2197 lines
51 KiB
HTML
2197 lines
51 KiB
HTML
|
||
<!doctype html>
|
||
<html lang="en" class="no-js">
|
||
<head>
|
||
|
||
<meta charset="utf-8">
|
||
<meta name="viewport" content="width=device-width,initial-scale=1">
|
||
|
||
<meta name="description" content="Single source of truth for the homelab">
|
||
|
||
|
||
|
||
<link rel="canonical" href="http://192.168.1.8:13080/ideas/litellm-claude-max-bridge/">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<link rel="icon" href="../../assets/images/favicon.png">
|
||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.6">
|
||
|
||
|
||
|
||
<title>Design: Claude Max Subscription → LiteLLM Gateway Bridge - nuclide.systems docs</title>
|
||
|
||
|
||
|
||
<link rel="stylesheet" href="../../assets/stylesheets/main.484c7ddc.min.css">
|
||
|
||
|
||
<link rel="stylesheet" href="../../assets/stylesheets/palette.ab4e12ef.min.css">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
||
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
|
||
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
|
||
|
||
|
||
|
||
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
|
||
|
||
|
||
|
||
|
||
|
||
</head>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<body dir="ltr" data-md-color-scheme="slate" data-md-color-primary="black" data-md-color-accent="blue">
|
||
|
||
|
||
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
|
||
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
|
||
<label class="md-overlay" for="__drawer"></label>
|
||
<div data-md-component="skip">
|
||
|
||
|
||
<a href="#design-claude-max-subscription-litellm-gateway-bridge" class="md-skip">
|
||
Skip to content
|
||
</a>
|
||
|
||
</div>
|
||
<div data-md-component="announce">
|
||
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<header class="md-header" data-md-component="header">
|
||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||
<a href="../.." title="nuclide.systems docs" class="md-header__button md-logo" aria-label="nuclide.systems docs" data-md-component="logo">
|
||
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||
|
||
</a>
|
||
<label class="md-header__button md-icon" for="__drawer">
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
|
||
</label>
|
||
<div class="md-header__title" data-md-component="header-title">
|
||
<div class="md-header__ellipsis">
|
||
<div class="md-header__topic">
|
||
<span class="md-ellipsis">
|
||
nuclide.systems docs
|
||
</span>
|
||
</div>
|
||
<div class="md-header__topic" data-md-component="header-topic">
|
||
<span class="md-ellipsis">
|
||
|
||
Design: Claude Max Subscription → LiteLLM Gateway Bridge
|
||
|
||
</span>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
<form class="md-header__option" data-md-component="palette">
|
||
|
||
|
||
|
||
|
||
<input class="md-option" data-md-color-media="(prefers-color-scheme: dark)" data-md-color-scheme="slate" data-md-color-primary="black" data-md-color-accent="blue" aria-hidden="true" type="radio" name="__palette" id="__palette_0">
|
||
|
||
|
||
|
||
|
||
|
||
<input class="md-option" data-md-color-media="(prefers-color-scheme: light)" data-md-color-scheme="default" data-md-color-primary="black" data-md-color-accent="blue" aria-hidden="true" type="radio" name="__palette" id="__palette_1">
|
||
|
||
|
||
</form>
|
||
|
||
|
||
|
||
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
|
||
|
||
|
||
|
||
|
||
|
||
<label class="md-header__button md-icon" for="__search">
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
|
||
</label>
|
||
<div class="md-search" data-md-component="search" role="dialog">
|
||
<label class="md-search__overlay" for="__search"></label>
|
||
<div class="md-search__inner" role="search">
|
||
<form class="md-search__form" name="search">
|
||
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
|
||
<label class="md-search__icon md-icon" for="__search">
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
|
||
</label>
|
||
<nav class="md-search__options" aria-label="Search">
|
||
|
||
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
|
||
</button>
|
||
</nav>
|
||
|
||
<div class="md-search__suggest" data-md-component="search-suggest"></div>
|
||
|
||
</form>
|
||
<div class="md-search__output">
|
||
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
|
||
<div class="md-search-result" data-md-component="search-result">
|
||
<div class="md-search-result__meta">
|
||
Initializing search
|
||
</div>
|
||
<ol class="md-search-result__list" role="presentation"></ol>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
</nav>
|
||
|
||
</header>
|
||
|
||
<div class="md-container" data-md-component="container">
|
||
|
||
|
||
|
||
|
||
|
||
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
