Committed by Hermes autonomous QA sprint 2026-08-13. These files were modified during the Aug 12 sprint but never committed.
478 lines
17 KiB
JavaScript
478 lines
17 KiB
JavaScript
const express = require('express');
|
|
const fs = require('fs');
|
|
const path = require('path');
|
|
const { execSync } = require('child_process');
|
|
const { TIMEOUTS } = require('../src/utilities/constants');
|
|
const { exists } = require('../src/utilities/fs-helpers');
|
|
const { paginate, parsePaginationParams } = require('../src/utilities/pagination');
|
|
const platformPaths = require('../platform-paths');
|
|
const { resolveServiceUrl } = require('../src/utilities/url-resolver');
|
|
const { success, error: errorResponse, errorResponse: sendError, ok, notFound } = require('../src/utils/responses');
|
|
const { ValidationError } = require('../src/utilities/errors');
|
|
|
|
/**
|
|
* Health routes factory
|
|
* @param {Object} deps - Explicit dependencies
|
|
* @param {Function} deps.fetchT - Fetch wrapper with timeout
|
|
* @param {string} deps.SERVICES_FILE - Path to services.json
|
|
* @param {Object} deps.servicesStateManager - State manager for services.json
|
|
* @param {Object} deps.siteConfig - Site configuration
|
|
* @param {Function} deps.buildServiceUrl - URL builder function
|
|
* @param {Function} deps.asyncHandler - Async route handler wrapper
|
|
* @param {Function} deps.logError - Error logging function
|
|
* @param {Object} deps.healthChecker - Health check manager instance
|
|
* @returns {express.Router}
|
|
*/
|
|
module.exports = function({
|
|
fetchT,
|
|
SERVICES_FILE,
|
|
servicesStateManager,
|
|
siteConfig,
|
|
buildServiceUrl,
|
|
asyncHandler,
|
|
logError,
|
|
healthChecker
|
|
}) {
|
|
const router = express.Router();
|
|
|
|
// In-memory cache for health results (local to this router)
|
|
let serviceHealthCache = {};
|
|
let lastHealthCheck = null;
|
|
|
|
/**
|
|
* Check a URL directly via fetch. Returns health object or null on failure.
|
|
*/
|
|
async function checkDirect(url) {
|
|
// Try HEAD first
|
|
try {
|
|
const controller = new AbortController();
|
|
const timeout = setTimeout(() => controller.abort(), TIMEOUTS.HTTP_DEFAULT);
|
|
const response = await fetchT(url, { method: 'HEAD', signal: controller.signal, redirect: 'follow' });
|
|
clearTimeout(timeout);
|
|
return {
|
|
status: response.ok || response.status < 500 ? 'healthy' : 'unhealthy',
|
|
statusCode: response.status,
|
|
url,
|
|
checkedAt: new Date().toISOString()
|
|
};
|
|
} catch { /* ignore */ }
|
|
|
|
// Fallback to GET
|
|
try {
|
|
const controller = new AbortController();
|
|
const timeout = setTimeout(() => controller.abort(), TIMEOUTS.HTTP_DEFAULT);
|
|
const response = await fetchT(url, { method: 'GET', signal: controller.signal, redirect: 'follow' });
|
|
clearTimeout(timeout);
|
|
return {
|
|
status: response.ok || response.status < 500 ? 'healthy' : 'unhealthy',
|
|
statusCode: response.status,
|
|
url,
|
|
checkedAt: new Date().toISOString()
|
|
};
|
|
} catch (e) {
|
|
return null; // Direct check completely failed
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Check a URL through a Pylon relay. Returns health object or null on failure.
