plano/resources/configuration_reference.html

432 lines
63 KiB
HTML
Raw Normal View History

<!DOCTYPE html>
<html :class="{ 'dark' : darkMode === true }" data-content_root="../" lang="en" x-data="{ darkMode: $persist(window.matchMedia('(prefers-color-scheme: dark)').matches), activeSection: ''}">
<head>
<script>
(function () {
// Set initial color scheme
if ((localStorage.getItem("_x_darkMode") === "true") || (window.matchMedia("(prefers-color-scheme: dark)").matches)) {
document.documentElement.classList.add("dark");
}
// Watch for media preference changes
window.matchMedia("(prefers-color-scheme: dark)").addEventListener("change", (event) => {
localStorage.setItem("_x_darkMode", event.matches);
document.documentElement.classList.toggle("dark", event.matches);
});
})();
</script>
<meta content="width=device-width, initial-scale=1.0" name="viewport"/>
<meta charset="utf-8"/>
<meta content="#ffffff" media="(prefers-color-scheme: light)" name="theme-color"/>
<meta content="#030711" media="(prefers-color-scheme: dark)" name="theme-color"/>
<meta content="width=device-width, initial-scale=1" name="viewport"/>
<title>Configuration Reference | Plano Docs v0.4.20</title>
<meta content="Configuration Reference | Plano Docs v0.4.20" property="og:title"/>
<meta content="Configuration Reference | Plano Docs v0.4.20" name="twitter:title"/>
<link href="../_static/pygments.css?v=73db4dac" rel="stylesheet" type="text/css"/>
<link href="../_static/theme.css?v=979577e3" rel="stylesheet" type="text/css"/>
<link href="../_static/sphinx-design.min.css?v=95c83b7e" rel="stylesheet" type="text/css"/>
<link href="../_static/css/custom.css?v=2929376a" rel="stylesheet" type="text/css"/>
<link href="../_static/awesome-sphinx-design.css?v=b1d4564d" rel="stylesheet" type="text/css"/>
<link href="./docs/resources/configuration_reference.html" rel="canonical"/>
<link href="../_static/favicon.ico" rel="icon"/>
<link href="../search.html" rel="search" title="Search"/>
<link href="cli_reference.html" rel="next" title="CLI Reference"/>
<link href="deployment.html" rel="prev" title="Deployment"/>
</head>
<body :class="{ 'overflow-hidden': showSidebar }" class="min-h-screen font-sans antialiased bg-background text-foreground" x-data="{ showSidebar: false, showScrollTop: false }">
<div @click.self="showSidebar = false" class="fixed inset-0 z-50 overflow-hidden bg-background/80 backdrop-blur-sm md:hidden" x-cloak="" x-show="showSidebar"></div><div class="relative flex flex-col min-h-screen" id="page"><a class="absolute top-0 left-0 z-[100] block bg-background p-4 text-xl transition -translate-x-full opacity-0 focus:translate-x-0 focus:opacity-100" href="#content">
Skip to content
</a><header class="sticky top-0 z-40 w-full border-b shadow-xs border-border bg-background/90 backdrop-blur"><div class="container flex items-center h-14">
<div class="hidden mr-4 md:flex">
<a class="flex items-center mr-6" href="../index.html">
<img alt="Logo" class="mr-2 dark:invert" height="24" src="../_static/favicon.ico" width="24"/><span class="hidden font-bold sm:inline-block text-clip whitespace-nowrap">Plano Docs v0.4.20</span>
</a></div><button @click="showSidebar = true" class="inline-flex items-center justify-center h-10 px-0 py-2 mr-2 text-base font-medium transition-colors rounded-md hover:text-accent-foreground hover:bg-transparent md:hidden" type="button">
<svg aria-hidden="true" fill="currentColor" height="24" viewbox="0 96 960 960" width="24" xmlns="http://www.w3.org/2000/svg">
<path d="M152.587 825.087q-19.152 0-32.326-13.174t-13.174-32.326q0-19.152 13.174-32.326t32.326-13.174h440q19.152 0 32.326 13.174t13.174 32.326q0 19.152-13.174 32.326t-32.326 13.174h-440Zm0-203.587q-19.152 0-32.326-13.174T107.087 576q0-19.152 13.174-32.326t32.326-13.174h320q19.152 0 32.326 13.174T518.087 576q0 19.152-13.174 32.326T472.587 621.5h-320Zm0-203.587q-19.152 0-32.326-13.174t-13.174-32.326q0-19.152 13.174-32.326t32.326-13.174h440q19.152 0 32.326 13.174t13.174 32.326q0 19.152-13.174 32.326t-32.326 13.174h-440ZM708.913 576l112.174 112.174q12.674 12.674 12.674 31.826t-12.674 31.826Q808.413 764.5 789.261 764.5t-31.826-12.674l-144-144Q600 594.391 600 576t13.435-31.826l144-144q12.674-12.674 31.826-12.674t31.826 12.674q12.674 12.674 12.674 31.826t-12.674 31.826L708.913 576Z"></path>
</svg>
<span class="sr-only">Toggle navigation menu</span>
</button>
<div class="flex items-center justify-between flex-1 gap-2 sm:gap-4 md:justify-end">
<div class="flex-1 w-full md:w-auto md:flex-none"><form @keydown.k.window.meta="$refs.search.focus()" action="../search.html" class="relative flex items-center group" id="searchbox" method="get">
<input aria-label="Search the docs" class="inline-flex items-center font-medium transition-colors bg-transparent focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 ring-offset-background border border-input hover:bg-accent focus:bg-accent hover:text-accent-foreground focus:text-accent-foreground hover:placeholder-accent-foreground py-2 px-4 relative h-9 w-full justify-start rounded-[0.5rem] text-sm text-muted-foreground sm:pr-12 md:w-40 lg:w-64" id="search-input" name="q" placeholder="Search ..." type="search" x-ref="search"/>
<kbd class="pointer-events-none absolute right-1.5 top-2 hidden h-5 select-none text-muted-foreground items-center gap-1 rounded border border-border bg-muted px-1.5 font-mono text-[10px] font-medium opacity-100 sm:flex group-hover:bg-accent group-hover:text-accent-foreground">
<span class="text-xs"></span>
K
</kbd>
</form>
</div>
<nav class="flex items-center gap-1">
<a href="https://github.com/katanemo/plano" rel="noopener nofollow" title="Visit repository on GitHub">
<div class="inline-flex items-center justify-center px-0 text-sm font-medium transition-colors rounded-md hover:bg-accent hover:text-accent-foreground h-9 w-9">
<svg fill="currentColor" height="26px" style="margin-top:-2px;display:inline" viewbox="0 0 45 44" xmlns="http://www.w3.org/2000/svg"><path clip-rule="evenodd" d="M22.477.927C10.485.927.76 10.65.76 22.647c0 9.596 6.223 17.736 14.853 20.608 1.087.2 1.483-.47 1.483-1.047 0-.516-.019-1.881-.03-3.693-6.04 1.312-7.315-2.912-7.315-2.912-.988-2.51-2.412-3.178-2.412-3.178-1.972-1.346.149-1.32.149-1.32 2.18.154 3.327 2.24 3.327 2.24 1.937 3.318 5.084 2.36 6.321 1.803.197-1.403.759-2.36 1.379-2.903-4.823-.548-9.894-2.412-9.894-10.734 0-2.37.847-4.31 2.236-5.828-.224-.55-.969-2.759.214-5.748 0 0 1.822-.584 5.972 2.226 1.732-.482 3.59-.722 5.437-.732 1.845.01 3.703.25 5.437.732 4.147-2.81 5.967-2.226 5.967-2.226 1.185 2.99.44 5.198.217 5.748 1.392 1.517 2.232 3.457 2.232 5.828 0 8.344-5.078 10.18-9.916 10.717.779.67 1.474 1.996 1.474 4.021 0 2.904-.027 5.247-.027 5.96 0 .58.392 1.256 1.493 1.044C37.981 40.375 44.2 32.24 44.2 22.647c0-11.996-9.726-21.72-21.722-21.72" fill="currentColor" fill-rule="evenodd"></path></svg>