|
||
<div class="md-grid">
|
||
<ul class="md-tabs__list">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../.." class="md-tabs__link">
|
||
|
||
|
||
|
||
|
||
|
||
Home
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../../CHANGELOG/" class="md-tabs__link">
|
||
|
||
|
||
|
||
|
||
|
||
Changelog
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../../RESUME/" class="md-tabs__link">
|
||
|
||
|
||
|
||
|
||
|
||
Resume
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../../ct-inventory/" class="md-tabs__link">
|
||
|
||
|
||
|
||
|
||
|
||
CT inventory
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../../infra/proxmox-state/" class="md-tabs__link">
|
||
|
||
|
||
|
||
Infra
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../../services/homelab-architecture/" class="md-tabs__link">
|
||
|
||
|
||
|
||
Services
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../../security/data-leak-audit-comparison/" class="md-tabs__link">
|
||
|
||
|
||
|
||
Security & audits
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../stack-ideas/" class="md-tabs__link">
|
||
|
||
|
||
|
||
Ideas
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-tabs__item">
|
||
<a href="../../history/traefik-migration/" class="md-tabs__link">
|
||
|
||
|
||
|
||
History
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</div>
|
||
</nav>
|
||
|
||
|
||
|
||
<main class="md-main" data-md-component="main">
|
||
<div class="md-main__inner md-grid">
|
||
|
||
|
||
|
||
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
|
||
<div class="md-sidebar__scrollwrap">
|
||
<div class="md-sidebar__inner">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<nav class="md-nav md-nav--primary md-nav--lifted" aria-label="Navigation" data-md-level="0">
|
||
<label class="md-nav__title" for="__drawer">
|
||
<a href="../.." title="nuclide.systems docs" class="md-nav__button md-logo" aria-label="nuclide.systems docs" data-md-component="logo">
|
||
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||
|
||
</a>
|
||
nuclide.systems docs
|
||
</label>
|
||
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../.." class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Home
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../CHANGELOG/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Changelog
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../RESUME/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Resume
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../ct-inventory/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
CT inventory
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--nested">
|
||
|
||
|
||
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_5" >
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Infra
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
|
||
<label class="md-nav__title" for="__nav_5">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
|
||
|
||
Infra
|
||
|
||
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../infra/proxmox-state/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Proxmox state
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../infra/portmap/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Port map
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../infra/storage/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Storage
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../infra/volumes/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Volumes
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../infra/docker-networks/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Docker networks
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../infra/connection-hosts/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Connection hosts
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../infra/proxmox-memory-audit/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Memory audit
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--nested">
|
||
|
||
|
||
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_6" >
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Services
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
|
||
<label class="md-nav__title" for="__nav_6">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
|
||
|
||
Services
|
||
|
||
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/homelab-architecture/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Homelab architecture
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/dev-environment/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Dev environment (Coder + Gitea)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/mcp-gateway/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
