AgentSkillsCN

retellai-known-pitfalls

识别并避免 Retell AI 反模式与常见集成错误。 在审查 Retell AI 代码中的问题、培训新开发人员或审计现有 Retell AI 集成是否违反最佳实践时使用。 可通过诸如“retellai 错误”、“retellai 反模式”、“retellai 潜在陷阱”、“retellai 不要这样做”、“retellai 代码审查”等短语触发。

SKILL.md
--- frontmatter
name: retellai-known-pitfalls
description: |
  Identify and avoid Retell AI anti-patterns and common integration mistakes.
  Use when reviewing Retell AI code for issues, onboarding new developers,
  or auditing existing Retell AI integrations for best practices violations.
  Trigger with phrases like "retellai mistakes", "retellai anti-patterns",
  "retellai pitfalls", "retellai what not to do", "retellai code review".
allowed-tools: Read, Grep
version: 1.0.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>

Retell AI Known Pitfalls

Overview

Common mistakes and anti-patterns when integrating with Retell AI.

Prerequisites

  • Access to Retell AI codebase for review
  • Understanding of async/await patterns
  • Knowledge of security best practices
  • Familiarity with rate limiting concepts

Pitfall #1: Synchronous API Calls in Request Path

❌ Anti-Pattern

typescript
// User waits for Retell AI API call
app.post('/checkout', async (req, res) => {
  const payment = await retellaiClient.processPayment(req.body);  // 2-5s latency
  const notification = await retellaiClient.sendEmail(payment);   // Another 1-2s
  res.json({ success: true });  // User waited 3-7s
});

✅ Better Approach

typescript
// Return immediately, process async
app.post('/checkout', async (req, res) => {
  const jobId = await queue.enqueue('process-checkout', req.body);
  res.json({ jobId, status: 'processing' });  // 50ms response
});

// Background job
async function processCheckout(data) {
  const payment = await retellaiClient.processPayment(data);
  await retellaiClient.sendEmail(payment);
}

Pitfall #2: Not Handling Rate Limits

❌ Anti-Pattern

typescript
// Blast requests, crash on 429
for (const item of items) {
  await retellaiClient.process(item);  // Will hit rate limit
}

✅ Better Approach

typescript
import pLimit from 'p-limit';

const limit = pLimit(5);  // Max 5 concurrent
const rateLimiter = new RateLimiter({ tokensPerSecond: 10 });

for (const item of items) {
  await rateLimiter.acquire();
  await limit(() => retellaiClient.process(item));
}

Pitfall #3: Leaking API Keys

❌ Anti-Pattern

typescript
// In frontend code (visible to users!)
const client = new RetellAIClient({
  apiKey: 'sk_live_ACTUAL_KEY_HERE',  // Anyone can see this
});

// In git history
git commit -m "add API key"  // Exposed forever

✅ Better Approach

typescript
// Backend only, environment variable
const client = new RetellAIClient({
  apiKey: process.env.RETELLAI_API_KEY,
});

// Use .gitignore
.env
.env.local
.env.*.local

Pitfall #4: Ignoring Idempotency

❌ Anti-Pattern

typescript
// Network error on response = duplicate charge!
try {
  await retellaiClient.charge(order);
} catch (error) {
  if (error.code === 'NETWORK_ERROR') {
    await retellaiClient.charge(order);  // Charged twice!
  }
}

✅ Better Approach

typescript
const idempotencyKey = `order-${order.id}-${Date.now()}`;

await retellaiClient.charge(order, {
  idempotencyKey,  // Safe to retry
});

Pitfall #5: Not Validating Webhooks

❌ Anti-Pattern

typescript
// Trust any incoming request
app.post('/webhook', (req, res) => {
  processWebhook(req.body);  // Attacker can send fake events
  res.sendStatus(200);
});

✅ Better Approach

typescript
app.post('/webhook',
  express.raw({ type: 'application/json' }),
  (req, res) => {
    const signature = req.headers['x-retellai-signature'];
    if (!verifyRetell AISignature(req.body, signature)) {
      return res.sendStatus(401);
    }
    processWebhook(JSON.parse(req.body));
    res.sendStatus(200);
  }
);