|
|
*/
|
|
async function checkViaPylon(pylonConfig, url) {
|
|
if (!pylonConfig?.url) return null;
|
|
try {
|
|
const probeUrl = `${pylonConfig.url}/probe?url=${encodeURIComponent(url)}`;
|
|
const headers = {};
|
|
if (pylonConfig.key) headers['x-pylon-key'] = pylonConfig.key;
|
|
const controller = new AbortController();
|
|
const timeout = setTimeout(() => controller.abort(), 12000);
|
|
const response = await fetchT(probeUrl, { method: 'GET', signal: controller.signal, headers });
|
|
clearTimeout(timeout);
|
|
if (!response.ok) return null;
|
|
const data = await response.json();
|
|
return {
|
|
status: data.status || 'unhealthy',
|
|
statusCode: data.statusCode,
|
|
responseTime: data.responseTime,
|
|
reason: data.reason,
|
|
url,
|
|
via: 'pylon',
|
|
checkedAt: data.checkedAt || new Date().toISOString()
|
|
};
|
|
} catch (_) {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
// ===== HEALTH / SERVICES =====
|
|
|
|
// Check health of all services (performs live checks)
|
|
router.get('/health/services', asyncHandler(async (req, res) => {
|
|
if (!await exists(SERVICES_FILE)) {
|
|
return success(res, { health: {} });
|
|
}
|
|
|
|
const servicesData = await servicesStateManager.read();
|
|
const services = Array.isArray(servicesData) ? servicesData : servicesData.services || [];
|
|
const health = {};
|
|
const pylonConfig = siteConfig?.pylon;
|
|
|
|
// Check each service
|
|
await Promise.all(services.map(async (service) => {
|
|
const serviceId = service.id || service.name?.toLowerCase();
|
|
if (!serviceId) return;
|
|
|
|
try {
|
|
const url = resolveServiceUrl(serviceId, service, siteConfig, buildServiceUrl);
|
|
if (!url) {
|
|
health[serviceId] = { status: 'unknown', reason: 'No URL configured' };
|
|
return;
|
|
}
|
|
|
|
// 1. Try direct check
|
|
let result = await checkDirect(url);
|
|
if (result) {
|
|
health[serviceId] = result;
|
|
return;
|
|
}
|
|
|
|
// 2. Direct failed — try through pylon relay
|
|
if (pylonConfig) {
|
|
result = await checkViaPylon(pylonConfig, url);
|
|
if (result) {
|
|
health[serviceId] = result;
|
|
return;
|
|
}
|
|
}
|
|
|
|
// 3. Both failed
|
|
health[serviceId] = {
|
|
status: 'unhealthy',
|
|
reason: pylonConfig ? 'Unreachable (direct + pylon)' : 'fetch failed',
|
|
url,
|
|
checkedAt: new Date().toISOString()
|
|
};
|
|
} catch (e) {
|
|
health[serviceId] = {
|
|
status: 'error',
|
|
reason: e.message,
|
|
checkedAt: new Date().toISOString()
|
|
};
|
|
}
|
|
}));
|
|
|
|
// Cache results
|
|
serviceHealthCache = health;
|
|
lastHealthCheck = new Date().toISOString();
|
|
|
|
const paginationParams = parsePaginationParams(req.query);
|
|
const healthEntries = Object.entries(health);
|
|
const result = paginate(healthEntries, paginationParams);
|
|
const paginatedHealth = Object.fromEntries(result.data);
|
|
success(res, {
|
|
health: paginatedHealth,
|
|
checkedAt: lastHealthCheck,
|
|
...(result.pagination && { pagination: result.pagination })
|
|
});
|
|
}, 'health-services'));
|
|
|
|
// Get cached health status (fast, no re-check)
|
|
router.get('/health/cached', asyncHandler(async (req, res) => {
|
|
success(res, {
|
|
health: serviceHealthCache,
|
|
lastCheck: lastHealthCheck,
|
|
cacheAge: lastHealthCheck ? Date.now() - new Date(lastHealthCheck).getTime() : null
|
|
});
|
|
}, 'health-cached'));
|
|
|
|
// Check health of single service
|
|
router.get('/health/service/:id', asyncHandler(async (req, res) => {
|
|
const serviceId = req.params.id;
|
|
|
|
// Load service config
|
|
if (!await exists(SERVICES_FILE)) {
|
|
const { NotFoundError } = require('../src/utilities/errors');
|
|
throw new NotFoundError('Services file');
|
|
}
|
|
|
|
const servicesData = await servicesStateManager.read();
|
|
const services = Array.isArray(servicesData) ? servicesData : servicesData.services || [];
|
|
const service = services.find(s => (s.id || s.name?.toLowerCase()) === serviceId);
|
|
|
|
if (!service) {
|
|
const { NotFoundError } = require('../src/utilities/errors');
|
|
throw new NotFoundError('Service');
|
|
}
|
|
|
|
// Determine URL
|
|
const url = resolveServiceUrl(serviceId, service, siteConfig, buildServiceUrl);
|
|