MCP gateway
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/mcp-servers/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
MCP servers
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/pocket-id/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Pocket-ID (OIDC)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/backrest/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Backrest (backups)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/databases/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Databases
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/secrets-manager/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Secrets manager
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/comfyui/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
ComfyUI
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/zoraxy/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Zoraxy
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/adguard-dns/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
AdGuard DNS
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/cloud-gpu/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Cloud GPU
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/arcane/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Arcane
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/doc-ingestion/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Doc ingestion pipeline
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../services/llm-benchmark/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
LLM benchmark
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--nested">
|
||
|
||
|
||
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_7" >
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Security & audits
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
|
||
<label class="md-nav__title" for="__nav_7">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
|
||
|
||
Security & audits
|
||
|
||
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../security/data-leak-audit-comparison/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Comparison
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../security/data-leak-audit-2026-05-20-tr004-cloud-sandbox/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
2026-05-20 · cloud-sandbox breach
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../security/data-leak-audit-2026-05-21-tr004-artifacts/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
2026-05-21 · artifacts (clean)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../security/audit-claude-code-meta/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Self-audit (Claude Code)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../security/transcripts/audit-chat-2026-05-21/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Transcript (audit session)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--nested">
|
||
|
||
|
||
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_8" >
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Ideas
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
|
||
<label class="md-nav__title" for="__nav_8">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
|
||
|
||
Ideas
|
||
|
||
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../stack-ideas/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Stack ideas
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--nested">
|
||
|
||
|
||
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_9" >
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_9" id="__nav_9_label" tabindex="0">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
History
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_9_label" aria-expanded="false">
|
||
<label class="md-nav__title" for="__nav_9">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
|
||
|
||
History
|
||
|
||
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../history/traefik-migration/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Traefik (abandoned 2026-05-16)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../history/traefik-migration-docker-labels/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Traefik labels (abandoned)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../history/mcp-gateway-requirements/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
MCP gateway requirements (superseded)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../history/scrubbing-list-2026-05-17/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Scrubbing list (2026-05-17)
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../history/case-study/" class="md-nav__link">
