File size: 10,091 Bytes
bee039d c46444f bee039d fad3b06 bee039d fad3b06 bee039d fad3b06 bee039d fad3b06 bee039d fad3b06 bee039d fad3b06 bee039d fad3b06 bee039d fad3b06 bee039d |
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 |
#!/usr/bin/env python3
"""
Service Health Monitor API
Real-time monitoring of all API services and data providers
Shows status, response times, success rates, and health metrics
"""
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel
from typing import Dict, Any, List, Optional
from datetime import datetime
import logging
import asyncio
import httpx
import time
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/api/health", tags=["Health Monitor"])
class ServiceStatus(BaseModel):
"""Service status model"""
name: str
status: str # "online", "offline", "rate_limited", "degraded"
response_time_ms: Optional[float] = None
last_check: str
last_error: Optional[str] = None
success_rate: Optional[float] = None
details: Optional[Dict[str, Any]] = None
class HealthMonitorResponse(BaseModel):
"""Health monitor response"""
timestamp: str
total_services: int
online: int
offline: int
rate_limited: int
degraded: int
services: List[ServiceStatus]
overall_health: str # "healthy", "degraded", "critical"
# Service configuration for health checks
SERVICES_CONFIG = {
"crypto_api_clean": {
"name": "Crypto API Clean",
"category": "Resource Database",
"endpoint": "https://really-amin-crypto-api-clean-fixed.hf.space/api/resources/stats",
"timeout": 10,
"sub_services": ["rpc_nodes (24)", "block_explorers (33)", "market_data_apis (33)", "news_apis (17)", "sentiment_apis (14)"],
"description": "281+ cryptocurrency resources across 12 categories",
"priority": 2
},
"crypto_dt_source": {
"name": "Crypto DT Source",
"category": "Unified Data API",
"endpoint": "https://crypto-dt-source.onrender.com/api/v1/status",
"timeout": 15,
"sub_services": ["prices", "klines", "sentiment", "models", "datasets"],
"description": "Unified API v2.0.0 with 4 AI models and 5 datasets",
"priority": 2
},
"coingecko": {
"name": "CoinGecko",
"category": "Data Provider",
"endpoint": "https://api.coingecko.com/api/v3/ping",
"timeout": 5,
"sub_services": ["prices", "market_data", "ohlcv"]
},
"binance": {
"name": "Binance",
"category": "Exchange",
"endpoint": "https://api.binance.com/api/v3/ping",
"timeout": 5,
"sub_services": ["spot", "futures", "websocket"]
},
"coincap": {
"name": "CoinCap",
"category": "Data Provider",
"endpoint": "https://api.coincap.io/v2/assets/bitcoin",
"timeout": 5,
"sub_services": ["assets", "markets", "rates"]
},
"cryptocompare": {
"name": "CryptoCompare",
"category": "Data Provider",
"endpoint": "https://min-api.cryptocompare.com/data/price?fsym=BTC&tsyms=USD",
"timeout": 5,
"sub_services": ["price", "historical", "social"]
},
"huggingface": {
"name": "HuggingFace Space",
"category": "Internal",
"endpoint": "/api/health/self",
"timeout": 3,
"sub_services": ["api", "websocket", "database"],
"internal": True
},
"backend_indicators": {
"name": "Technical Indicators",
"category": "Internal",
"endpoint": "/api/indicators/services",
"timeout": 3,
"sub_services": ["rsi", "macd", "bollinger_bands", "comprehensive"],
"internal": True
},
"backend_market": {
"name": "Market Data API",
"category": "Internal",
"endpoint": "/api/market/crypto/list",
"timeout": 3,
"sub_services": ["prices", "ohlcv", "tickers"],
"internal": True
}
}
def get_base_url() -> str:
"""Get the base URL for internal services"""
import os
# For HF Spaces
if os.getenv("SPACE_ID"):
return f"https://{os.getenv('SPACE_ID')}.hf.space"
# For local development
return "http://localhost:7860"
async def check_service_health(service_id: str, config: Dict[str, Any]) -> ServiceStatus:
"""
Check the health of a single service
"""
start_time = time.time()
try:
# Build URL for internal services
endpoint = config["endpoint"]
if config.get("internal", False):
base_url = get_base_url()
endpoint = f"{base_url}{endpoint}" if not endpoint.startswith("http") else endpoint
