Xidong-AI/dsh-rate-limiter

README 摘要

dsh-rate-limiter English 中文 A proactive rate limiter plugin for DeepSeek Harness ( dsh ): it controls the request rate per provider (token bucket) before model requests are issued, and queues the request with a delay instead of failing when the limit is exceeded — avoiding upstream 429s. It complements the official dsh-llm-retry (exponential backoff after failure): rate limiting comes first (prevention), backoff comes last (safety net); the two do not interfere with each other. Features - Per-provider token bucket, enforced before the request is sent (proactive prevention) - Over-limit requests are queued with a delay instead of rejected (no 429s, no lost requests) - Unconfigured providers pass through untouched (zero intrusion) - Queued waits honor the abort signal: stopping the user interrupts the wait immediately - Hand-written reservation-based token bucket (concurrency-safe), zero third-party rate-limiting dependencies - Mounts on agent/request , coexists naturally with dsh-llm-retry Installation Install from npm: npm registry URLs are case-sensitive; use the lowercase package name. Or install directly from GitHub: For local development, add the checkout directly: After instal…

分类