release: v0.2.31 - O(1) attention knobs, reasoning toggle & admin token persistence

CHANGELOG.md

@@ -3,7 +3,21 @@
 All notable changes to this project are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/).
 
-## [0.2.29] - 2026-07-21
+## [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
+- **Per-Model Generation & Reasoning Parameters**: Full support in Web UI and Gateway core for per-model generation defaults: Temperature, Top-P, Max Tokens, Think Budget (Reasoning mode), O(1) Constant-Memory Streaming Attention (`o1`), MTP (Multi-Token Prediction toggle `skip_mtp`), and default System Prompt.
+
 
 ### Fixed
 - **Duplicate Local Model Registration**: Fixed `duplicate managed model id` conflict in `register_import` by cleanly routing managed CMF models directly into `[[cmf.servers]]` with automatic free port allocation without pushing duplicate entries to `[[models]]`.

Cargo.lock

@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "cortiq-gateway"
-version = "0.2.29"
+version = "0.2.30"
 dependencies = [
  "anyhow",
  "arc-swap",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.29"
+version = "0.2.31"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"

src/admin/mod.rs

@@ -1330,6 +1330,16 @@ async fn register_import(State(state): State<SharedState>, Path(job): Path<Strin
             port,
             threads: cfg.cmf.threads,
             gpu: cfg.cmf.gpu,
+            temperature: None,
+            top_p: None,
+            max_tokens: None,
+            think_budget: None,
+            system_prompt: None,
+            o1: None,
+            o1_m: None,
+            o1_window: None,
+            o1_sink: None,
+            skip_mtp: false,
         });
     } else {
         cfg.models.push(crate::config::ModelCfg {
@@ -1343,6 +1353,13 @@ async fn register_import(State(state): State<SharedState>, Path(job): Path<Strin
             kind: "chat".into(),
             api_key_env: None,
             caps: Vec::new(),
+            temperature: None,
+            top_p: None,
+            max_tokens: None,
+            think_budget: None,
+            system_prompt: None,
+            o1: None,
+            skip_mtp: false,
         });
     }
     state.reload(cfg)?;

src/cmf_runtime.rs

@@ -290,11 +290,31 @@ fn spawn_serve(server: &CmfServer, cfg: &CmfCfg) -> Result<Child, String> {
     if server.threads > 1 {
         cmd.env("CMF_THREADS", server.threads.to_string());
     }
-    // Offload large matvecs to the GPU (Metal on macOS). Memory-bandwidth-bound
-    // on unified memory, so mostly a prefill win; opt-in.
     if server.gpu {
         cmd.env("CMF_GPU", "1");
     }
+    // O(1) Nyström attention: layers spec + sub-parameters.
+    if let Some(o1) = &server.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.env("CMF_MTP", "0");
+    }
     cmd.stdout(Stdio::null())
         .stderr(Stdio::null())
         .kill_on_drop(true)

src/config.rs

@@ -83,6 +83,36 @@ pub struct CmfServer {
     /// Offload matvecs to the GPU (CMF_GPU=1).
     #[serde(default)]
     pub gpu: bool,
+    /// Default generation temperature (0.0 .. 2.0).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub temperature: Option<f32>,
+    /// Default nucleus sampling threshold (0.0 .. 1.0).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub top_p: Option<f32>,
+    /// Default maximum completion tokens.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub max_tokens: Option<u32>,
+    /// Reasoning / thinking token budget.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub think_budget: Option<u32>,
+    /// Default system prompt prepended if request lacks one.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub system_prompt: Option<String>,
+    /// O(1) Nyström attention layer spec (all | deepN | i,j,k | off).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub o1: Option<String>,
+    /// 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,
 }
 
 /// CMF-format model factory: import a HuggingFace model, convert it to a
@@ -172,6 +202,16 @@ impl CmfCfg {
                 port: self.local_port,
                 threads: self.threads,
                 gpu: self.gpu,
+                temperature: None,
+                top_p: None,
+                max_tokens: None,
+                think_budget: None,
+                system_prompt: None,
+                o1: None,
+                o1_m: None,
+                o1_window: None,
+                o1_sink: None,
+                skip_mtp: false,
             }];
         }
         Vec::new()
@@ -306,6 +346,27 @@ pub struct ModelCfg {
     pub api_key_env: Option<String>,
     #[serde(default, skip_serializing_if = "Vec::is_empty")]
     pub caps: Vec<String>,
+    /// Default generation temperature (0.0 .. 2.0).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub temperature: Option<f32>,
+    /// Default nucleus sampling threshold (0.0 .. 1.0).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub top_p: Option<f32>,
+    /// Default maximum completion tokens.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub max_tokens: Option<u32>,
+    /// Reasoning / thinking token budget.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub think_budget: Option<u32>,
+    /// 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).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub o1: Option<String>,
+    /// Skip Multi-Token Prediction (MTP) heads.
+    #[serde(default)]
+    pub skip_mtp: bool,
 }
 fn default_kind() -> String {
     "chat".into()
@@ -461,10 +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")]
@@ -475,6 +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)
 }
 