</div>
</a>
<button @click="darkMode = !darkMode" class="relative inline-flex items-center justify-center px-0 text-sm font-medium transition-colors rounded-md hover:bg-accent hover:text-accent-foreground h-9 w-9" title="Toggle color scheme" type="button">
<svg class="absolute transition-all scale-100 rotate-0 dark:-rotate-90 dark:scale-0" fill="currentColor" height="16" viewbox="0 96 960 960" width="16" xmlns="http://www.w3.org/2000/svg">
<path d="M480 685q45.456 0 77.228-31.772Q589 621.456 589 576q0-45.456-31.772-77.228Q525.456 467 480 467q-45.456 0-77.228 31.772Q371 530.544 371 576q0 45.456 31.772 77.228Q434.544 685 480 685Zm0 91q-83 0-141.5-58.5T280 576q0-83 58.5-141.5T480 376q83 0 141.5 58.5T680 576q0 83-58.5 141.5T480 776ZM80 621.5q-19.152 0-32.326-13.174T34.5 576q0-19.152 13.174-32.326T80 530.5h80q19.152 0 32.326 13.174T205.5 576q0 19.152-13.174 32.326T160 621.5H80Zm720 0q-19.152 0-32.326-13.174T754.5 576q0-19.152 13.174-32.326T800 530.5h80q19.152 0 32.326 13.174T925.5 576q0 19.152-13.174 32.326T880 621.5h-80Zm-320-320q-19.152 0-32.326-13.174T434.5 256v-80q0-19.152 13.174-32.326T480 130.5q19.152 0 32.326 13.174T525.5 176v80q0 19.152-13.174 32.326T480 301.5Zm0 720q-19.152 0-32.326-13.17Q434.5 995.152 434.5 976v-80q0-19.152 13.174-32.326T480 850.5q19.152 0 32.326 13.174T525.5 896v80q0 19.152-13.174 32.33-13.174 13.17-32.326 13.17ZM222.174 382.065l-43-42Q165.5 327.391 166 308.239t13.174-33.065q13.435-13.674 32.587-13.674t32.065 13.674l42.239 43q12.674 13.435 12.555 31.706-.12 18.272-12.555 31.946-12.674 13.674-31.445 13.413-18.772-.261-32.446-13.174Zm494 494.761-42.239-43q-12.674-13.435-12.674-32.087t12.674-31.565Q686.609 756.5 705.38 757q18.772.5 32.446 13.174l43 41.761Q794.5 824.609 794 843.761t-13.174 33.065Q767.391 890.5 748.239 890.5t-32.065-13.674Zm-42-494.761Q660.5 369.391 661 350.62q.5-18.772 13.174-32.446l41.761-43Q728.609 261.5 747.761 262t33.065 13.174q13.674 13.435 13.674 32.587t-13.674 32.065l-43 42.239q-13.435 12.674-31.706 12.555-18.272-.12-31.946-12.555Zm-495 494.761Q165.5 863.391 165.5 844.239t13.674-32.065l43-42.239q13.435-12.674 32.087-12.674t31.565 12.674Q299.5 782.609 299 801.38q-.5 18.772-13.174 32.446l-41.761 43Q231.391 890.5 212.239 890t-33.065-13.174ZM480 576Z"></path>
</svg>
<svg class="absolute transition-all scale-0 rotate-90 dark:rotate-0 dark:scale-100" fill="currentColor" height="16" viewbox="0 96 960 960" width="16" xmlns="http://www.w3.org/2000/svg">
<path d="M480 936q-151 0-255.5-104.5T120 576q0-138 90-239.5T440 218q25-3 39 18t-1 44q-17 26-25.5 55t-8.5 61q0 90 63 153t153 63q31 0 61.5-9t54.5-25q21-14 43-1.5t19 39.5q-14 138-117.5 229T480 936Zm0-80q88 0 158-48.5T740 681q-20 5-40 8t-40 3q-123 0-209.5-86.5T364 396q0-20 3-40t8-40q-78 32-126.5 102T200 576q0 116 82 198t198 82Zm-10-270Z"></path>
</svg>
</button>
</nav>
</div>
</div>
</header>
<div class="flex-1"><div class="container md:grid md:grid-cols-[220px_minmax(0,1fr)] md:gap-6 lg:grid-cols-[240px_minmax(0,1fr)] lg:gap-10"><aside :aria-hidden="!showSidebar" :class="{ 'translate-x-0': showSidebar }" class="fixed inset-y-0 left-0 md:top-14 z-50 md:z-30 bg-background md:bg-transparent transition-all duration-100 -translate-x-full md:translate-x-0 ml-0 p-6 md:p-0 md:-ml-2 md:h-[calc(100vh-3.5rem)] w-5/6 md:w-full overflow-y-auto border-r border-border md:sticky" id="left-sidebar">
<a class="justify-start text-sm md:!hidden bg-background" href="../index.html">
<img alt="Logo" class="mr-2 dark:invert" height="16" src="../_static/favicon.ico" width="16"/><span class="font-bold text-clip whitespace-nowrap">Plano Docs v0.4.20</span>
</a>
<div class="relative overflow-hidden md:overflow-auto my-4 md:my-0">
<div class="overflow-y-auto h-full w-full relative pr-6">
<script async="" src="https://www.googletagmanager.com/gtag/js?id=G-EH2VW19FXE"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-EH2VW19FXE');
</script>
<nav class="table w-full min-w-full my-6 lg:my-8">
<p class="caption" role="heading"><span class="caption-text">Get Started</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../get_started/overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../get_started/intro_to_plano.html">Intro to Plano</a></li>
<li class="toctree-l1"><a class="reference internal" href="../get_started/quickstart.html">Quickstart</a></li>
<li class="toctree-l1"><a class="reference internal" href="../get_started/quickstart.html#next-steps">Next Steps</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Concepts</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../concepts/listeners.html">Listeners</a></li>
<li class="toctree-l1"><a class="reference internal" href="../concepts/agents.html">Agents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../concepts/filter_chain.html">Filter Chains</a></li>
<li class="toctree-l1" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="../concepts/llm_providers/llm_providers.html">Model (LLM) Providers<button @click.prevent.stop="expanded = !expanded" type="button" x-cloak=""><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul x-cloak="" x-show="expanded">
<li class="toctree-l2"><a class="reference internal" href="../concepts/llm_providers/supported_providers.html">Supported Providers &amp; Configuration</a></li>
<li class="toctree-l2"><a class="reference internal" href="../concepts/llm_providers/client_libraries.html">Client Libraries</a></li>
<li class="toctree-l2"><a class="reference internal" href="../concepts/llm_providers/model_aliases.html">Model Aliases</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../concepts/prompt_target.html">Prompt Target</a></li>
<li class="toctree-l1"><a class="reference internal" href="../concepts/signals.html">Signals™</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Guides</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../guides/orchestration.html">Orchestration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../guides/llm_router.html">LLM Routing</a></li>