|
||
|
||
|
||
|
||
<span class="md-ellipsis">
|
||
|
||
|
||
Case study
|
||
|
||
|
||
|
||
</span>
|
||
|
||
|
||
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
|
||
</li>
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
|
||
<div class="md-sidebar__scrollwrap">
|
||
<div class="md-sidebar__inner">
|
||
|
||
|
||
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__title" for="__toc">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Table of contents
|
||
</label>
|
||
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#problem" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
Problem
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#approaches" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
Approaches
|
||
|
||
</span>
|
||
</a>
|
||
|
||
<nav class="md-nav" aria-label="Approaches">
|
||
<ul class="md-nav__list">
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#a-session-cookie-reverse-engineering-not-recommended" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
A — Session Cookie Reverse-Engineering (not recommended)
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#b-claude-code-cli-bridge-recommended" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
B — Claude Code CLI Bridge (recommended)
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#c-official-api-budget-cap-stop-gap" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
C — Official API + Budget Cap (stop-gap)
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
</ul>
|
||
</nav>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#recommended-architecture-option-b" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
Recommended Architecture (Option B)
|
||
|
||
</span>
|
||
</a>
|
||
|
||
<nav class="md-nav" aria-label="Recommended Architecture (Option B)">
|
||
<ul class="md-nav__list">
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#claude-max-bridge-service" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
claude-max-bridge service
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#litellm-config-additions" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
LiteLLM config additions
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#rate-limit-handling" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
Rate limit handling
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
</ul>
|
||
</nav>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#volume-estimate" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
Volume estimate
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#risks" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
Risks
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#implementation-plan" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
Implementation plan
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#open-questions" class="md-nav__link">
|
||
<span class="md-ellipsis">
|
||
|
||
Open questions
|
||
|
||
</span>
|
||
</a>
|
||
|
||
</li>
|
||
|
||
</ul>
|
||
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="md-content" data-md-component="content">
|
||
|
||
<article class="md-content__inner md-typeset">
|
||
|
||
|
||
|
||
|
||
|
||
<h1 id="design-claude-max-subscription-litellm-gateway-bridge">Design: Claude Max Subscription → LiteLLM Gateway Bridge<a class="headerlink" href="#design-claude-max-subscription-litellm-gateway-bridge" title="Permanent link">¶</a></h1>
|
||
<p><strong>Status</strong>: Proposal — not implemented<br />
|
||
<strong>Context</strong>: LiteLLM at <code>https://ai.nuclide.systems</code> currently has no Anthropic models. Claude Max subscription (claude.ai) provides high-rate access to Sonnet 4.5/4.6 and Opus 4.7 but is decoupled from Anthropic API billing. This doc explores bridging the two.</p>
|
||
<h2 id="problem">Problem<a class="headerlink" href="#problem" title="Permanent link">¶</a></h2>
|
||
<p>Claude Max and the Anthropic API are separate products with separate billing:</p>
|
||
<table>
|
||
<thead>
|
||
<tr>
|
||
<th></th>
|
||
<th>Claude Max</th>
|
||
<th>Anthropic API</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr>
|
||
<td>Auth</td>
|
||
<td>OAuth / browser session</td>
|
||
<td>API key</td>
|
||
</tr>
|
||
<tr>
|
||
<td>Billing</td>
|
||
<td>Flat monthly subscription</td>
|
||
<td>Per-token</td>
|
||
</tr>
|
||
<tr>
|
||
<td>Rate limits</td>
|
||
<td>5h rolling windows, model-specific</td>
|
||
<td>Tier-based RPM/TPM</td>
|
||
</tr>
|
||
<tr>
|
||
<td>Access</td>
|
||
<td>claude.ai web + Claude Code CLI</td>
|
||
<td>Any HTTP client</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<p>The goal is to surface Max-subscription capacity through LiteLLM so that LobeHub, n8n, Coder workspaces, and other internal tools can call <code>claude-sonnet-4-6</code> at zero marginal cost and fall back to paid providers only when Max limits are hit.</p>