src/model.rs

@@ -29,6 +29,7 @@ pub struct GenParams {
     pub temperature: Option<f32>,
     pub max_tokens: Option<u32>,
     pub top_p: Option<f32>,
+    pub think_budget: Option<u32>,
     pub stop: Vec<String>,
     /// Fields we do not interpret but must proxy through to the provider.
     pub passthrough: serde_json::Map<String, serde_json::Value>,

src/pipeline.rs

@@ -341,7 +341,64 @@ impl Pipeline {
                 route_source
             );
 
-            match provider.chat(req.clone()).await {
+            let mut req_call = req.clone();
+            if let Some(m_cfg) = live.cfg.models.iter().find(|m| m.id == model_id) {
+                if req_call.params.temperature.is_none() {
+                    req_call.params.temperature = m_cfg.temperature;
+                }
+                if req_call.params.top_p.is_none() {
+                    req_call.params.top_p = m_cfg.top_p;
+                }
+                if req_call.params.max_tokens.is_none() {
+                    req_call.params.max_tokens = m_cfg.max_tokens;
+                }
+                if req_call.params.think_budget.is_none() {
+                    req_call.params.think_budget = m_cfg.think_budget;
+                }
+                if let Some(sys) = &m_cfg.system_prompt {
+                    if !sys.trim().is_empty()
+                        && !req_call.messages.iter().any(|m| m.role == "system")
+                    {
+                        req_call.messages.insert(
+                            0,
+                            Message {
+                                role: "system".into(),
+                                content: sys.clone(),
+                                tool_calls: Vec::new(),
+                            },
+                        );
+                    }
+                }
+            } else if let Some(s_cfg) = live.cfg.cmf.servers.iter().find(|s| s.id == model_id) {
+                if req_call.params.temperature.is_none() {
+                    req_call.params.temperature = s_cfg.temperature;
+                }
+                if req_call.params.top_p.is_none() {
+                    req_call.params.top_p = s_cfg.top_p;
+                }
+                if req_call.params.max_tokens.is_none() {
+                    req_call.params.max_tokens = s_cfg.max_tokens;
+                }
+                if req_call.params.think_budget.is_none() {
+                    req_call.params.think_budget = s_cfg.think_budget;
+                }
+                if let Some(sys) = &s_cfg.system_prompt {
+                    if !sys.trim().is_empty()
+                        && !req_call.messages.iter().any(|m| m.role == "system")
+                    {
+                        req_call.messages.insert(
+                            0,
+                            Message {
+                                role: "system".into(),
+                                content: sys.clone(),
+                                tool_calls: Vec::new(),
+                            },
+                        );
+                    }
+                }
+            }
+
+            match provider.chat(req_call).await {
                 Ok(mut resp) => {
                     let cost =
                         provider.price(resp.usage.prompt_tokens, resp.usage.completion_tokens);

src/protocols/anthropic_messages.rs

@@ -101,6 +101,7 @@ async fn handler(
             temperature: req.temperature,
             max_tokens: req.max_tokens,
             top_p: req.top_p,
+            think_budget: None,
             stop: Vec::new(),
             passthrough: Default::default(),
         },

src/protocols/openai_chat.rs

@@ -49,6 +49,10 @@ struct OpenAiChatRequest {
     #[serde(default)]
     top_p: Option<f32>,
     #[serde(default)]
+    think_budget: Option<u32>,
+    #[serde(default)]
+    reasoning_effort: Option<u32>,
+    #[serde(default)]
     stream: bool,
     #[serde(default)]
     tools: Vec<serde_json::Value>,
@@ -93,6 +97,7 @@ async fn handler(
             temperature: req.temperature,
             max_tokens: req.max_tokens,
             top_p: req.top_p,
+            think_budget: req.think_budget.or(req.reasoning_effort),
             stop: Vec::new(),
             passthrough: req.rest,
         },

