release: v0.2.32 mobile admin console

CHANGELOG.md

@@ -3,6 +3,26 @@
 All notable changes to this project are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/).
 
+## [0.2.32] - 2026-07-22
+
+### Added
+- **Responsive mobile admin console**: Added a hamburger navigation drawer, touch-friendly controls, phone-sized forms and cards, scrollable tables, compact toolbars, safe-area support, and mobile bottom-sheet dialogs across the admin interface.
+- **Accessible mobile interactions**: Navigation and dialogs now support backdrop dismissal, Escape-key closing, reduced-motion preferences, and explicit accessibility attributes.
+
+### Fixed
+- **Add model dialog**: Restored the missing `opt` helper import that prevented the Add model button from opening its form.
+- **Local model settings on phones**: Reflowed managed CMF server controls to avoid clipped fields and actions on narrow screens.
+
+## [0.2.31] - 2026-07-22
+
+### Added
+- **Structured O(1) Nyström Attention & Reasoning Control**: Enhanced settings drawer with structured parameter sections for O(1) Nyström Streaming Attention (`o1_m`, `o1_window`, `o1_sink`), Generation (Temp, Top-P, MaxTokens, System Prompt), Reasoning ("Disable reasoning" toggle mapping to `think_budget = 0` for Qwen3/3.5 models), and Runtime (`skip_mtp` via `CMF_MTP=0`).
+- **Persistent Admin Token Configuration**: Support for explicit `token` field in `config/gateway.toml` under `[admin]` block to prevent authorization invalidation across restarts.
+
+### Fixed
+- **JavaScript UI Helper Restoration**: Restored `opt(...)` helper in `web/js/ui.js` and `web/js/views/import.js` to ensure HF model import modal options render smoothly.
+- **Engine Command Flag Accuracy**: Fixed `CMF_MTP=0` environment flag pass-through for `cortiq serve` processes.
+
 ## [0.2.30] - 2026-07-22
 
 ### Added

Cargo.lock

@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "cortiq-gateway"
-version = "0.2.30"
+version = "0.2.32"
 dependencies = [
  "anyhow",
  "arc-swap",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.30"
+version = "0.2.32"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"

src/admin/mod.rs

@@ -1336,6 +1336,9 @@ async fn register_import(State(state): State<SharedState>, Path(job): Path<Strin
             think_budget: None,
             system_prompt: None,
             o1: None,
+            o1_m: None,
+            o1_window: None,
+            o1_sink: None,
             skip_mtp: false,
         });
     } else {

src/cmf_runtime.rs

@@ -293,13 +293,27 @@ fn spawn_serve(server: &CmfServer, cfg: &CmfCfg) -> Result<Child, String> {
     if server.gpu {
         cmd.env("CMF_GPU", "1");
     }
+    // O(1) Nyström attention: layers spec + sub-parameters.
     if let Some(o1) = &server.o1 {
-        if !o1.trim().is_empty() && o1 != "off" {
-            cmd.arg("--o1").arg(o1);
+        let s = o1.trim();
+        if !s.is_empty() {
+            // Pass even "off" so it explicitly overrides a file converter hint.
+            cmd.arg("--o1").arg(s);
         }
     }
+    if let Some(m) = server.o1_m {
+        cmd.arg("--o1-m").arg(m.to_string());
+    }
+    if let Some(w) = server.o1_window {
+        cmd.arg("--o1-window").arg(w.to_string());
+    }
+    if let Some(sink) = server.o1_sink {
+        cmd.arg("--o1-sink").arg(sink.to_string());
+    }
+    // MTP (Multi-Token Prediction) speculative decoding: the engine reads
+    // CMF_MTP env; "0" disables.  There is no CLI flag for this.
     if server.skip_mtp {
-        cmd.arg("--skip-mtp");
+        cmd.env("CMF_MTP", "0");
     }
     cmd.stdout(Stdio::null())
         .stderr(Stdio::null())