<li class="toctree-l1"><a class="reference internal" href="../guides/function_calling.html">Function Calling</a></li>
<li class="toctree-l1" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="../guides/observability/observability.html">Observability<button @click.prevent.stop="expanded = !expanded" type="button" x-cloak=""><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul x-cloak="" x-show="expanded">
<li class="toctree-l2"><a class="reference internal" href="../guides/observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../guides/observability/monitoring.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../guides/observability/access_logging.html">Access Logging</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../guides/prompt_guard.html">Guardrails</a></li>
<li class="toctree-l1"><a class="reference internal" href="../guides/state.html">Conversational State</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul class="current">
<li class="toctree-l1" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="tech_overview/tech_overview.html">Tech Overview<button @click.prevent.stop="expanded = !expanded" type="button" x-cloak=""><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul x-cloak="" x-show="expanded">
<li class="toctree-l2"><a class="reference internal" href="tech_overview/request_lifecycle.html">Request Lifecycle</a></li>
<li class="toctree-l2"><a class="reference internal" href="tech_overview/model_serving.html">Bright Staff</a></li>
<li class="toctree-l2"><a class="reference internal" href="tech_overview/threading_model.html">Threading Model</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="deployment.html">Deployment</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Configuration Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="cli_reference.html">CLI Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="llms_txt.html">llms.txt</a></li>
</ul>
</nav>
</div>
</div>
<button @click="showSidebar = false" class="absolute md:hidden right-4 top-4 rounded-sm opacity-70 transition-opacity hover:opacity-100" type="button">
<svg class="h-4 w-4" fill="currentColor" height="24" stroke="none" viewbox="0 96 960 960" width="24" xmlns="http://www.w3.org/2000/svg">
<path d="M480 632 284 828q-11 11-28 11t-28-11q-11-11-11-28t11-28l196-196-196-196q-11-11-11-28t11-28q11-11 28-11t28 11l196 196 196-196q11-11 28-11t28 11q11 11 11 28t-11 28L536 576l196 196q11 11 11 28t-11 28q-11 11-28 11t-28-11L480 632Z"></path>
</svg>
</button>
</aside>
<main class="relative py-6 lg:gap-10 lg:py-8 xl:grid xl:grid-cols-[1fr_300px]">
<div class="w-full min-w-0 mx-auto">
<nav aria-label="breadcrumbs" class="flex items-center mb-4 space-x-1 text-sm text-muted-foreground">
<a class="overflow-hidden text-ellipsis whitespace-nowrap hover:text-foreground" href="../index.html">
<span class="hidden md:inline">Plano Docs v0.4.20</span>
<svg aria-label="Home" class="md:hidden" fill="currentColor" height="18" stroke="none" viewbox="0 96 960 960" width="18" xmlns="http://www.w3.org/2000/svg">
<path d="M240 856h120V616h240v240h120V496L480 316 240 496v360Zm-80 80V456l320-240 320 240v480H520V696h-80v240H160Zm320-350Z"></path>
</svg>
</a>
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Configuration Reference</span>
</nav>
<div id="content" role="main">
<section id="configuration-reference">
<span id="id1"></span><h1>Configuration Reference<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#configuration-reference"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
<p>The following is a complete reference of the <code class="docutils literal notranslate"><span class="pre">plano_config.yml</span></code> that controls the behavior of a single instance of
the Plano gateway. This where you enable capabilities like routing to upstream LLm providers, defining prompt_targets
where prompts get routed to, apply guardrails, and enable critical agent observability features.</p>
<div class="literal-block-wrapper docutils container" id="id2">
<div class="code-block-caption"><span class="caption-text"><a class="reference download internal" download="" href="../_downloads/c86f9e8fb1f2994b1ba4a0b98481410e/plano_config_full_reference.yaml"><code class="xref download docutils literal notranslate"><span class="pre">Plano</span> <span class="pre">Configuration</span> <span class="pre">-</span> <span class="pre">Full</span> <span class="pre">Reference</span></code></a></span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#id2"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="c1"># Plano Gateway configuration version</span>
</span><span id="line-2"><span class="linenos"> 2</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.3.0</span>
</span><span id="line-3"><span class="linenos"> 3</span>
</span><span id="line-4"><span class="linenos"> 4</span><span class="c1"># External HTTP agents - API type is controlled by request path (/v1/responses, /v1/messages, /v1/chat/completions)</span>
</span><span id="line-5"><span class="linenos"> 5</span><span class="nt">agents</span><span class="p">:</span>
</span><span id="line-6"><span class="linenos"> 6</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">weather_agent</span><span class="w"> </span><span class="c1"># Example agent for weather</span>
</span><span id="line-7"><span class="linenos"> 7</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://localhost:10510</span>
</span><span id="line-8"><span class="linenos"> 8</span>
</span><span id="line-9"><span class="linenos"> 9</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">flight_agent</span><span class="w"> </span><span class="c1"># Example agent for flights</span>
</span><span id="line-10"><span class="linenos"> 10</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://localhost:10520</span>
</span><span id="line-11"><span class="linenos"> 11</span>
</span><span id="line-12"><span class="linenos"> 12</span><span class="c1"># MCP filters applied to requests/responses (e.g., input validation, query rewriting)</span>
</span><span id="line-13"><span class="linenos"> 13</span><span class="nt">filters</span><span class="p">:</span>
</span><span id="line-14"><span class="linenos"> 14</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span><span class="w"> </span><span class="c1"># Example filter for input validation</span>
