Production Deployment

This guide covers deploying Enclave to production environments, including configuration, monitoring, and operational best practices.

Deployment Architecture

Single-Server Deployment

For smaller workloads:

Distributed Deployment

For production scale:

Pre-Deployment Checklist

Security

Performance

Configure worker pool for CPU-bound loads
Set up Redis for distributed sessions
Configure connection pooling
Enable response compression
Set up CDN for static assets

Monitoring

Infrastructure

Configuration

Environment Variables

# Server
NODE_ENV=production
PORT=3000

# Enclave
ENCLAVE_SECURITY_LEVEL=STRICT
ENCLAVE_TIMEOUT=30000
ENCLAVE_MAX_TOOL_CALLS=100
ENCLAVE_MAX_ITERATIONS=10000
ENCLAVE_MEMORY_LIMIT=67108864  # 64MB

# AI Scoring
ENCLAVE_SCORING_ENABLED=true
ENCLAVE_SCORING_THRESHOLD=70

# Worker Pool (optional)
ENCLAVE_WORKER_POOL_SIZE=4
ENCLAVE_WORKER_MAX_MEMORY=134217728  # 128MB

# Redis (for distributed mode)
REDIS_URL=redis://localhost:6379

# Logging
LOG_LEVEL=info
LOG_FORMAT=json

Production Configuration

// src/config/enclave.ts
import { Enclave } from '@enclave-vm/core';

export function createProductionEnclave(toolHandler: Function) {
  return new Enclave({
    // Security
    securityLevel: 'STRICT',

    // Limits
    timeout: parseInt(process.env.ENCLAVE_TIMEOUT || '30000'),
    maxToolCalls: parseInt(process.env.ENCLAVE_MAX_TOOL_CALLS || '100'),
    maxIterations: parseInt(process.env.ENCLAVE_MAX_ITERATIONS || '10000'),
    memoryLimit: parseInt(process.env.ENCLAVE_MEMORY_LIMIT || '67108864'),

    // AI Scoring
    scoringGate: process.env.ENCLAVE_SCORING_ENABLED === 'true' ? {
      scorer: 'rule-based',
      blockThreshold: parseInt(process.env.ENCLAVE_SCORING_THRESHOLD || '70'),
    } : undefined,

    // Tool handling
    toolHandler,

    // Logging
    onLog: (level, message, data) => {
      logger.log(level, message, data);
    },
  });
}

Docker Deployment

Dockerfile

FROM node:20-slim

# Security: Run as non-root user
RUN useradd -m -u 1001 enclave
WORKDIR /app

# Install dependencies
COPY package*.json ./
RUN npm ci --production

# Copy application
COPY --chown=enclave:enclave . .

# Security: Drop capabilities
USER enclave

# Health check
HEALTHCHECK --interval=30s --timeout=3s --start-period=5s \
  CMD curl -f http://localhost:3000/health || exit 1

EXPOSE 3000
CMD ["node", "dist/server.js"]

Docker Compose

# docker-compose.yml
version: '3.8'

services:
  api:
    build: .
    ports:
      - "3000:3000"
    environment:
      - NODE_ENV=production
      - REDIS_URL=redis://redis:6379
    depends_on:
      - redis
    deploy:
      replicas: 2
      resources:
        limits:
          memory: 512M
        reservations:
          memory: 256M

  redis:
    image: redis:7-alpine
    volumes:
      - redis-data:/data
    command: redis-server --appendonly yes

volumes:
  redis-data:

Kubernetes Deployment

Deployment Manifest

# k8s/deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: enclave-api
spec:
  replicas: 3
  selector:
    matchLabels:
      app: enclave-api
  template:
    metadata:
      labels:
        app: enclave-api
    spec:
      containers:
        - name: api
          image: your-registry/enclave-api:latest
          ports:
            - containerPort: 3000
          env:
            - name: NODE_ENV
              value: "production"
            - name: REDIS_URL
              valueFrom:
                secretKeyRef:
                  name: enclave-secrets
                  key: redis-url
          resources:
            requests:
              memory: "256Mi"
              cpu: "250m"
            limits:
              memory: "512Mi"
              cpu: "500m"
          livenessProbe:
            httpGet:
              path: /health
              port: 3000
            initialDelaySeconds: 10
            periodSeconds: 10
          readinessProbe:
            httpGet:
              path: /ready
              port: 3000
            initialDelaySeconds: 5
            periodSeconds: 5