src/config.rs

@@ -98,10 +98,19 @@ pub struct CmfServer {
     /// Default system prompt prepended if request lacks one.
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub system_prompt: Option<String>,
-    /// O(1) constant-memory streaming attention hint (all, deep, custom, off).
+    /// O(1) Nyström attention layer spec (all | deepN | i,j,k | off).
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub o1: Option<String>,
-    /// Skip Multi-Token Prediction (MTP) heads.
+    /// O(1) landmark budget (default 32; ≥4).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub o1_m: Option<u32>,
+    /// O(1) exact-window width (default 128).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub o1_window: Option<u32>,
+    /// O(1) permanent exact sink keys (default 4, StreamingLLM discipline).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub o1_sink: Option<u32>,
+    /// Disable Multi-Token Prediction speculative decoding (CMF_MTP=0).
     #[serde(default)]
     pub skip_mtp: bool,
 }
@@ -199,6 +208,9 @@ impl CmfCfg {
                 think_budget: None,
                 system_prompt: None,
                 o1: None,
+                o1_m: None,
+                o1_window: None,
+                o1_sink: None,
                 skip_mtp: false,
             }];
         }
@@ -510,10 +522,12 @@ pub struct AdminCfg {
     /// Whether the admin panel and admin API (`/admin`, `/admin/api/*`) are enabled.
     #[serde(default = "default_admin_enabled")]
     pub enabled: bool,
-    /// Name of the env variable holding the admin token. If unset (or empty),
-    /// a token is generated at startup and printed to the log.
+    /// Name of the env variable holding the admin token.
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub token_env: Option<String>,
+    /// Persistent admin token configured directly in toml.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub token: Option<String>,
     /// Optional separate bind address for the admin surface (e.g. `127.0.0.1:9001`).
     /// If unset, the admin interface lives on the main `listen` address under `/admin`.
     #[serde(default, skip_serializing_if = "Option::is_none")]
@@ -524,6 +538,7 @@ impl Default for AdminCfg {
         Self {
             enabled: default_admin_enabled(),
             token_env: None,
+            token: None,
             listen: None,
         }
     }

src/main.rs

@@ -61,6 +61,11 @@ fn resolve_admin_token(cfg: &Config, args: &Args) -> (String, bool) {
             return (t.clone(), false);
         }
     }
+    if let Some(t) = &cfg.admin.token {
+        if !t.is_empty() {
+            return (t.clone(), false);
+        }
+    }
     (admin::random_token(24), true)
 }
 