</span><span id="line-15"><span class="linenos"> 15</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://localhost:10500</span>
</span><span id="line-16"><span class="linenos"> 16</span><span class="w"> </span><span class="c1"># type: mcp (default)</span>
</span><span id="line-17"><span class="linenos"> 17</span><span class="w"> </span><span class="c1"># transport: streamable-http (default)</span>
</span><span id="line-18"><span class="linenos"> 18</span><span class="w"> </span><span class="c1"># tool: input_guards (default - same as filter id)</span>
</span><span id="line-19"><span class="linenos"> 19</span>
</span><span id="line-20"><span class="linenos"> 20</span><span class="c1"># LLM provider configurations with API keys and model routing</span>
</span><span id="line-21"><span class="linenos"> 21</span><span class="nt">model_providers</span><span class="p">:</span>
</span><span id="line-22"><span class="linenos"> 22</span><span class="w"> </span><span class="p p-Indicator">-</span><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/gpt-4o</span>
</span><span id="line-23"><span class="linenos"> 23</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
</span><span id="line-24"><span class="linenos"> 24</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-25"><span class="linenos"> 25</span>
</span><span id="line-26"><span class="linenos"> 26</span><span class="w"> </span><span class="p p-Indicator">-</span><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/gpt-4o-mini</span>
</span><span id="line-27"><span class="linenos"> 27</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
</span><span id="line-28"><span class="linenos"> 28</span>
</span><span id="line-29"><span class="linenos"> 29</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-sonnet-4-0</span>
</span><span id="line-30"><span class="linenos"> 30</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
</span><span id="line-31"><span class="linenos"> 31</span>
</span><span id="line-32"><span class="linenos"> 32</span><span class="w"> </span><span class="p p-Indicator">-</span><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">mistral/ministral-3b-latest</span>
</span><span id="line-33"><span class="linenos"> 33</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$MISTRAL_API_KEY</span>
</span><span id="line-34"><span class="linenos"> 34</span>
</span><span id="line-35"><span class="linenos"> 35</span><span class="w"> </span><span class="c1"># routing_preferences: tags a model with named capabilities so Plano's LLM router</span>
</span><span id="line-36"><span class="linenos"> 36</span><span class="w"> </span><span class="c1"># can select the best model for each request based on intent. Requires the</span>
</span><span id="line-37"><span class="linenos"> 37</span><span class="w"> </span><span class="c1"># Plano-Orchestrator model (or equivalent) to be configured in overrides.llm_routing_model.</span>
</span><span id="line-38"><span class="linenos"> 38</span><span class="w"> </span><span class="c1"># Each preference has a name (short label) and a description (used for intent matching).</span>
</span><span id="line-39"><span class="linenos"> 39</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq/llama-3.3-70b-versatile</span>
</span><span id="line-40"><span class="linenos"> 40</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$GROQ_API_KEY</span>
</span><span id="line-41"><span class="linenos"> 41</span><span class="w"> </span><span class="nt">routing_preferences</span><span class="p">:</span>
</span><span id="line-42"><span class="linenos"> 42</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">code generation</span>
</span><span id="line-43"><span class="linenos"> 43</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">generating new code snippets, functions, or boilerplate based on user prompts or requirements</span>
</span><span id="line-44"><span class="linenos"> 44</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">code review</span>
</span><span id="line-45"><span class="linenos"> 45</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reviewing, analyzing, and suggesting improvements to existing code</span>
</span><span id="line-46"><span class="linenos"> 46</span>
</span><span id="line-47"><span class="linenos"> 47</span><span class="w"> </span><span class="c1"># passthrough_auth: forwards the client's Authorization header upstream instead of</span>
</span><span id="line-48"><span class="linenos"> 48</span><span class="w"> </span><span class="c1"># using the configured access_key. Useful for LiteLLM or similar proxy setups.</span>
</span><span id="line-49"><span class="linenos"> 49</span><span class="w"> </span><span class="p p-Indicator">-</span><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/gpt-4o-litellm</span>
</span><span id="line-50"><span class="linenos"> 50</span><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://litellm.example.com</span>
</span><span id="line-51"><span class="linenos"> 51</span><span class="w"> </span><span class="nt">passthrough_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-52"><span class="linenos"> 52</span>
</span><span id="line-53"><span class="linenos"> 53</span><span class="w"> </span><span class="c1"># Custom/self-hosted endpoint with explicit http_host override</span>
</span><span id="line-54"><span class="linenos"> 54</span><span class="w"> </span><span class="p p-Indicator">-</span><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/llama-3.3-70b</span>
</span><span id="line-55"><span class="linenos"> 55</span><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://api.custom-provider.com</span>
</span><span id="line-56"><span class="linenos"> 56</span><span class="w"> </span><span class="nt">http_host</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.custom-provider.com</span>
</span><span id="line-57"><span class="linenos"> 57</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$CUSTOM_API_KEY</span>
</span><span id="line-58"><span class="linenos"> 58</span>
</span><span id="line-59"><span class="linenos"> 59</span><span class="c1"># Model aliases - use friendly names instead of full provider model names</span>
</span><span id="line-60"><span class="linenos"> 60</span><span class="nt">model_aliases</span><span class="p">:</span>