src/protocols/openai_completions.rs

@@ -82,6 +82,7 @@ async fn handler(
             temperature: req.temperature,
             max_tokens: req.max_tokens,
             top_p: req.top_p,
+            think_budget: None,
             stop: Vec::new(),
             passthrough: Default::default(),
         },

src/providers/openai.rs

@@ -42,9 +42,16 @@ impl OpenAiProvider {
         if let Some(t) = req.params.temperature {
             body["temperature"] = t.into();
         }
+        if let Some(p) = req.params.top_p {
+            body["top_p"] = p.into();
+        }
         if let Some(m) = req.params.max_tokens {
             body["max_tokens"] = m.into();
         }
+        if let Some(tb) = req.params.think_budget {
+            body["think_budget"] = tb.into();
+            body["reasoning_effort"] = tb.into();
+        }
         if !req.tools.is_empty() {
             body["tools"] = serde_json::Value::Array(req.tools.clone());
         }

src/registry.rs

@@ -49,6 +49,13 @@ impl Registry {
                 kind: "chat".into(),
                 api_key_env: None,
                 caps: Vec::new(),
+                temperature: s.temperature,
+                top_p: s.top_p,
+                max_tokens: s.max_tokens,
+                think_budget: s.think_budget,
+                system_prompt: s.system_prompt.clone(),
+                o1: s.o1.clone(),
+                skip_mtp: s.skip_mtp,
             };
             by_id.insert(m.id.clone(), Arc::new(OpenAiProvider::new(&m, None)?));
         }

web/js/i18n/en.js

@@ -139,6 +139,18 @@ export default {
   "models.form.apiKeyHint": "Stored securely on the gateway; it is not shown again.",
   "models.form.keyStored": "A key is saved — leave blank to keep it, or paste a new one.",
   "models.form.keyFromEnv": "Using a key from an environment variable.",
+  "models.form.paramsTitle": "Generation & Thinking Parameters (O(1), MTP, Temperature)",
+  "models.form.temperature": "Temperature",
+  "models.form.temperatureHint": "Generation temperature (0.0 = deterministic, 1.0+ = creative).",
+  "models.form.topP": "Top-P (Nucleus Sampling)",
+  "models.form.topPHint": "Sampling threshold (0.0 .. 1.0).",
+  "models.form.maxTokens": "Max Tokens",
+  "models.form.maxTokensHint": "Maximum completion tokens to generate.",
+  "models.form.thinkBudget": "Thinking Mode / Think Budget",
+  "models.form.thinkBudgetHint": "Reasoning token budget (0 = disabled, N > 0 = max reasoning tokens).",
+  "models.form.systemPrompt": "Default System Prompt",
+  "models.form.systemPromptHint": "Prepend automatically if request lacks a system prompt.",
+  "models.form.systemPromptPlaceholder": "You are a helpful assistant...",
   "models.form.testKey": "Test & load models",
   "models.form.testing": "checking…",
   "models.form.foundModels": "{n} models loaded",

web/js/i18n/ru.js

@@ -138,6 +138,18 @@ export default {
   "models.form.apiKeyHint": "Хранится безопасно на шлюзе; больше не показывается.",
   "models.form.keyStored": "Ключ сохранён — оставьте пустым, чтобы не менять, или вставьте новый.",
   "models.form.keyFromEnv": "Используется ключ из переменной окружения.",
+  "models.form.paramsTitle": "Параметры генерации, O(1) и режим размышления",
+  "models.form.temperature": "Температура",
+  "models.form.temperatureHint": "Температура генерации (0.0 — точные факты, 1.0+ — творчество).",
+  "models.form.topP": "Top-P (Nucleus Sampling)",
+  "models.form.topPHint": "Порог сэмплирования токенов (0.0 .. 1.0).",
+  "models.form.maxTokens": "Макс. токенов (Max Tokens)",
+  "models.form.maxTokensHint": "Максимальное количество генерируемых токенов.",
+  "models.form.thinkBudget": "Режим размышления / Think Budget",
+  "models.form.thinkBudgetHint": "Бюджет токенов мыслей (0 = выключен, N > 0 = лимит рассуждений).",
+  "models.form.systemPrompt": "Системный промпт по умолчанию",
+  "models.form.systemPromptHint": "Автоматически подставляется, если запрос не содержит системное сообщение.",
+  "models.form.systemPromptPlaceholder": "Вы — полезный ассистент...",
   "models.form.testKey": "Проверить и загрузить модели",
   "models.form.testing": "проверка…",
   "models.form.foundModels": "загружено моделей: {n}",