web/css/styles.css

@@ -397,3 +397,170 @@ tbody tr:hover td { background: var(--hover); }
 .mono.kv { display: flex; gap: 6px; padding: 1px 0; white-space: normal; overflow-wrap: anywhere; word-break: break-word; }
 .mono.kv .kv-k { color: var(--muted, #9aa4b2); flex: 0 0 auto; }
 .mono.kv .kv-v { font-weight: 600; overflow-wrap: anywhere; word-break: break-word; min-width: 0; }
+
+/* ---- responsive shell + touch layout ----------------------------------- */
+.menu-toggle, .nav-close, .mobile-nav-backdrop { display: none; }
+.hamburger { width: 18px; display: flex; flex-direction: column; gap: 4px; }
+.hamburger i { display: block; height: 2px; border-radius: 2px; background: currentColor; }
+body.modal-open { overflow: hidden; }
+
+@media (max-width: 980px) {
+  .app { display: block; min-height: 100dvh; }
+  .main { min-height: 100dvh; }
+  .menu-toggle { display: inline-flex; flex: 0 0 auto; }
+  .nav-close { display: inline-flex; margin-left: auto; flex: 0 0 auto; font-size: 24px; line-height: 1; }
+  .brand-copy { min-width: 0; }
+
+  .sidebar {
+    display: flex;
+    position: fixed;
+    inset: 0 auto 0 0;
+    width: min(84vw, 310px);
+    height: 100dvh;
+    padding: max(18px, env(safe-area-inset-top)) 14px max(14px, env(safe-area-inset-bottom));
+    z-index: 70;
+    box-shadow: 18px 0 45px rgba(0, 0, 0, .42);
+    transform: translateX(-104%);
+    visibility: hidden;
+    transition: transform .22s ease, visibility 0s linear .22s;
+    overflow-y: auto;
+  }
+  .app.nav-open .sidebar {
+    transform: translateX(0);
+    visibility: visible;
+    transition: transform .22s ease;
+  }
+  .mobile-nav-backdrop {
+    display: block;
+    position: fixed;
+    inset: 0;
+    z-index: 65;
+    width: 100%;
+    height: 100%;
+    border: 0;
+    background: rgba(3, 7, 18, .62);
+    opacity: 0;
+    visibility: hidden;
+    pointer-events: none;
+    transition: opacity .22s ease, visibility 0s linear .22s;
+  }
+  .app.nav-open .mobile-nav-backdrop {
+    opacity: 1;
+    visibility: visible;
+    pointer-events: auto;
+    transition: opacity .22s ease;
+  }
+  body.mobile-nav-open { overflow: hidden; }
+
+  .topbar { padding: 10px 18px; min-height: 58px; gap: 10px; }
+  .topbar .title { min-width: 0; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }
+  .topbar .right { gap: 8px; min-width: 0; }
+  .content { max-width: none; padding: 22px 20px 52px; }
+}
+
+@media (max-width: 720px) {
+  body { font-size: 14px; }
+  .status-pills { display: none; }
+  .topbar { padding: 9px 12px; }
+  .content { padding: 18px 14px 42px; }
+
+  .page-head { margin-bottom: 16px; }
+  .page-head > .flex { align-items: stretch; flex-direction: column; }
+  .page-head > .flex > .btn { width: 100%; }
+  .page-head p { line-height: 1.45; }
+
+  .card { padding: 15px; margin-bottom: 14px; border-radius: 12px; }
+  .card .card-head { align-items: flex-start; flex-wrap: wrap; }
+  .card .card-head .right { width: 100%; margin-left: 0; flex-wrap: wrap; }
+  .grid { gap: 14px; }
+  .kpis { gap: 10px; margin-bottom: 14px; }
+  .kpi { padding: 12px; border-radius: 11px; }
+  .kpi .big { font-size: 21px; }
+
+  .row { display: grid; grid-template-columns: minmax(0, 1fr); gap: 0; }
+  .row > * { min-width: 0; width: 100%; }
+  input, select, textarea { min-height: 44px; font-size: 16px; }
+  input[type="checkbox"], input[type="radio"] { min-height: 0; }
+  .check { min-height: 36px; margin-bottom: 8px; }
+  .btn, .icon-btn { min-height: 44px; }
+  .btn { padding: 10px 14px; }
+  .btn.sm, .btn.small { min-height: 38px; padding: 8px 11px; }
+
+  .table-wrap {
+    width: 100%;
+    overflow-x: auto;
+    overscroll-behavior-x: contain;
+    -webkit-overflow-scrolling: touch;
+    scrollbar-width: thin;
+  }
+  .table-wrap table { min-width: max-content; }
+  th, td { padding: 10px; }
+
+  .tierrow { align-items: flex-start; flex-direction: column; gap: 8px; }
+  .tierrow .tname { width: auto; }
+  .chips { width: 100%; }
+  .togglerow { align-items: flex-start; }
+
+  .pg { gap: 14px; }
+  .routecard .kv { flex-wrap: wrap; }
+  .routecard .kv .v { max-width: 100%; overflow-wrap: anywhere; }
+  .answer { padding: 12px; }
+  .seg { max-width: 100%; overflow-x: auto; }
+  .seg button { min-height: 40px; white-space: nowrap; }
+
+  .hf-grid { grid-template-columns: 1fr; max-height: 56dvh; }
+  .job-head, .actions { align-items: stretch; flex-wrap: wrap; }
+  .actions .btn { flex: 1 1 150px; }
+  .key-row { flex-direction: column; }
+  .key-row .btn { width: 100%; }
+  .cmf-server-row { align-items: stretch !important; padding: 10px; border: 1px solid var(--border-soft); border-radius: 10px; }
+  .cmf-server-row > input, .cmf-server-row > select { width: 100% !important; min-width: 0 !important; flex: 1 1 100% !important; }
+  .cmf-server-row > .btn { flex: 1 1 calc(50% - 6px); }
+  .cmf-server-row > .small { flex: 1 1 100%; }
+
+  .modal-backdrop { align-items: flex-end; padding: 8px 0 0; }
+  .modal {
+    max-width: none;
+    max-height: calc(100dvh - 8px);
+    overflow-y: auto;
+    padding: 18px 15px max(14px, env(safe-area-inset-bottom));
+    border-radius: 18px 18px 0 0;
+  }
+  .modal .modal-foot {
+    position: sticky;
+    bottom: calc(-1 * max(14px, env(safe-area-inset-bottom)));
+    margin: 12px -15px 0;
+    padding: 12px 15px max(14px, env(safe-area-inset-bottom));
+    background: color-mix(in srgb, var(--card) 94%, transparent);
+    backdrop-filter: blur(10px);
+    border-top: 1px solid var(--border-soft);
+  }
+  .modal .modal-foot .btn { flex: 1; }
+
+  .toasts { left: 12px; right: 12px; bottom: max(12px, env(safe-area-inset-bottom)); }
+  .toast { min-width: 0; width: 100%; }
+  .login-wrap { align-items: flex-start; padding: max(20px, env(safe-area-inset-top)) 14px; }
+  .login-card { padding: 22px 18px; margin-top: 8dvh; }
+}
+
+@media (max-width: 480px) {
+  .topbar .title { font-size: 14px; }
+  .topbar .right { gap: 6px; }
+  .lang-select { width: 54px; min-height: 44px; padding: 6px; }
+  .icon-btn { width: 42px; height: 42px; }
+  .kpis { grid-template-columns: repeat(2, minmax(0, 1fr)); }
+  .kpi .lbl { line-height: 1.25; }
+  .barlist .b { grid-template-columns: minmax(0, 1fr) auto; gap: 6px 10px; }
+  .barlist .b .track { grid-column: 1 / -1; grid-row: 2; }
+  .barlist .b .val { min-width: 0; }
+  .empty { padding: 28px 12px; }
+}
+
+@media (max-width: 360px) {
+  .topbar .title { display: none; }
+  .kpis { grid-template-columns: 1fr; }
+}
+
+@media (prefers-reduced-motion: reduce) {
+  .sidebar, .mobile-nav-backdrop { transition: none; }
+}