</span><span id="line-61"><span class="linenos"> 61</span><span class="w"> </span><span class="nt">fast-llm</span><span class="p">:</span>
</span><span id="line-62"><span class="linenos"> 62</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o-mini</span>
</span><span id="line-63"><span class="linenos"> 63</span>
</span><span id="line-64"><span class="linenos"> 64</span><span class="w"> </span><span class="nt">smart-llm</span><span class="p">:</span>
</span><span id="line-65"><span class="linenos"> 65</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
</span><span id="line-66"><span class="linenos"> 66</span>
</span><span id="line-67"><span class="linenos"> 67</span><span class="c1"># HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access</span>
</span><span id="line-68"><span class="linenos"> 68</span><span class="nt">listeners</span><span class="p">:</span>
</span><span id="line-69"><span class="linenos"> 69</span><span class="w"> </span><span class="c1"># Agent listener for routing requests to multiple agents</span>
</span><span id="line-70"><span class="linenos"> 70</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">agent</span>
</span><span id="line-71"><span class="linenos"> 71</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">travel_booking_service</span>
</span><span id="line-72"><span class="linenos"> 72</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8001</span>
</span><span id="line-73"><span class="linenos"> 73</span><span class="w"> </span><span class="nt">router</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">plano_orchestrator_v1</span>
</span><span id="line-74"><span class="linenos"> 74</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-75"><span class="linenos"> 75</span><span class="w"> </span><span class="nt">agents</span><span class="p">:</span>
</span><span id="line-76"><span class="linenos"> 76</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">rag_agent</span>
</span><span id="line-77"><span class="linenos"> 77</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">virtual assistant for retrieval augmented generation tasks</span>
</span><span id="line-78"><span class="linenos"> 78</span><span class="w"> </span><span class="nt">input_filters</span><span class="p">:</span>
</span><span id="line-79"><span class="linenos"> 79</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-80"><span class="linenos"> 80</span>
</span><span id="line-81"><span class="linenos"> 81</span><span class="w"> </span><span class="c1"># Model listener for direct LLM access</span>
</span><span id="line-82"><span class="linenos"> 82</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model</span>
</span><span id="line-83"><span class="linenos"> 83</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model_1</span>
</span><span id="line-84"><span class="linenos"> 84</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-85"><span class="linenos"> 85</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">12000</span>
</span><span id="line-86"><span class="linenos"> 86</span><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">30s</span><span class="w"> </span><span class="c1"># Request timeout (e.g. "30s", "60s")</span>
</span><span id="line-87"><span class="linenos"> 87</span><span class="w"> </span><span class="nt">max_retries</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span><span class="w"> </span><span class="c1"># Number of retries on upstream failure</span>
</span><span id="line-88"><span class="linenos"> 88</span><span class="w"> </span><span class="nt">input_filters</span><span class="p">:</span><span class="w"> </span><span class="c1"># Filters applied before forwarding to LLM</span>
</span><span id="line-89"><span class="linenos"> 89</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-90"><span class="linenos"> 90</span><span class="w"> </span><span class="nt">output_filters</span><span class="p">:</span><span class="w"> </span><span class="c1"># Filters applied to LLM responses before returning to client</span>
</span><span id="line-91"><span class="linenos"> 91</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-92"><span class="linenos"> 92</span>
</span><span id="line-93"><span class="linenos"> 93</span><span class="w"> </span><span class="c1"># Prompt listener for function calling (for prompt_targets)</span>
</span><span id="line-94"><span class="linenos"> 94</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt</span>
</span><span id="line-95"><span class="linenos"> 95</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt_function_listener</span>
</span><span id="line-96"><span class="linenos"> 96</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-97"><span class="linenos"> 97</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
</span><span id="line-98"><span class="linenos"> 98</span>
</span><span id="line-99"><span class="linenos"> 99</span><span class="c1"># Reusable service endpoints</span>
</span><span id="line-100"><span class="linenos">100</span><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-101"><span class="linenos">101</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-102"><span class="linenos">102</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
</span><span id="line-103"><span class="linenos">103</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
</span><span id="line-104"><span class="linenos">104</span><span class="w"> </span><span class="nt">protocol</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http</span><span class="w"> </span><span class="c1"># http or https</span>
</span><span id="line-105"><span class="linenos">105</span>
</span><span id="line-106"><span class="linenos">106</span><span class="w"> </span><span class="nt">mistral_local</span><span class="p">:</span>
</span><span id="line-107"><span class="linenos">107</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:8001</span>
</span><span id="line-108"><span class="linenos">108</span>
</span><span id="line-109"><span class="linenos">109</span><span class="w"> </span><span class="nt">secure_service</span><span class="p">:</span>
</span><span id="line-110"><span class="linenos">110</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.example.com:443</span>
