chore(ct116): capture production state (LiteLLM 1.99.1, nginx /ui //docs, router decommission, trove agent)
This commit is contained in:
agent-zero
@@ -70,7 +70,7 @@ body{background:var(--bg);color:var(--text);font-family:-apple-system,BlinkMacSy
|
||||
</div>
|
||||
|
||||
<script>
|
||||
const COLORS={'qwen3.6-35B-A3B':'#10b981','qwen3.6-27B-code':'#8b5cf6','gemma-4-12b':'#3b82f6'};
|
||||
const COLORS={'qwen3.6-35B-A3B':'#10b981','qwen3.6-27B-code':'#8b5cf6','gpu-vision':'#3b82f6'};
|
||||
const HISTORY=[]; // rolling 60 sample history for chart
|
||||
function Q(id){return document.getElementById(id)}
|
||||
|
||||
|
||||
+11
-11
@@ -119,7 +119,7 @@ body { background: #0b0f17; color: #bcc3cd; font-family: -apple-system, BlinkMac
|
||||
<div class="d-flex gap-2">
|
||||
<select id="scatter-model" onchange="loadScatter()" style="font-size:10px;background:#1e293b;color:#94a3b8;border:1px solid #334155;border-radius:4px;padding:2px 6px">
|
||||
<option value="all">All Models</option>
|
||||
<option value="gemma-4-12b">12B VLM</option>
|
||||
<option value="gpu-vision">12B VLM</option>
|
||||
<option value="qwen3.6-27B-code">27B Dense</option>
|
||||
<option value="qwen3.6-35B-A3B">35B MoE</option>
|
||||
</select>
|
||||
@@ -136,9 +136,9 @@ body { background: #0b0f17; color: #bcc3cd; font-family: -apple-system, BlinkMac
|
||||
</div>
|
||||
|
||||
<script>
|
||||
var MC={'gemma-4-12b':'#22c55e','qwen3.6-27B-code':'#f59e0b','qwen3.6-35B-A3B':'#a78bfa'};
|
||||
var ML={'gemma-4-12b':'Gemma 4 12B','qwen3.6-27B-code':'Qwen Code','qwen3.6-35B-A3B':'Qwen MoE'};
|
||||
var GL={'qwen3.6-35B-A3B':'MoE - Strix Halo','qwen3.6-27B-code':'Dense - RTX 3090','gemma-4-12b':'VLM - RTX 5070'};
|
||||
var MC={'gpu-vision':'#22c55e','qwen3.6-27B-code':'#f59e0b','qwen3.6-35B-A3B':'#a78bfa'};
|
||||
var ML={'gpu-vision':'Gemma 4 12B','qwen3.6-27B-code':'Qwen Code','qwen3.6-35B-A3B':'Qwen MoE'};
|
||||
var GL={'qwen3.6-35B-A3B':'MoE - Strix Halo','qwen3.6-27B-code':'Dense - RTX 3090','gpu-vision':'VLM - RTX 5070'};
|
||||
function $(id){return document.getElementById(id);}
|
||||
|
||||
function render(data){
|
||||
@@ -147,7 +147,7 @@ var t=Object.values(data.route_counts||{}).reduce((a,b)=>a+b,0);
|
||||
var ta=0,tm=0;data.gpus.forEach(function(g){ta+=(g.active_requests||0);tm+=(g.max_concurrent||1)});
|
||||
$('kpi-total').textContent=t;$('kpi-active').textContent=ta+'/'+tm;$('kpi-agents').textContent=Object.keys(data.agent_counts||{}).length;
|
||||
$('update-time').textContent=new Date().toLocaleTimeString();
|
||||
var ids={'qwen3.6-35B-A3B':'gpu-moe','qwen3.6-27B-code':'gpu-dense','gemma-4-12b':'gpu-light'};
|
||||
var ids={'qwen3.6-35B-A3B':'gpu-moe','qwen3.6-27B-code':'gpu-dense','gpu-vision':'gpu-light'};
|
||||
data.gpus.forEach(function(g){
|
||||
var el=$(ids[g.id]);if(!el)return;
|
||||
var a=g.active_requests||0,mx=g.max_concurrent||1;
|
||||
@@ -179,14 +179,14 @@ var sc=pct>=100?'#ef4444':pct>=50?'#f59e0b':'#22c55e';
|
||||
var circ=188.5,dash=(pct/100)*circ;
|
||||
