Ilker ManapandClaude Opus 5
1839832b8b
Pasting the gateway's address into a browser returned 404, which looks like a broken endpoint rather than one that tells you how to use it. Two pages, and the split between them is a security boundary rather than a layout choice. The landing page is served without a key — it has to be, because the person reading it is the one who does not have one yet — so it contains no data at all: it says how to connect, not what is here. Model names stay behind /v1/models. It reconstructs the address from the forwarded headers so the copy-pasteable example names the address the client actually used rather than the internal one; those headers are reflected into displayed text and never used for a decision. The dashboard shows nodes, models, replicas, placement failures and usage, and lives on the admin listener only. That listener is loopback-bound and also serves pprof, which can dump the process heap — where API keys sit in plaintext — so reaching the page from elsewhere is an SSH tunnel's job. It is read-only: anything that mints a credential stays in `llmgw keys`, where it needs a shell rather than a browser session this project has no way to authenticate. Mounting the landing page uncovered a hole in the exemption list. An entry ending in "/" was a prefix rule, and "/" ends in "/", so exempting the landing page would have exempted every path there is — authentication still installed, still logging, and letting the whole API through. "/" is now exact, with a test enumerating what must and must not be exempt. Server-rendered templates and one stylesheet, embedded. The single-binary goal rules out a JavaScript toolchain and nothing on either page needs one. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
96 lines
3.9 KiB
HTML
96 lines
3.9 KiB
HTML
{{define "dashboard"}}<!doctype html>
|
||
<html lang="en"><head>
|
||
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
|
||
<meta http-equiv="refresh" content="{{.RefreshSec}}">
|
||
<title>llmgw — cluster</title><link rel="stylesheet" href="/_static/base.css">
|
||
</head><body><div class="wrap">
|
||
<header>
|
||
<h1>Cluster</h1>
|
||
<p class="sub">{{.NodeCount}} nodes · {{.ReadyReplicas}} of {{.TotalReplicas}} replicas ready · {{.ModelCount}} models</p>
|
||
<nav>
|
||
<a href="/metrics">metrics</a>
|
||
<a href="/debug/pprof/">pprof</a>
|
||
<a href="/api/v1/nodes">api</a>
|
||
</nav>
|
||
</header>
|
||
|
||
<h2>Nodes</h2>
|
||
{{if .Nodes}}
|
||
<table><tr><th>Node</th><th>State</th><th class="num">GPUs</th><th>Classes</th><th>Fabrics</th><th class="num">Replicas</th><th>Last seen</th><th>Agent</th></tr>
|
||
{{range .Nodes}}<tr>
|
||
<td><code>{{.ID}}</code>{{if .MgmtAddr}} <span class="note">{{.MgmtAddr}}</span>{{end}}</td>
|
||
<td class="state state-{{.State}}">{{.State}}</td>
|
||
<td class="num">{{.GPUFree}}/{{.GPUTotal}}</td>
|
||
<td>{{join .Classes}}</td>
|
||
<td>{{join .Fabrics}}</td>
|
||
<td class="num">{{.Replicas}}</td>
|
||
<td>{{or .LastSeenAgo "—"}}</td>
|
||
<td><span class="note">{{or .AgentVersion "—"}}</span></td>
|
||
</tr>{{if .Unhealthy}}<tr><td colspan="8" class="note">{{join .Unhealthy}}</td></tr>{{end}}
|
||
{{end}}</table>
|
||
{{else}}<p class="empty">No agents have registered.</p>{{end}}
|
||
|
||
<h2>Models</h2>
|
||
{{if .Models}}
|
||
<table><tr><th>Model</th><th>Aliases</th><th class="num">Ready</th><th class="num">Wanted</th><th>Profiles</th><th>Fallbacks</th></tr>
|
||
{{range .Models}}<tr>
|
||
<td><code>{{.Name}}</code></td>
|
||
<td>{{join .Aliases}}</td>
|
||
<td class="num">{{.Ready}}</td>
|
||
<td class="num">{{.Min}}–{{.Max}}</td>
|
||
<td>{{join .Profiles}}</td>
|
||
<td>{{join .Fallbacks}}</td>
|
||
</tr>{{end}}</table>
|
||
{{else}}<p class="empty">The catalog is empty.</p>{{end}}
|
||
|
||
{{if .Unplaced}}
|
||
<h2>Why nothing was placed</h2>
|
||
{{range .Unplaced}}
|
||
<p><code>{{.Model}}</code></p>
|
||
<pre>{{range .Rejections}}{{.Profile}} @ {{or .Pool "-"}}{{if .Node}}/{{.Node}}{{end}}: {{.Reason}}
|
||
{{end}}</pre>
|
||
{{end}}
|
||
{{end}}
|
||
|
||
<h2>Replicas</h2>
|
||
{{if .Replicas}}
|
||
<table><tr><th>Replica</th><th>Model</th><th>State</th><th>Pool</th><th>Endpoint</th><th class="num">Age</th><th>Nodes</th></tr>
|
||
{{range .Replicas}}<tr>
|
||
<td><code>{{.ID}}</code></td>
|
||
<td>{{.Model}}</td>
|
||
<td class="state state-{{.State}}">{{.State}}</td>
|
||
<td>{{or .Pool "—"}}</td>
|
||
<td>{{if .Endpoint}}<code>{{.Endpoint}}</code>{{else}}—{{end}}</td>
|
||
<td class="num">{{duration .AgeSec}}</td>
|
||
<td>{{range .Shards}}<code>{{.Node}}</code> {{end}}</td>
|
||
</tr>{{if .Err}}<tr><td colspan="7" class="note">{{.Err}}</td></tr>{{end}}
|
||
{{end}}</table>
|
||
{{else}}<p class="empty">No replicas.</p>{{end}}
|
||
|
||
<h2>Usage <span class="note">— last 24 hours</span></h2>
|
||
{{if .AuthEnabled}}
|
||
{{if .Usage}}
|
||
<table><tr><th>Key</th><th>Project</th><th class="num">Requests</th><th class="num">Errors</th><th class="num">Prompt</th><th class="num">Completion</th><th class="num">Spend</th><th>Last</th></tr>
|
||
{{range .Usage}}<tr>
|
||
<td>{{if .KeyName}}{{.KeyName}} <span class="note">{{.KeyPrefix}}</span>{{else}}<code>{{.KeyID}}</code>{{end}}</td>
|
||
<td>{{.ProjectID}}</td>
|
||
<td class="num">{{.Requests}}</td>
|
||
<td class="num">{{if .Errors}}<span class="state-failed">{{.Errors}}</span>{{else}}0{{end}}</td>
|
||
<td class="num">{{.Prompt}}</td>
|
||
<td class="num">{{.Completion}}</td>
|
||
<td class="num">{{units .CostMicros}}</td>
|
||
<td><span class="note">{{ago .LastAt}}</span></td>
|
||
</tr>{{end}}</table>
|
||
<p class="note">Spend is in units, whatever a unit was configured to mean. Usage is
|
||
written in batches, so the last few seconds may be missing.</p>
|
||
{{else}}<p class="empty">No requests recorded in the last 24 hours.</p>{{end}}
|
||
{{else}}
|
||
<p class="empty">Authentication is off, so there is no identity to account against.</p>
|
||
{{end}}
|
||
|
||
<footer>
|
||
<span>llmgw {{.Version}} · refreshes every {{.RefreshSec}}s</span>
|
||
<span>{{.Now}}</span>
|
||
</footer>
|
||
</div></body></html>{{end}}
|