|
||
<h2 id="approaches">Approaches<a class="headerlink" href="#approaches" title="Permanent link">¶</a></h2>
|
||
<h3 id="a-session-cookie-reverse-engineering-not-recommended">A — Session Cookie Reverse-Engineering (not recommended)<a class="headerlink" href="#a-session-cookie-reverse-engineering-not-recommended" title="Permanent link">¶</a></h3>
|
||
<p>Several community projects (e.g. <code>claude-unofficial-api</code>) scrape the claude.ai WebSocket/HTTP protocol and expose an OpenAI-compatible endpoint. LiteLLM would point at this as a custom <code>openai/</code> provider.</p>
|
||
<p><strong>Pros</strong>: Exposes the full web model lineup; streaming works.<br />
|
||
<strong>Cons</strong>: Violates Anthropic ToS; breaks on any claude.ai front-end change; auth flow requires persisting browser cookies; no multimodal or tool-use parity guarantees.</p>
|
||
<p><strong>Verdict</strong>: Avoid. Fragile and non-compliant.</p>
|
||
<hr />
|
||
<h3 id="b-claude-code-cli-bridge-recommended">B — Claude Code CLI Bridge (recommended)<a class="headerlink" href="#b-claude-code-cli-bridge-recommended" title="Permanent link">¶</a></h3>
|
||
<p>Claude Code CLI (<code>claude</code>) is already installed on CT 104 and authenticated with the Max subscription via <code>~/.claude/</code>. It ships a <code>--print</code> / <code>--output-format stream-json</code> mode designed for non-interactive use, and Anthropic explicitly supports programmatic use of the CLI.</p>
|
||
<p>A small <strong><code>claude-max-bridge</code></strong> service wraps this CLI as an OpenAI-compatible HTTP endpoint. LiteLLM registers it as a custom <code>openai/</code> base URL. No ToS issues — this is the supported surface.</p>
|
||
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a>LobeHub / n8n / Coder / Claude Code
|
||
<a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a> │
|
||
<a id="__codelineno-0-3" name="__codelineno-0-3" href="#__codelineno-0-3"></a> ▼
|
||
<a id="__codelineno-0-4" name="__codelineno-0-4" href="#__codelineno-0-4"></a> LiteLLM Gateway (ai.nuclide.systems)
|
||
<a id="__codelineno-0-5" name="__codelineno-0-5" href="#__codelineno-0-5"></a> │ model: claude-sonnet-4-6 → openai/claude-sonnet-4-6
|
||
<a id="__codelineno-0-6" name="__codelineno-0-6" href="#__codelineno-0-6"></a> │ api_base: http://claude-max-bridge:8000
|
||
<a id="__codelineno-0-7" name="__codelineno-0-7" href="#__codelineno-0-7"></a> ▼
|
||
<a id="__codelineno-0-8" name="__codelineno-0-8" href="#__codelineno-0-8"></a> claude-max-bridge (new container, CT 104 ai-internal)
|
||
<a id="__codelineno-0-9" name="__codelineno-0-9" href="#__codelineno-0-9"></a> │ subprocess: claude --model ... --print --output-format stream-json
|
||
<a id="__codelineno-0-10" name="__codelineno-0-10" href="#__codelineno-0-10"></a> ▼
|
||
<a id="__codelineno-0-11" name="__codelineno-0-11" href="#__codelineno-0-11"></a> ~/.claude/ (Max subscription session)
|
||
<a id="__codelineno-0-12" name="__codelineno-0-12" href="#__codelineno-0-12"></a> │
|
||
<a id="__codelineno-0-13" name="__codelineno-0-13" href="#__codelineno-0-13"></a> ▼
|
||
<a id="__codelineno-0-14" name="__codelineno-0-14" href="#__codelineno-0-14"></a> Anthropic (claude.ai)
|
||
</code></pre></div>
|
||
<p><strong>Pros</strong>:
|
||
- Uses the officially supported programmatic interface
|
||
- Auth is already set up; no cookie management
|
||
- <code>claude</code> CLI handles retries, token limits, context window management
|
||
- Subprocess overhead is ~200–400 ms cold; warm invocations faster</p>
|
||
<p><strong>Cons</strong>:
|
||
- One subprocess per request — cannot multiplex a single session (unlike streaming HTTP)
|
||
- CLI is tied to the single authenticated user; no multi-user isolation
|
||
- Max rate limits apply per-account, same pool as interactive use
|
||
- Claude Code SDK (TypeScript) is cleaner but adds Node dependency</p>
|
||
<hr />
|
||
<h3 id="c-official-api-budget-cap-stop-gap">C — Official API + Budget Cap (stop-gap)<a class="headerlink" href="#c-official-api-budget-cap-stop-gap" title="Permanent link">¶</a></h3>
|
||
<p>Add Anthropic API key to LiteLLM with a hard budget cap (e.g. $20/month). Use it for Claude-specific features (tool use, long context) and let the existing free SAIA/Gemini fallback chain absorb general-purpose traffic.</p>
|
||
<p><strong>Pros</strong>: Zero implementation work; full API feature parity.<br />
|
||
<strong>Cons</strong>: Still costs money; no benefit from Max subscription.</p>
|
||
