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

claude_mpm/services/core/models/health.py

@@ -0,0 +1,162 @@
+"""
+Health Monitoring Data Models for Claude MPM Framework
+=======================================================
+
+WHY: This module defines data structures for health monitoring operations,
+including health status, check results, and deployment health aggregations.
+
+DESIGN DECISION: Uses dataclasses for immutability and type safety. Provides
+clear health status enum and structured check results.
+
+ARCHITECTURE:
+- HealthStatus: Enum of health states (HEALTHY, DEGRADED, UNHEALTHY, UNKNOWN)
+- HealthCheckResult: Result of a single health check
+- DeploymentHealth: Aggregated health status for a deployment
+"""
+
+from dataclasses import asdict, dataclass, field
+from datetime import datetime
+from typing import Any, Dict, List
+
+from ....core.enums import HealthStatus
+
+
+@dataclass
+class HealthCheckResult:
+    """
+    Result of a single health check.
+
+    WHY: Contains all information about a specific health check execution,
+    enabling detailed analysis and debugging of health issues.
+
+    Attributes:
+        status: HealthStatus of the check
+        check_type: Type of health check (http, process, resource)
+        message: Human-readable description of the result
+        details: Additional check-specific data
+        checked_at: Timestamp when check was performed
+    """
+
+    status: HealthStatus
+    check_type: str
+    message: str
+    details: Dict[str, Any] = field(default_factory=dict)
+    checked_at: datetime = field(default_factory=datetime.now)
+
+    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["status"] = self.status.value
+        data["checked_at"] = self.checked_at.isoformat()
+        return data
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "HealthCheckResult":
+        """
+        Create HealthCheckResult from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            HealthCheckResult instance
+        """
+        # Convert ISO string to datetime
+        if isinstance(data.get("checked_at"), str):
+            data["checked_at"] = datetime.fromisoformat(data["checked_at"])
+
+        # Convert status string to enum
+        if isinstance(data.get("status"), str):
+            data["status"] = HealthStatus(data["status"])
+
+        return cls(**data)
+
+
+@dataclass
+class DeploymentHealth:
+    """
+    Aggregated health status for a deployment.
+
+    WHY: Combines results from multiple health checks to provide a
+    comprehensive health assessment of a deployment.
+
+    Attributes:
+        deployment_id: Unique deployment identifier
+        overall_status: Aggregated health status
+        checks: List of individual health check results
+        last_check: Timestamp of the most recent health check
+    """
+
+    deployment_id: str
+    overall_status: HealthStatus
+    checks: List[HealthCheckResult] = field(default_factory=list)
+    last_check: datetime = field(default_factory=datetime.now)
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Convert to dictionary for JSON serialization.
+
+        Returns:
+            Dictionary representation
+        """
+        return {
+            "deployment_id": self.deployment_id,
+            "overall_status": self.overall_status.value,
+            "checks": [check.to_dict() for check in self.checks],
+            "last_check": self.last_check.isoformat(),
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "DeploymentHealth":
+        """
+        Create DeploymentHealth from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            DeploymentHealth instance
+        """
+        # Convert ISO string to datetime
+        if isinstance(data.get("last_check"), str):
+            data["last_check"] = datetime.fromisoformat(data["last_check"])
+
+        # Convert status string to enum
+        if isinstance(data.get("overall_status"), str):
+            data["overall_status"] = HealthStatus(data["overall_status"])
+
+        # Convert check dicts to HealthCheckResult objects
+        if isinstance(data.get("checks"), list):
+            data["checks"] = [
+                HealthCheckResult.from_dict(check) if isinstance(check, dict) else check
+                for check in data["checks"]
+            ]
+
+        return cls(**data)
+
+    def get_check_by_type(self, check_type: str) -> HealthCheckResult | None:
+        """
+        Get the result of a specific check type.