Service and Ingress

# k8s/service.yaml
apiVersion: v1
kind: Service
metadata:
  name: enclave-api
spec:
  selector:
    app: enclave-api
  ports:
    - port: 80
      targetPort: 3000
---
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: enclave-api
  annotations:
    kubernetes.io/ingress.class: nginx
    cert-manager.io/cluster-issuer: letsencrypt-prod
spec:
  tls:
    - hosts:
        - api.example.com
      secretName: enclave-tls
  rules:
    - host: api.example.com
      http:
        paths:
          - path: /
            pathType: Prefix
            backend:
              service:
                name: enclave-api
                port:
                  number: 80

Monitoring

Health Endpoints

// src/routes/health.ts
import { Router } from 'express';

const router = Router();

// Liveness check - is the process running?
router.get('/health', (req, res) => {
  res.json({ status: 'ok' });
});

// Readiness check - can we handle requests?
router.get('/ready', async (req, res) => {
  try {
    // Check dependencies
    await redis.ping();
    res.json({ status: 'ready' });
  } catch (error) {
    res.status(503).json({ status: 'not ready', error: error.message });
  }
});

export default router;

Metrics

// src/metrics.ts
import { Counter, Histogram, Gauge, Registry } from 'prom-client';

export const registry = new Registry();

// Execution metrics
export const executionCounter = new Counter({
  name: 'enclave_executions_total',
  help: 'Total number of code executions',
  labelNames: ['status', 'security_level'],
  registers: [registry],
});

export const executionDuration = new Histogram({
  name: 'enclave_execution_duration_seconds',
  help: 'Code execution duration in seconds',
  buckets: [0.1, 0.5, 1, 2, 5, 10, 30],
  registers: [registry],
});

export const toolCallCounter = new Counter({
  name: 'enclave_tool_calls_total',
  help: 'Total number of tool calls',
  labelNames: ['tool', 'status'],
  registers: [registry],
});

export const activeExecutions = new Gauge({
  name: 'enclave_active_executions',
  help: 'Number of currently running executions',
  registers: [registry],
});

Structured Logging

// src/logger.ts
import pino from 'pino';

export const logger = pino({
  level: process.env.LOG_LEVEL || 'info',
  formatters: {
    level: (label) => ({ level: label }),
  },
  base: {
    service: 'enclave-api',
    version: process.env.npm_package_version,
  },
});

// Execution logging
export function logExecution(
  sessionId: string,
  code: string,
  result: ExecutionResult
) {
  logger.info({
    event: 'execution_complete',
    sessionId,
    codeLength: code.length,
    success: result.success,
    duration: result.stats?.duration,
    toolCalls: result.stats?.toolCallCount,
    error: result.error?.code,
  });
}

Error Handling

Global Error Handler

// src/middleware/errorHandler.ts
import { Request, Response, NextFunction } from 'express';
import { logger } from '../logger';

export function errorHandler(
  error: Error,
  req: Request,
  res: Response,
  next: NextFunction
) {
  // Log error
  logger.error({
    event: 'unhandled_error',
    error: error.message,
    stack: error.stack,
    path: req.path,
    method: req.method,
  });

  // Don't leak internal errors
  if (process.env.NODE_ENV === 'production') {
    res.status(500).json({
      error: 'Internal server error',
      requestId: req.id,
    });
  } else {
    res.status(500).json({
      error: error.message,
      stack: error.stack,
    });
  }
}

Graceful Shutdown

// src/server.ts
import { createTerminus } from '@godaddy/terminus';

function onSignal() {
  logger.info('Server shutting down...');
  return Promise.all([
    // Close database connections
    db.close(),
    // Close Redis
    redis.quit(),
    // Dispose enclaves
    enclavePool.dispose(),
  ]);
}

function onShutdown() {
  logger.info('Server shutdown complete');
}

createTerminus(server, {
  signal: 'SIGINT',
  healthChecks: {
    '/health': () => Promise.resolve(),
  },
  onSignal,
  onShutdown,
  timeout: 30000,
});