var h='<div class=\"d-inline-block position-relative mb-2\"><svg width=\"72\" height=\"72\"><circle cx=\"36\" cy=\"36\" r=\"30\" fill=\"none\" stroke=\"#1e293b\" stroke-width=\"6\"/><circle cx=\"36\" cy=\"36\" r=\"30\" fill=\"none\" stroke=\"'+sc+'\" stroke-width=\"6\" stroke-dasharray=\"'+dash+' '+(circ-dash)+'\" stroke-linecap=\"round\" transform=\"rotate(-90 36 36)\"/></svg><div style=\"position:absolute;top:50%;left:50%;transform:translate(-50%,-50%);text-align:center\"><div class=\"ring-label\" style=\"color:'+sc+'\">'+ta+'</div><div class=\"ring-sublabel\">/ '+tm+' slots</div></div></div>';
|
||||
h+='<div class=\"fw-bold mb-2 small\" style=\"color:'+sc+'\">'+st+'</div>';
|
||||
var lb={'qwen3.6-35B-A3B':'MoE','qwen3.6-27B-code':'Dense','gemma-4-12b':'VLM'};
|
||||
var lb={'qwen3.6-35B-A3B':'MoE','qwen3.6-27B-code':'Dense','gpu-vision':'VLM'};
|
||||
data.gpus.forEach(function(g){var a=g.active_requests||0,mx=g.max_concurrent||1,gp=mx>0?Math.round(a/mx*100):0;h+='<div class=\"d-flex align-items-center gap-2 mb-1 justify-content-center\"><span class=\"small\" style=\"min-width:32px;text-align:right;font-size:10px\">'+(lb[g.id]||g.id)+'</span><div style=\"flex:1;max-width:70px;height:3px;background:#1e293b;border-radius:2px;overflow:hidden\"><div style=\"height:100%;width:'+gp+'%;background:'+sc+';border-radius:2px\"></div></div><span class=\"small\" style=\"min-width:22px;font-size:10px\">'+a+'/'+mx+'</span></div>'});
|
||||
el.innerHTML=h;
|
||||
}
|
||||
|
||||
function renderGPUMetrics(data){
|
||||
var el=$('gpu-metrics-card');if(!el)return;
|
||||
var lb={'qwen3.6-35B-A3B':'MoE','qwen3.6-27B-code':'Dense','gemma-4-12b':'VLM'};
|
||||
var lb={'qwen3.6-35B-A3B':'MoE','qwen3.6-27B-code':'Dense','gpu-vision':'VLM'};
|
||||
var h='';data.gpus.forEach(function(g){
|
||||
var nm=lb[g.id]||g.id,tp=g.temp_c||0,ut=g.gpu_util_pct||0,pw=g.power_w||0,pl=g.power_limit_w||0;
|
||||
var tc=tp>85?'#ef4444':tp>70?'#f59e0b':'#22c55e',uc=ut>90?'#ef4444':ut>70?'#f59e0b':'#22c55e';
|
||||
@@ -219,8 +219,8 @@ function loadPerf(){fetch('/api/performance?window='+perfWindow).then(function(r
|
||||
function renderPerf(d){
|
||||
var models=d.models||[],reasons=d.reasons||[],agents=d.agents||[],sum=d.summary||{};
|
||||
// Latency bars: p50/p95/p99 per model
|
||||
var mlab={'qwen3.6-35B-A3B':'35B MoE','qwen3.6-27B-code':'27B Dense','gemma-4-12b':'12B VLM'};
|
||||
var mcol={'qwen3.6-35B-A3B':'#a78bfa','qwen3.6-27B-code':'#f59e0b','gemma-4-12b':'#22c55e'};
|
||||
var mlab={'qwen3.6-35B-A3B':'35B MoE','qwen3.6-27B-code':'27B Dense','gpu-vision':'12B VLM'};
|
||||
var mcol={'qwen3.6-35B-A3B':'#a78bfa','qwen3.6-27B-code':'#f59e0b','gpu-vision':'#22c55e'};
|
||||
if(!models.length){$('perf-latency').innerHTML='<div class="text-secondary small text-center py-4">Accumulating data...</div>';return;}
|
||||
var maxLat=Math.max(...models.map(function(m){return m.latency.p99||0}),1);
|
||||
var latHTML=models.map(function(m){
|
||||
@@ -270,8 +270,8 @@ fetch('/api/scatter?window=24&model='+m).then(function(r){return r.json()}).then
|
||||
function renderScatter(d){
|
||||
var pts=d.points||[],el=$('scatter-plot'),lg=$('scatter-legend');
|
||||
if(!pts.length){el.innerHTML='<div class="text-secondary small text-center py-5">No data yet</div>';return;}
|
||||
