dsh-offpeak: DSH Host Plugin for Automatically Managing Peak-Period Sessions and Requests
dsh-offpeak is a core plugin for DeepSeek Harness, designed to intercept requests during API peak periods to avoid rate-limiting failures. It intercepts, before dispatch, requests targeting the official source or explicitly listed models, and supports turn gating and request-level guards. It provides peak/off-peak policy configuration and session continuous-run exemptions, and manages the interception list, time zone, and peak windows through a Web panel. It is compatible with DSH host versions, supports either hold (suspension) or error throwing, and requires Node.js >= 20.
Read MoreDeepSeek Harness Plugin: LLM Call Rate Limiter
`dsh-llm-rate-limiter` is a plugin for DeepSeek Harness that mitigates API rate limiting or excessive resource consumption when calling LLM interfaces. It allows independent per-model configuration of concurrency, RPM, and burst traffic limits, provides token bucket and sliding window rate-limiting algorithms, and supports queueing or rejection policies. It includes an interactive GUI configuration panel, real-time status monitoring, and hot reloading, enabling policy adjustments without editing files. It is suitable for developers who need fine-grained control over LLM call frequency in DSH environments.
Read MoreIntroduction 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.
Read More@zhourenke/dsh-agent-rate-limit: Automatically Add TPM/RPM Rate Limits for DSH
The DSH Agent loop can easily exceed rate limits, triggering HTTP 429 errors. The `@zhourenke/dsh-agent-rate-limit` plugin inserts an adaptive delay layer before the LLM streaming pipeline, uses a sliding window algorithm to manage the request queue, and requests are queued before vendor rate limits are reached to prevent conversation interruptions. The plugin works with default configuration, supports TPM/RPM limits, safety factor adjustment, and hot configuration reloading, but shared window state is not supported and it does not guarantee that rate limit violations will never occur.
Read More