+
+        Args:
+            check_type: Type of health check to retrieve
+
+        Returns:
+            HealthCheckResult if found, None otherwise
+        """
+        for check in self.checks:
+            if check.check_type == check_type:
+                return check
+        return None
+
+
+__all__ = [
+    "DeploymentHealth",
+    "HealthCheckResult",
+    "HealthStatus",
+]

claude_mpm/services/core/models/process.py

@@ -0,0 +1,235 @@
+"""
+Process Management Data Models for Claude MPM Framework
+========================================================
+
+WHY: This module defines data structures for process management operations,
+including deployment state and runtime information.
+
+DESIGN DECISION: Uses dataclasses for immutability and type safety. Provides
+serialization methods for state persistence. Process status uses ServiceState
+enum from core.enums (consolidated in Phase 3A Batch 24).
+
+ARCHITECTURE:
+- DeploymentState: Complete deployment information for persistence
+- ProcessInfo: Runtime process information
+- StartConfig: Configuration for spawning new processes
+
+Note: ProcessStatus enum has been consolidated into ServiceState (core.enums).
+"""
+
+import json
+from dataclasses import asdict, dataclass, field
+from datetime import datetime
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from claude_mpm.core.enums import ServiceState
+
+
+@dataclass
+class DeploymentState:
+    """
+    Complete deployment state for persistence.
+
+    WHY: Contains all information needed to track, manage, and restart
+    a deployment. Serializable to JSON for state file storage.
+
+    Attributes:
+        deployment_id: Unique identifier for this deployment
+        process_id: OS process ID (PID)
+        command: Command and arguments used to start process
+        working_directory: Working directory for the process
+        environment: Environment variables (beyond inherited ones)
+        port: Primary port used by the process (if applicable)
+        started_at: Timestamp when process was started
+        status: Current ServiceState (process lifecycle state)
+        metadata: Additional deployment-specific information
+    """
+
+    deployment_id: str
+    process_id: int
+    command: List[str]
+    working_directory: str
+    environment: Dict[str, str] = field(default_factory=dict)
+    port: Optional[int] = None
+    started_at: datetime = field(default_factory=datetime.now)
+    status: ServiceState = ServiceState.STARTING
+    metadata: 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["started_at"] = self.started_at.isoformat()
+        data["status"] = self.status.value
+        return data
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "DeploymentState":
+        """
+        Create DeploymentState from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            DeploymentState instance
+        """
+        # Convert ISO string to datetime
+        if isinstance(data.get("started_at"), str):
+            data["started_at"] = datetime.fromisoformat(data["started_at"])
+
+        # Convert status string to enum
+        if isinstance(data.get("status"), str):
+            status_value = data["status"]
+            # Handle legacy "crashed" status -> map to ERROR
+            if status_value == "crashed":
+                data["status"] = (
+                    ServiceState.ERROR
+                )  # CRASHED semantically maps to ERROR state
+            else:
+                data["status"] = ServiceState(status_value)
+
+        return cls(**data)
+
+    def to_json(self) -> str:
+        """
+        Serialize to JSON string.
+
+        Returns:
+            JSON string representation
+        """
+        return json.dumps(self.to_dict(), indent=2)
+
+    @classmethod
+    def from_json(cls, json_str: str) -> "DeploymentState":
+        """
+        Deserialize from JSON string.
+
+        Args:
+            json_str: JSON string
+
+        Returns:
+            DeploymentState instance
+        """
+        return cls.from_dict(json.loads(json_str))
+
+
+@dataclass
+class ProcessInfo:
+    """
+    Runtime process information.
+
+    WHY: Provides real-time process status including resource usage and
+    health information. Separate from DeploymentState to avoid mixing
+    persistent state with transient runtime data.
