Asong6824/dsh-llm-rate-limit

Plugin插件 Native原生 ⭐ 2 MIT Models & Routing模型与路由

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

Project Overview项目介绍

dsh-llm-rate-limit is a native DeepSeek Harness (DSH) plugin authored by Asong6824 and distributed as an npm package named dsh-llm-rate-limit. It is installed through the official DSH plugin manager for either the Web or Headless profile using dsh plugin --profile web add dsh-llm-rate-limit, and GitHub source installs are supported via dsh plugin --profile web add github:Asong6824/dsh-llm-rate-limit#v0.1.1. The bundle ships a default bucket for deepseek-official at 30 requests per minute, burst of 1, two concurrent slots, plus a bounded queue, and it also covers Volcengine Ark and other DSH providers with per-provider RPM, concurrency, FIFO queueing, and adaptive cooldown controls.

The typical workflow starts by editing the llm-rate-limit section inside $DSH_HOME/profiles/<profile>/cordis.patch.yml, where each provider key must match GenerateOptions.provider exactly so that requests, maxConcurrentRequests, queue (maxSize, maxWaitMs, auxiliary: reject) and cooldown (codes, statuses, initialDelayMs, maxDelayMs, maxProviderDelayMs, jitterRatio) can be tuned. Optional tokens blocks add per-minute and burst token ceilings with estimatedOutputTokens and imageTokens; omitting tokens keeps RPM and concurrency without a local token cap. Admissions are emitted as durable wait/start events for DSH session diagnostics.

It targets users running parallel agents, subagents, retries, and background traffic that produce HTTP 429 or throttling against DeepSeek or Ark. The plugin depends on DeepSeek Harness 0.1.0-rc.8 or newer and Node.js 22.19 or newer, is released under MIT, and exposes process-local state that resets on DSH restart. It deliberately omits distributed quotas, automatic retries, and provider failover, and it treats every dsh-llm-retry attempt as an independent admission. Development relies on pnpm install and pnpm run check, with CI workflows publishing tagged releases to npm.

dsh-llm-rate-limit 是面向 DeepSeek Harness (DSH) 的原生速率限制插件,由 Asong6824 以 npm 包形式发布,支持 Web 与 Headless 两种 DSH profile 安装(命令 dsh plugin --profile web add dsh-llm-rate-limit),也可通过 GitHub 安装指定版本。它内置 deepseek-official 默认桶(每分钟 30 次、突发 1、并发 2),同时为 Volcengine Ark 等其他 DSH provider 提供 RPM、并发、FIFO 队列与自适应冷却。

典型流程是编辑 $DSH_HOME/profiles/<profile>/cordis.patch.yml 中的 llm-rate-limit 配置节,按 GenerateOptions.provider 精确命名 provider 来设置 perMinute、burst、maxConcurrentRequests、queue(maxSize/maxWaitMs/auxiliary)、cooldown(codes/statuses/initialDelayMs/maxDelayMs/jitterRatio),可选加入 tokens 预算。请求经它预占容量后入队等待,429 等触发共享冷却,成功后再核销估算 token。适用于多 agent、subagent、重试与后台请求同时压向 DeepSeek 或 Ark、频繁出现 429 与突发流量的场景。

依赖 DSH ≥0.1.0-rc.8 与 Node.js ≥22.19,MIT 协议,状态仅限进程内、DSH 重启即清空,明确不提供分布式配额、自动重试与 provider 故障转移,每次 dsh-llm-retry 重试需独立准入。开发侧 pnpm install && pnpm run check,CI 与 npm 发布工作流完备。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 2 stars - very few users, little community feedback星标只有 2,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add dsh-llm-rate-limit

把 Asong6824/dsh-llm-rate-limit 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-llm-rate-limit

npm downloads CI license

English | 中文

A DeepSeek Harness (DSH) plugin that prevents avoidable API rate-limit errors by pacing LLM requests before they reach the provider. It provides per-provider RPM limits, optional token budgets, concurrency control, bounded FIFO queuing, and adaptive cooldown for DeepSeek API, Volcengine Ark, and other DSH providers.

Use it when parallel agents, subagents, retries, or background requests are producing HTTP 429 errors, provider throttling, or traffic bursts.

Install from npm

Install the latest release into the Web profile:

dsh plugin --profile web add dsh-llm-rate-limit
dsh web

Pin a version for reproducible environments:

dsh plugin --profile web add dsh-llm-rate-limit@0.1.1

Install separately for Headless:

dsh plugin --profile headless add dsh-llm-rate-limit

GitHub installation is also supported:

dsh plugin --profile web add github:Asong6824/dsh-llm-rate-limit#v0.1.1

The bundled default protects deepseek-official with 30 requests per minute, burst 1, two concurrent requests, and a bounded queue.

Features

  • Provider-scoped requests-per-minute token buckets with configurable burst capacity.
  • Optional estimated-token-per-minute budgets with actual-usage reconciliation.
  • Concurrency limits and bounded FIFO queues with timeout and cancellation.
  • Adaptive cooldown for provider error codes, HTTP statuses, and Retry-After.
  • Explicit auxiliary-request shedding so background traffic does not block primary work.
  • Durable admission wait/start events for DSH session diagnostics.
  • Clean lifecycle disposal without abandoning queued or active requests.
  • Retry-aware admission: every dsh-llm-retry attempt is admitted independently; this plugin never retries requests itself.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-continue 下一个 Next agent-switch →