Ilker ManapandClaude Opus 5
859f08da9b
CI / test (push) Successful in 1m19s
Two things the dashboard was missing: it could not act, and it was a column of numbers. Account administration moves to /admin/users — approving into a project, suspending, reinstating. That is the work an operator does constantly and it should not need a terminal. Three things stay on the CLI, and the line is not arbitrary: promoting someone to admin, resetting a password, and issuing a key on another person's behalf each turn a stolen admin session into more than it was — permanent access, or somebody else's account. Approving and suspending do not. Suspending signs the account out everywhere, or suspension is advisory until the session happens to expire, and an admin cannot suspend themselves, which is not a thing an interface should let you do by misclicking. The charts are inline SVG generated in Go. A charting library would mean a JavaScript toolchain in CI and a megabyte of bundle for what is a list of rectangles, and the single-binary goal rules that out. Hourly over a day: fine enough to show a working day, coarse enough that one slow minute is not an incident. Empty hours are filled in, because a chart with hours missing where nothing happened reads as a chart with hours missing from the data. The SVG is marked as trusted HTML, so everything that reaches it is either a number this package computed or escaped explicitly, and a bar's colour can only be one of four names — a colour that could be anything is a way to write CSS into every page the chart appears on. There are tests for both. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
108 lines
4.3 KiB
HTML
108 lines
4.3 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="/admin/users">accounts</a>
|
||
<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>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}}
|
||
|
||
<footer>
|
||
<span>llmgw {{.Version}} · refreshes every {{.RefreshSec}}s</span>
|
||
<span>{{.Now}}</span>
|
||
</footer>
|
||
</div></body></html>{{end}}
|