web/js/app.js

@@ -28,6 +28,17 @@ export const appState = { meta: null, health: null, version: "" };
 // allaigate site — where router keys are issued and topped up
 export const SITE_URL = "https://api.allaigate.com/";
 
+let mobileNavOpen = false;
+
+function setMobileNav(open) {
+  mobileNavOpen = !!open;
+  const app = document.querySelector(".app");
+  if (app) app.classList.toggle("nav-open", mobileNavOpen);
+  document.body.classList.toggle("mobile-nav-open", mobileNavOpen);
+  const toggle = document.querySelector(".menu-toggle");
+  if (toggle) toggle.setAttribute("aria-expanded", String(mobileNavOpen));
+}
+
 function currentRoute() {
   const id = location.hash.replace(/^#\/?/, "") || "dashboard";
   return ROUTES.find((r) => r.id === id) || ROUTES[0];
@@ -42,17 +53,18 @@ const FAVICON =
 function sidebar(activeId) {
   return h(
     "aside",
-    { class: "sidebar", id: "sidebar" },
+    { class: "sidebar", id: "sidebar", "aria-label": "Main navigation" },
     h(
       "div",
       { class: "brand" },
       h("img", { src: FAVICON, alt: "" }),
-      h("div", {}, h("b", {}, "allaigate"), h("div", { class: "sub" }, t("brand.sub")))
+      h("div", { class: "brand-copy" }, h("b", {}, "allaigate"), h("div", { class: "sub" }, t("brand.sub"))),
+      h("button", { class: "icon-btn nav-close", type: "button", title: "Close menu", "aria-label": "Close menu", onClick: () => setMobileNav(false) }, "×")
     ),
     ...ROUTES.map((r) =>
       h(
         "a",
-        { class: "nav-item" + (r.id === activeId ? " active" : ""), href: "#/" + r.id },
+        { class: "nav-item" + (r.id === activeId ? " active" : ""), href: "#/" + r.id, onClick: () => setMobileNav(false) },
         h("span", { class: "ico" }, r.icon),
         t("nav." + r.id)
       )
@@ -85,7 +97,7 @@ function statusPills() {
     : t("status.checking");
   return h(
     "div",
-    { class: "flex" },
+    { class: "flex status-pills" },
     h(
       "span",
       { class: "pill" },
@@ -136,6 +148,19 @@ function topbar(activeId) {
   return h(
     "header",
     { class: "topbar" },
+    h(
+      "button",
+      {
+        class: "icon-btn menu-toggle",
+        type: "button",
+        title: "Menu",
+        "aria-label": "Open menu",
+        "aria-controls": "sidebar",
+        "aria-expanded": String(mobileNavOpen),
+        onClick: () => setMobileNav(!mobileNavOpen),
+      },
+      h("span", { class: "hamburger", "aria-hidden": "true" }, h("i"), h("i"), h("i"))
+    ),
     h("div", { class: "title" }, t("nav." + activeId)),
     h(
       "div",
@@ -175,12 +200,15 @@ async function renderView() {
 
