feat: system/http/traefik collectors and docker auto-discovery (M3)

Adds the remaining monitor types: a systeminformation-backed system
widget (single-flight cached so multiple widgets don't force
concurrent samples), an http widget with per-widget consecutive-
failure tracking, and a traefik widget that reads router/entrypoint/
middleware status from Traefik's own API. Also adds opt-in label-based
docker auto-discovery (discovery.docker in config.yml): containers
carrying traefik.enable=true are turned into docker widgets in a
synthetic "Discovered" group, re-scanned on a timer and whenever
config.yml changes, with manual widgets always taking precedence over
a discovered one for the same container.

Fixes a real bug surfaced while testing discovery: Next's App Router
bundles app/** through its own compiler pass, separate from server.ts
(run directly via tsx), so configStore/effectiveConfigStore were
silently instantiated twice - one instance watched and updated by
server.ts, another frozen instance read by SSR. Live config edits were
never reflected on page load without a full process restart. Both
stores now key their singleton off globalThis, which both module
graphs share within the same process.

Verified against a real Traefik v3 container (API-driven router list,
ping-based http check) and a labeled nginx container (auto-discovery),
including that a config.yml edit now shows up in a fresh page load
without restarting the server, in both dev and the production build.

lib/collectors/http.ts

@@ -0,0 +1,18 @@
+import type { HttpCheckResult } from "@/lib/types/http-result";
+
+export async function collectHttp(
+  url: string,
+  method: string,
+  timeoutMs: number,
+  expectedStatus: number
+): Promise<Omit<HttpCheckResult, "consecutiveFailures">> {
+  const start = performance.now();
+  try {
+    const response = await fetch(url, { method, signal: AbortSignal.timeout(timeoutMs), redirect: "follow" });
+    const latencyMs = Math.round(performance.now() - start);
+    return { up: response.status === expectedStatus, statusCode: response.status, latencyMs, error: null };
+  } catch (err) {
+    const latencyMs = Math.round(performance.now() - start);
+    return { up: false, statusCode: null, latencyMs, error: (err as Error).message };
+  }
+}

lib/collectors/scheduler.ts

@@ -3,9 +3,13 @@ import type { Config, Widget } from "@/lib/config/schema";
 import { flattenWidgets } from "@/lib/config/widgets";
 import { parseDuration } from "@/lib/config/duration";
 import { collectDockerContainer } from "./docker";
+import { collectSystem } from "./system";
+import { collectHttp } from "./http";
+import { collectTraefik } from "./traefik";
 import type { WidgetResult } from "@/lib/types/widget-result";
 
 const dockerLimit = pLimit(4);
+const httpLimit = pLimit(8);
 
 type ResultListener = (widgetId: string, result: WidgetResult) => void;
 
@@ -13,14 +17,23 @@ interface Job {
   widget: Widget;
   intervalMs: number;
   timer: ReturnType<typeof setInterval>;
+  consecutiveFailures: number;
 }
 
+const COLLECTOR_TYPES = new Set<Widget["type"]>(["docker", "database", "system", "http", "traefik"]);
+
 function isCollectorWidget(widget: Widget): boolean {
-  return widget.type === "docker" || widget.type === "database";
+  return COLLECTOR_TYPES.has(widget.type);
 }
 
 function getIntervalMs(widget: Widget): number {
-  if (widget.type === "docker" || widget.type === "database") {
+  if (
+    widget.type === "docker" ||
+    widget.type === "database" ||
+    widget.type === "system" ||
+    widget.type === "http" ||
+    widget.type === "traefik"
+  ) {
     return parseDuration(widget.interval);
   }
   return 30_000;
@@ -33,6 +46,15 @@ function sameTarget(a: Widget, b: Widget): boolean {
   if (a.type === "database" && b.type === "database") {
     return a.containerName === b.containerName;
   }
+  if (a.type === "system" && b.type === "system") {
+    return true;
+  }
+  if (a.type === "http" && b.type === "http") {
+    return a.url === b.url && a.method === b.method && a.expect.status === b.expect.status;
+  }
+  if (a.type === "traefik" && b.type === "traefik") {
+    return a.apiUrl === b.apiUrl;
+  }
   return false;
 }
 
@@ -45,6 +67,20 @@ async function collect(widget: Widget): Promise<WidgetResult> {
     const data = await dockerLimit(() => collectDockerContainer(widget.containerName, true));
     return { type: "database", data };
   }
+  if (widget.type === "system") {
+    const data = await collectSystem();
+    return { type: "system", data };
+  }
+  if (widget.type === "http") {
+    const data = await httpLimit(() =>
+      collectHttp(widget.url, widget.method, parseDuration(widget.timeout), widget.expect.status)
+    );
+    return { type: "http", data: { ...data, consecutiveFailures: 0 } };
+  }
+  if (widget.type === "traefik") {
+    const data = await collectTraefik(widget.apiUrl);
+    return { type: "traefik", data };
+  }
   throw new Error(`No collector for widget type "${widget.type}"`);
 }
 