const pylonConfig = siteConfig?.pylon;
|
|
|
|
// Try direct, then pylon relay
|
|
let result = await checkDirect(url);
|
|
if (!result && pylonConfig) {
|
|
result = await checkViaPylon(pylonConfig, url);
|
|
}
|
|
if (!result) {
|
|
result = {
|
|
status: 'unhealthy',
|
|
reason: pylonConfig ? 'Unreachable (direct + pylon)' : 'fetch failed',
|
|
url,
|
|
checkedAt: new Date().toISOString()
|
|
};
|
|
}
|
|
|
|
success(res, { serviceId, health: result });
|
|
}, 'health-service'));
|
|
|
|
// ===== HEALTH / PROBE (Pylon-compatible) =====
|
|
|
|
// Probe endpoint — lets this DashCaddy act as a pylon for other instances
|
|
router.get('/health/probe', asyncHandler(async (req, res) => {
|
|
const targetUrl = req.query.url;
|
|
if (!targetUrl) {
|
|
throw new ValidationError('Missing ?url= parameter');
|
|
}
|
|
const result = await checkDirect(targetUrl);
|
|
res.json(result || {
|
|
status: 'unhealthy',
|
|
reason: 'fetch failed',
|
|
url: targetUrl,
|
|
checkedAt: new Date().toISOString()
|
|
});
|
|
}, 'health-probe'));
|
|
|
|
// Pylon status — check if the configured pylon is reachable
|
|
router.get('/health/pylon', asyncHandler(async (req, res) => {
|
|
const pylonConfig = siteConfig?.pylon;
|
|
if (!pylonConfig?.url) {
|
|
return success(res, { configured: false });
|
|
}
|
|
try {
|
|
const headers = {};
|
|
if (pylonConfig.key) headers['x-pylon-key'] = pylonConfig.key;
|
|
const response = await fetchT(`${pylonConfig.url}/health`, {
|
|
method: 'GET',
|
|
headers
|
|
}, 5000);
|
|
const data = await response.json();
|
|
success(res, { configured: true, reachable: true, pylon: data });
|
|
} catch (e) {
|
|
success(res, { configured: true, reachable: false, error: e.message });
|
|
}
|
|
}, 'health-pylon'));
|
|
|
|
// ===== HEALTH / CA =====
|
|
|
|
// Get CA certificate health status
|
|
router.get('/health/ca', asyncHandler(async (req, res) => {
|
|
// Try deployed location first, then Caddy PKI location
|
|
const deployedCertPath = path.join(platformPaths.caCertDir, 'root.crt');
|
|
const pkiCertPath = platformPaths.pkiRootCert;
|
|
const rootCertPath = await exists(deployedCertPath) ? deployedCertPath : pkiCertPath;
|
|
|
|
try {
|
|
// Check if certificate exists
|
|
if (!await exists(rootCertPath)) {
|
|
return sendError(res, 404, 'Root CA certificate not found', { caStatus: 'error', daysUntilExpiration: null });
|
|
}
|
|
|
|
const dates = execSync(`openssl x509 -in "${rootCertPath}" -noout -dates`).toString();
|
|
const notAfter = dates.match(/notAfter=(.*)/)[1].trim();
|
|
const expirationDate = new Date(notAfter);
|
|
const daysUntilExpiration = Math.floor((expirationDate - new Date()) / (1000 * 60 * 60 * 24));
|
|
|
|
// Alert thresholds
|
|
let caStatus = 'healthy';
|
|
let message = `CA certificate valid for ${daysUntilExpiration} days`;
|
|
|
|
if (daysUntilExpiration < 0) {
|
|
caStatus = 'critical';
|
|
message = `CA certificate EXPIRED ${Math.abs(daysUntilExpiration)} days ago!`;
|
|
} else if (daysUntilExpiration < 7) {
|
|
caStatus = 'critical';
|
|
message = `CA certificate expires in ${daysUntilExpiration} days!`;
|
|
} else if (daysUntilExpiration < 30) {
|
|
caStatus = 'critical';
|
|
message = `CA certificate expires in ${daysUntilExpiration} days!`;
|
|
} else if (daysUntilExpiration < 90) {
|
|
caStatus = 'warning';
|
|
message = `CA certificate expires in ${daysUntilExpiration} days`;
|
|
}
|
|
|
|
ok(res, {
|
|
caStatus,
|
|
message,
|
|
daysUntilExpiration,
|
|
expiresAt: notAfter
|
|
});
|
|
} catch (error) {
|
|
await logError('GET /api/health/ca', error);
|
|
sendError(res, 500, error.message, { caStatus: 'error', daysUntilExpiration: null });
|
|
}
|
|
}, 'health-ca'));
|
|
|
|
// ===== HEALTH CHECK (health-checker module) =====
|
|
|
|
// Get current status for all services
|
|
// Returns {status: {...per-service}} plus a {summary} block for the System Overview widget
|
|
// — see skill references/totp-and-system-overview-pitfalls.md §3
|
|
router.get('/health-checks/status', asyncHandler(async (req, res) => {
|
|
const status = healthChecker.getCurrentStatus();
|
|
const entries = Object.values(status || {});
|
|
// Treat 'up'/'healthy' as healthy, everything else as unhealthy.