 function renderShell() {
   const route = currentRoute();
+  mobileNavOpen = false;
+  document.body.classList.remove("mobile-nav-open");
   mount(
     document.getElementById("app"),
     h(
       "div",
       { class: "app" },
       sidebar(route.id),
+      h("button", { class: "mobile-nav-backdrop", type: "button", tabindex: "-1", "aria-label": "Close menu", onClick: () => setMobileNav(false) }),
       h("main", { class: "main" }, topbar(route.id), h("div", { class: "content", id: "view" }))
     )
   );
@@ -243,6 +271,12 @@ onLangChange(() => {
 window.addEventListener("hashchange", () => {
   if (document.querySelector(".app")) renderShell();
 });
+window.addEventListener("keydown", (e) => {
+  if (e.key === "Escape" && mobileNavOpen) setMobileNav(false);
+});
+window.addEventListener("resize", () => {
+  if (window.innerWidth > 980 && mobileNavOpen) setMobileNav(false);
+});
 setInterval(() => {
   if (document.querySelector(".app")) refreshHealth();
 }, 20000);

web/js/ui.js

@@ -23,6 +23,10 @@ export function clear(node) {
   while (node && node.firstChild) node.removeChild(node.firstChild);
 }
 
+export function opt(v, label, sel) {
+  return h("option", { value: v, selected: sel ? true : null }, label || v);
+}
+
 export function mount(node, ...children) {
   clear(node);
   for (const c of children.flat())
@@ -46,7 +50,14 @@ export function toast(msg, kind = "info", ms = 3200) {
 // Modal dialog. `body` is a DOM node; `onSave` returns a Promise; returns nothing.
 export function modal(title, body, onSave, saveLabel) {
   const backdrop = h("div", { class: "modal-backdrop" });
-  const close = () => backdrop.remove();
+  const onKeydown = (e) => {
+    if (e.key === "Escape") close();
+  };
+  const close = () => {
+    backdrop.remove();
+    document.body.classList.remove("modal-open");
+    document.removeEventListener("keydown", onKeydown);
+  };
   backdrop.addEventListener("click", (e) => {
     if (e.target === backdrop) close();
   });
@@ -73,6 +84,8 @@ export function modal(title, body, onSave, saveLabel) {
     )
   );
   backdrop.appendChild(card);
+  document.body.classList.add("modal-open");
+  document.addEventListener("keydown", onKeydown);
   document.body.appendChild(backdrop);
   return { close };
 }

web/js/views/import.js

@@ -2,7 +2,7 @@
 // live progress view. Search HF, pick quantization + advanced params, watch
 // the conversion (multiple in parallel, resumable across tab switches), then
 // register the result as a local model.
-import { h, mount, toast } from "../ui.js";
+import { h, mount, toast, opt } from "../ui.js";
 import { t } from "../i18n.js";
 import { api } from "../api.js";
 
