CAPTCHA 解决工作人员的运行状况检查端点 (实用指南)

您的验证码解决工作器看起来还活着——进程正在运行——但它在 10 分钟内没有成功解决任务。 API 密钥已耗尽，或者工作人员陷入循环。如果没有健康检查，您的编排器就会不断地将工作路由给已死亡的工作人员。运行状况端点让负载均衡器和 Kubernetes 检测问题并重新路由。

三种类型的健康检查

查看	问题	失败响应
活跃度	进程是否正在运行？	重启容器
准备情况	可以接受工作吗？	停止路由流量
依赖	上游服务还好吗？	优雅地降级

Python：Flask 健康端点

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：表达健康端点

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"));

Kubernetes 配置

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

健康检查响应代码

端点	200	503
`/health/live`	流程响应	进程冻结 - 重新启动
`/health/ready`	可以接受工作	停止发送任务
`/health/dependencies`	所有依赖项都OK	上游降级

操作员阈值

使用就绪性来阻止新工作，使用活动性来触发重启，并使用平衡警报来捕获吞吐量下降的情况。
将运行状况检查与队列深度、最近错误率和依赖项可达性联系起来，而不是仅与进程正常运行时间联系起来。
保持值班响应人员可见的阈值，以便健康变化是可操作的而不是嘈杂的。

故障排除

问题	原因	处理方式
Worker不断重启	活性阈值太低	增加 `failureThreshold` 或 `periodSeconds`
启动期间工作线程标记为未就绪	尚无解决方案被视为“太长”	仅在第一次解决后检查 `seconds_since_last_solve`
平衡检查会减慢运行状况端点	每个请求都会调用 API	使用 TTL 缓存余额（建议 60 秒）
健康端点本身崩溃	检查中未处理的异常	将每个检查包装在 try/except 中；返回降级而不是 500
依赖性检查的误报	余额检查期间出现网络故障	通过重新验证时失效的方法使用缓存值