feat(import): O(1) attention options in Advanced (cortiq >= 0.2.0)

- New Advanced controls on the import page: O(1) attention spec (off / all /
  deep N / explicit layer list) plus the --o1-m / --o1-window / --o1-sink knobs
  with validated defaults (32 / 128 / 4) and explanatory hints.
- Backend passes --o1* to the native `cortiq convert`; fails fast with clear
  messages when combined with Python-only options, used on GGUF imports, or
  when the installed cortiq predates 0.2.0 (the hint needs the new runtime).
- The hint is recorded in the .cmf header (weights byte-identical); the runtime
  applies it at load. Verified end-to-end: converted a model with --o1 all and
  the runtime logged "o1 nystrom attention: 2/2 layer(s)".

Cargo.lock

@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "cortiq-gateway"
-version = "0.2.13"
+version = "0.2.15"
 dependencies = [
  "anyhow",
  "arc-swap",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.13"
+version = "0.2.15"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"

src/admin/mod.rs

@@ -165,7 +165,7 @@ pub fn api_routes(admin_token: String) -> Router<SharedState> {
             "/admin/api/secrets",
             get(list_secrets).put(set_secret).delete(clear_secret),
         )
-        .route("/admin/api/stats", get(get_stats))
+        .route("/admin/api/stats", get(get_stats).delete(clear_stats))
         .route("/admin/api/shadow", get(get_shadow))
         .route("/admin/api/hf/search", get(hf_search))
         .route("/admin/api/import", get(list_imports).post(start_import))
@@ -1197,6 +1197,13 @@ async fn get_stats(State(state): State<SharedState>, Query(q): Query<StatsQuery>
     ok(snap)
 }
 
+/// Clear all recorded stats/logs (in-memory aggregates, series, recent requests)
+/// and truncate the JSONL log — the dashboard "Clear logs" button.
+async fn clear_stats(State(state): State<SharedState>) -> ApiResult {
+    state.stats.clear();
+    ok(json!({ "ok": true }))
+}
+
 /// Self-warming shadow loop: per-task-type promotion state, Wilson-LB of the
 /// judged pass-rate, and whether the local model is serving it yet.
 async fn get_shadow(State(state): State<SharedState>) -> ApiResult {

src/cmf_runtime.rs

@@ -238,7 +238,7 @@ fn parse_ver(s: &str) -> (u32, u32, u32) {
     )
 }
 
-fn version_lt(a: &str, b: &str) -> bool {
+pub(crate) fn version_lt(a: &str, b: &str) -> bool {
     parse_ver(a) < parse_ver(b)
 }
 

src/import.rs

@@ -71,6 +71,20 @@ pub struct ImportParams {
     pub shard_max_gb: Option<f32>,
     #[serde(default)]
     pub skip_mtp: bool,
+    /// O(1) Nyström attention hint (native converter, cortiq ≥ 0.2.0):
+    /// `all` | `deepN` | `i,j,k`. Weights pass through unchanged — the runtime
+    /// reads the hint at load. Empty/None/"off" = exact attention.
+    #[serde(default)]
+    pub o1: Option<String>,
+    /// Landmark budget for the o1 hint (validated default 32).
+    #[serde(default)]
+    pub o1_m: Option<usize>,
+    /// Exact-window width for the o1 hint (validated default 128).
+    #[serde(default)]
+    pub o1_window: Option<usize>,
+    /// Permanent exact sink keys for the o1 hint (validated default 4).
+    #[serde(default)]
+    pub o1_sink: Option<usize>,
 }
 fn default_quant() -> String {
     "Q8_2F".into()
@@ -269,6 +283,34 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
             cfg.converter
         ));
     }
+    // O(1) attention hint — native-converter feature (cortiq ≥ 0.2.0). Fail fast
+    // with a clear message instead of a mid-job "unexpected argument" error.
+    let o1 =
+        p.o1.as_deref()
+            .map(str::trim)
+            .filter(|s| !s.is_empty() && *s != "off")
+            .map(str::to_string);
+    if o1.is_some() {
+        if use_python {
+            return Err(
+                "O(1) attention is supported by the native converter only — remove the \
+                 linear-core / v-bit shape / mean-bits options to use it"
+                    .into(),
+            );
+        }
+        if p.repo.to_ascii_lowercase().contains("gguf") {
+            return Err("O(1) attention is not supported for GGUF imports yet".into());
+        }
+        let ver = crate::cmf_runtime::installed_version(&cfg.cortiq_bin);
+        if let Some(v) = &ver {
+            if crate::cmf_runtime::version_lt(v, "0.2.0") {
+                return Err(format!(
+                    "O(1) attention needs cortiq ≥ 0.2.0 (installed: {v}) — update the runtime \
+                     in Settings → Local models"
+                ));
+            }
+        }
+    }
     let _ = std::fs::create_dir_all(&cfg.models_dir);
     let base = if p.name.trim().is_empty() {
         sanitize(p.repo.rsplit('/').next().unwrap_or(&p.repo))
@@ -384,6 +426,23 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
             a.push("--hf-token".into());
             a.push(t.clone());
         }
+        // O(1) attention hint (weights unchanged; the runtime reads it at load)
+        if let Some(spec) = &o1 {
+            a.push("--o1".into());
+            a.push(spec.clone());
+            if let Some(m) = p.o1_m {
+                a.push("--o1-m".into());
+                a.push(m.to_string());
+            }
+            if let Some(w) = p.o1_window {
+                a.push("--o1-window".into());
+                a.push(w.to_string());
+            }
+            if let Some(s) = p.o1_sink {
+                a.push("--o1-sink".into());
+                a.push(s.to_string());
+            }
+        }
         (
             cfg.cortiq_bin.clone(),
             a,