|
|
// Health check status values come from healthChecker — typically 'up'/'down' but
|
|
// also 'healthy'/'unhealthy' or 'online'/'offline' depending on the source. Be
|
|
// permissive on the healthy side so a service in any positive state counts.
|
|
const healthy = entries.filter(s => {
|
|
const st = (s && (s.status || s.state)) || '';
|
|
return st === 'up' || st === 'healthy' || st === 'online';
|
|
}).length;
|
|
const unhealthy = entries.filter(s => {
|
|
const st = (s && (s.status || s.state)) || '';
|
|
return st === 'down' || st === 'unhealthy' || st === 'offline' || st === 'error';
|
|
}).length;
|
|
const unknown = entries.length - healthy - unhealthy;
|
|
const summary = { healthy, unhealthy, unknown, total: entries.length };
|
|
success(res, { status, summary });
|
|
}, 'health-check-status'));
|
|
|
|
// Get service statistics
|
|
router.get('/health-checks/:serviceId/stats', asyncHandler(async (req, res) => {
|
|
const hours = parseInt(req.query.hours) || 24;
|
|
const stats = healthChecker.getServiceStats(req.params.serviceId, hours);
|
|
if (!stats) {
|
|
const { NotFoundError } = require('../src/utilities/errors');
|
|
throw new NotFoundError('Service');
|
|
}
|
|
success(res, { stats });
|
|
}, 'health-check-stats'));
|
|
|
|
// Configure health check
|
|
router.post('/health-checks/:serviceId/configure', asyncHandler(async (req, res) => {
|
|
healthChecker.configureService(req.params.serviceId, req.body);
|
|
success(res, { message: 'Health check configured' });
|
|
}, 'health-check-configure'));
|
|
|
|
// Remove health check configuration
|
|
router.delete('/health-checks/:serviceId/configure', asyncHandler(async (req, res) => {
|
|
healthChecker.removeService(req.params.serviceId);
|
|
success(res, { message: 'Health check removed' });
|
|
}, 'health-check-remove'));
|
|
|
|
// Get open incidents
|
|
router.get('/health-checks/incidents', asyncHandler(async (req, res) => {
|
|
const incidents = healthChecker.getOpenIncidents();
|
|
const paginationParams = parsePaginationParams(req.query);
|
|
const result = paginate(incidents, paginationParams);
|
|
success(res, { incidents: result.data, ...(result.pagination && { pagination: result.pagination }) });
|
|
}, 'health-check-incidents'));
|
|
|
|
// Get incident history
|
|
router.get('/health-checks/incidents/history', asyncHandler(async (req, res) => {
|
|
const paginationParams = parsePaginationParams(req.query);
|
|
// When paginating, fetch all history so pagination can slice correctly
|
|
const fetchLimit = paginationParams ? Number.MAX_SAFE_INTEGER : (parseInt(req.query.limit) || 50);
|
|
const history = healthChecker.getIncidentHistory(fetchLimit);
|
|
const result = paginate(history, paginationParams);
|
|
success(res, { history: result.data, ...(result.pagination && { pagination: result.pagination }) });
|
|
}, 'health-check-incidents-history'));
|
|
|
|
// ── DC-075: System health endpoint for operators/uptime monitoring ─────────
|
|
// Returns a single "is everything OK" summary suitable for external monitors
|
|
// like UptimeRobot or BetterStack. No auth required (read-only status).
