Health Check Endpoints untuk CAPTCHA Solver Workers

CAPTCHA solver worker Anda tampak hidup — prosesnya berjalan — namun belum berhasil menyelesaikan task dalam 10 menit. API key mungkin habis, atau worker terjebak dalam satu loop. Tanpa health check, orkestrator terus mengarahkan pekerjaan ke worker yang sudah mati. Health endpoints memungkinkan load balancer dan Kubernetes mendeteksi masalah dan melakukan rerouting.

Tiga Jenis Health Check

Python: Health Check Endpoint Flask

import requests
import time
import threading
from flask import Flask, jsonify
from dataclasses import dataclass, field

API_KEY = "YOUR_API_KEY"
RESULT_URL = "https://ocr.captchaai.com/res.php"

app = Flask(__name__)


@dataclass
class WorkerHealth:
    """Tracks worker health metrics."""
    started_at: float = field(default_factory=time.monotonic)
    last_solve_at: float = 0.0
    total_solved: int = 0
    total_failed: int = 0
    consecutive_failures: int = 0
    balance: float | None = None
    balance_checked_at: float = 0.0
    _lock: threading.Lock = field(default_factory=threading.Lock)

    def record_success(self):
        with self._lock:
            self.total_solved += 1
            self.last_solve_at = time.monotonic()
            self.consecutive_failures = 0

    def record_failure(self):
        with self._lock:
            self.total_failed += 1
            self.consecutive_failures += 1

    @property
    def success_rate(self) -> float:
        total = self.total_solved + self.total_failed
        return self.total_solved / total if total > 0 else 1.0

    @property
    def seconds_since_last_solve(self) -> float:
        if self.last_solve_at == 0:
            return time.monotonic() - self.started_at
        return time.monotonic() - self.last_solve_at


health = WorkerHealth()

# Thresholds
MAX_CONSECUTIVE_FAILURES = 10
MAX_SECONDS_WITHOUT_SOLVE = 600  # 10 minutes
MIN_BALANCE = 1.0


def check_balance() -> float | None:
    """Check CaptchaAI balance."""
    now = time.monotonic()
    # Cache balance for 60 seconds
    if health.balance is not None and now - health.balance_checked_at < 60:
        return health.balance

    try:
        resp = requests.get(RESULT_URL, params={
            "key": API_KEY, "action": "getbalance", "json": 1,
        }, timeout=10).json()
        health.balance = float(resp.get("request", 0))
        health.balance_checked_at = now
        return health.balance
    except Exception:
        return health.balance  # Return cached value on error


@app.route("/health/live")
def liveness():
    """Liveness probe — is the process responsive?"""
    return jsonify({"status": "ok", "uptime_s": int(time.monotonic() - health.started_at)}), 200


@app.route("/health/ready")
def readiness():
    """Readiness probe — can the worker accept tasks?"""
    issues = []

    # Check consecutive failures
    if health.consecutive_failures >= MAX_CONSECUTIVE_FAILURES:
        issues.append(f"consecutive_failures={health.consecutive_failures}")

    # Check time since last solve
    if health.total_solved > 0 and health.seconds_since_last_solve > MAX_SECONDS_WITHOUT_SOLVE:
        issues.append(f"no_solve_for={int(health.seconds_since_last_solve)}s")

    # Check balance
    balance = check_balance()
    if balance is not None and balance < MIN_BALANCE:
        issues.append(f"low_balance=${balance:.2f}")

    if issues:
        return jsonify({
            "status": "not_ready",
            "issues": issues,
            "stats": {
                "solved": health.total_solved,
                "failed": health.total_failed,
                "success_rate": round(health.success_rate, 3),
            },
        }), 503

    return jsonify({
        "status": "ready",
        "stats": {
            "solved": health.total_solved,
            "failed": health.total_failed,
            "success_rate": round(health.success_rate, 3),
            "balance": balance,
        },
    }), 200


@app.route("/health/dependencies")
def dependencies():
    """Check upstream dependencies."""
    checks = {}

    # CaptchaAI API reachability
    try:
        resp = requests.get(RESULT_URL, params={
            "key": API_KEY, "action": "getbalance", "json": 1,
        }, timeout=10)
        checks["captchaai_api"] = {
            "status": "ok" if resp.status_code == 200 else "degraded",
            "response_ms": int(resp.elapsed.total_seconds() * 1000),
        }
    except Exception as e:
        checks["captchaai_api"] = {"status": "down", "error": str(e)}

    all_ok = all(c["status"] == "ok" for c in checks.values())
    return jsonify({
        "status": "ok" if all_ok else "degraded",
        "checks": checks,
    }), 200 if all_ok else 503


# --- Worker loop (runs in background) ---

def worker_loop():
    """Simulated CAPTCHA solving worker."""
    while True:
        try:
            # ... solve CAPTCHA logic ...
            health.record_success()
        except Exception:
            health.record_failure()
        time.sleep(1)


threading.Thread(target=worker_loop, daemon=True).start()

