feat: bot performance monitoring

src/api/index.js

@@ -17,6 +17,7 @@ import healthRouter from './routes/health.js';
 import membersRouter from './routes/members.js';
 import moderationRouter from './routes/moderation.js';
 import notificationsRouter from './routes/notifications.js';
+import performanceRouter from './routes/performance.js';
 import ticketsRouter from './routes/tickets.js';
 import webhooksRouter from './routes/webhooks.js';
 
@@ -59,6 +60,9 @@ router.use('/moderation', requireAuth(), auditLogMiddleware(), moderationRouter)
 // GET-only; no audit middleware needed (reads are not mutating actions)
 router.use('/guilds', requireAuth(), auditLogRouter);
 
+// Performance metrics — require x-api-secret (authenticated via route handler)
+router.use('/performance', performanceRouter);
+
 // Notification webhook management routes — require API secret or OAuth2 JWT
 router.use('/guilds', requireAuth(), auditLogMiddleware(), notificationsRouter);
 

src/api/routes/performance.js

@@ -0,0 +1,122 @@
+/**
+ * Performance Metrics Route
+ *
+ * Returns bot performance metrics including memory usage, CPU utilization,
+ * response time statistics, and configurable alert thresholds.
+ *
+ * All endpoints require x-api-secret authentication.
+ */
+
+import { Router } from 'express';
+import { PerformanceMonitor } from '../../modules/performanceMonitor.js';
+import { isValidSecret } from '../middleware/auth.js';
+
+const router = Router();
+
+/**
+ * @openapi
+ * /performance:
+ *   get:
+ *     tags:
+ *       - Performance
+ *     summary: Get performance metrics snapshot
+ *     description: >
+ *       Returns the full performance snapshot including current stats,
+ *       time-series data for memory/CPU, response time samples and summary,
+ *       and configured alert thresholds. Requires x-api-secret header.
+ *     parameters:
+ *       - in: header
+ *         name: x-api-secret
+ *         schema:
+ *           type: string
+ *         required: true
+ *     responses:
+ *       "200":
+ *         description: Performance snapshot
+ *       "401":
+ *         description: Unauthorized
+ */
+router.get('/', (req, res) => {
+  if (!isValidSecret(req.headers['x-api-secret'])) {
+    return res.status(401).json({ error: 'Unauthorized' });
+  }
+
+  const monitor = PerformanceMonitor.getInstance();
+  const snapshot = monitor.getSnapshot();
+  res.json(snapshot);
+});
+
+/**
+ * @openapi
+ * /performance/thresholds:
+ *   get:
+ *     tags:
+ *       - Performance
+ *     summary: Get alert thresholds
+ *     security:
+ *       - apiSecret: []
+ *     responses:
+ *       "200":
+ *         description: Current thresholds
+ *   put:
+ *     tags:
+ *       - Performance
+ *     summary: Update alert thresholds
+ *     description: Partial update — only supplied fields are changed.
+ *     security:
+ *       - apiSecret: []
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             type: object
+ *             properties:
+ *               memoryHeapMb:
+ *                 type: number
+ *               memoryRssMb:
+ *                 type: number
+ *               cpuPercent:
+ *                 type: number
+ *               responseTimeMs:
+ *                 type: number
+ *     responses:
+ *       "200":
+ *         description: Updated thresholds
+ */
+router.get('/thresholds', (req, res) => {
+  if (!isValidSecret(req.headers['x-api-secret'])) {
+    return res.status(401).json({ error: 'Unauthorized' });
+  }
+
+  const monitor = PerformanceMonitor.getInstance();
+  res.json(monitor.getThresholds());
+});
+
+router.put('/thresholds', (req, res) => {
+  if (!isValidSecret(req.headers['x-api-secret'])) {
+    return res.status(401).json({ error: 'Unauthorized' });
+  }
+
+  const allowed = new Set(['memoryHeapMb', 'memoryRssMb', 'cpuPercent', 'responseTimeMs']);
+  const update = {};
+
+  for (const [key, val] of Object.entries(req.body ?? {})) {
+    if (!allowed.has(key)) continue;
+    const num = Number(val);
+    if (!Number.isFinite(num) || num <= 0) {
+      return res.status(400).json({ error: `Invalid value for ${key}: must be a positive number` });
+    }
+    update[key] = num;
+  }
+
+  if (Object.keys(update).length === 0) {
+    return res.status(400).json({ error: 'No valid threshold fields provided' });
+  }
+
+  const monitor = PerformanceMonitor.getInstance();
+  monitor.setThresholds(update);
+  res.json(monitor.getThresholds());
+});
+
+export default router;