</span><span id="line-111"><span class="linenos">111</span><span class="w"> </span><span class="nt">protocol</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https</span>
</span><span id="line-112"><span class="linenos">112</span><span class="w"> </span><span class="nt">http_host</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.example.com</span><span class="w"> </span><span class="c1"># Override the Host header sent upstream</span>
</span><span id="line-113"><span class="linenos">113</span>
</span><span id="line-114"><span class="linenos">114</span><span class="c1"># Optional top-level system prompt applied to all prompt_targets</span>
</span><span id="line-115"><span class="linenos">115</span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
</span><span id="line-116"><span class="linenos">116</span><span class="w"> </span><span class="no">You are a helpful assistant. Always respond concisely and accurately.</span>
</span><span id="line-117"><span class="linenos">117</span>
</span><span id="line-118"><span class="linenos">118</span><span class="c1"># Prompt targets for function calling and API orchestration</span>
</span><span id="line-119"><span class="linenos">119</span><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-120"><span class="linenos">120</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">get_current_weather</span>
</span><span id="line-121"><span class="linenos">121</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Get current weather at a location.</span>
</span><span id="line-122"><span class="linenos">122</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-123"><span class="linenos">123</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">location</span>
</span><span id="line-124"><span class="linenos">124</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">The location to get the weather for</span>
</span><span id="line-125"><span class="linenos">125</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-126"><span class="linenos">126</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">string</span>
</span><span id="line-127"><span class="linenos">127</span><span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">City, State</span>
</span><span id="line-128"><span class="linenos">128</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">days</span>
</span><span id="line-129"><span class="linenos">129</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">the number of days for the request</span>
</span><span id="line-130"><span class="linenos">130</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-131"><span class="linenos">131</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">int</span>
</span><span id="line-132"><span class="linenos">132</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-133"><span class="linenos">133</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-134"><span class="linenos">134</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/weather</span>
</span><span id="line-135"><span class="linenos">135</span><span class="w"> </span><span class="nt">http_method</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">POST</span>
</span><span id="line-136"><span class="linenos">136</span><span class="w"> </span><span class="c1"># Per-target system prompt (overrides top-level system_prompt for this target)</span>
</span><span id="line-137"><span class="linenos">137</span><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a weather expert. Provide accurate and concise weather information.</span>
</span><span id="line-138"><span class="linenos">138</span><span class="w"> </span><span class="c1"># auto_llm_dispatch_on_response: when true, the LLM is called again with the</span>
</span><span id="line-139"><span class="linenos">139</span><span class="w"> </span><span class="c1"># function response to produce a final natural-language answer for the user</span>
</span><span id="line-140"><span class="linenos">140</span><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-141"><span class="linenos">141</span>
</span><span id="line-142"><span class="linenos">142</span><span class="c1"># Rate limits - control token usage per model and request selector</span>
</span><span id="line-143"><span class="linenos">143</span><span class="nt">ratelimits</span><span class="p">:</span>
</span><span id="line-144"><span class="linenos">144</span><span class="w"> </span><span class="p p-Indicator">-</span><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/gpt-4o</span>
</span><span id="line-145"><span class="linenos">145</span><span class="w"> </span><span class="nt">selector</span><span class="p">:</span>
</span><span id="line-146"><span class="linenos">146</span><span class="w"> </span><span class="nt">key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-user-id</span><span class="w"> </span><span class="c1"># HTTP header key used to identify the rate-limit subject</span>
</span><span id="line-147"><span class="linenos">147</span><span class="w"> </span><span class="nt">value</span><span class="p">:</span><span class="w"> </span><span class="s">"*"</span><span class="w"> </span><span class="c1"># Wildcard matches any value; use a specific string to target one</span>
</span><span id="line-148"><span class="linenos">148</span><span class="w"> </span><span class="nt">limit</span><span class="p">:</span>
</span><span id="line-149"><span class="linenos">149</span><span class="w"> </span><span class="nt">tokens</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100000</span><span class="w"> </span><span class="c1"># Maximum tokens allowed in the given time unit</span>
</span><span id="line-150"><span class="linenos">150</span><span class="w"> </span><span class="nt">unit</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">hour</span><span class="w"> </span><span class="c1"># Time unit: "minute", "hour", or "day"</span>
</span><span id="line-151"><span class="linenos">151</span>
</span><span id="line-152"><span class="linenos">152</span><span class="w"> </span><span class="p p-Indicator">-</span><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/gpt-4o-mini</span>
</span><span id="line-153"><span class="linenos">153</span><span class="w"> </span><span class="nt">selector</span><span class="p">:</span>
</span><span id="line-154"><span class="linenos">154</span><span class="w"> </span><span class="nt">key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-org-id</span>