Pitfall #6: Missing Error Handling

❌ Anti-Pattern

typescript
// Crashes on any error
const result = await retellaiClient.get(id);
console.log(result.data.nested.value);  // TypeError if missing

✅ Better Approach

typescript
try {
  const result = await retellaiClient.get(id);
  console.log(result?.data?.nested?.value ?? 'default');
} catch (error) {
  if (error instanceof Retell AINotFoundError) {
    return null;
  }
  if (error instanceof Retell AIRateLimitError) {
    await sleep(error.retryAfter);
    return this.get(id);  // Retry
  }
  throw error;  // Rethrow unknown errors
}

Pitfall #7: Hardcoding Configuration

❌ Anti-Pattern

typescript
const client = new RetellAIClient({
  timeout: 5000,  // Too short for some operations
  baseUrl: 'https://api.retellai.com',  // Can't change for staging
});

✅ Better Approach

typescript
const client = new RetellAIClient({
  timeout: parseInt(process.env.RETELLAI_TIMEOUT || '30000'),
  baseUrl: process.env.RETELLAI_BASE_URL || 'https://api.retellai.com',
});

Pitfall #8: Not Implementing Circuit Breaker

❌ Anti-Pattern

typescript
// When Retell AI is down, every request hangs
for (const user of users) {
  await retellaiClient.sync(user);  // All timeout sequentially
}

✅ Better Approach

typescript
import CircuitBreaker from 'opossum';

const breaker = new CircuitBreaker(retellaiClient.sync, {
  timeout: 10000,
  errorThresholdPercentage: 50,
  resetTimeout: 30000,
});

// Fails fast when circuit is open
for (const user of users) {
  await breaker.fire(user).catch(handleFailure);
}

Pitfall #9: Logging Sensitive Data

❌ Anti-Pattern

typescript
console.log('Request:', JSON.stringify(request));  // Logs API key, PII
console.log('User:', user);  // Logs email, phone

✅ Better Approach

typescript
const redacted = {
  ...request,
  apiKey: '[REDACTED]',
  user: { id: user.id },  // Only non-sensitive fields
};
console.log('Request:', JSON.stringify(redacted));

Pitfall #10: No Graceful Degradation

❌ Anti-Pattern

typescript
// Entire feature broken if Retell AI is down
const recommendations = await retellaiClient.getRecommendations(userId);
return renderPage({ recommendations });  // Page crashes

✅ Better Approach

typescript
let recommendations;
try {
  recommendations = await retellaiClient.getRecommendations(userId);
} catch (error) {
  recommendations = await getFallbackRecommendations(userId);
  reportDegradedService('retellai', error);
}
return renderPage({ recommendations, degraded: !recommendations });

Instructions

Step 1: Review for Anti-Patterns

Scan codebase for each pitfall pattern.

Step 2: Prioritize Fixes

Address security issues first, then performance.

Step 3: Implement Better Approach

Replace anti-patterns with recommended patterns.

Step 4: Add Prevention

Set up linting and CI checks to prevent recurrence.

Output

  • Anti-patterns identified
  • Fixes prioritized and implemented
  • Prevention measures in place
  • Code quality improved

Error Handling

IssueCauseSolution
Too many findingsLegacy codebasePrioritize security first
Pattern not detectedComplex codeManual review
False positiveSimilar codeWhitelist exceptions
Fix breaks testsBehavior changeUpdate tests

Examples

Quick Pitfall Scan

bash
# Check for common pitfalls
grep -r "sk_live_" --include="*.ts" src/        # Key leakage
grep -r "console.log" --include="*.ts" src/     # Potential PII logging

Resources

Quick Reference Card

PitfallDetectionPrevention
Sync in requestHigh latencyUse queues
Rate limit ignore429 errorsImplement backoff
Key leakageGit history scanEnv vars, .gitignore
No idempotencyDuplicate recordsIdempotency keys
Unverified webhooksSecurity auditSignature verification
Missing error handlingCrashesTry-catch, types
Hardcoded configCode reviewEnvironment variables
No circuit breakerCascading failuresopossum, resilience4j
Logging PIILog auditRedaction middleware
No degradationTotal outagesFallback systems