|
|
router.get('/system/health', asyncHandler(async (req, res) => {
|
|
const checks = {};
|
|
|
|
// Service health from health checker
|
|
try {
|
|
const status = healthChecker.getCurrentStatus();
|
|
const entries = Object.values(status || {});
|
|
const unhealthy = entries.filter(s => {
|
|
const st = (s && (s.status || s.state)) || '';
|
|
return st === 'down' || st === 'unhealthy' || st === 'offline' || st === 'error';
|
|
}).length;
|
|
const total = entries.length;
|
|
const knownHealthy = entries.filter(s => {
|
|
const st = (s && (s.status || s.state)) || '';
|
|
return st === 'up' || st === 'healthy' || st === 'online';
|
|
}).length;
|
|
checks.services = {
|
|
status: unhealthy === 0 ? 'ok' : (unhealthy < total ? 'degraded' : 'down'),
|
|
healthy: knownHealthy,
|
|
unhealthy,
|
|
unknown: total - knownHealthy - unhealthy,
|
|
total,
|
|
};
|
|
} catch {
|
|
checks.services = { status: 'unknown' };
|
|
}
|
|
|
|
// Memory usage
|
|
try {
|
|
const os = require('os');
|
|
const total = os.totalmem ? os.totalmem() : 0;
|
|
const free = os.freemem ? os.freemem() : 0;
|
|
checks.memory = {
|
|
status: free / total > 0.1 ? 'ok' : 'warning',
|
|
usedPercent: parseFloat((((total - free) / total) * 100).toFixed(1)),
|
|
totalMB: Math.round(total / 1048576),
|
|
freeMB: Math.round(free / 1048576),
|
|
};
|
|
} catch {
|
|
checks.memory = { status: 'unknown' };
|
|
}
|
|
|
|
// Disk space (data dir)
|
|
try {
|
|
const { execSync } = require('child_process');
|
|
const dfOutput = execSync('df -h --output=pcent,size,avail ' + (platformPaths.dataDir || '/'), { encoding: 'utf8', timeout: 3000 });
|
|
const lines = dfOutput.trim().split('\n');
|
|
if (lines.length >= 2) {
|
|
const parts = lines[1].trim().split(/\s+/);
|
|
const usedPercent = parseInt(parts[0]);
|
|
checks.diskSpace = {
|
|
status: usedPercent < 90 ? 'ok' : (usedPercent < 95 ? 'warning' : 'critical'),
|
|
usedPercent,
|
|
total: parts[1],
|
|
available: parts[2],
|
|
};
|
|
}
|
|
} catch {
|
|
checks.diskSpace = { status: 'unknown' };
|
|
}
|
|
|
|
// Uptime
|
|
const uptime = process.uptime();
|
|
checks.uptime = {
|
|
seconds: Math.round(uptime),
|
|
human: `${Math.floor(uptime / 3600)}h ${Math.floor((uptime % 3600) / 60)}m`,
|
|
};
|
|
|
|
// Open incidents
|
|
try {
|
|
const incidents = healthChecker.getOpenIncidents();
|
|
checks.incidents = {
|
|
status: incidents.length === 0 ? 'ok' : 'degraded',
|
|
count: incidents.length,
|
|
};
|
|
} catch {
|
|
checks.incidents = { status: 'unknown', count: 0 };
|
|
}
|
|
|
|
// Overall status: 'unknown' is treated as degraded (not healthy)
|
|
const statuses = Object.values(checks).map(c => c.status);
|
|
const overall = statuses.includes('down') || statuses.includes('critical') ? 'unhealthy'
|
|
: statuses.some(s => s === 'degraded' || s === 'warning' || s === 'unknown') ? 'degraded'
|
|
: 'healthy';
|
|
|
|
res.set('Cache-Control', 'no-store');
|
|
success(res, {
|
|
status: overall,
|
|
timestamp: new Date().toISOString(),
|
|
checks,
|
|
});
|
|
}, 'system-health'));
|
|
|
|
return router;
|
|
};
|