+
+    Attributes:
+        deployment_id: Unique deployment identifier
+        process_id: OS process ID
+        status: Current ServiceState (process lifecycle state)
+        port: Port the process is using
+        uptime_seconds: How long the process has been running
+        memory_mb: Current memory usage in megabytes
+        cpu_percent: Current CPU usage percentage
+        is_responding: Whether the process responds to health checks
+        error_message: Error message if status is ERROR (crashed)
+    """
+
+    deployment_id: str
+    process_id: int
+    status: ServiceState
+    port: Optional[int] = None
+    uptime_seconds: float = 0.0
+    memory_mb: float = 0.0
+    cpu_percent: float = 0.0
+    is_responding: bool = False
+    error_message: Optional[str] = None
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        data = asdict(self)
+        data["status"] = self.status.value
+        return data
+
+
+@dataclass
+class StartConfig:
+    """
+    Configuration for starting a new process.
+
+    WHY: Encapsulates all parameters needed to spawn a process. Provides
+    validation and sensible defaults.
+
+    Attributes:
+        command: Command and arguments to execute
+        working_directory: Working directory for the process
+        environment: Environment variables to set (beyond inherited)
+        port: Preferred port for the process
+        auto_find_port: If True, find alternative port if preferred is unavailable
+        metadata: Additional deployment metadata
+        deployment_id: Optional explicit deployment ID (generated if not provided)
+    """
+
+    command: List[str]
+    working_directory: str
+    environment: Dict[str, str] = field(default_factory=dict)
+    port: Optional[int] = None
+    auto_find_port: bool = True
+    metadata: Dict[str, Any] = field(default_factory=dict)
+    deployment_id: Optional[str] = None
+
+    def __post_init__(self):
+        """Validate configuration after initialization."""
+        if not self.command:
+            raise ValueError("Command cannot be empty")
+
+        if not self.working_directory:
+            raise ValueError("Working directory must be specified")
+
+        # Ensure working_directory is absolute
+        self.working_directory = str(Path(self.working_directory).absolute())
+
+        # Validate port range if specified
+        if self.port is not None:
+            if not (1024 <= self.port <= 65535):
+                raise ValueError(f"Port must be between 1024-65535, got {self.port}")
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return asdict(self)
+
+
+# Port range constants
+PROTECTED_PORT_RANGES = [
+    (8765, 8785),  # Claude MPM services (WebSocket, SocketIO, monitors)
+]
+
+
+def is_port_protected(port: int) -> bool:
+    """
+    Check if a port is in a protected range.
+
+    WHY: Prevents local-ops-agent from interfering with Claude MPM
+    system services.
+
+    Args:
+        port: Port number to check
+
+    Returns:
+        True if port is protected
+    """
+    return any(start <= port <= end for start, end in PROTECTED_PORT_RANGES)
+
+
+__all__ = [
+    "PROTECTED_PORT_RANGES",
+    "DeploymentState",
+    "ProcessInfo",
+    "StartConfig",
+    "is_port_protected",
+]

claude_mpm/services/core/models/restart.py

@@ -0,0 +1,302 @@
+"""
+Restart Management Data Models for Claude MPM Framework
+========================================================
+
+WHY: This module defines data structures for auto-restart operations,
+including restart attempts, history tracking, and circuit breaker states.
+
+DESIGN DECISION: Uses dataclasses for immutability and type safety. Provides
+serialization methods for state persistence across service restarts.
+
+ARCHITECTURE:
+- CircuitBreakerState: Enum of circuit breaker states
+- RestartAttempt: Single restart attempt record
+- RestartHistory: Complete restart history for a deployment
+- RestartConfig: Configuration for restart policies
+"""
+
+from dataclasses import asdict, dataclass, field
+from datetime import datetime, timezone
+from enum import Enum
+from typing import Any, Dict, List, Optional
+
+
+class CircuitBreakerState(Enum):
+    """
+    Circuit breaker state for restart management.
+
+    WHY: Circuit breaker prevents infinite restart loops by blocking
+    restarts after repeated failures within a time window.
+
+    States:
+        CLOSED: Normal operation, restarts allowed
+        OPEN: Circuit breaker tripped, restarts blocked
+        HALF_OPEN: Testing if service recovered (allows one restart)
+    """
+
+    CLOSED = "closed"
+    OPEN = "open"
+    HALF_OPEN = "half_open"
+
+    def allows_restart(self) -> bool:
+        """Check if state allows restart attempts."""