@@ -31,9 +31,6 @@ function field(label, control, hint) {
   return h("label", { class: "field" }, h("span", {}, label), control,
     hint ? h("div", { class: "hint" }, hint) : null);
 }
-function opt(v, label, sel) {
-  return h("option", { value: v, selected: sel ? true : null }, label || v);
-}
 function fmtNum(n) {
   if (n == null) return "—";
   if (n >= 1e6) return (n / 1e6).toFixed(1) + "M";

web/js/views/models.js

@@ -1,5 +1,5 @@
 // Models — pool table with add/edit modal, probe, and per-model secret entry.
-import { h, mount, modal, toast, confirmDialog, money } from "../ui.js";
+import { h, mount, modal, toast, confirmDialog, money, opt } from "../ui.js";
 import { t } from "../i18n.js";
 import { api } from "../api.js";
 import { appState } from "../app.js";
@@ -7,9 +7,6 @@ import { appState } from "../app.js";
 function field(label, control, hint) {
   return h("label", { class: "field" }, h("span", {}, label), control, hint ? h("div", { class: "hint" }, hint) : null);
 }
-function opt(v, label, sel) {
-  return h("option", { value: v, selected: sel ? true : null }, label || v);
-}
 
 function keyBadge(src) {
   const map = { store: "store", env: "env", missing: "bad", none: "" };
@@ -124,10 +121,10 @@ function modelForm(meta, existing) {
   const maxTokIn = h("input", { type: "number", min: "1", placeholder: "2048", value: m.max_tokens ?? "" });
   const thinkIn = h("input", { type: "number", min: "0", placeholder: "1024", value: m.think_budget ?? "" });
   const o1Sel = h("select", {},
-    opt("", t("import.adv.auto")),
-    opt("all", "all — O(1) Attention"),
-    opt("deep", "deep — O(1) Deep"),
-    opt("off", "off — Standard"));
+    h("option", { value: "" }, t("import.adv.auto")),
+    h("option", { value: "all" }, "all — O(1) Attention"),
+    h("option", { value: "deep" }, "deep — O(1) Deep"),
+    h("option", { value: "off" }, "off — Standard"));
   if (m.o1) o1Sel.value = m.o1;
   const skipMtpCb = h("input", { type: "checkbox", checked: m.skip_mtp ? true : null });
   const sysPromptIn = h("textarea", { rows: 2, placeholder: t("models.form.systemPromptPlaceholder"), value: m.system_prompt || "" });

web/js/views/settings.js

@@ -253,36 +253,85 @@ export async function renderSettings() {
       } catch (e) { mount(st, String(e.message || e)); }
       checkBtn.disabled = false;
     });
-    // ⚙ Model Generation & Thinking Parameters drawer
-    const tempIn = h("input", { type: "number", step: "0.05", min: "0", max: "2.0", placeholder: "0.7", value: sv.temperature ?? "", style: "width:65px" });
-    const topPIn = h("input", { type: "number", step: "0.05", min: "0", max: "1.0", placeholder: "0.9", value: sv.top_p ?? "", style: "width:65px" });
-    const maxTokIn = h("input", { type: "number", min: "1", placeholder: "2048", value: sv.max_tokens ?? "", style: "width:80px" });
-    const thinkIn = h("input", { type: "number", min: "0", placeholder: "1024", value: sv.think_budget ?? "", style: "width:80px" });
-    const o1Sel = h("select", { style: "width:110px" },
-      opt("", "O(1) auto"),
-      opt("all", "O(1) all"),
-      opt("deep", "O(1) deep"),
-      opt("off", "O(1) off"));
-    if (sv.o1) o1Sel.value = sv.o1;
-    const skipMtpCb = h("input", { type: "checkbox", checked: sv.skip_mtp ? true : null });
-    const sysIn = h("input", { placeholder: t("models.form.systemPromptPlaceholder"), value: sv.system_prompt || "", style: "flex:1" });
 
