feat: add metrics poller with ring buffers and GPU aggregates

tests/metrics-poller.test.ts

@@ -0,0 +1,63 @@
+import assert from "node:assert/strict";
+import { readFileSync } from "node:fs";
+import { test } from "node:test";
+import { type LlamaSwapConfig } from "../src/lib/util";
+import { MetricsPoller } from "../src/lib/metrics-poller";
+import { parseGpuMetrics } from "../src/lib/metrics-parser";
+
+const FIXTURE = readFileSync(new URL("./fixtures/metrics.txt", import.meta.url), "utf8");
+const FIXTURE2 = FIXTURE
+  .replace(/llamaswap_gpu_util_percent\{id="0"[^}]*\} 100/, 'llamaswap_gpu_util_percent{id="0",name="RTX PRO 6000"} 30')
+  .replace(/llamaswap_gpu_util_percent\{id="1"[^}]*\} 100/, 'llamaswap_gpu_util_percent{id="1",name="RTX PRO 6000"} 50')
+  .replace(/llamaswap_gpu_util_percent\{id="2"[^}]*\} 100/, 'llamaswap_gpu_util_percent{id="2",name="RTX 5090"} 80');
+
+function stubFetch(bodies: string[]) {
+  let i = 0;
+  return async () => bodies[Math.min(i++, bodies.length - 1)];
+}
+
+const CFG: LlamaSwapConfig = { baseUrl: "http://test" };
+
+test("poller stores per-GPU history and computes aggregates", async () => {
+  const poller = new MetricsPoller(CFG, 5000, stubFetch([FIXTURE, FIXTURE2]));
+  await poller.tick();
+  await poller.tick();
+
+  assert.equal(poller.getValue("0", "util_percent"), 30);
+  assert.deepEqual(poller.getHistory("0", "util_percent"), [100, 30]);
+
+  const allUtil = poller.getValue("all", "util_percent");
+  assert.ok(allUtil !== undefined);
+  assert.ok(Math.abs(allUtil - (30 + 50 + 80) / 3) < 1e-9);
+
+  const allTemp = poller.getValue("all", "temperature");
+  assert.equal(allTemp, 64);
+
+  const allPower = poller.getValue("all", "power");
+  assert.ok(allPower !== undefined);
+  assert.ok(Math.abs(allPower - (316.56 + 336.17 + 377.28)) < 1e-9);
+
+  assert.deepEqual(poller.gpus().map((g) => g.id), ["0", "1", "2"]);
+  assert.equal(poller.gpus()[2].name, "NVIDIA GeForce RTX 5090");
+});
+
+test("poller ring buffer caps at 60 samples", async () => {
+  const poller = new MetricsPoller(CFG, 5000, stubFetch([FIXTURE]));
+  for (let i = 0; i < 70; i++) await poller.tick();
+  assert.equal(poller.getHistory("0", "fan").length, 60);
+});
+
+test("poller reports offline after a fetch failure and recovers", async () => {
+  let fail = true;
+  const fetchFn = async () => {
+    if (fail) throw new Error("boom");
+    return FIXTURE;
+  };
+  const poller = new MetricsPoller(CFG, 5000, fetchFn);
+  await poller.tick();
+  assert.equal(poller.isOffline(), true);
+  fail = false;
+  await poller.tick();
+  assert.equal(poller.isOffline(), false);
+  assert.ok(poller.getValue("0", "util_percent") !== undefined);
+});