backup

src/server/api/health.py

@@ -0,0 +1,266 @@
+"""Health check endpoints for system monitoring and status verification."""
+
+import logging
+from datetime import datetime
+from typing import Any, Dict, Optional
+
+import psutil
+from fastapi import APIRouter, Depends, HTTPException
+from pydantic import BaseModel
+from sqlalchemy import text
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from src.server.utils.dependencies import get_database_session
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/health", tags=["health"])
+
+
+class HealthStatus(BaseModel):
+    """Basic health status response."""
+
+    status: str
+    timestamp: str
+    version: str = "1.0.0"
+
+
+class DatabaseHealth(BaseModel):
+    """Database health status."""
+
+    status: str
+    connection_time_ms: float
+    message: Optional[str] = None
+
+
+class SystemMetrics(BaseModel):
+    """System resource metrics."""
+
+    cpu_percent: float
+    memory_percent: float
+    memory_available_mb: float
+    disk_percent: float
+    disk_free_mb: float
+    uptime_seconds: float
+
+
+class DependencyHealth(BaseModel):
+    """Health status of external dependencies."""
+
+    database: DatabaseHealth
+    filesystem: Dict[str, Any]
+    system: SystemMetrics
+
+
+class DetailedHealthStatus(BaseModel):
+    """Comprehensive health check response."""
+
+    status: str
+    timestamp: str
+    version: str = "1.0.0"
+    dependencies: DependencyHealth
+    startup_time: datetime
+
+
+# Global startup time
+startup_time = datetime.now()
+
+
+async def check_database_health(db: AsyncSession) -> DatabaseHealth:
+    """Check database connection and performance.
+
+    Args:
+        db: Database session dependency.
+
+    Returns:
+        DatabaseHealth: Database status and connection time.
+    """
+    try:
+        import time
+
+        start_time = time.time()
+        await db.execute(text("SELECT 1"))
+        connection_time = (time.time() - start_time) * 1000  # Convert to milliseconds
+
+        return DatabaseHealth(
+            status="healthy",
+            connection_time_ms=connection_time,
+            message="Database connection successful",
+        )
+    except Exception as e:
+        logger.error(f"Database health check failed: {e}")
+        return DatabaseHealth(
+            status="unhealthy",
+            connection_time_ms=0,
+            message=f"Database connection failed: {str(e)}",
+        )
+
+
+async def check_filesystem_health() -> Dict[str, Any]:
+    """Check filesystem availability and permissions.
+
+    Returns:
+        dict: Filesystem status and available space.
+    """
+    try:
+        import os
+
+        data_dir = "data"
+        logs_dir = "logs"
+
+        data_accessible = os.path.exists(data_dir) and os.access(data_dir, os.W_OK)
+        logs_accessible = os.path.exists(logs_dir) and os.access(logs_dir, os.W_OK)
+
+        return {
+            "status": "healthy" if (data_accessible and logs_accessible) else "degraded",
+            "data_dir_writable": data_accessible,
+            "logs_dir_writable": logs_accessible,
+            "message": "Filesystem check completed",
+        }
+    except Exception as e:
+        logger.error(f"Filesystem health check failed: {e}")
+        return {
+            "status": "unhealthy",
+            "message": f"Filesystem check failed: {str(e)}",
+        }
+
+
+def get_system_metrics() -> SystemMetrics:
+    """Get system resource metrics.
+
+    Returns:
+        SystemMetrics: CPU, memory, disk, and uptime information.
+    """
+    try:
+        import os
+        import time
+
+        # CPU usage
+        cpu_percent = psutil.cpu_percent(interval=1)
+
+        # Memory usage
+        memory_info = psutil.virtual_memory()
+        memory_percent = memory_info.percent
+        memory_available_mb = memory_info.available / (1024 * 1024)
+
+        # Disk usage
+        disk_info = psutil.disk_usage("/")
+        disk_percent = disk_info.percent
+        disk_free_mb = disk_info.free / (1024 * 1024)
+
+        # Uptime
+        boot_time = psutil.boot_time()
+        uptime_seconds = time.time() - boot_time
+
+        return SystemMetrics(
+            cpu_percent=cpu_percent,
+            memory_percent=memory_percent,
+            memory_available_mb=memory_available_mb,
+            disk_percent=disk_percent,
+            disk_free_mb=disk_free_mb,
+            uptime_seconds=uptime_seconds,
+        )
+    except Exception as e:
+        logger.error(f"System metrics collection failed: {e}")
+        raise HTTPException(
+            status_code=500, detail=f"Failed to collect system metrics: {str(e)}"
+        )
+
+
+@router.get("", response_model=HealthStatus)
+async def basic_health_check() -> HealthStatus:
+    """Basic health check endpoint.
+
+    Returns:
+        HealthStatus: Simple health status with timestamp.
+    """
+    logger.debug("Basic health check requested")
+    return HealthStatus(
+        status="healthy",
+        timestamp=datetime.now().isoformat(),
+    )
+
+
+@router.get("/detailed", response_model=DetailedHealthStatus)
+async def detailed_health_check(
+    db: AsyncSession = Depends(get_database_session),
+) -> DetailedHealthStatus:
+    """Comprehensive health check endpoint.
+
+    Checks database, filesystem, and system metrics.
+
+    Args:
+        db: Database session dependency.
+
+    Returns:
+        DetailedHealthStatus: Comprehensive health information.
+    """
+    logger.debug("Detailed health check requested")
+
+    try:
+        # Check dependencies
+        database_health = await check_database_health(db)
+        filesystem_health = await check_filesystem_health()
+        system_metrics = get_system_metrics()
+
+        # Determine overall status
+        overall_status = "healthy"
+        if database_health.status != "healthy":
+            overall_status = "degraded"
+        if filesystem_health.get("status") != "healthy":
+            overall_status = "degraded"
+
+        dependencies = DependencyHealth(
+            database=database_health,
+            filesystem=filesystem_health,
+            system=system_metrics,
+        )
+
+        return DetailedHealthStatus(
+            status=overall_status,
+            timestamp=datetime.now().isoformat(),
+            dependencies=dependencies,
+            startup_time=startup_time,
+        )
+    except Exception as e:
+        logger.error(f"Detailed health check failed: {e}")
+        raise HTTPException(status_code=500, detail="Health check failed")
+
+
+@router.get("/metrics", response_model=SystemMetrics)
+async def get_metrics() -> SystemMetrics:
+    """Get system resource metrics.
+
+    Returns:
+        SystemMetrics: Current CPU, memory, disk, and uptime metrics.
+    """
+    logger.debug("System metrics requested")
+    return get_system_metrics()
+
+
+@router.get("/metrics/prometheus")
+async def get_prometheus_metrics() -> str:
+    """Get metrics in Prometheus format.
+
+    Returns:
+        str: Prometheus formatted metrics.
+    """
+    from src.server.utils.metrics import get_metrics_collector
+
+    logger.debug("Prometheus metrics requested")
+    collector = get_metrics_collector()
+    return collector.export_prometheus_format()
+
+
+@router.get("/metrics/json")
+async def get_metrics_json() -> Dict[str, Any]:
+    """Get metrics as JSON.
+
+    Returns:
+        dict: Metrics in JSON format.
+    """
+    from src.server.utils.metrics import get_metrics_collector
+
+    logger.debug("JSON metrics requested")
+    collector = get_metrics_collector()
+    return collector.export_json()