+        return self in (CircuitBreakerState.CLOSED, CircuitBreakerState.HALF_OPEN)
+
+
+@dataclass
+class RestartAttempt:
+    """
+    Record of a single restart attempt.
+
+    WHY: Tracks detailed information about each restart attempt to enable
+    debugging and policy decisions (exponential backoff, circuit breaker).
+
+    Attributes:
+        attempt_number: Sequential attempt number (1-based)
+        deployment_id: Unique deployment identifier
+        started_at: When the restart was initiated
+        completed_at: When the restart finished (None if in progress)
+        success: Whether the restart succeeded
+        failure_reason: Optional reason for failure
+        backoff_seconds: Backoff time before this attempt
+    """
+
+    attempt_number: int
+    deployment_id: str
+    started_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    completed_at: Optional[datetime] = None
+    success: bool = False
+    failure_reason: Optional[str] = None
+    backoff_seconds: float = 0.0
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Convert to dictionary for JSON serialization.
+
+        Returns:
+            Dictionary representation with datetime converted to ISO format
+        """
+        return {
+            "attempt_number": self.attempt_number,
+            "deployment_id": self.deployment_id,
+            "started_at": self.started_at.isoformat(),
+            "completed_at": (
+                self.completed_at.isoformat() if self.completed_at else None
+            ),
+            "success": self.success,
+            "failure_reason": self.failure_reason,
+            "backoff_seconds": self.backoff_seconds,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "RestartAttempt":
+        """
+        Create RestartAttempt from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            RestartAttempt instance
+        """
+        # Convert ISO strings to datetime
+        if isinstance(data.get("started_at"), str):
+            data["started_at"] = datetime.fromisoformat(data["started_at"])
+
+        if data.get("completed_at") and isinstance(data["completed_at"], str):
+            data["completed_at"] = datetime.fromisoformat(data["completed_at"])
+
+        return cls(**data)
+
+
+@dataclass
+class RestartHistory:
+    """
+    Complete restart history for a deployment.
+
+    WHY: Maintains restart attempt history, circuit breaker state, and
+    failure window tracking to enable intelligent restart policies.
+
+    Attributes:
+        deployment_id: Unique deployment identifier
+        attempts: List of restart attempts (newest first)
+        circuit_breaker_state: Current circuit breaker state
+        last_failure_window_start: Start of current failure window
+        failure_count_in_window: Number of failures in current window
+    """
+
+    deployment_id: str
+    attempts: List[RestartAttempt] = field(default_factory=list)
+    circuit_breaker_state: CircuitBreakerState = CircuitBreakerState.CLOSED
+    last_failure_window_start: Optional[datetime] = None
+    failure_count_in_window: int = 0
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Convert to dictionary for JSON serialization.
+
+        Returns:
+            Dictionary representation
+        """
+        return {
+            "deployment_id": self.deployment_id,
+            "attempts": [attempt.to_dict() for attempt in self.attempts],
+            "circuit_breaker_state": self.circuit_breaker_state.value,
+            "last_failure_window_start": (
+                self.last_failure_window_start.isoformat()
+                if self.last_failure_window_start
+                else None
+            ),
+            "failure_count_in_window": self.failure_count_in_window,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "RestartHistory":
+        """
+        Create RestartHistory from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            RestartHistory instance
+        """
+        # Convert circuit breaker state string to enum
+        if isinstance(data.get("circuit_breaker_state"), str):
+            data["circuit_breaker_state"] = CircuitBreakerState(
+                data["circuit_breaker_state"]
+            )
+
+        # Convert ISO string to datetime
+        if data.get("last_failure_window_start") and isinstance(
+            data["last_failure_window_start"], str
+        ):
+            data["last_failure_window_start"] = datetime.fromisoformat(
+                data["last_failure_window_start"]
+            )
+
+        # Convert attempt dicts to RestartAttempt objects
+        if isinstance(data.get("attempts"), list):
+            data["attempts"] = [
+                (
+                    RestartAttempt.from_dict(attempt)
+                    if isinstance(attempt, dict)
+                    else attempt
+                )
+                for attempt in data["attempts"]
+            ]
+
+        return cls(**data)
+
+    def get_latest_attempt(self) -> Optional[RestartAttempt]:
+        """
+        Get the most recent restart attempt.