var mcol={'qwen3.6-35B-A3B':'#a78bfa','qwen3.6-27B-code':'#f59e0b','gemma-4-12b':'#22c55e','unknown':'#38bdf8'};
|
||||
var mlab={'qwen3.6-35B-A3B':'35B MoE','qwen3.6-27B-code':'27B Dense','gemma-4-12b':'12B VLM'};
|
||||
var mcol={'qwen3.6-35B-A3B':'#a78bfa','qwen3.6-27B-code':'#f59e0b','gpu-vision':'#22c55e','unknown':'#38bdf8'};
|
||||
var mlab={'qwen3.6-35B-A3B':'35B MoE','qwen3.6-27B-code':'27B Dense','gpu-vision':'12B VLM'};
|
||||
var maxX=Math.max.apply(null,pts.map(function(p){return p.prompt_tokens||0}))||1000;
|
||||
var maxY=Math.max.apply(null,pts.map(function(p){return p.inference_ms||0}))||5000;
|
||||
// Log scale for X axis (prompt tokens vary widely)
|
||||
|
||||
@@ -362,7 +362,7 @@ function dashboard() {
|
||||
try {
|
||||
const metrics = await fetch('/metrics/circuit-breaker').then(r => r.json());
|
||||
this.gpuHealth = [
|
||||
{ id: 'gemma3-70b', name: 'Gemma 3 70B', model: 'gemma3-70b', health_score: metrics.gemma3_70b?.gpu_health_score || 39.4, vram_pct: 45, temp: 78, load: 65, is_preferred: true },
|
||||
{ id: 'gpu-vision', name: 'Qwen3.5-9B Vision', model: 'gpu-vision', health_score: metrics.gpu_vision?.gpu_health_score || 39.4, vram_pct: 45, temp: 78, load: 65, is_preferred: true },
|
||||
{ id: 'deepseek-v3', name: 'DeepSeek V3', model: 'deepseek-v3', health_score: metrics.deepseek_v3?.gpu_health_score || 45.9, vram_pct: 60, temp: 82, load: 50, is_preferred: false },
|
||||
{ id: 'mistral-small', name: 'Mistral Small', model: 'mistral-small', health_score: metrics.mistral_small?.gpu_health_score || 35.0, vram_pct: 30, temp: 65, load: 40, is_preferred: false }
|
||||
];
|
||||
@@ -388,7 +388,7 @@ function dashboard() {
|
||||
async fetchSessionAnalytics() {
|
||||
try {
|
||||
this.sessionData = {
|
||||
distribution: { 'gemma3-70b': 45, 'deepseek-v3': 30, 'mistral-small': 25 },
|
||||
distribution: { 'gpu-vision': 45, 'deepseek-v3': 30, 'mistral-small': 25 },
|
||||
trend: Array.from({ length: 24 }, (_, i) => ({ time: `${i}:00`, sessions: Math.floor(Math.random() * 20) + 10 })),
|
||||
peaks: { '09:00': 25, '14:00': 30, '18:00': 20 }
|
||||
};
|
||||
@@ -400,7 +400,7 @@ function dashboard() {
|
||||
try {
|
||||
this.systemPerf = {
|
||||
latency: { p50: Math.floor(Math.random() * 50) + 100, p95: Math.floor(Math.random() * 200) + 250, p99: Math.floor(Math.random() * 500) + 400 },
|
||||
errorRates: { 'gemma3-70b': Math.random() * 0.01, 'deepseek-v3': Math.random() * 0.02, 'mistral-small': Math.random() * 0.015 }
|
||||
errorRates: { 'gpu-vision': Math.random() * 0.01, 'deepseek-v3': Math.random() * 0.02, 'mistral-small': Math.random() * 0.015 }
|
||||
};
|
||||
console.log('System performance loaded');
|
||||
} catch (error) { console.error('Failed to load system performance:', error); }
|
||||
@@ -434,7 +434,7 @@ function dashboard() {
|
||||
},
|
||||
|
||||
getGPUColor(name) {
|
||||
const colors = { 'gemma3-70b': '#3b82f6', 'deepseek-v3': '#8b5cf6', 'mistral-small': '#10b981' };
|
||||
const colors = { 'gpu-vision': '#3b82f6', 'deepseek-v3': '#8b5cf6', 'mistral-small': '#10b981' };
|
||||
return colors[name] || '#9ca3af';
|
||||
}
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user