</span><span id="line-155"><span class="linenos">155</span><span class="w"> </span><span class="nt">value</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">acme-corp</span>
</span><span id="line-156"><span class="linenos">156</span><span class="w"> </span><span class="nt">limit</span><span class="p">:</span>
</span><span id="line-157"><span class="linenos">157</span><span class="w"> </span><span class="nt">tokens</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">500000</span>
</span><span id="line-158"><span class="linenos">158</span><span class="w"> </span><span class="nt">unit</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">day</span>
</span><span id="line-159"><span class="linenos">159</span>
</span><span id="line-160"><span class="linenos">160</span><span class="c1"># Global behavior overrides</span>
</span><span id="line-161"><span class="linenos">161</span><span class="nt">overrides</span><span class="p">:</span>
</span><span id="line-162"><span class="linenos">162</span><span class="w"> </span><span class="c1"># Threshold for routing a request to a prompt_target (0.01.0). Lower = more permissive.</span>
</span><span id="line-163"><span class="linenos">163</span><span class="w"> </span><span class="nt">prompt_target_intent_matching_threshold</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.7</span>
</span><span id="line-164"><span class="linenos">164</span><span class="w"> </span><span class="c1"># Trim conversation history to fit within the model's context window</span>
</span><span id="line-165"><span class="linenos">165</span><span class="w"> </span><span class="nt">optimize_context_window</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-166"><span class="linenos">166</span><span class="w"> </span><span class="c1"># Use Plano's agent orchestrator for multi-agent request routing</span>
</span><span id="line-167"><span class="linenos">167</span><span class="w"> </span><span class="nt">use_agent_orchestrator</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
</span><span id="line-168"><span class="linenos">168</span><span class="w"> </span><span class="c1"># Connect timeout for upstream provider clusters (e.g., "5s", "10s"). Default: "5s"</span>
</span><span id="line-169"><span class="linenos">169</span><span class="w"> </span><span class="nt">upstream_connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10s</span>
</span><span id="line-170"><span class="linenos">170</span><span class="w"> </span><span class="c1"># Path to the trusted CA bundle for upstream TLS verification</span>
</span><span id="line-171"><span class="linenos">171</span><span class="w"> </span><span class="nt">upstream_tls_ca_path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/etc/ssl/certs/ca-certificates.crt</span>
</span><span id="line-172"><span class="linenos">172</span><span class="w"> </span><span class="c1"># Model used for intent-based LLM routing (must be listed in model_providers)</span>
</span><span id="line-173"><span class="linenos">173</span><span class="w"> </span><span class="nt">llm_routing_model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Plano-Orchestrator</span>
</span><span id="line-174"><span class="linenos">174</span><span class="w"> </span><span class="c1"># Model used for agent orchestration (must be listed in model_providers)</span>
</span><span id="line-175"><span class="linenos">175</span><span class="w"> </span><span class="nt">agent_orchestration_model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Plano-Orchestrator</span>
</span><span id="line-176"><span class="linenos">176</span><span class="w"> </span><span class="c1"># Disable agentic signal analysis (frustration, repetition, escalation, etc.)</span>
</span><span id="line-177"><span class="linenos">177</span><span class="w"> </span><span class="c1"># on LLM responses to save CPU. Default: false.</span>
</span><span id="line-178"><span class="linenos">178</span><span class="w"> </span><span class="nt">disable_signals</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
</span><span id="line-179"><span class="linenos">179</span>
</span><span id="line-180"><span class="linenos">180</span><span class="c1"># Model affinity — pin routing decisions for agentic loops</span>
</span><span id="line-181"><span class="linenos">181</span><span class="nt">routing</span><span class="p">:</span>
</span><span id="line-182"><span class="linenos">182</span><span class="w"> </span><span class="nt">session_ttl_seconds</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">600</span><span class="w"> </span><span class="c1"># How long a pinned session lasts (default: 600s / 10 min)</span>
</span><span id="line-183"><span class="linenos">183</span><span class="w"> </span><span class="nt">session_max_entries</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span><span class="w"> </span><span class="c1"># Max cached sessions before eviction (upper limit: 10000)</span>
</span><span id="line-184"><span class="linenos">184</span><span class="w"> </span><span class="c1"># session_cache controls the backend used to store affinity state.</span>
</span><span id="line-185"><span class="linenos">185</span><span class="w"> </span><span class="c1"># "memory" (default) is in-process and works for single-instance deployments.</span>
</span><span id="line-186"><span class="linenos">186</span><span class="w"> </span><span class="c1"># "redis" shares state across replicas — required for multi-replica / Kubernetes setups.</span>
</span><span id="line-187"><span class="linenos">187</span><span class="w"> </span><span class="nt">session_cache</span><span class="p">:</span>
</span><span id="line-188"><span class="linenos">188</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">memory</span><span class="w"> </span><span class="c1"># "memory" (default) or "redis"</span>
</span><span id="line-189"><span class="linenos">189</span><span class="w"> </span><span class="c1"># url is required when type is "redis". Supports redis:// and rediss:// (TLS).</span>
</span><span id="line-190"><span class="linenos">190</span><span class="w"> </span><span class="c1"># url: redis://localhost:6379</span>
</span><span id="line-191"><span class="linenos">191</span><span class="w"> </span><span class="c1"># tenant_header: x-org-id # optional; when set, keys are scoped as plano:affinity:{tenant_id}:{session_id}</span>