src/api/server.js

@@ -5,6 +5,7 @@
 
 import express from 'express';
 import { error, info, warn } from '../logger.js';
+import { PerformanceMonitor } from '../modules/performanceMonitor.js';
 import apiRouter from './index.js';
 import { rateLimit } from './middleware/rateLimit.js';
 import { stopAuthCleanup } from './routes/auth.js';
@@ -69,6 +70,17 @@ export function createApp(client, dbPool) {
   // Raw OpenAPI spec (JSON) — public for Mintlify
   app.get('/api/docs.json', (_req, res) => res.json(swaggerSpec));
 
+  // Response time tracking for performance monitoring
+  app.use('/api/v1', (req, res, next) => {
+    const start = Date.now();
+    res.on('finish', () => {
+      const duration = Date.now() - start;
+      const label = `${req.method} ${req.path}`;
+      PerformanceMonitor.getInstance().recordResponseTime(label, duration, 'api');
+    });
+    next();
+  });
+
   // Mount API routes under /api/v1
   app.use('/api/v1', apiRouter);
 

src/index.js

@@ -50,6 +50,7 @@ import { startGithubFeed, stopGithubFeed } from './modules/githubFeed.js';
 import { checkMem0Health, markUnavailable } from './modules/memory.js';
 import { startTempbanScheduler, stopTempbanScheduler } from './modules/moderation.js';
 import { loadOptOuts } from './modules/optout.js';
+import { PerformanceMonitor } from './modules/performanceMonitor.js';
 import { startScheduler, stopScheduler } from './modules/scheduler.js';
 import { startTriage, stopTriage } from './modules/triage.js';
 import { startVoiceFlush, stopVoiceFlush } from './modules/voice.js';
@@ -126,6 +127,9 @@ client.commands = new Collection();
 // Initialize health monitor
 const healthMonitor = HealthMonitor.getInstance();
 
+// Initialize performance monitor (singleton; start() called in ClientReady handler)
+const perfMonitor = PerformanceMonitor.getInstance();
+
 /** @type {ReturnType<typeof setInterval> | null} Health degraded check interval */
 let healthCheckInterval = null;
 
@@ -266,7 +270,9 @@ client.on('interactionCreate', async (interaction) => {
       return;
     }
 
+    const _cmdStart = Date.now();
     await command.execute(interaction);
+    perfMonitor.recordResponseTime(commandName, Date.now() - _cmdStart, 'command');
     info('Command executed', {
       command: commandName,
       user: interaction.user.tag,
@@ -309,6 +315,9 @@ async function gracefulShutdown(signal) {
   stopTriage();
   stopConversationCleanup();
   stopTempbanScheduler();
+  stopScheduler();
+  stopGithubFeed();
+  perfMonitor.stop();
   stopBotStatus();
   stopVoiceFlush();
 
@@ -506,6 +515,9 @@ async function startup() {
   // Register event handlers with live config reference
   registerEventHandlers(client, config, healthMonitor);
 
+  // Start performance monitor
+  perfMonitor.start();
+
   // Start triage module (per-channel message classification + response)
   await startTriage(client, config, healthMonitor);