File size: 12,603 Bytes
6993919 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 | #!/usr/bin/env python3
"""
RMI Health Monitoring Cron
============================
Checks: backend health, worker health (base + solana), Redis connectivity.
POSTs alerts to a webhook if anything is down.
Run via cron every 1-5 minutes:
*/2 * * * * cd /root/backend && python3 scripts/health_monitor.py >> /var/log/rmi_health.log 2>&1
Environment variables:
HEALTH_WEBHOOK_URL β webhook URL for alerts (Slack, Discord, PagerDuty, etc.)
BACKEND_URL β backend health endpoint (default: http://localhost:8000/health)
REDIS_HOST β Redis host (default: localhost)
REDIS_PORT β Redis port (default: 6379)
REDIS_PASSWORD β Redis password (default: empty)
BASE_WORKER_URL β Base worker health endpoint
SOLANA_WORKER_URL β Solana worker health endpoint
Author: RMI Development
Date: 2026-05-20
"""
import json
import logging
import os
import sys
import time
import urllib.error
import urllib.request
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s [%(levelname)s] %(message)s",
)
logger = logging.getLogger("health_monitor")
# ββ Configuration βββββββββββββββββββββββββββββββββββββββββββββββββ
HEALTH_WEBHOOK_URL = os.getenv("HEALTH_WEBHOOK_URL", "")
BACKEND_URL = os.getenv("BACKEND_URL", "http://localhost:8000/health")
REDIS_HOST = os.getenv("REDIS_HOST", "localhost")
REDIS_PORT = int(os.getenv("REDIS_PORT", "6379"))
REDIS_PASSWORD = os.getenv("REDIS_PASSWORD", "")
BASE_WORKER_URL = os.getenv("BASE_WORKER_URL", "http://localhost:8000/api/v1/x402/fallback/status")
SOLANA_WORKER_URL = os.getenv("SOLANA_WORKER_URL", "")
CHECK_TIMEOUT = 10 # seconds
ALERT_COOLDOWN = 300 # 5 minutes β don't re-alert for same service within this window
# Track last alert time per service to avoid spam
_last_alerts: dict = {}
def _load_cooldown_state():
"""Load alert cooldown state from file (survives restarts)."""
try:
state_file = "/tmp/rmi_health_cooldown.json"
if os.path.exists(state_file):
with open(state_file) as f:
return json.load(f)
except Exception:
pass
return {}
def _save_cooldown_state(state: dict):
"""Save alert cooldown state to file."""
try:
state_file = "/tmp/rmi_health_cooldown.json"
with open(state_file, "w") as f:
json.dump(state, f)
except Exception:
pass
def _should_alert(service: str) -> bool:
"""Check if we should send an alert (respects cooldown)."""
now = time.time()
state = _load_cooldown_state()
last = state.get(service, 0)
if now - last < ALERT_COOLDOWN:
return False
state[service] = now
_save_cooldown_state(state)
return True
# ββ Health checks ββββββββββββββββββββββββββββββββββββββββββββββββββ
def check_backend() -> dict:
"""Check backend /health endpoint."""
try:
req = urllib.request.Request(BACKEND_URL, method="GET")
req.add_header("Accept", "application/json")
with urllib.request.urlopen(req, timeout=CHECK_TIMEOUT) as resp:
data = json.loads(resp.read().decode())
return {"service": "backend", "status": "healthy", "details": data}
except Exception as e:
return {"service": "backend", "status": "down", "error": str(e)[:200]}
def check_redis() -> dict:
"""Check Redis connectivity."""
try:
import redis
r = redis.Redis(
host=REDIS_HOST,
port=REDIS_PORT,
password=REDIS_PASSWORD,
decode_responses=True,
)
r.ping()
info = r.info("server")
return {
"service": "redis",
"status": "healthy",
"details": {
"version": info.get("redis_version", "unknown"),
"uptime_seconds": info.get("uptime_in_seconds", 0),
"connected_clients": info.get("connected_clients", 0),
"used_memory_human": info.get("used_memory_human", "unknown"),
},
}
except Exception as e:
return {"service": "redis", "status": "down", "error": str(e)[:200]}
def check_base_worker() -> dict:
"""Check Base x402 worker/gateway health."""
try:
req = urllib.request.Request(BASE_WORKER_URL, method="GET")
req.add_header("Accept", "application/json")
with urllib.request.urlopen(req, timeout=CHECK_TIMEOUT) as resp:
data = json.loads(resp.read().decode())
return {"service": "base_worker", "status": "healthy", "details": data}
except Exception as e:
return {"service": "base_worker", "status": "down", "error": str(e)[:200]}
def check_solana_worker() -> dict:
"""Check Solana x402 worker/gateway health."""
if not SOLANA_WORKER_URL:
return {
"service": "solana_worker",
"status": "not_configured",
"details": "SOLANA_WORKER_URL not set",
}
try:
req = urllib.request.Request(SOLANA_WORKER_URL, method="GET")
req.add_header("Accept", "application/json")
with urllib.request.urlopen(req, timeout=CHECK_TIMEOUT) as resp:
data = json.loads(resp.read().decode())
return {"service": "solana_worker", "status": "healthy", "details": data}
except Exception as e:
return {"service": "solana_worker", "status": "down", "error": str(e)[:200]}
# ββ Alert dispatch ββββββββββββββββββββββββββββββββββββββββββββββββββ
def send_alert(results: list):
"""POST alert to webhook for any down services."""
