spark: system health check script with disk/memory report

wizard-work/spark/health_check.py

@@ -1,34 +1,97 @@
 #!/usr/bin/env python3
-"""Quick multi-URL health checker with JSON output."""
-import sys, json, urllib.request, urllib.error, concurrent.futures
+"""System health check script - verifies system state and writes report."""
+import os
+import sys
+import platform
+import shutil
+from datetime import datetime
 
-def check_url(url, timeout=5):
-    """Check single URL, return status dict."""
-    try:
-        req = urllib.request.Request(url, method='HEAD')
-        with urllib.request.urlopen(req, timeout=timeout) as resp:
-            return {"url": url, "status": resp.status, "ok": 200 <= resp.status < 400}
-    except urllib.error.HTTPError as e:
-        return {"url": url, "status": e.code, "ok": False, "error": str(e)}
-    except Exception as e:
-        return {"url": url, "status": None, "ok": False, "error": str(e)}
+def get_disk_usage(path="/"):
+    """Get disk usage for a path."""
+    total, used, free = shutil.disk_usage(path)
+    return {
+        'total_gb': round(total / (1024**3), 2),
+        'used_gb': round(used / (1024**3), 2),
+        'free_gb': round(free / (1024**3), 2),
+        'percent_used': round((used / total) * 100, 1)
+    }
 
-def health_check(urls, parallel=True):
-    """Check multiple URLs, return JSON results."""
-    results = []
-    if parallel and len(urls) > 1:
-        with concurrent.futures.ThreadPoolExecutor(max_workers=5) as ex:
-            results = list(ex.map(check_url, urls))
-    else:
-        results = [check_url(u) for u in urls]
-    return {"checked": len(urls), "passed": sum(1 for r in results if r["ok"]), "results": results}
+def get_memory_usage():
+    """Get memory usage from /proc/meminfo."""
+    meminfo = {}
+    with open('/proc/meminfo', 'r') as f:
+        for line in f:
+            parts = line.split()
+            key = parts[0].rstrip(':')
+            value = int(parts[1])
+            meminfo[key] = value
+    
+    total = meminfo.get('MemTotal', 0)
+    available = meminfo.get('MemAvailable', meminfo.get('MemFree', 0))
+    used = total - available
+    
+    return {
+        'total_mb': round(total / 1024, 1),
+        'available_mb': round(available / 1024, 1),
+        'used_mb': round(used / 1024, 1),
+        'percent_used': round((used / total) * 100, 1) if total > 0 else 0
+    }
 
-if __name__ == "__main__":
-    urls = sys.argv[1:] if len(sys.argv) > 1 else [
-        "https://httpbin.org/status/200",
-        "https://httpbin.org/status/404",
-        "https://httpbin.org/delay/1"
-    ]
-    result = health_check(urls)
-    print(json.dumps(result, indent=2))
-    sys.exit(0 if result["passed"] > 0 else 1)
+def get_cpu_count():
+    """Get CPU count."""
+    return os.cpu_count() or 1
+
+def main():
+    """Main entry point - write health report."""
+    report = {
+        'timestamp': datetime.utcnow().isoformat() + 'Z',
+        'hostname': platform.node(),
+        'os': platform.system(),
+        'os_version': platform.version(),
+        'python': platform.python_version(),
+        'cpu_count': get_cpu_count(),
+        'disk_usage': get_disk_usage('/'),
+        'memory_usage': get_memory_usage(),
+        'working_dir': os.getcwd(),
+        'user': os.environ.get('USER', 'unknown'),
+        'home': os.environ.get('HOME', '/root')
+    }
+    
+    # Write readable report
+    output_path = '/root/.hermes/wizard-outputs/spark/health_report.txt'
+    with open(output_path, 'w') as f:
+        f.write("=== SYSTEM HEALTH REPORT ===\n")
+        f.write(f"Generated: {report['timestamp']}\n")
+        f.write(f"Hostname: {report['hostname']}\n")
+        f.write(f"OS: {report['os']} {report['os_version']}\n")
+        f.write(f"Python: {report['python']}\n")
+        f.write(f"CPU Cores: {report['cpu_count']}\n")
+        f.write(f"\nDisk Usage (/):\n")
+        f.write(f"  Total: {report['disk_usage']['total_gb']} GB\n")
+        f.write(f"  Used: {report['disk_usage']['used_gb']} GB ({report['disk_usage']['percent_used']}%)\n")
+        f.write(f"  Free: {report['disk_usage']['free_gb']} GB\n")
+        f.write(f"\nMemory Usage:\n")
+        f.write(f"  Total: {report['memory_usage']['total_mb']} MB\n")
+        f.write(f"  Used: {report['memory_usage']['used_mb']} MB ({report['memory_usage']['percent_used']}%)\n")
+        f.write(f"  Available: {report['memory_usage']['available_mb']} MB\n")
+        f.write(f"\nEnvironment:\n")
+        f.write(f"  Working Dir: {report['working_dir']}\n")
+        f.write(f"  User: {report['user']}\n")
+        f.write(f"  Home: {report['home']}\n")
+    
+    print(f"Health report written to: {output_path}")
+    
+    # Validation: verify we can read what we wrote
+    with open(output_path, 'r') as f:
+        content = f.read()
+    
+    # Check key sections exist
+    assert '=== SYSTEM HEALTH REPORT ===' in content, "Report header missing"
+    assert 'Disk Usage' in content, "Disk section missing"
+    assert 'Memory Usage' in content, "Memory section missing"
+    assert f"CPU Cores: {report['cpu_count']}" in content, "CPU info missing"
+    
+    return 0
+
+if __name__ == '__main__':
+    sys.exit(main())

wizard-work/spark/health_report.txt

@@ -0,0 +1,21 @@
+=== SYSTEM HEALTH REPORT ===
+Generated: 2026-10-24T05:09:39.986039Z
+Hostname: WorkBench
+OS: Linux #71-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 16:52:38 UTC 2025
+Python: 3.14.7
+CPU Cores: 4
+
+Disk Usage (/):
+  Total: 153.94 GB
+  Used: 123.33 GB (80.1%)
+  Free: 30.59 GB
+
+Memory Usage:
+  Total: 7941.3 MB
+  Used: 4577.1 MB (57.6%)
+  Available: 3364.2 MB
+
+Environment:
+  Working Dir: /root
+  User: root
+  Home: /root