<p><strong>Verdict</strong>: Valid fallback if B proves too complex, or as a complement for tool-heavy workloads that need the official API surface.</p>
|
||
<hr />
|
||
<h2 id="recommended-architecture-option-b">Recommended Architecture (Option B)<a class="headerlink" href="#recommended-architecture-option-b" title="Permanent link">¶</a></h2>
|
||
<h3 id="claude-max-bridge-service">claude-max-bridge service<a class="headerlink" href="#claude-max-bridge-service" title="Permanent link">¶</a></h3>
|
||
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a>/opt/stacks/ai/claude-max-bridge/
|
||
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a> Dockerfile
|
||
<a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a> server.py # FastAPI, ~150 lines
|
||
<a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a> docker-compose.yml (or entry in ai/docker-compose.yml)
|
||
</code></pre></div>
|
||
<p><strong>Dockerfile</strong> — reuse the existing <code>claude</code> CLI install:
|
||
<div class="highlight"><pre><span></span><code><a id="__codelineno-2-1" name="__codelineno-2-1" href="#__codelineno-2-1"></a><span class="k">FROM</span><span class="w"> </span><span class="s">python:3.12-slim</span>
|
||
<a id="__codelineno-2-2" name="__codelineno-2-2" href="#__codelineno-2-2"></a><span class="k">RUN</span><span class="w"> </span>pip<span class="w"> </span>install<span class="w"> </span>fastapi<span class="w"> </span>uvicorn
|
||
<a id="__codelineno-2-3" name="__codelineno-2-3" href="#__codelineno-2-3"></a><span class="c"># Mount ~/.claude from host; claude binary from host PATH or copied in</span>
|
||
<a id="__codelineno-2-4" name="__codelineno-2-4" href="#__codelineno-2-4"></a><span class="k">COPY</span><span class="w"> </span>server.py<span class="w"> </span>/app/server.py
|
||
<a id="__codelineno-2-5" name="__codelineno-2-5" href="#__codelineno-2-5"></a><span class="k">CMD</span><span class="w"> </span><span class="p">[</span><span class="s2">"uvicorn"</span><span class="p">,</span><span class="w"> </span><span class="s2">"app.server:app"</span><span class="p">,</span><span class="w"> </span><span class="s2">"--host"</span><span class="p">,</span><span class="w"> </span><span class="s2">"0.0.0.0"</span><span class="p">,</span><span class="w"> </span><span class="s2">"--port"</span><span class="p">,</span><span class="w"> </span><span class="s2">"8000"</span><span class="p">]</span>
|
||
</code></pre></div></p>
|
||
<p><strong>server.py</strong> — OpenAI <code>/v1/chat/completions</code> shim:
|
||
<div class="highlight"><pre><span></span><code><a id="__codelineno-3-1" name="__codelineno-3-1" href="#__codelineno-3-1"></a><span class="c1"># POST /v1/chat/completions</span>
|
||
<a id="__codelineno-3-2" name="__codelineno-3-2" href="#__codelineno-3-2"></a><span class="c1"># Translates messages[] → claude --print --model ... --output-format stream-json</span>
|
||
<a id="__codelineno-3-3" name="__codelineno-3-3" href="#__codelineno-3-3"></a><span class="c1"># Streams NDJSON lines back as SSE (text/event-stream)</span>
|
||
<a id="__codelineno-3-4" name="__codelineno-3-4" href="#__codelineno-3-4"></a><span class="c1"># Maps finish_reason, usage tokens from CLI output headers</span>
|
||
</code></pre></div></p>
|
||
<p>Key translation notes:
|
||
- <code>messages</code> → write to a temp file, pass via <code>--input-file</code> (avoids shell quoting issues)
|
||
- <code>stream: true</code> → parse <code>stream-json</code> lines, emit <code>data: {...}</code> SSE chunks
|
||
- <code>stream: false</code> → buffer all chunks, return single response object
|
||
- <code>max_tokens</code>, <code>temperature</code>, <code>system</code> → map to <code>--max-tokens</code>, <code>--temperature</code>, <code>--system</code>
|
||
- Tool use: <strong>not supported</strong> in first iteration; return 501 for requests with <code>tools</code>
|
||
- Model name passthrough: <code>claude-sonnet-4-6</code> → <code>--model claude-sonnet-4-6</code></p>
|
||
<h3 id="litellm-config-additions">LiteLLM config additions<a class="headerlink" href="#litellm-config-additions" title="Permanent link">¶</a></h3>
|
||
<div class="highlight"><pre><span></span><code><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a><span class="nt">model_list</span><span class="p">:</span>
|
||
<a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model_name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">claude-sonnet-4-6</span>
|
||
<a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a><span class="w"> </span><span class="nt">litellm_params</span><span class="p">:</span>
|
||
<a id="__codelineno-4-4" name="__codelineno-4-4" href="#__codelineno-4-4"></a><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/claude-sonnet-4-6</span>
|