async with httpx.AsyncClient() as client:
response = await client.get(
endpoint,
timeout=config.get("timeout", 5),
follow_redirects=True
)
response_time = (time.time() - start_time) * 1000 # Convert to ms
# Determine status
if response.status_code == 200:
status = "online"
elif response.status_code == 429:
status = "rate_limited"
elif 500 <= response.status_code < 600:
status = "degraded"
else:
status = "offline"
# Calculate success rate (simplified - in production, use historical data)
success_rate = 100.0 if status == "online" else 50.0 if status == "degraded" else 0.0
return ServiceStatus(
name=config["name"],
status=status,
response_time_ms=round(response_time, 2),
last_check=datetime.utcnow().isoformat() + "Z",
last_error=None if status == "online" else f"HTTP {response.status_code}",
success_rate=success_rate,
details={
"category": config.get("category", "Unknown"),
"sub_services": config.get("sub_services", []),
"http_status": response.status_code
}
)
except asyncio.TimeoutError:
return ServiceStatus(
name=config["name"],
status="offline",
response_time_ms=config.get("timeout", 5) * 1000,
last_check=datetime.utcnow().isoformat() + "Z",
last_error="Request timeout",
success_rate=0.0,
details={
"category": config.get("category", "Unknown"),
"sub_services": config.get("sub_services", []),
"error_type": "timeout"
}
)
except httpx.ConnectError as e:
return ServiceStatus(
name=config["name"],
status="offline",
response_time_ms=None,
last_check=datetime.utcnow().isoformat() + "Z",
last_error=f"Connection failed: {str(e)[:100]}",
success_rate=0.0,
details={
"category": config.get("category", "Unknown"),
"sub_services": config.get("sub_services", []),
"error_type": "connection_error"
}
)
except Exception as e:
logger.error(f"Error checking {service_id}: {e}")
return ServiceStatus(
name=config["name"],
status="offline",
response_time_ms=None,
last_check=datetime.utcnow().isoformat() + "Z",
last_error=str(e)[:100],
success_rate=0.0,
details={
"category": config.get("category", "Unknown"),
"sub_services": config.get("sub_services", []),
"error_type": "unknown_error"
}
)
@router.get("/monitor", response_model=HealthMonitorResponse)
async def get_service_health():
"""
Get health status of all services
Returns real-time status of all API providers and internal services
"""
try:
# Check all services concurrently
tasks = [
check_service_health(service_id, config)
for service_id, config in SERVICES_CONFIG.items()
]
services = await asyncio.gather(*tasks)
# Calculate statistics
online = sum(1 for s in services if s.status == "online")
offline = sum(1 for s in services if s.status == "offline")
rate_limited = sum(1 for s in services if s.status == "rate_limited")
degraded = sum(1 for s in services if s.status == "degraded")
# Determine overall health
total = len(services)
if online == total:
overall_health = "healthy"
elif online >= total * 0.7:
overall_health = "degraded"
else:
overall_health = "critical"
return HealthMonitorResponse(
timestamp=datetime.utcnow().isoformat() + "Z",
total_services=total,
online=online,
offline=offline,
rate_limited=rate_limited,
degraded=degraded,
services=services,
overall_health=overall_health
)
except Exception as e:
logger.error(f"Health monitor error: {e}")
raise HTTPException(status_code=500, detail=f"Failed to check service health: {str(e)}")
@router.get("/self")
async def health_check():
"""
Simple health check endpoint for this service
"""
return {
"status": "healthy",
"service": "crypto-intelligence-hub",
"timestamp": datetime.utcnow().isoformat() + "Z",
"version": "1.0.0"
}
@router.get("/services")
async def list_monitored_services():
"""
List all monitored services with their configuration
"""
return {
"success": True,
"total_services": len(SERVICES_CONFIG),
"services": [
{
"id": service_id,
"name": config["name"],
"category": config.get("category", "Unknown"),
"sub_services": config.get("sub_services", [])
}
for service_id, config in SERVICES_CONFIG.items()
],
"timestamp": datetime.utcnow().isoformat() + "Z"
}
|