JavaScript: Health Check Endpoint Express

const express = require("express");

const API_KEY = "YOUR_API_KEY";
const RESULT_URL = "https://ocr.captchaai.com/res.php";

const app = express();

const health = {
  startedAt: Date.now(),
  lastSolveAt: 0,
  totalSolved: 0,
  totalFailed: 0,
  consecutiveFailures: 0,
  balance: null,
  balanceCheckedAt: 0,

  recordSuccess() {
    this.totalSolved++;
    this.lastSolveAt = Date.now();
    this.consecutiveFailures = 0;
  },

  recordFailure() {
    this.totalFailed++;
    this.consecutiveFailures++;
  },

  get successRate() {
    const total = this.totalSolved + this.totalFailed;
    return total > 0 ? this.totalSolved / total : 1;
  },
};

async function checkBalance() {
  if (health.balance !== null && Date.now() - health.balanceCheckedAt < 60000) {
    return health.balance;
  }
  try {
    const url = `${RESULT_URL}?key=${API_KEY}&action=getbalance&json=1`;
    const resp = await (await fetch(url)).json();
    health.balance = parseFloat(resp.request);
    health.balanceCheckedAt = Date.now();
    return health.balance;
  } catch {
    return health.balance;
  }
}

app.get("/health/live", (req, res) => {
  res.json({ status: "ok", uptimeMs: Date.now() - health.startedAt });
});

app.get("/health/ready", async (req, res) => {
  const issues = [];

  if (health.consecutiveFailures >= 10) {
    issues.push(`consecutive_failures=${health.consecutiveFailures}`);
  }

  if (health.totalSolved > 0) {
    const silentMs = Date.now() - health.lastSolveAt;
    if (silentMs > 600_000) {
      issues.push(`no_solve_for=${Math.round(silentMs / 1000)}s`);
    }
  }

  const balance = await checkBalance();
  if (balance !== null && balance < 1.0) {
    issues.push(`low_balance=$${balance.toFixed(2)}`);
  }

  const stats = {
    solved: health.totalSolved,
    failed: health.totalFailed,
    successRate: Math.round(health.successRate * 1000) / 1000,
    balance,
  };

  if (issues.length > 0) {
    return res.status(503).json({ status: "not_ready", issues, stats });
  }
  res.json({ status: "ready", stats });
});

app.get("/health/dependencies", async (req, res) => {
  const checks = {};
  try {
    const start = Date.now();
    const url = `${RESULT_URL}?key=${API_KEY}&action=getbalance&json=1`;
    const resp = await fetch(url);
    checks.captchaaiApi = {
      status: resp.ok ? "ok" : "degraded",
      responseMs: Date.now() - start,
    };
  } catch (e) {
    checks.captchaaiApi = { status: "down", error: e.message };
  }

  const allOk = Object.values(checks).every((c) => c.status === "ok");
  res.status(allOk ? 200 : 503).json({
    status: allOk ? "ok" : "degraded",
    checks,
  });
});

app.listen(8080, () => console.log("Health server on :8080"));

Konfigurasi Kubernetes

apiVersion: apps/v1
kind: Deployment
metadata:
  name: captcha-worker
spec:
  replicas: 3
  template:
    spec:
      containers:

        - name: worker
          image: captcha-worker:latest
          ports:

            - containerPort: 8080
          livenessProbe:
            httpGet:
              path: /health/live
              port: 8080
            initialDelaySeconds: 10
            periodSeconds: 15
            failureThreshold: 3
          readinessProbe:
            httpGet:
              path: /health/ready
              port: 8080
            initialDelaySeconds: 5
            periodSeconds: 10
            failureThreshold: 2

Kode Respons Health Check

Threshold Operator

• Gunakan readiness untuk memblokir pekerjaan baru, liveness untuk memicu restart, dan alert balance untuk mendeteksi penurunan throughput.
• Kaitkan health check dengan kedalaman queue, error rate terkini, dan keterjangkauan dependency, bukan hanya uptime proses.
• Jaga agar nilai threshold tetap visible bagi on-call engineer sehingga perubahan kesehatan bisa ditindaklanjuti.

Pemecahan Masalah

Pertanyaan Umum

Seberapa sering Kubernetes harus probe health endpoint?

Liveness: setiap 10–30 detik dengan failure threshold 3. Readiness: setiap 5–10 detik dengan failure threshold 2. Probe lebih sering mendeteksi masalah lebih cepat tapi menambah overhead.

Haruskah health endpoint memanggil API CaptchaAI?

Hanya untuk readiness dan dependency check, dan selalu cache hasilnya. Liveness probe tidak boleh melakukan external call — harus respons instan untuk membuktikan proses berjalan.

Bagaimana cara memantau kesehatan beberapa worker?

Expose metrik kesehatan dalam format Prometheus (/metrics) di samping health endpoint. Agregasikan semua worker dengan Grafana dashboard untuk melihat kesehatan seluruh fleet.

Artikel Terkait

• Skrip Pemantauan Pemeriksaan Kesehatan Captchaai

Langkah Selanjutnya

Jadikan pekerja CAPTCHA Anda siap produksi —dapatkan kunci API CaptchaAI Andadan menambahkan titik akhir pemeriksaan kesehatan.

Panduan terkait:

• Pola Pemutus Sirkuit untuk Panggilan API CAPTCHA
• Pola Sekat untuk Pemecahan CAPTCHA
• Memantau Tingkat Penyelesaian CAPTCHA dengan Prometheus dan Grafana