Asong6824/dsh-llm-rate-limit
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。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-llm-rate-limit(Asong6824/dsh-llm-rate-limit)
仓库:https://github.com/Asong6824/dsh-llm-rate-limit
本站详情页:https://www.yhbd.top/plugins/asong6824-dsh-llm-rate-limit/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-08-20 · 主语言 JavaScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- 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
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-retryattempt 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 →
Q00/ouroboros
crafter-station/petdex
whiteguo233/OpenBiliClaw
anywhere-labs/Agents-Anywhere
agentrq/agentrq
freestylefly/wesight