feat: ops & UX batch — jobs survive restarts, logs/system in the console, media queue, gallery, chat, exact stream tokens

Fifteen changes aimed at the first day of real use:

- Import and media jobs persist to <data>/jobs-*.json and reload on start
  (running ones settle as errors); the Register button no longer vanishes
  because the gateway restarted.
- Docker ships the cortiq binary (built in the builder stage) — local .cmf
  chat models and image/video generation now work in containers, where
  auto-install never could (no cargo in the runtime image). libvulkan1 added
  for optional GPU offload.
- Open admin console on 0.0.0.0 without a token now warns in the log and
  shows a dismissible banner — the VPS footgun is at least labeled.
- "Restart gateway" button in Settings: stops managed model servers, spawns
  a fresh copy (bind retried while the port frees), Docker relies on the
  container restart policy instead.
- Dashboard "System" panel: CPU sparkline + load, RAM (with the gateway's
  own RSS), free disk at the models dir — sampled by sysinfo every 2 s.
- Featured model cards warn "not enough disk" / "may not fit in RAM" before
  the download, from the same live snapshot.
- Log viewer in the sidebar: a 500-line in-memory ring fed by a second
  ANSI-free tracing layer; filter, level, pause, copy.
- Update check: crates.io polled twice a day, the console shows an
  "update available" notice.
- Media generations queue up (with position shown) instead of being
  rejected; progress gained an honest ETA from measured throughput.
- Generation gallery under the image/video tabs: lazy PPM thumbnails,
  click to reopen with seed/steps, delete.
- Playground chat is a real dialogue now: history is resent, bubbles,
  Clear, Cmd/Ctrl+Enter.
- "Connect your app" snippets (curl / Python / JS) on the keys page, with
  the real key inlined right after creation.
- One-click benchmark on the Models page via `cortiq bench --json`.
- Config export now downloads the actual gateway.toml (comments intact);
  import accepts TOML (validated, hot-reloaded) and the legacy JSON.
- Streaming token counts are exact when the model server provides usage
  (cortiq-server patch, shipped separately); the gateway fallback now
  counts content chunks (1/token on cortiq) instead of chars/4.

Wizard's Finish lands on the Playground. 37 new strings in all 7 languages.

web/js/views/settings.js

@@ -1,7 +1,7 @@
 // Settings — router/route/breaker/log/telemetry/stats + export/import config.
-import { h, mount, toast } from "../ui.js";
+import { h, mount, toast, confirmDialog } from "../ui.js";
 import { t } from "../i18n.js";
-import { api } from "../api.js";
+import { api, getToken, postRaw } from "../api.js";
 import { appState, SITE_URL } from "../app.js";
 
 // A small "?" badge with a hover/focus tooltip explaining a setting.
@@ -480,22 +480,33 @@ export async function renderSettings() {
   });
 
   async function exportConfig() {
-    const cfg = await api.getConfig();
-    const blob = new Blob([JSON.stringify(cfg, null, 2)], { type: "application/json" });
-    const url = URL.createObjectURL(blob);
-    const a = h("a", { href: url, download: "gateway-config.json" });
+    // the real gateway.toml from disk — comments and all
+    const tok = getToken();
+    const headers = {};
+    if (tok) headers["Authorization"] = "Bearer " + tok;
+    const r = await fetch("/admin/api/config/export", { headers });
+    if (!r.ok) {
+      toast(await r.text(), "bad");
+      return;
+    }
+    const url = URL.createObjectURL(await r.blob());
+    const a = h("a", { href: url, download: "gateway.toml" });
     document.body.appendChild(a);
     a.click();
     a.remove();
     URL.revokeObjectURL(url);
   }
-  const fileIn = h("input", { type: "file", accept: ".json,application/json", style: "display:none" });
+  const fileIn = h("input", { type: "file", accept: ".toml,.json,application/json", style: "display:none" });
   fileIn.addEventListener("change", async () => {
     const f = fileIn.files[0];
     if (!f) return;
     try {
-      const cfg = JSON.parse(await f.text());
-      await api.putConfig(cfg);
+      const text = await f.text();
+      if (f.name.endsWith(".json")) {
+        await api.putConfig(JSON.parse(text)); // legacy JSON export
+      } else {
+        await postRaw("/config/import", text); // gateway.toml — validated + hot-reloaded
+      }
       toast(t("toast.imported"), "good");
     } catch (e) {
       toast(String(e.message || e), "bad");
@@ -503,6 +514,29 @@ export async function renderSettings() {
     fileIn.value = "";
   });
 
+  const restartBtn = h("button", { class: "btn danger" }, "⟳ " + t("settings.restart"));
+  restartBtn.addEventListener("click", async () => {
+    if (!(await confirmDialog(t("settings.restartConfirm")))) return;
+    restartBtn.disabled = true;
+    try {
+      await api.restart();
+      toast(t("settings.restarting"), "good");
+      // the gateway comes back on the same port — reload once it answers
+      const poll = setInterval(async () => {
+        try {
+          await api.health();
+          clearInterval(poll);
+          location.reload();
+        } catch {
+          /* still restarting */
+        }
+      }, 1000);
+    } catch (e) {
+      toast(String(e.message || e), "bad");
+      restartBtn.disabled = false;
+    }
+  });
+
   mount(
     root,
     h(
@@ -623,7 +657,9 @@ export async function renderSettings() {
         { class: "flex wrap" },
         h("button", { class: "btn", onClick: exportConfig }, t("settings.export")),
         h("button", { class: "btn", onClick: () => fileIn.click() }, t("settings.import")),
-        fileIn
+        fileIn,
+        h("div", { class: "grow" }),
+        restartBtn
       )
     )
   );