import logging, json, time, uuid

class FoundryLogger:
    def __init__(self):
        self.logger = logging.getLogger("foundry")
        handler = logging.StreamHandler()
        handler.setFormatter(logging.Formatter("%(message)s"))
        self.logger.addHandler(handler)
        self.logger.setLevel(logging.INFO)

    def log_api_call(self, method: str, endpoint: str, status: int, duration_ms: float):
        self.logger.info(json.dumps({
            "timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
            "request_id": str(uuid.uuid4())[:8],
            "service": "foundry",
            "method": method,
            "endpoint": endpoint,
            "status": status,
            "duration_ms": round(duration_ms, 2),
            "level": "error" if status >= 400 else "info",
        }))

from prometheus_client import Counter, Histogram, Gauge

foundry_requests = Counter(
    "foundry_api_requests_total",
    "Total Foundry API requests",
    ["method", "endpoint", "status"],
)
foundry_latency = Histogram(
    "foundry_api_latency_seconds",
    "Foundry API request latency",
    ["endpoint"],
    buckets=[0.1, 0.25, 0.5, 1.0, 2.5, 5.0, 10.0],
)
foundry_health = Gauge(
    "foundry_api_healthy",
    "1 if Foundry API is reachable, 0 otherwise",
)

def instrumented_call(client, method, *args, **kwargs):
    endpoint = method.__qualname__
    start = time.monotonic()
    try:
        result = method(*args, **kwargs)
        status = 200
        return result
    except foundry.ApiError as e:
        status = e.status_code
        raise
    finally:
        duration = time.monotonic() - start
        foundry_requests.labels(method="API", endpoint=endpoint, status=str(status)).inc()
        foundry_latency.labels(endpoint=endpoint).observe(duration)

import time

async def foundry_health_check():
    start = time.monotonic()
    try:
        list(client.ontologies.Ontology.list())
        latency = (time.monotonic() - start) * 1000
        foundry_health.set(1)
        return {"status": "healthy", "latency_ms": round(latency, 1)}
    except Exception as e:
        foundry_health.set(0)
        return {"status": "unhealthy", "error": str(e)}

groups:
  - name: foundry
    rules:
      - alert: FoundryAPIDown
        expr: foundry_api_healthy == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Foundry API unreachable for 2+ minutes"

      - alert: FoundryHighErrorRate
        expr: rate(foundry_api_requests_total{status=~"5.."}[5m]) > 0.05
        for: 5m
        labels:
          severity: warning

      - alert: FoundryHighLatency
        expr: histogram_quantile(0.99, foundry_api_latency_seconds_bucket) > 10
        for: 10m
        labels:
          severity: warning

# Request rate by status
rate(foundry_api_requests_total[5m])

# P99 latency
histogram_quantile(0.99, rate(foundry_api_latency_seconds_bucket[5m]))

# Error ratio
sum(rate(foundry_api_requests_total{status=~"[45].."}[5m]))
/ sum(rate(foundry_api_requests_total[5m]))