proxy, ui: add pending requests count to the main dashboard (#516)

add a real time counter of pending (inflight) requests to the UI.
This commit is contained in:
Brian Mendonca
2026-02-16 09:41:15 -08:00
committed by GitHub
parent d33d51fa75
commit 1688bdd1e9
6 changed files with 133 additions and 25 deletions
+24 -4
View File
@@ -1,5 +1,5 @@
<script lang="ts">
import { metrics } from "../stores/api";
import { inFlightRequests, metrics } from "../stores/api";
import TokenHistogram from "./TokenHistogram.svelte";
interface HistogramData {
@@ -15,7 +15,14 @@
let stats = $derived.by(() => {
const totalRequests = $metrics.length;
if (totalRequests === 0) {
return { totalRequests: 0, totalInputTokens: 0, totalOutputTokens: 0, tokenStats: { p99: "0", p95: "0", p50: "0" }, histogramData: null };
return {
totalRequests: 0,
totalInputTokens: 0,
totalOutputTokens: 0,
inFlightRequests: $inFlightRequests,
tokenStats: { p99: "0", p95: "0", p50: "0" },
histogramData: null,
};
}
const totalInputTokens = $metrics.reduce((sum, m) => sum + m.input_tokens, 0);
@@ -24,7 +31,14 @@
// Calculate token statistics using output_tokens and duration_ms
const validMetrics = $metrics.filter((m) => m.duration_ms > 0 && m.output_tokens > 0);
if (validMetrics.length === 0) {
return { totalRequests, totalInputTokens, totalOutputTokens, tokenStats: { p99: "0", p95: "0", p50: "0" }, histogramData: null };
return {
totalRequests,
totalInputTokens,
totalOutputTokens,
inFlightRequests: $inFlightRequests,
tokenStats: { p99: "0", p95: "0", p50: "0" },
histogramData: null,
};
}
// Calculate tokens/second for each valid metric
@@ -63,6 +77,7 @@
totalRequests,
totalInputTokens,
totalOutputTokens,
inFlightRequests: $inFlightRequests,
tokenStats: {
p99: p99.toFixed(2),
p95: p95.toFixed(2),
@@ -95,7 +110,12 @@
<tbody class="bg-surface divide-y divide-card-border-inner">
<tr class="hover:bg-secondary">
<td class="px-4 py-4 text-sm font-semibold text-gray-900 dark:text-white">{stats.totalRequests}</td>
<td class="px-4 py-4 text-sm font-semibold text-gray-900 dark:text-white">
<div class="flex flex-col gap-1">
<span class="text-xs font-medium text-gray-500 dark:text-gray-400">Completed: {nf.format(stats.totalRequests)}</span>
<span class="text-xs font-medium text-gray-500 dark:text-gray-400">Waiting: {nf.format(stats.inFlightRequests)}</span>
</div>
</td>
<td class="px-4 py-4 text-sm text-gray-700 dark:text-gray-300 border-l border-gray-200 dark:border-white/10">
<div class="flex items-center gap-2">
+5 -1
View File
@@ -38,8 +38,12 @@ export interface LogData {
data: string;
}
export interface InFlightStats {
total: number;
}
export interface APIEventEnvelope {
type: "modelStatus" | "logData" | "metrics";
type: "modelStatus" | "logData" | "metrics" | "inflight";
data: string;
}
+9 -1
View File
@@ -1,5 +1,5 @@
import { writable } from "svelte/store";
import type { Model, Metrics, VersionInfo, LogData, APIEventEnvelope, ReqRespCapture } from "../lib/types";
import type { Model, Metrics, VersionInfo, LogData, APIEventEnvelope, ReqRespCapture, InFlightStats } from "../lib/types";
import { connectionState } from "./theme";
const LOG_LENGTH_LIMIT = 1024 * 100; /* 100KB of log data */
@@ -9,6 +9,7 @@ export const models = writable<Model[]>([]);
export const proxyLogs = writable<string>("");
export const upstreamLogs = writable<string>("");
export const metrics = writable<Metrics[]>([]);
export const inFlightRequests = writable<number>(0);
export const versionInfo = writable<VersionInfo>({
build_date: "unknown",
commit: "unknown",
@@ -29,6 +30,7 @@ export function enableAPIEvents(enabled: boolean): void {
apiEventSource?.close();
apiEventSource = null;
metrics.set([]);
inFlightRequests.set(0);
return;
}
@@ -46,6 +48,7 @@ export function enableAPIEvents(enabled: boolean): void {
proxyLogs.set("");
upstreamLogs.set("");
metrics.set([]);
inFlightRequests.set(0);
models.set([]);
retryCount = 0;
connectionState.set("connected");
@@ -83,6 +86,11 @@ export function enableAPIEvents(enabled: boolean): void {
metrics.update((prevMetrics) => [...newMetrics, ...prevMetrics]);
break;
}
case "inflight": {
const stats = JSON.parse(message.data) as InFlightStats;
inFlightRequests.set(stats.total ?? 0);
break;
}
}
} catch (err) {
console.error(e.data, err);