@@ -87,9 +123,9 @@ class CollectorScheduler {
 
       if (existing) clearInterval(existing.timer);
 
-      const run = () => this.runJob(instance.id, instance.widget);
+      const run = () => this.runJob(instance.id);
       const timer = setInterval(run, intervalMs);
-      this.jobs.set(instance.id, { widget: instance.widget, intervalMs, timer });
+      this.jobs.set(instance.id, { widget: instance.widget, intervalMs, timer, consecutiveFailures: 0 });
       run();
     }
 
@@ -107,13 +143,22 @@ class CollectorScheduler {
     this.jobs.clear();
   }
 
-  private async runJob(id: string, widget: Widget): Promise<void> {
+  private async runJob(id: string): Promise<void> {
+    const job = this.jobs.get(id);
+    if (!job) return;
+
     let result: WidgetResult;
     try {
-      result = await collect(widget);
+      result = await collect(job.widget);
+      if (result.type === "http") {
+        job.consecutiveFailures = result.data.up ? 0 : job.consecutiveFailures + 1;
+        result = { type: "http", data: { ...result.data, consecutiveFailures: job.consecutiveFailures } };
+      }
     } catch (err) {
       result = { type: "error", message: (err as Error).message };
     }
+
+    if (!this.jobs.has(id)) return;
     this.lastResults.set(id, result);
     for (const listener of this.listeners) listener(id, result);
   }

lib/collectors/system.ts

@@ -0,0 +1,52 @@
+import si from "systeminformation";
+import type { SystemResult } from "@/lib/types/system-result";
+
+const CACHE_MS = 1_000;
+
+let lastSample: { data: SystemResult; ts: number } | null = null;
+let inFlight: Promise<SystemResult> | null = null;
+
+function pickDisk(disks: si.Systeminformation.FsSizeData[]): si.Systeminformation.FsSizeData | undefined {
+  return disks.find((disk) => disk.mount === "/") ?? disks.sort((a, b) => b.size - a.size)[0];
+}
+
+async function sample(): Promise<SystemResult> {
+  const [load, mem, disks, net] = await Promise.all([
+    si.currentLoad(),
+    si.mem(),
+    si.fsSize(),
+    si.networkStats(),
+  ]);
+
+  const disk = pickDisk(disks);
+  const primaryNet = net[0];
+
+  return {
+    cpuPercent: load.currentLoad,
+    memUsedBytes: mem.active,
+    memTotalBytes: mem.total,
+    diskUsedBytes: disk?.used ?? 0,
+    diskTotalBytes: disk?.size ?? 0,
+    netRxBytesPerSec: primaryNet?.rx_sec ?? 0,
+    netTxBytesPerSec: primaryNet?.tx_sec ?? 0,
+  };
+}
+
+export async function collectSystem(): Promise<SystemResult> {
+  const now = Date.now();
+  if (lastSample && now - lastSample.ts < CACHE_MS) {
+    return lastSample.data;
+  }
+  if (inFlight) return inFlight;
+
+  inFlight = sample()
+    .then((data) => {
+      lastSample = { data, ts: Date.now() };
+      return data;
+    })
+    .finally(() => {
+      inFlight = null;
+    });
+
+  return inFlight;
+}

lib/collectors/traefik.ts

@@ -0,0 +1,48 @@
+import type { TraefikResult } from "@/lib/types/traefik-result";
+
+interface RawRouter {
+  name: string;
+  rule: string;
+  service: string;
+  status: string;
+  tls?: unknown;
+  entryPoints?: string[];
+}
+
+interface RawEntrypoint {
+  name: string;
+  address: string;
+}
+
+async function fetchJson<T>(url: string): Promise<T | null> {
+  const response = await fetch(url, { signal: AbortSignal.timeout(5_000) });
+  if (!response.ok) return null;
+  return (await response.json()) as T;
+}
+
+export async function collectTraefik(apiUrl: string): Promise<TraefikResult> {
+  const base = apiUrl.replace(/\/$/, "");
+
+  const [routers, entrypoints, middlewares] = await Promise.all([
+    fetchJson<RawRouter[]>(`${base}/http/routers`),
+    fetchJson<RawEntrypoint[]>(`${base}/entrypoints`),
+    fetchJson<unknown[]>(`${base}/http/middlewares`),
+  ]);
+
+  if (routers === null) {
+    throw new Error(`Traefik API at ${base}/http/routers is unreachable or returned an error`);
+  }
+
+  return {
+    routers: routers.map((router) => ({
+      name: router.name,
+      rule: router.rule,
+      service: router.service,
+      status: router.status,
+      tls: Boolean(router.tls),
+      entryPoints: router.entryPoints ?? [],
+    })),
+    entrypoints: (entrypoints ?? []).map((ep) => ({ name: ep.name, address: ep.address })),
+    middlewaresCount: middlewares?.length ?? 0,
+  };
+}