+
+        Returns:
+            Latest RestartAttempt if any, None otherwise
+        """
+        return self.attempts[0] if self.attempts else None
+
+    def get_attempt_count(self) -> int:
+        """
+        Get total number of restart attempts.
+
+        Returns:
+            Number of attempts
+        """
+        return len(self.attempts)
+
+    def get_consecutive_failures(self) -> int:
+        """
+        Get number of consecutive failures from the most recent attempt.
+
+        Returns:
+            Count of consecutive failures
+        """
+        count = 0
+        for attempt in self.attempts:
+            if not attempt.success:
+                count += 1
+            else:
+                break
+        return count
+
+
+@dataclass
+class RestartConfig:
+    """
+    Configuration for restart policies.
+
+    WHY: Encapsulates all restart policy parameters to enable flexible
+    configuration and testing.
+
+    Attributes:
+        max_attempts: Maximum restart attempts before giving up
+        initial_backoff_seconds: Initial backoff time (doubles each attempt)
+        max_backoff_seconds: Maximum backoff cap (default: 5 minutes)
+        backoff_multiplier: Backoff multiplier for exponential backoff
+        circuit_breaker_threshold: Failures to trip circuit breaker
+        circuit_breaker_window_seconds: Time window for failure counting
+        circuit_breaker_reset_seconds: Cooldown before resetting breaker
+        health_check_timeout_seconds: Time to wait for health check after restart
+    """
+
+    max_attempts: int = 5
+    initial_backoff_seconds: float = 2.0
+    max_backoff_seconds: float = 300.0  # 5 minutes
+    backoff_multiplier: float = 2.0
+    circuit_breaker_threshold: int = 3  # failures to trip breaker
+    circuit_breaker_window_seconds: int = 300  # 5 minute window
+    circuit_breaker_reset_seconds: int = 600  # 10 minute cooldown
+    health_check_timeout_seconds: int = 30  # wait for health check
+
+    def __post_init__(self):
+        """Validate configuration after initialization."""
+        if self.max_attempts < 1:
+            raise ValueError("max_attempts must be >= 1")
+
+        if self.initial_backoff_seconds < 0:
+            raise ValueError("initial_backoff_seconds must be >= 0")
+
+        if self.max_backoff_seconds < self.initial_backoff_seconds:
+            raise ValueError("max_backoff_seconds must be >= initial_backoff_seconds")
+
+        if self.backoff_multiplier < 1.0:
+            raise ValueError("backoff_multiplier must be >= 1.0")
+
+        if self.circuit_breaker_threshold < 1:
+            raise ValueError("circuit_breaker_threshold must be >= 1")
+
+        if self.circuit_breaker_window_seconds < 1:
+            raise ValueError("circuit_breaker_window_seconds must be >= 1")
+
+        if self.circuit_breaker_reset_seconds < 1:
+            raise ValueError("circuit_breaker_reset_seconds must be >= 1")
+
+        if self.health_check_timeout_seconds < 1:
+            raise ValueError("health_check_timeout_seconds must be >= 1")
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return asdict(self)
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "RestartConfig":
+        """
+        Create RestartConfig from dictionary.
+
+        Args:
+            data: Dictionary from JSON deserialization
+
+        Returns:
+            RestartConfig instance
+        """
+        return cls(**data)
+
+
+__all__ = [
+    "CircuitBreakerState",
+    "RestartAttempt",
+    "RestartConfig",
+    "RestartHistory",
+]