult.SUCCESS,
                 message=f"All {checked} agents up-to-date",
                 details={"checked": checked},
             )
@@ -249,7 +250,7 @@ class AgentCheck(BaseDiagnosticCheck):
         except Exception as e:
             return DiagnosticResult(
                 category="Agent Versions",
-                status=DiagnosticStatus.WARNING,
+                status=ValidationSeverity.WARNING,
                 message=f"Could not check versions: {e!s}",
                 details={"error": str(e)},
             )
@@ -273,7 +274,7 @@ class AgentCheck(BaseDiagnosticCheck):
             else:
                 return DiagnosticResult(
                     category="Agent Validation",
-                    status=DiagnosticStatus.SKIPPED,
+                    status=OperationResult.SKIPPED,
                     message="No agents to validate",
                     details={},
                 )
@@ -301,14 +302,14 @@ class AgentCheck(BaseDiagnosticCheck):
             if invalid:
                 return DiagnosticResult(
                     category="Agent Validation",
-                    status=DiagnosticStatus.WARNING,
+                    status=ValidationSeverity.WARNING,
                     message=f"{len(invalid)} validation issue(s)",
                     details={"issues": invalid, "validated": validated},
                 )
 
             return DiagnosticResult(
                 category="Agent Validation",
-                status=DiagnosticStatus.OK,
+                status=OperationResult.SUCCESS,
                 message=f"All {validated} agents valid",
                 details={"validated": validated},
             )
@@ -316,7 +317,7 @@ class AgentCheck(BaseDiagnosticCheck):
         except Exception as e:
             return DiagnosticResult(
                 category="Agent Validation",
-                status=DiagnosticStatus.WARNING,
+                status=ValidationSeverity.WARNING,
                 message=f"Validation failed: {e!s}",
                 details={"error": str(e)},
             )
@@ -358,14 +359,14 @@ class AgentCheck(BaseDiagnosticCheck):
         if issues:
             return DiagnosticResult(
                 category="Common Issues",
-                status=DiagnosticStatus.WARNING,
+                status=ValidationSeverity.WARNING,
                 message=f"{len(issues)} issue(s) found",
                 details={"issues": issues},
             )
 
         return DiagnosticResult(
             category="Common Issues",
-            status=DiagnosticStatus.OK,
+            status=OperationResult.SUCCESS,
             message="No common issues detected",
             details={},
         )