scrum4me-docker/bin/health-server.js

#!/usr/bin/env node
// health-server.js
//
// Een minimaal HTTP-endpoint dat de daemon-state uitleest:
//   - /health   → JSON met status, last batch, failures, token-status
//   - /healthz  → 200 OK (minimal liveness, voor docker healthcheck)
//
// State komt uit ${AGENT_STATE_DIR}/state.json. Marker-files:
//   - UNHEALTHY      → 503, te veel opeenvolgende fouten
//   - TOKEN_EXPIRED  → 503, een credential is verlopen
//
// Geen externe deps — gebruikt alleen node built-ins.

const http = require('node:http');
const fs = require('node:fs/promises');
const path = require('node:path');

const STATE_DIR = process.env.AGENT_STATE_DIR || '/var/run/agent';
const PORT = Number(process.env.AGENT_HEALTH_PORT || 8080);

// Als de heartbeat ouder is dan dit, beschouwen we de daemon als zombie.
const STALE_HEARTBEAT_SECONDS = 360;  // 6 min — wrapper schrijft elke iteratie

const STATE_FILE = path.join(STATE_DIR, 'state.json');
const UNHEALTHY_MARKER = path.join(STATE_DIR, 'UNHEALTHY');
const TOKEN_EXPIRED_MARKER = path.join(STATE_DIR, 'TOKEN_EXPIRED');

async function exists(p) {
    try {
        await fs.access(p);
        return true;
    } catch {
        return false;
    }
}

async function readState() {
    try {
        const raw = await fs.readFile(STATE_FILE, 'utf8');
        return JSON.parse(raw);
    } catch (err) {
        return { status: 'unknown', error: String(err) };
    }
}

function ageSeconds(iso) {
    if (!iso) return null;
    const then = Date.parse(iso);
    if (Number.isNaN(then)) return null;
    return Math.floor((Date.now() - then) / 1000);
}

async function buildResponse() {
    const state = await readState();
    const tokenExpired = await exists(TOKEN_EXPIRED_MARKER);
    const unhealthy = await exists(UNHEALTHY_MARKER);

    const heartbeatAgeS = ageSeconds(state.heartbeatAt);
    const heartbeatStale =
        heartbeatAgeS !== null && heartbeatAgeS > STALE_HEARTBEAT_SECONDS;

    let httpStatus = 200;
    let effectiveStatus = state.status || 'unknown';

    if (tokenExpired) {
        httpStatus = 503;
        effectiveStatus = 'token-expired';
    } else if (unhealthy) {
        httpStatus = 503;
        effectiveStatus = 'unhealthy';
    } else if (heartbeatStale) {
        httpStatus = 503;
        effectiveStatus = 'stale';
    }

    const body = {
        status: effectiveStatus,
        rawStatus: state.status,
        startedAt: state.startedAt,
        heartbeatAt: state.heartbeatAt,
        heartbeatAgeSeconds: heartbeatAgeS,
        lastBatchAt: state.lastBatchAt,
        lastBatchExit: state.lastBatchExit,
        currentBatchStartedAt: state.currentBatchStartedAt,
        consecutiveFailures: state.consecutiveFailures ?? 0,
        markers: {
            tokenExpired,
            unhealthy,
        },
    };

    return { httpStatus, body };
}

const server = http.createServer(async (req, res) => {
    if (req.url === '/healthz') {
        res.writeHead(200, { 'content-type': 'text/plain' });
        res.end('ok\n');
        return;
    }
    if (req.url === '/health') {
        try {
            const { httpStatus, body } = await buildResponse();
            res.writeHead(httpStatus, {
                'content-type': 'application/json',
                'cache-control': 'no-store',
            });
            res.end(JSON.stringify(body, null, 2));
        } catch (err) {
            res.writeHead(500, { 'content-type': 'application/json' });
            res.end(JSON.stringify({ status: 'error', error: String(err) }));
        }
        return;
    }
    res.writeHead(404, { 'content-type': 'text/plain' });
    res.end('not found\n');
});

server.listen(PORT, '0.0.0.0', () => {
    console.log(`[health-server] listening on :${PORT}`);
});

for (const sig of ['SIGTERM', 'SIGINT']) {
    process.on(sig, () => {
        console.log(`[health-server] received ${sig}, shutting down`);
        server.close(() => process.exit(0));
        setTimeout(() => process.exit(1), 5000).unref();
    });
}