||
<a id="__codelineno-4-5" name="__codelineno-4-5" href="#__codelineno-4-5"></a><span class="w"> </span><span class="nt">api_base</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://claude-max-bridge:8000</span>
|
||
<a id="__codelineno-4-6" name="__codelineno-4-6" href="#__codelineno-4-6"></a><span class="w"> </span><span class="nt">api_key</span><span class="p">:</span><span class="w"> </span><span class="s">"dummy"</span><span class="w"> </span><span class="c1"># bridge ignores it; LiteLLM requires a value</span>
|
||
<a id="__codelineno-4-7" name="__codelineno-4-7" href="#__codelineno-4-7"></a><span class="w"> </span><span class="nt">stream_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">120</span>
|
||
<a id="__codelineno-4-8" name="__codelineno-4-8" href="#__codelineno-4-8"></a><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">120</span>
|
||
<a id="__codelineno-4-9" name="__codelineno-4-9" href="#__codelineno-4-9"></a>
|
||
<a id="__codelineno-4-10" name="__codelineno-4-10" href="#__codelineno-4-10"></a><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model_name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">claude-opus-4-7</span>
|
||
<a id="__codelineno-4-11" name="__codelineno-4-11" href="#__codelineno-4-11"></a><span class="w"> </span><span class="nt">litellm_params</span><span class="p">:</span>
|
||
<a id="__codelineno-4-12" name="__codelineno-4-12" href="#__codelineno-4-12"></a><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/claude-opus-4-7</span>
|
||
<a id="__codelineno-4-13" name="__codelineno-4-13" href="#__codelineno-4-13"></a><span class="w"> </span><span class="nt">api_base</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://claude-max-bridge:8000</span>
|
||
<a id="__codelineno-4-14" name="__codelineno-4-14" href="#__codelineno-4-14"></a><span class="w"> </span><span class="nt">api_key</span><span class="p">:</span><span class="w"> </span><span class="s">"dummy"</span>
|
||
<a id="__codelineno-4-15" name="__codelineno-4-15" href="#__codelineno-4-15"></a><span class="w"> </span><span class="nt">stream_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">180</span>
|
||
<a id="__codelineno-4-16" name="__codelineno-4-16" href="#__codelineno-4-16"></a><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">180</span>
|
||
<a id="__codelineno-4-17" name="__codelineno-4-17" href="#__codelineno-4-17"></a>
|
||
<a id="__codelineno-4-18" name="__codelineno-4-18" href="#__codelineno-4-18"></a><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model_name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">claude-haiku-4-5</span>
|
||
<a id="__codelineno-4-19" name="__codelineno-4-19" href="#__codelineno-4-19"></a><span class="w"> </span><span class="nt">litellm_params</span><span class="p">:</span>
|
||
<a id="__codelineno-4-20" name="__codelineno-4-20" href="#__codelineno-4-20"></a><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/claude-haiku-4-5-20251001</span>
|
||
<a id="__codelineno-4-21" name="__codelineno-4-21" href="#__codelineno-4-21"></a><span class="w"> </span><span class="nt">api_base</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://claude-max-bridge:8000</span>
|
||
<a id="__codelineno-4-22" name="__codelineno-4-22" href="#__codelineno-4-22"></a><span class="w"> </span><span class="nt">api_key</span><span class="p">:</span><span class="w"> </span><span class="s">"dummy"</span>
|
||
<a id="__codelineno-4-23" name="__codelineno-4-23" href="#__codelineno-4-23"></a><span class="w"> </span><span class="nt">stream_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">60</span>
|
||
<a id="__codelineno-4-24" name="__codelineno-4-24" href="#__codelineno-4-24"></a><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">60</span>
|
||
</code></pre></div>
|
||
<p>Add to <code>router_settings.fallbacks</code> — Max hits rate limit → fall to SAIA:
|
||
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a><span class="nt">fallbacks</span><span class="p">:</span>
|
||
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">claude-sonnet-4-6</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">qwen3.5-397b-a17b</span><span class="p p-Indicator">]</span>
|
||
<a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">claude-opus-4-7</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">qwen3.5-397b-a17b</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">mistral-large-latest</span><span class="p p-Indicator">]</span>
|
||
<a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">claude-haiku-4-5</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">qwen3.5-122b-a10b</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">cerebras-llama-3.1-8b</span><span class="p p-Indicator">]</span>
