Hot-reload sshHosts/knownDevices from hosts.yaml, no restart needed

Checks the file's mtime on each poll cycle (already running every
30s) rather than adding a separate file-watcher or admin UI. Proxmox
hosts already needed no config (auto-discovered every poll); this
covers the two lists that did. A parse failure logs and keeps the
previous config running instead of crashing the poller.

Closes #14.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

apps/api/src/index.ts

@@ -1,8 +1,9 @@
 import "dotenv/config";
+import { statSync } from "node:fs";
 import Fastify from "fastify";
 import fastifyCookie from "@fastify/cookie";
 import fastifySession from "@fastify/session";
-import { loadConfig } from "./config/index.js";
+import { loadConfig, type AppConfig } from "./config/index.js";
 import { openDb, upsertSnapshots, pruneOldSnapshots } from "./db/index.js";
 import { seedAdminUser } from "./auth/local.js";
 import { ProxmoxCollector } from "./collectors/proxmox.js";
@@ -17,15 +18,8 @@ import { initOidc } from "./auth/oidc.js";
 
 const HOSTS_CONFIG_PATH = process.env.HOSTS_CONFIG_PATH ?? "../../config/hosts.yaml";
 
-async function main() {
-  const cfg = loadConfig(HOSTS_CONFIG_PATH);
-  const db = openDb(cfg.dbPath);
-
-  if (cfg.adminPassword) {
-    seedAdminUser(db, cfg.adminUsername, cfg.adminPassword);
-  }
-
-  const collectors: Collector[] = [
+function buildCollectors(cfg: AppConfig): Collector[] {
+  return [
     new ProxmoxCollector({
       host: cfg.proxmox.host,
       node: cfg.proxmox.node,
@@ -34,8 +28,50 @@ async function main() {
     }),
     ...cfg.sshHosts.map((h) => new SshHostCollector(h)),
   ];
+}
+
+async function main() {
+  const cfg = loadConfig(HOSTS_CONFIG_PATH);
+  const db = openDb(cfg.dbPath);
+
+  if (cfg.adminPassword) {
+    seedAdminUser(db, cfg.adminUsername, cfg.adminPassword);
+  }
+
+  // Proxmox-monitored hosts (the node + every LXC) auto-discover on every poll
+  // already — no config needed there. sshHosts and knownDevices, though, are
+  // declared in hosts.yaml and used to need a container restart to pick up
+  // changes. Re-checking the file's mtime on each poll cycle (already running
+  // every 30s) avoids that without adding a separate file-watcher/admin UI.
+  let knownDevices = cfg.knownDevices;
+  let collectors = buildCollectors(cfg);
+  let hostsConfigMtimeMs = statSync(HOSTS_CONFIG_PATH).mtimeMs;
+
+  function reloadHostsConfigIfChanged() {
+    let mtimeMs: number;
+    try {
+      mtimeMs = statSync(HOSTS_CONFIG_PATH).mtimeMs;
+    } catch {
+      return;
+    }
+    if (mtimeMs === hostsConfigMtimeMs) return;
+    hostsConfigMtimeMs = mtimeMs;
+    try {
+      const reloaded = loadConfig(HOSTS_CONFIG_PATH);
+      collectors = buildCollectors(reloaded);
+      knownDevices = reloaded.knownDevices;
+      app.log.info(
+        { sshHosts: reloaded.sshHosts.length, knownDevices: reloaded.knownDevices.size },
+        "config/hosts.yaml changed, reloaded"
+      );
+    } catch (err) {
+      app.log.error({ err }, "failed to reload config/hosts.yaml, keeping previous config");
+    }
+  }
 
   async function pollOnce() {
+    reloadHostsConfigIfChanged();
+
     for (const collector of collectors) {
       try {
         const snapshots = await collector.collect();
@@ -47,7 +83,7 @@ async function main() {
     pruneOldSnapshots(db, cfg.snapshotRetentionHours);
 
     try {
-      await refreshDevices(db, cfg.discoveryFilePath, cfg.knownDevices);
+      await refreshDevices(db, cfg.discoveryFilePath, knownDevices);
     } catch (err) {
       app.log.error({ err }, "device discovery refresh failed");
     }

docs/hot-reload.md

@@ -0,0 +1,18 @@
+# Editing monitored hosts without a redeploy
+
+`config/hosts.yaml`'s `sshHosts` and `knownDevices` lists are re-read on the next poll
+cycle (checks the file's mtime, reloads if changed) — no container restart needed.
+
+- **Proxmox-monitored hosts** (the node + every LXC) need no config at all — they're
+  auto-discovered from the Proxmox API on every poll already.
+- **SSH-monitored hosts** (`sshHosts`): edit `config/hosts.yaml` on the deploy host
+  directly (`/opt/homelab-monitor/config/hosts.yaml` on CT122), save, wait up to one
+  poll interval (`POLL_INTERVAL_SECONDS`, default 30s). Adding a *new* SSH host still
+  needs a one-time manual step first — installing the forced-command key on the target
+  (see `docs/ssh-collector-key-setup.md`) — that part can't be automated away, so a web
+  form wouldn't make this fully self-service regardless of hot-reload.
+- **`knownDevices`** (device discovery labeling): same file, same reload path, no
+  manual step needed since it's just a label list.
+
+If the file fails to parse (bad YAML), the error is logged and the **previous**
+in-memory config keeps running rather than crashing the poller.