rate-limit

梁文峰时间高峰自动拦截官方 DeepSeek 请求

Auto-retry failed API requests to keep DSH conversations going. Supports configurable status codes and error codes. 自动重试失败的 API 请求，让 DSH 对话不中断。支持自定义状态码和错误码。

DeepSeek Harness (dsh) plugin: automatic session handoff when a session keeps hitting 429 TPM rate limits — cancel old, summarize handover, continue in a fresh session. True handoff, never parallel.

DeepSeek Harness 请求重试插件：模型请求失败且错误信息命中关键词时，在内置重试策略耗尽后继续自动追加重试；设置面板可管理关键词与退避参数。

DSH plugin: rate-limit model calls per provider/model via FIFO queues (minIntervalMs + maxConcurrent) on the llm/stream waterfall

DeepSeek Harness plugin for provider/model-aware adaptive rate-limit pacing, visible retries, and free-model recovery.

DeepSeek Harness plugin for LLM API rate limiting, concurrency control, FIFO queuing, token budgets, and adaptive 429 cooldown

该仓库暂未提供项目说明。