|
||
</code></pre></div></p>
|
||
<h3 id="rate-limit-handling">Rate limit handling<a class="headerlink" href="#rate-limit-handling" title="Permanent link">¶</a></h3>
|
||
<p>The bridge should detect the CLI's rate-limit exit code / stderr message and return HTTP 429. LiteLLM's router will then trigger the fallback chain. No custom logic needed in LiteLLM itself.</p>
|
||
<p>Max limits as of 2026 (approximate, vary by plan tier):
|
||
- Sonnet 4.6: ~50 messages / 5-hour window at Pro; higher at Max
|
||
- Opus 4.7: ~10–20 messages / 5-hour window
|
||
- Haiku 4.5: effectively unlimited under Max</p>
|
||
<h2 id="volume-estimate">Volume estimate<a class="headerlink" href="#volume-estimate" title="Permanent link">¶</a></h2>
|
||
<p>Typical homelab workloads (LobeHub chat, n8n automations, Coder coding assist) generate maybe 200–500 completions/day. Max's 5-hour windows reset 4–5× daily, so the practical limit is not usually hit unless Opus is used heavily.</p>
|
||
<h2 id="risks">Risks<a class="headerlink" href="#risks" title="Permanent link">¶</a></h2>
|
||
<table>
|
||
<thead>
|
||
<tr>
|
||
<th>Risk</th>
|
||
<th>Mitigation</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr>
|
||
<td>CLI API changes between Claude Code releases</td>
|
||
<td>Pin the <code>claude</code> binary version; watch for breaking changes in release notes</td>
|
||
</tr>
|
||
<tr>
|
||
<td>Max rate limit shared with interactive use</td>
|
||
<td>Monitor via <code>claude usage</code>; bridge adds <code>X-Max-Usage</code> header from CLI output</td>
|
||
</tr>
|
||
<tr>
|
||
<td>Auth session expiry</td>
|
||
<td>Bridge returns 401 on auth failure; detect and alert via Gotify</td>
|
||
</tr>
|
||
<tr>
|
||
<td>Subprocess latency (cold start)</td>
|
||
<td>Keep a warm subprocess pool (1–2 persistent processes) using <code>--interactive</code> + message passing, or accept the 200–400 ms overhead</td>
|
||
</tr>
|
||
<tr>
|
||
<td>No tool use support</td>
|
||
<td>Fallback chain routes tool-use requests to API providers (Gemini, Mistral)</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<h2 id="implementation-plan">Implementation plan<a class="headerlink" href="#implementation-plan" title="Permanent link">¶</a></h2>
|
||
<ol>
|
||
<li>Write <code>server.py</code> shim (~150 lines) + Dockerfile</li>
|
||
<li>Build image on CT 104, add to <code>ai/docker-compose.yml</code></li>
|
||
<li>Bind-mount <code>~/.claude</code> read-only into the container</li>
|
||
<li>Add model entries to <code>litellm-config/config.yaml</code></li>
|
||
<li>Test streaming via <code>curl</code> against the bridge directly</li>
|
||
<li>Test end-to-end via LiteLLM → LobeHub</li>
|
||
<li>Watch <code>docker logs claude-max-bridge</code> for rate-limit / auth errors for 48h</li>
|
||
</ol>
|
||
<h2 id="open-questions">Open questions<a class="headerlink" href="#open-questions" title="Permanent link">¶</a></h2>
|
||
<ul>
|
||
<li>Does <code>claude --print</code> support all message roles (<code>system</code>, <code>user</code>, <code>assistant</code> turns)? Needs verification with multi-turn conversation format.</li>
|
||
<li>Should the bridge be on CT 104 (access to <code>~/.claude</code>) or CT 109 ops (remote docker socket to CT 104)? CT 104 is simpler for v1.</li>
|
||
<li>Is there an official Claude Code SDK for Python? (TypeScript SDK exists at <code>@anthropic-ai/claude-code</code>; Python wrapper may be cleaner than shelling out.)</li>
|
||
</ul>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
</article>
|
||
</div>
|
||
|
||
|
||
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
|
||
</div>
|
||
|
||
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
|
||
Back to top
|
||
</button>
|
||
|
||
</main>
|
||
|
||
<footer class="md-footer">
|
||
|
||
<div class="md-footer-meta md-typeset">
|
||
<div class="md-footer-meta__inner md-grid">
|
||
<div class="md-copyright">
|
||
|
||
|
||
Made with
|
||
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
|
||
Material for MkDocs
|
||
</a>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
</div>
|
||
</footer>
|
||
|
||
</div>
|
||
<div class="md-dialog" data-md-component="dialog">
|
||
<div class="md-dialog__inner md-typeset"></div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
|
||
<script id="__config" type="application/json">{"annotate": null, "base": "../..", "features": ["navigation.tabs", "navigation.sections", "navigation.expand", "navigation.top", "search.highlight", "search.suggest", "content.code.copy"], "search": "../../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||
|
||
|
||
<script src="../../assets/javascripts/bundle.79ae519e.min.js"></script>
|
||
|
||
|
||
</body>
|
||
</html> |