Security Hardening

Rate Limiting

import rateLimit from 'express-rate-limit';

const executionLimiter = rateLimit({
  windowMs: 60 * 1000, // 1 minute
  max: 30, // 30 executions per minute
  message: { error: 'Too many requests, please try again later' },
  standardHeaders: true,
  legacyHeaders: false,
});

app.use('/api/execute', executionLimiter);

Request Validation

import { z } from 'zod';

const executeSchema = z.object({
  code: z.string().min(1).max(100000),
  timeout: z.number().min(1000).max(300000).optional(),
  context: z.record(z.unknown()).optional(),
});

app.post('/api/execute', async (req, res) => {
  const parsed = executeSchema.safeParse(req.body);

  if (!parsed.success) {
    return res.status(400).json({
      error: 'Invalid request',
      details: parsed.error.issues,
    });
  }

  // Execute with validated input
  const result = await enclave.run(parsed.data.code);
  res.json(result);
});

Performance Tuning

Connection Pooling

// Reuse Enclave instances
class EnclavePool {
  private pool: Enclave[] = [];
  private available: Enclave[] = [];

  constructor(size: number, config: EnclaveConfig) {
    for (let i = 0; i < size; i++) {
      const enclave = new Enclave(config);
      this.pool.push(enclave);
      this.available.push(enclave);
    }
  }

  async acquire(): Promise<Enclave> {
    if (this.available.length > 0) {
      return this.available.pop()!;
    }
    // Wait for one to become available
    return new Promise((resolve) => {
      const check = setInterval(() => {
        if (this.available.length > 0) {
          clearInterval(check);
          resolve(this.available.pop()!);
        }
      }, 10);
    });
  }

  release(enclave: Enclave) {
    this.available.push(enclave);
  }

  dispose() {
    this.pool.forEach(e => e.dispose());
  }
}

Deployment Platforms

Vercel

// vercel.json
{
  "functions": {
    "api/**/*.ts": {
      "memory": 1024,
      "maxDuration": 30
    }
  }
}

Railway

# railway.toml
[build]
builder = "nixpacks"

[deploy]
healthcheckPath = "/health"
healthcheckTimeout = 30

Render

# render.yaml
services:
  - type: web
    name: enclave-api
    env: node
    buildCommand: npm ci && npm run build
    startCommand: npm start
    healthCheckPath: /health
    envVars:
      - key: NODE_ENV
        value: production

Scaling - Scale to handle more load
Security Hardening - Secure your deployment
Common Errors - Troubleshooting guide

​Deployment Architecture

​Single-Server Deployment

​Distributed Deployment

​Pre-Deployment Checklist

​Security

​Performance

​Monitoring

​Infrastructure

​Configuration

​Environment Variables

​Production Configuration

​Docker Deployment

​Dockerfile

​Docker Compose

​Kubernetes Deployment

​Deployment Manifest

​Service and Ingress

​Monitoring

​Health Endpoints

​Metrics

​Structured Logging

​Error Handling

​Global Error Handler

​Graceful Shutdown

​Security Hardening

​Rate Limiting

​Request Validation

​Performance Tuning

​Connection Pooling

​Deployment Platforms

​Vercel

​Railway

​Render

​Related

Deployment Architecture

Single-Server Deployment

Distributed Deployment

Pre-Deployment Checklist

Security

Performance

Monitoring

Infrastructure

Configuration

Environment Variables

Production Configuration

Docker Deployment

Dockerfile

Docker Compose

Kubernetes Deployment

Deployment Manifest

Service and Ingress

Monitoring

Health Endpoints

Metrics

Structured Logging

Error Handling

Global Error Handler

Graceful Shutdown

Security Hardening

Rate Limiting

Request Validation

Performance Tuning

Connection Pooling

Deployment Platforms

Vercel

Railway

Render

Related