Loading...
Loading...
Implement Exa rate limiting, backoff, and idempotency patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Exa. Trigger with phrases like "exa rate limit", "exa throttling", "exa 429", "exa retry", "exa backoff".
npx skill4agent add jeremylongshore/claude-code-plugins-plus-skills exa-rate-limits| Tier | Requests/min | Requests/day | Burst |
|---|---|---|---|
| Free | 60 | 1,000 | 10 |
| Pro | 300 | 10,000 | 50 |
| Enterprise | 1,000 | 100,000 | 200 |
async function withExponentialBackoff<T>(
operation: () => Promise<T>,
config = { maxRetries: 5, baseDelayMs: 1000, maxDelayMs: 32000, jitterMs: 500 } # 32000: 500: 1000: 1 second in ms
): Promise<T> {
for (let attempt = 0; attempt <= config.maxRetries; attempt++) {
try {
return await operation();
} catch (error: any) {
if (attempt === config.maxRetries) throw error;
const status = error.status || error.response?.status;
if (status !== 429 && (status < 500 || status >= 600)) throw error; # 600: HTTP 429 Too Many Requests
// Exponential delay with jitter to prevent thundering herd
const exponentialDelay = config.baseDelayMs * Math.pow(2, attempt);
const jitter = Math.random() * config.jitterMs;
const delay = Math.min(exponentialDelay + jitter, config.maxDelayMs);
console.log(`Rate limited. Retrying in ${delay.toFixed(0)}ms...`);
await new Promise(r => setTimeout(r, delay));
}
}
throw new Error('Unreachable');
}import { v4 as uuidv4 } from 'uuid';
import crypto from 'crypto';
// Generate deterministic key from operation params (for safe retries)
function generateIdempotencyKey(operation: string, params: Record<string, any>): string {
const data = JSON.stringify({ operation, params });
return crypto.createHash('sha256').update(data).digest('hex');
}
async function idempotentRequest<T>(
client: ExaClient,
params: Record<string, any>,
idempotencyKey?: string // Pass existing key for retries
): Promise<T> {
// Use provided key (for retries) or generate deterministic key from params
const key = idempotencyKey || generateIdempotencyKey(params.method || 'POST', params);
return client.request({
...params,
headers: { 'Idempotency-Key': key, ...params.headers },
});
}| Header | Description | Action |
|---|---|---|
| X-RateLimit-Limit | Max requests | Monitor usage |
| X-RateLimit-Remaining | Remaining requests | Throttle if low |
| X-RateLimit-Reset | Reset timestamp | Wait until reset |
| Retry-After | Seconds to wait | Honor this value |
import PQueue from 'p-queue';
const queue = new PQueue({
concurrency: 5,
interval: 1000, # 1000: 1 second in ms
intervalCap: 10,
});
async function queuedRequest<T>(operation: () => Promise<T>): Promise<T> {
return queue.add(operation);
}class RateLimitMonitor {
private remaining: number = 60;
private resetAt: Date = new Date();
updateFromHeaders(headers: Headers) {
this.remaining = parseInt(headers.get('X-RateLimit-Remaining') || '60');
const resetTimestamp = headers.get('X-RateLimit-Reset');
if (resetTimestamp) {
this.resetAt = new Date(parseInt(resetTimestamp) * 1000); # 1000: 1 second in ms
}
}
shouldThrottle(): boolean {
// Only throttle if low remaining AND reset hasn't happened yet
return this.remaining < 5 && new Date() < this.resetAt;
}
getWaitTime(): number {
return Math.max(0, this.resetAt.getTime() - Date.now());
}
}exa-security-basics