if not HEALTH_WEBHOOK_URL:
logger.warning("HEALTH_WEBHOOK_URL not set β skipping alert dispatch")
return
down_services = [r for r in results if r.get("status") == "down"]
if not down_services:
return # All healthy
# Filter by cooldown
alertable = [s for s in down_services if _should_alert(s["service"])]
if not alertable:
logger.info(f"{len(down_services)} service(s) down but in alert cooldown")
return
# Build alert payload
alert_lines = []
for s in alertable:
alert_lines.append(f"**{s['service']}** is DOWN: {s.get('error', 'unknown error')}")
# Support multiple webhook formats
# Slack/Discord format
payload = {
"text": f"RMI Health Alert β {len(alertable)} service(s) down",
"attachments": [
{
"title": "Service Health Alert",
"color": "danger",
"text": "\n".join(alert_lines),
"footer": "RMI Health Monitor",
"ts": int(time.time()),
}
],
# Also include raw data for custom webhooks
"services": alertable,
"all_results": results,
}
# Try sending
try:
data = json.dumps(payload).encode()
req = urllib.request.Request(
HEALTH_WEBHOOK_URL,
data=data,
method="POST",
headers={"Content-Type": "application/json"},
)
with urllib.request.urlopen(req, timeout=10) as resp:
logger.info(f"Alert sent to webhook: HTTP {resp.status} β {len(alertable)} services down")
except Exception as e:
logger.error(f"Failed to send alert to webhook: {e}")
def send_recovery_alert(recovered: list):
"""Send recovery notification."""
if not HEALTH_WEBHOOK_URL or not recovered:
return
# Clear cooldown for recovered services
state = _load_cooldown_state()
for s in recovered:
service_name = s["service"]
if service_name in state:
del state[service_name]
_save_cooldown_state(state)
alertable = [s for s in recovered if _should_alert(f"{s['service']}_recovery")]
if not alertable:
return
lines = [f"**{s['service']}** is back UP" for s in alertable]
payload = {
"text": f"RMI Recovery β {len(alertable)} service(s) recovered",
"attachments": [
{
"title": "Service Recovery",
"color": "good",
"text": "\n".join(lines),
"footer": "RMI Health Monitor",
"ts": int(time.time()),
}
],
}
try:
data = json.dumps(payload).encode()
req = urllib.request.Request(
HEALTH_WEBHOOK_URL,
data=data,
method="POST",
headers={"Content-Type": "application/json"},
)
with urllib.request.urlopen(req, timeout=10):
logger.info(f"Recovery alert sent: {len(alertable)} services recovered")
except Exception as e:
logger.error(f"Failed to send recovery alert: {e}")
# ββ Previous state tracking βββββββββββββββββββββββββββββββββββββββββ
def _load_prev_state():
"""Load previous health state for recovery detection."""
try:
state_file = "/tmp/rmi_health_state.json"
if os.path.exists(state_file):
with open(state_file) as f:
return json.load(f)
except Exception:
pass
return {}
def _save_prev_state(state: dict):
"""Save current health state for recovery detection."""
try:
state_file = "/tmp/rmi_health_state.json"
with open(state_file, "w") as f:
json.dump(state, f)
except Exception:
pass
# ββ Main ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
def main():
"""Run all health checks and dispatch alerts."""
# Support loading from any .env file
if "--dotenv" in sys.argv:
import dotenv
idx = sys.argv.index("--dotenv")
if idx + 1 < len(sys.argv):
dotenv.load_dotenv(sys.argv[idx + 1])
else:
dotenv.load_dotenv()
elif os.path.exists("/root/.env"):
try:
from dotenv import load_dotenv
load_dotenv("/root/.env")
except ImportError:
pass
# Re-read config after dotenv
global HEALTH_WEBHOOK_URL, BACKEND_URL, REDIS_HOST, REDIS_PORT, REDIS_PASSWORD
global BASE_WORKER_URL, SOLANA_WORKER_URL
HEALTH_WEBHOOK_URL = os.getenv("HEALTH_WEBHOOK_URL", "")
BACKEND_URL = os.getenv("BACKEND_URL", "http://localhost:8000/health")
REDIS_HOST = os.getenv("REDIS_HOST", "localhost")
REDIS_PORT = int(os.getenv("REDIS_PORT", "6379"))
REDIS_PASSWORD = os.getenv("REDIS_PASSWORD", "")
BASE_WORKER_URL = os.getenv("BASE_WORKER_URL", "http://localhost:8000/api/v1/x402/fallback/status")
SOLANA_WORKER_URL = os.getenv("SOLANA_WORKER_URL", "")
logger.info("Running health checks...")
results = [
check_backend(),
check_redis(),
check_base_worker(),
check_solana_worker(),
]
# Detect recoveries
prev_state = _load_prev_state()
current_state = {r["service"]: r["status"] for r in results}
recovered = []
for r in results:
if r["status"] == "healthy" and prev_state.get(r["service"]) == "down":
recovered.append(r)
# Save current state
_save_prev_state(current_state)
# Log results
for r in results:
status = r["status"]
if status == "healthy":
logger.info(f" {r['service']}: healthy")
elif status == "not_configured":
logger.info(f" {r['service']}: not configured (skipped)")
else:
logger.error(f" {r['service']}: DOWN β {r.get('error', 'unknown')}")
# Send alerts for down services
send_alert(results)
# Send recovery alerts
if recovered:
send_recovery_alert(recovered)
for r in recovered:
logger.info(f" {r['service']}: RECOVERED")
# Print summary
healthy = sum(1 for r in results if r["status"] == "healthy")
total = len(results)
down = sum(1 for r in results if r["status"] == "down")
logger.info(f"Health summary: {healthy}/{total} healthy, {down} down")
# Exit with error code if anything is down (useful for cron monitoring)
if down > 0:
sys.exit(1)
else:
sys.exit(0)
if __name__ == "__main__":
main()
|