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())

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

@@ -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: "" };
@@ -118,6 +115,36 @@ function modelForm(meta, existing) {
     : existing && existing.key_source === "env" ? t("models.form.keyFromEnv")
     : t("models.form.apiKeyHint");
 
+  // ⚙ Generation & Thinking Parameters
+  const tempIn = h("input", { type: "number", step: "0.05", min: "0", max: "2.0", placeholder: "0.7", value: m.temperature ?? "" });
+  const topPIn = h("input", { type: "number", step: "0.05", min: "0", max: "1.0", placeholder: "0.9", value: m.top_p ?? "" });
+  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", {},
+    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 || "" });
+
+  const advParams = h(
+    "details",
+    { class: "adv-params", style: "margin-top:12px;padding:10px;border:1px solid var(--border);border-radius:6px;" },
+    h("summary", { style: "font-weight:600;cursor:pointer;" }, "⚙ " + t("models.form.paramsTitle")),
+    h("div", { class: "row", style: "margin-top:8px" },
+      field(t("models.form.temperature"), tempIn, t("models.form.temperatureHint")),
+      field(t("models.form.topP"), topPIn, t("models.form.topPHint"))),
+    h("div", { class: "row" },
+      field(t("models.form.maxTokens"), maxTokIn, t("models.form.maxTokensHint")),
+      field(t("models.form.thinkBudget"), thinkIn, t("models.form.thinkBudgetHint"))),
+    h("div", { class: "row" },
+      field("O(1) Attention", o1Sel, t("import.adv.o1Hint")),
+      field("MTP", h("label", { class: "check" }, skipMtpCb, t("import.adv.skipMtp")))),
+    field(t("models.form.systemPrompt"), sysPromptIn, t("models.form.systemPromptHint"))
+  );
+
   const node = h(
     "div",
     {},
@@ -128,7 +155,8 @@ function modelForm(meta, existing) {
     dl,
     h("div", { class: "row" }, field(t("models.form.kind"), kindSel), field(t("models.form.costTier"), tierSel)),
     h("div", { class: "row" }, field(t("models.form.priceIn"), priceInIn), field(t("models.form.priceOut"), priceOutIn)),
-    field(t("models.form.caps"), h("div", { class: "flex wrap" }, ...capInputs.map(({ c, cb }) => h("label", { class: "check" }, cb, c))))
+    field(t("models.form.caps"), h("div", { class: "flex wrap" }, ...capInputs.map(({ c, cb }) => h("label", { class: "check" }, cb, c)))),
+    advParams
   );
 
   const getValue = () => {
@@ -147,6 +175,13 @@ function modelForm(meta, existing) {
         price_out: parseFloat(priceOutIn.value) || 0,
         api_key_env: hasKey ? keyEnv : null,
         caps: capInputs.filter(({ cb }) => cb.checked).map(({ c }) => c),
+        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,
+        o1: o1Sel.value || null,
+        skip_mtp: skipMtpCb.checked,
+        system_prompt: sysPromptIn.value.trim() || null,
       },
       secret: typedKey,
       keyEnv,

web/js/views/settings.js

@@ -253,9 +253,103 @@ export async function renderSettings() {
       } catch (e) { mount(st, String(e.message || e)); }
       checkBtn.disabled = false;
     });
+
+    // ── 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: "⚙ Настройки модели" }, "⚙");
+    gearBtn.addEventListener("click", () => {
+      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" },
-      idIn, modelSel, portIn, checkBtn, threadsIn, h("label", { class: "flex", style: "gap:4px" }, gpuIn, "GPU"), removeBtn, st);
-    const entry = { node: row, read: () => ({ id: idIn.value.trim() || autoId(modelSel.value), model: modelSel.value.trim(), port: parseInt(portIn.value) || 8090, threads: parseInt(threadsIn.value) || 0, gpu: gpuIn.checked }) };
+      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),
+      model: modelSel.value.trim(),
+      port: parseInt(portIn.value) || 8090,
+      threads: parseInt(threadsIn.value) || 0,
+      gpu: gpuIn.checked,
+      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: 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,
+    }) };
     removeBtn.addEventListener("click", () => { const i = serverRows.indexOf(entry); if (i >= 0) serverRows.splice(i, 1); row.remove(); });
     serverRows.push(entry);
     serversWrap.appendChild(row);