Pre-submission Checklist / 提交前检查

• I have searched the existing issues and this feature has not been requested / 我已搜索现有 issues，此功能尚未被提出
• I have read the documentation / 我已阅读文档

Problem Statement / 问题描述

If a provider has rate limits for a model and the model replies that it is unavailable until x time using standard 429 response code, the model should not be attempted again until the rate limit time is over.

Proposed Solution / 期望方案

If hitting rate limits, don't try for a minimum of x seconds defined in the config, if a provider is telling you when you can access it again, use that.

Alternatives Considered / 备选方案

No response

Feature Category / 功能分类

Load Balancing / Failover / 负载均衡 / 故障切换

Additional Context / 其他补充信息

No response