-    const drawer = h("div", { class: "flex wrap gap-sm", style: "display:none;width:100%;margin-top:4px;padding:6px;background:var(--bg-subtle);border-radius:4px;align-items:center" },
-      h("span", { class: "small muted" }, "Temp:"), tempIn,
-      h("span", { class: "small muted" }, "Top-P:"), topPIn,
-      h("span", { class: "small muted" }, "MaxTokens:"), maxTokIn,
-      h("span", { class: "small muted" }, "ThinkBudget:"), thinkIn,
-      o1Sel,
-      h("label", { class: "check small" }, skipMtpCb, "Skip MTP"),
-      h("span", { class: "small muted" }, "System:"), sysIn
+    // ── O(1) Nyström Attention ──
+    // NOT a "reasoning mode". This is a memory-efficient streaming attention
+    // kernel (Nyström/landmark) that replaces standard KV-cache attention,
+    // giving O(1) memory per decode step instead of O(n).
+    const o1Sel = h("select", { style: "width:120px", title: "O(1) Nyström attention layer spec: which layers replace KV-cache with streaming Nyström attention" },
+      h("option", { value: "" }, "O(1) авто"),
+      h("option", { value: "all" }, "O(1) все слои"),
+      h("option", { value: "deep" }, "O(1) глубокие"),
+      h("option", { value: "off" }, "O(1) выкл."));
+    if (sv.o1) o1Sel.value = sv.o1;
+    const o1mIn = h("input", { type: "number", min: "4", placeholder: "32", value: sv.o1_m ?? "", style: "width:55px", title: "Landmark budget (≥4, default 32). More landmarks ≠ better: m=64 measured worse." });
+    const o1wIn = h("input", { type: "number", min: "1", placeholder: "128", value: sv.o1_window ?? "", style: "width:60px", title: "Exact-window width — main quality lever (default 128)" });
+    const o1sinkIn = h("input", { type: "number", min: "0", placeholder: "4", value: sv.o1_sink ?? "", style: "width:50px", title: "Permanent exact sink keys, StreamingLLM discipline (default 4)" });
+
+    // ── Generation parameters ──
+    const tempIn = h("input", { type: "number", step: "0.05", min: "0", max: "2.0", placeholder: "0.7", value: sv.temperature ?? "", style: "width:60px" });
+    const topPIn = h("input", { type: "number", step: "0.05", min: "0", max: "1.0", placeholder: "0.9", value: sv.top_p ?? "", style: "width:60px" });
+    const maxTokIn = h("input", { type: "number", min: "1", placeholder: "2048", value: sv.max_tokens ?? "", style: "width:75px" });
+    // think_budget = 0 means reasoning disabled (enable_thinking=false);
+    // null = model decides; N>0 = token budget for the <think> block.
+    const noThinkCb = h("input", { type: "checkbox", checked: (sv.think_budget === 0) ? true : null, title: "Отключить режим размышлений (think_budget=0, enable_thinking=false для Qwen3/3.5)" });
+    const thinkIn = h("input", { type: "number", min: "1", placeholder: "авто", value: (sv.think_budget && sv.think_budget > 0) ? sv.think_budget : "", style: "width:75px", title: "Бюджет токенов на размышления (think_budget). Пустое = модель решает сама." });
+    if (sv.think_budget === 0) thinkIn.disabled = true;
+    noThinkCb.addEventListener("change", () => {
+      thinkIn.disabled = noThinkCb.checked;
+      if (noThinkCb.checked) thinkIn.value = "";
+    });
+    const sysIn = h("input", { placeholder: "System prompt (optional)", value: sv.system_prompt || "", style: "flex:1;min-width:200px" });
+
+    // ── MTP (Multi-Token Prediction): speculative decoding, NOT reasoning ──
+    const skipMtpCb = h("input", { type: "checkbox", checked: sv.skip_mtp ? true : null, title: "Disable MTP speculative decoding (env CMF_MTP=0)" });
+
+    // ── Settings drawer ──
+    const drawerStyle = "display:none;width:100%;margin-top:6px;padding:10px 12px;background:var(--bg-subtle);border-radius:6px;border:1px solid var(--border)";
+    const groupStyle = "display:flex;flex-wrap:wrap;gap:8px;align-items:center;padding:4px 0";
+    const labelStyle = "font-size:11px;color:var(--text-muted);font-weight:600;text-transform:uppercase;letter-spacing:0.5px;width:100%;margin-bottom:2px";
+
+    const drawer = h("div", { style: drawerStyle },
+      // Group 1: O(1) Nyström Attention
+      h("div", { style: labelStyle }, "O(1) Nyström Attention"),
+      h("div", { style: groupStyle },
+        h("span", { class: "small muted" }, "Слои:"), o1Sel,
+        h("span", { class: "small muted" }, "m:"), o1mIn,
+        h("span", { class: "small muted" }, "Window:"), o1wIn,
+        h("span", { class: "small muted" }, "Sink:"), o1sinkIn
+      ),
+      h("hr", { style: "border:none;border-top:1px solid var(--border);margin:6px 0" }),
+      // Group 2: Generation
+      h("div", { style: labelStyle }, "Генерация"),
+      h("div", { style: groupStyle },
+        h("span", { class: "small muted" }, "Temp:"), tempIn,
+        h("span", { class: "small muted" }, "Top-P:"), topPIn,
+        h("span", { class: "small muted" }, "Max токенов:"), maxTokIn
+      ),
+      h("div", { style: groupStyle },
+        h("span", { class: "small muted" }, "System prompt:"), sysIn
+      ),
+      h("hr", { style: "border:none;border-top:1px solid var(--border);margin:6px 0" }),
+      // Group 3: Reasoning (thinking)
+      h("div", { style: labelStyle }, "Режим размышлений"),
+      h("div", { style: groupStyle },
+        h("label", { class: "check small", title: "Для моделей Qwen3/3.5: enable_thinking=false — модель отвечает напрямую без блока <think>" }, noThinkCb, "Отключить размышления"),
+        h("span", { class: "small muted" }, "Think budget:"), thinkIn
+      ),
+      h("hr", { style: "border:none;border-top:1px solid var(--border);margin:6px 0" }),
+      // Group 4: Runtime
+      h("div", { style: labelStyle }, "Runtime"),
+      h("div", { style: groupStyle },
+        h("label", { class: "check small", title: "MTP — Multi-Token Prediction (спекулятивное декодирование). Отключение замедляет генерацию, но стабилизирует output." }, skipMtpCb, "Отключить MTP")
+      )
     );
 