</span><span id="line-192"><span class="linenos">192</span>
</span><span id="line-193"><span class="linenos">193</span><span class="c1"># State storage for multi-turn conversation history</span>
</span><span id="line-194"><span class="linenos">194</span><span class="nt">state_storage</span><span class="p">:</span>
</span><span id="line-195"><span class="linenos">195</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">memory</span><span class="w"> </span><span class="c1"># "memory" (in-process) or "postgres" (persistent)</span>
</span><span id="line-196"><span class="linenos">196</span><span class="w"> </span><span class="c1"># connection_string is required when type is postgres.</span>
</span><span id="line-197"><span class="linenos">197</span><span class="w"> </span><span class="c1"># Supports environment variable substitution: $VAR or ${VAR}</span>
</span><span id="line-198"><span class="linenos">198</span><span class="w"> </span><span class="c1"># connection_string: postgresql://user:$DB_PASS@localhost:5432/plano</span>
</span><span id="line-199"><span class="linenos">199</span>
</span><span id="line-200"><span class="linenos">200</span><span class="c1"># Input guardrails applied globally to all incoming requests</span>
</span><span id="line-201"><span class="linenos">201</span><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span id="line-202"><span class="linenos">202</span><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-203"><span class="linenos">203</span><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-204"><span class="linenos">204</span><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-205"><span class="linenos">205</span><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="s">"I'm</span><span class="nv"> </span><span class="s">sorry,</span><span class="nv"> </span><span class="s">I</span><span class="nv"> </span><span class="s">can't</span><span class="nv"> </span><span class="s">help</span><span class="nv"> </span><span class="s">with</span><span class="nv"> </span><span class="s">that</span><span class="nv"> </span><span class="s">request."</span>
</span><span id="line-206"><span class="linenos">206</span>
</span><span id="line-207"><span class="linenos">207</span><span class="c1"># OpenTelemetry tracing configuration</span>
</span><span id="line-208"><span class="linenos">208</span><span class="nt">tracing</span><span class="p">:</span>
</span><span id="line-209"><span class="linenos">209</span><span class="w"> </span><span class="c1"># Random sampling percentage (1-100)</span>
</span><span id="line-210"><span class="linenos">210</span><span class="w"> </span><span class="nt">random_sampling</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100</span>
</span><span id="line-211"><span class="linenos">211</span><span class="w"> </span><span class="c1"># Include internal Plano spans in traces</span>
</span><span id="line-212"><span class="linenos">212</span><span class="w"> </span><span class="nt">trace_arch_internal</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
</span><span id="line-213"><span class="linenos">213</span><span class="w"> </span><span class="c1"># gRPC endpoint for OpenTelemetry collector (e.g., Jaeger, Tempo)</span>
</span><span id="line-214"><span class="linenos">214</span><span class="w"> </span><span class="nt">opentracing_grpc_endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://localhost:4317</span>
</span><span id="line-215"><span class="linenos">215</span><span class="w"> </span><span class="nt">span_attributes</span><span class="p">:</span>
</span><span id="line-216"><span class="linenos">216</span><span class="w"> </span><span class="c1"># Propagate request headers whose names start with these prefixes as span attributes</span>
</span><span id="line-217"><span class="linenos">217</span><span class="w"> </span><span class="nt">header_prefixes</span><span class="p">:</span>
</span><span id="line-218"><span class="linenos">218</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-user-</span>
</span><span id="line-219"><span class="linenos">219</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-org-</span>
</span><span id="line-220"><span class="linenos">220</span><span class="w"> </span><span class="c1"># Static key/value pairs added to every span</span>
</span><span id="line-221"><span class="linenos">221</span><span class="w"> </span><span class="nt">static</span><span class="p">:</span>
</span><span id="line-222"><span class="linenos">222</span><span class="w"> </span><span class="nt">environment</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">production</span>
</span><span id="line-223"><span class="linenos">223</span><span class="w"> </span><span class="nt">service.team</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">platform</span>
</span></code></pre></div>
</div>
</div>
</section>
</div><div class="flex justify-between items-center pt-6 mt-12 border-t border-border gap-4">
<div class="mr-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="deployment.html">
<svg class="mr-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="15 18 9 12 15 6"></polyline>
</svg>
Deployment
</a>
</div>
<div class="ml-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="cli_reference.html">
CLI Reference
<svg class="ml-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="9 18 15 12 9 6"></polyline>
</svg>
</a>
</div>
</div></div>
</main>
</div>
</div><footer class="py-6 border-t border-border md:py-0">
<div class="container flex flex-col items-center justify-between gap-4 md:h-24 md:flex-row">
<div class="flex flex-col items-center gap-4 px-8 md:flex-row md:gap-2 md:px-0">
<p class="text-sm leading-loose text-center text-muted-foreground md:text-left">© 2026, Katanemo Labs, a DigitalOcean Company Last updated: Apr 23, 2026. </p>
</div>
</div>
</footer>
</div>
<script src="../_static/documentation_options.js?v=6df19ec7"></script>
<script src="../_static/doctools.js?v=9bcbadda"></script>
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
<script defer="defer" src="../_static/theme.js?v=d6a9845b"></script>
<script src="../_static/design-tabs.js?v=f930bc37"></script>
<script src="../_static/js/fix-copy.js?v=2f5cab98"></script>
</body>
</html>