The Retry Budget: Why My n8n LLM Workflows Retry Exactly Once, Then Page a Human

说明与用途

文章说明了如何在 n8n 中为 LLM 工作流设置重试预算，以节省令牌并通过将错误分类为三组并应用不同的重试策略来提高可靠性。

问题

When an LLM completion fails validation, it is unclear whether to retry automatically or send it to human review, risking unnecessary cost and inefficiency.

结果

Implemented a retry budget that reduces unnecessary prompt costs, improves reliability, and provides clear escalation to human review.

工作流

• Classify error type and count attempts in a Code node
• If transient and attempts ≤3, set action to retry_backoff
• If repairable and first attempt, set action to retry_with_feedback
• If deterministic or repeated repairable failure, set action to review
• Route based on action field to retry or review queue

证据

Every LLM failure in my workflows falls into one of three buckets, and each bucket gets a different response:

来源

I logged 200 repairable failures over a month. First feedback-retry success rate: 71%. Second retry on the remaining 29%: 9% of those.

来源