Why AI Apps Crash Under Real Traffic (And How to Fix It in 2 Lines) A developer released @rohan9024/retrykit v2.0.0, a zero-dependency TypeScript reliability library for AI apps that replaces generic retry wrappers such as p-retry with LLM-aware handling of rate limits, multi-key rotation, circuit breaking, stream recovery and context compaction. The package's wrapAI() helper sets maxRetries to 0 on official SDKs to prevent stacked retries from multiplying into 9x-12x traffic storms, quarantines keys on hard billing errors like insufficient_quota instead of sleeping, and preserves tool-call message pairs when trimming context. TL;DR: Generic retry wrappers like p-retry or while loops weren't built for LLM APIs. They multiply SDK retries into 9x–12x traffic storms , sleep on hard billing errors insufficient quota , corrupt streamed UI text on mid-stream disconnects, and break tool-call message histories. @rohan9024/retrykit https://github.com/rohan9024/retrykit v2.0.0 is a zero-dependency TypeScript reliability engine for AI apps that solves rate limits, multi-key rotation, circuit breaking, stream recovery, and atomic context compaction in one package. If you have ever shipped an AI feature with OpenAI, Anthropic, or Gemini, you have probably seen this story play out in production: 429 Too Many Requests or Anthropic returns 529 Overloaded . maxRetries: 2 by default . Wrapping your own 3-retry loop around it means 3 × 4 This guide explains why standard HTTP retry logic fails on LLM APIs and how to fix it cleanly in under a minute using RetryKit @rohan9024/retrykit . Before writing code, it helps to understand what actually goes wrong when you use a generic retry helper for LLMs: maxRetries Multiplication Most official AI SDKs already retry failed requests twice internally. When developers add a custom retry wrapper or queue around the SDK without setting maxRetries: 0 , retries multiply instead of adding up—flooding your own API quota during an outage. insufficient quota Not every 429 error means "slow down and try again." OpenAI returns 429 for insufficient quota or spend limits, and Anthropic returns enforced spend limit reached . Waiting 1s → 2s → 4s → 8s on a dead key just freezes your user's request for 15+ seconds for no reason. You should quarantine that key immediately and rotate to a backup key with zero sleep. Providers return rate-limit resets in wildly different formats: retry-after-ms milliseconds retry-after seconds or HTTP date strings "464ms" , "1m30s" anthropic-ratelimit-requests-reset Generic backoff ignores these headers—retrying either too early hitting another 429 or much too late. Suppose your LLM streams 40 tokens to the user's chat screen and then stalls on token 41. If a naive wrapper restarts the HTTP call from scratch and yields tokens from the beginning, your user sees the first paragraph pasted twice . Safe streaming recovery must treat pre-first-token failures differently from mid-stream failures where resuming requires an explicit checkpoint mechanism like getCheckpoint . When an agent hits a context limit and you trim older chat messages blindly, you can accidentally delete an assistant message containing tool calls while leaving its tool response behind or vice versa . Both OpenAI and Anthropic reject orphaned tool pairs with a hard 400 Bad Request . @rohan9024/retrykit Zero Dependencies, AI-Native @rohan9024/retrykit https://www.npmjs.com/package/@rohan9024/retrykit is a lightweight, zero-dependency TypeScript reliability library built specifically for AI apps, Node.js backends, and Edge runtimes Node = 20 , Bun, Deno, Cloudflare Workers . Install it with your package manager: npm install @rohan9024/retrykit Also works with pnpm add @rohan9024/retrykit , yarn add @rohan9024/retrykit , or bun add @rohan9024/retrykit . The fastest way to protect an existing codebase is @rohan9024/retrykit/auto : python import OpenAI from "openai"; import { wrapAI } from "@rohan9024/retrykit/auto"; const openai = wrapAI new OpenAI { apiKey: process.env.OPENAI API KEY } , { provider: "openai" } ; // Use the SDK exactly as before: const response = await openai.chat.completions.create { model: "gpt-4o", messages: { role: "user", content: "Explain circuit breakers simply." } , } ; wrapAI handles automatically under the hood: maxRetries: 0 so the SDK and RetryKit never stack retries. OPENAI API KEYS comma-separated or OPENAI API KEY 1 , OPENAI API KEY 2 , etc. plus ANTHROPIC API KEYS and GEMINI API KEYS . Authorization , x-api-key , x-goog-api-key instead of mutating shared global client state. credit