spark: add system metrics collector script with JSON output

wizard-work/spark/sys_metrics.py

@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+"""System metrics collector - outputs JSON to stdout."""
+
+import json
+import os
+import shutil
+
+def get_disk_usage():
+    """Get disk usage for root filesystem."""
+    usage = shutil.disk_usage('/')
+    return {
+        "total": usage.total,
+        "used": usage.used,
+        "free": usage.free,
+        "percent_used": round(usage.used / usage.total * 100, 2)
+    }
+
+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) * 1024
+    available = meminfo.get('MemAvailable', meminfo.get('MemFree', 0)) * 1024
+    used = total - available
+    
+    return {
+        "total": total,
+        "used": used,
+        "available": available,
+        "percent_used": round(used / total * 100, 2) if total > 0 else 0
+    }
+
+def get_load_average():
+    """Get system load average."""
+    load1, load5, load15 = os.getloadavg()
+    return {
+        "1min": load1,
+        "5min": load5,
+        "15min": load15
+    }
+
+def get_uptime():
+    """Get system uptime in seconds."""
+    with open('/proc/uptime', 'r') as f:
+        uptime_seconds = float(f.readline().split()[0])
+    return round(uptime_seconds, 2)
+
+def main():
+    metrics = {
+        "disk": get_disk_usage(),
+        "memory": get_memory_usage(),
+        "load_average": get_load_average(),
+        "uptime_seconds": get_uptime()
+    }
+    print(json.dumps(metrics, indent=2))
+
+if __name__ == "__main__":
+    main()

wizard-work/spark/verify_metrics.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+"""Verify sys_metrics.py produces valid JSON output."""
+
+import json
+import subprocess
+
+result = subprocess.run(
+    ['python3', '/root/.hermes/wizard-outputs/spark/sys_metrics.py'],
+    capture_output=True,
+    text=True
+)
+
+if result.returncode != 0:
+    print(f"FAILED: Script exited with code {result.returncode}")
+    exit(1)
+
+try:
+    data = json.loads(result.stdout)
+except json.JSONDecodeError as e:
+    print(f"FAILED: Invalid JSON - {e}")
+    exit(1)
+
+required_keys = ['disk', 'memory', 'load_average', 'uptime_seconds']
+for key in required_keys:
+    if key not in data:
+        print(f"FAILED: Missing key '{key}'")
+        exit(1)
+
+# Verify disk has required fields
+disk_fields = ['total', 'used', 'free', 'percent_used']
+for field in disk_fields:
+    if field not in data['disk']:
+        print(f"FAILED: Disk missing field '{field}'")
+        exit(1)
+
+# Verify memory has required fields
+mem_fields = ['total', 'used', 'available', 'percent_used']
+for field in mem_fields:
+    if field not in data['memory']:
+        print(f"FAILED: Memory missing field '{field}'")
+        exit(1)
+
+# Verify load_average has required fields
+load_fields = ['1min', '5min', '15min']
+for field in load_fields:
+    if field not in data['load_average']:
+        print(f"FAILED: Load average missing field '{field}'")
+        exit(1)
+
+print("VERIFIED: sys_metrics.py produces valid JSON with all required fields")
+print(f"Keys: {list(data.keys())}")
+print(f"Disk usage: {data['disk']['percent_used']}%")
+print(f"Memory usage: {data['memory']['percent_used']}%")
+print(f"Load average: {data['load_average']['1min']}")
+print(f"Uptime: {data['uptime_seconds']} seconds")