Ilker ManapandClaude Opus 5
3b67b1fe42
CI / test (push) Successful in 1m25s
Clicking "metrics" on the web dashboard answered "no api key was provided". The page is served twice and its navigation assumed one of them. Metrics, pprof and the management API exist on the admin listener; account administration, the profile and the chat exist on the client-facing port. The nav offered the first set in both places, so on the public port those links fell through to the API-key middleware — which is a far more confusing way to say "that is not here" than a 404 would have been. Each page now offers what is actually reachable from it, and the public one says where the rest lives rather than pretending it does not exist, including why that port is not exposed: pprof can dump the process heap, and the heap holds every API key in plaintext. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
121 lines
4.7 KiB
HTML
121 lines
4.7 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>
|
||
{{if .OnAdminListener}}
|
||
<a href="/metrics">metrics</a>
|
||
<a href="/debug/pprof/">pprof</a>
|
||
<a href="/api/v1/nodes">api</a>
|
||
{{else}}
|
||
<a href="/admin/users">accounts</a>
|
||
<a href="/profile">your keys</a>
|
||
<a href="/chat">chat</a>
|
||
{{end}}
|
||
</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>Traffic <span class="note">— last 24 hours, hourly</span></h2>
|
||
{{if .HasCharts}}
|
||
<p class="note">Requests</p>{{.RequestChart}}
|
||
<div class="chart-row">
|
||
<div><p class="note">Tokens</p>{{.TokenChart}}</div>
|
||
<div><p class="note">Mean latency</p>{{.LatencyChart}}</div>
|
||
</div>
|
||
{{else if .AuthEnabled}}
|
||
<p class="empty">No traffic recorded yet.</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}}
|
||
|
||
{{if not .OnAdminListener}}
|
||
<p class="note">Metrics, pprof and the management API are on the admin listener,
|
||
which is bound to loopback and not reachable from here. pprof can dump the
|
||
process heap, where API keys sit in plaintext, which is why that port is not
|
||
exposed:
|
||
<code>ssh -L 9090:127.0.0.1:9090 <control-plane></code></p>
|
||
{{end}}
|
||
|
||
<footer>
|
||
<span>llmgw {{.Version}} · refreshes every {{.RefreshSec}}s</span>
|
||
<span>{{.Now}}</span>
|
||
</footer>
|
||
</div></body></html>{{end}}
|