-    const gearBtn = h("button", { class: "btn small", type: "button", title: "⚙ " + t("models.form.paramsTitle") }, "⚙");
+    const gearBtn = h("button", { class: "btn small", type: "button", title: "⚙ Настройки модели" }, "⚙");
     gearBtn.addEventListener("click", () => {
-      drawer.style.display = drawer.style.display === "none" ? "flex" : "none";
+      drawer.style.display = drawer.style.display === "none" ? "block" : "none";
     });
 
-    const row = h("div", { class: "flex wrap", style: "gap:6px;align-items:center;margin:6px 0" },
+    const row = h("div", { class: "flex wrap cmf-server-row", style: "gap:6px;align-items:center;margin:6px 0" },
       idIn, modelSel, portIn, checkBtn, threadsIn, h("label", { class: "flex", style: "gap:4px" }, gpuIn, "GPU"), gearBtn, removeBtn, st, drawer);
     const entry = { node: row, read: () => ({
       id: idIn.value.trim() || autoId(modelSel.value),
@@ -293,8 +342,11 @@ export async function renderSettings() {
       temperature: tempIn.value !== "" ? parseFloat(tempIn.value) : null,
       top_p: topPIn.value !== "" ? parseFloat(topPIn.value) : null,
       max_tokens: maxTokIn.value !== "" ? parseInt(maxTokIn.value) : null,
-      think_budget: thinkIn.value !== "" ? parseInt(thinkIn.value) : null,
+      think_budget: noThinkCb.checked ? 0 : (thinkIn.value !== "" ? parseInt(thinkIn.value) : null),
       o1: o1Sel.value || null,
+      o1_m: o1mIn.value !== "" ? parseInt(o1mIn.value) : null,
+      o1_window: o1wIn.value !== "" ? parseInt(o1wIn.value) : null,
+      o1_sink: o1sinkIn.value !== "" ? parseInt(o1sinkIn.value) : null,
       skip_mtp: skipMtpCb.checked,
       system_prompt: sysIn.value.trim() || null,
     }) };