balance exhausted , organization spend limit exceeded , project spend limit exceeded , and enforced spend limit reached and rotates immediately instead of wasting sleep time. AbortController signals attemptTimeoutMs , totalDeadlineMs so timed-out network calls actually abort instead of leaking sockets. Already have a big TypeScript project? Run the built-in static doctor CLI to find unguarded AI clients and hidden double-retry loops: npx @rohan9024/retrykit doctor It scans your source files and points to the exact file and line where: new OpenAI ... or new Anthropic ... is called without protection maxRetries 0 could trigger double-retry amplification You can also scaffold a project starter config safely with: npx @rohan9024/retrykit init --dry-run RetryKit v2.0.0 ships clean ESM + CommonJS + TypeScript declarations across focused subpaths with "sideEffects": false : | Import Path | What It Solves | |---|---| | @rohan9024/retrykit/auto | Drop-in wrapAI proxy, multi-key discovery discoverApiKeys , SDK retry neutralization | | @rohan9024/retrykit/core | Core retry , CircuitBreaker , KeyPool , backoff + jitter, linked timeouts | | @rohan9024/retrykit/fetch | Composable createRetryFetch with safe body cloning & idempotency checks | | @rohan9024/retrykit/stream | Streaming watchdog & explicit getCheckpoint -based safe recovery | | @rohan9024/retrykit/compaction | Tool-call-safe atomic context compaction never orphans tool calls / tool results | | @rohan9024/retrykit/budget | RetryBudget and TokenBucketRetryBudget to cap retry amplification | | @rohan9024/retrykit/ai-sdk | Zero-dependency structural middleware transformParams , wrapGenerate , wrapStream for Vercel AI SDK | | @rohan9024/retrykit/mcp | Safe Model Context Protocol MCP retry wrapper read-only allowlists; never retries unsafe tools/call by default | | @rohan9024/retrykit/validate | Retry-on-validation-failure utilities | | Capability | @rohan9024/retrykit v2.0 | p-retry / async-retry | cockatiel | Raw OpenAI / Anthropic SDK | |---|---|---|---|---| | Zero runtime dependencies | Yes 0 | No | Yes | Full SDK | | OpenAI / Anthropic reset header parsing | Yes 464ms , 1m30s , RFC 3339, 529 | No | No | Basic | | Hard billing error fast-rotation | Yes | No sleeps & fails | No | No | | Per-request multi-key rotation | Yes | No | No | No | | Circuit breakers + token-bucket retry budgets | Yes | No | Partial | No | | Checkpoint-safe stream handling | Yes getCheckpoint | No | No | No | | Atomic tool-call context compaction | Yes | No | No | No | | Vercel AI SDK & MCP adapters included | Yes | No | No | No | | AI Coding Agent Skill + CLI doctor | Yes | No | No | No | Building with an AI coding assistant? RetryKit includes an official Agent Skill skills/retrykit/SKILL.md following the agentskills.io standard , llms.txt , llms-full.txt , AGENTS.md , and context7.json . npx skills add rohan9024/retrykit --skill retrykit "Inspect my project for AI SDK calls openai , @anthropic-ai/sdk , Vercel AI SDK, or fetch LLM requests . Run npx @rohan9024/retrykit doctor , install @rohan9024/retrykit with my project's package manager, wrap the clients using @rohan9024/retrykit/auto , ensure maxRetries: 0 is set to prevent double-retry storms, and verify with tests." You can also run RetryKit's built-in stdio MCP diagnostic server in any MCP-compatible editor: npx @rohan9024/retrykit mcp Use @rohan9024/retrykit/auto wrapAI or @rohan9024/retrykit/core retry + TokenBucketRetryBudget . RetryKit automatically sets request-level maxRetries: 0 on wrapped OpenAI/Anthropic SDK calls so SDK retries and custom retries never multiply, while honoring retry-after-ms , x-ratelimit-reset- , and jittered backoff. 429 insufficient quota errors? No. Sleeping and retrying an exhausted key wastes latency. RetryKit detects insufficient quota , credit balance exhausted , organization spend limit exceeded , project spend limit exceeded , and enforced spend limit reached , failing fast on that key so a backup key can take over immediately. If a stream fails mid-way after chunks have already been emitted, silently replaying from the beginning would duplicate text. RetryKit refuses silent replay after output begins unless you supply an explicit getCheckpoint recovery mechanism. No. @rohan9024/retrykit has "dependencies": {} zero runtime dependencies and exposes tree-shakeable ESM/CJS subpath exports with "sideEffects": false . npm install @rohan9024/retrykit If RetryKit saves you from a production 429 incident, leave a star on GitHub or open an issue telling us which AI SDK or framework adapter you want next