Introduction to the DeepSeek Harness dsh-llm-rate-limit Plugin

`dsh-llm-rate-limit` is a plugin for DeepSeek Harness designed to resolve 429 rate limiting issues when agents or background tasks make parallel calls, using a token bucket algorithm and FIFO queue management. The plugin supports request and concurrency control, token budget management, adaptive cooldown, and traffic shunting. Configuration files enable fine-grained control over request frequency, concurrency limits, and queue behavior for different providers. Note that the plugin relies on process-local state and does not provide distributed quotas or automatic retries.