src/stats.rs

@@ -83,9 +83,23 @@ impl Totals {
         self.cost_usd += r.cost_usd;
         self.latency_ms_sum += r.latency_ms;
     }
+    /// Accumulate another Totals into this one (for windowed aggregation).
+    fn merge(&mut self, o: &Totals) {
+        self.requests += o.requests;
+        self.ok += o.ok;
+        self.errors += o.errors;
+        self.failovers += o.failovers;
+        self.prompt_tokens += o.prompt_tokens;
+        self.completion_tokens += o.completion_tokens;
+        self.cost_usd += o.cost_usd;
+        self.latency_ms_sum += o.latency_ms_sum;
+    }
 }
 
-/// Per-minute bucket for time-series charts.
+/// Per-minute bucket. Beyond the chart fields it carries the per-group breakdown
+/// and failovers so the admin snapshot can be computed for ANY time window by
+/// summing the in-window buckets (the internal fields are not serialized into
+/// the `series` payload).
 #[derive(Clone, Debug, Default, Serialize)]
 pub struct Bucket {
     pub minute: u64, // unix seconds, rounded down to the minute
@@ -95,15 +109,25 @@ pub struct Bucket {
     pub completion_tokens: u64,
     pub cost_usd: f64,
     pub latency_ms_sum: u64,
+    #[serde(skip)]
+    pub failovers: u64,
+    #[serde(skip)]
+    pub by_model: HashMap<String, Totals>,
+    #[serde(skip)]
+    pub by_account: HashMap<String, Totals>,
+    #[serde(skip)]
+    pub by_tier: HashMap<String, Totals>,
+    #[serde(skip)]
+    pub by_label: HashMap<String, Totals>,
 }
 
 #[derive(Default)]
 struct Inner {
+    /// All-time totals + per-model (used by the Prometheus counters, which must
+    /// be monotonic — the windowed admin snapshot is derived from the buckets).
     total: Totals,
     by_model: HashMap<String, Totals>,
-    by_account: HashMap<String, Totals>,
-    by_tier: HashMap<String, Totals>,
-    by_label: HashMap<String, Totals>,
+    /// Per-minute buckets — the single source for the windowed admin snapshot.
     buckets: VecDeque<Bucket>,
     recent: VecDeque<RequestRecord>,
 }
@@ -166,31 +190,14 @@ impl Stats {
     }
 
     fn apply_aggregates(inner: &mut Inner, rec: &RequestRecord, retention_secs: u64) {
+        // all-time counters for Prometheus; the windowed snapshot is derived
+        // from the buckets below.
         inner.total.apply(rec);
         inner
             .by_model
             .entry(rec.model_id.clone())
             .or_default()
             .apply(rec);
-        inner
-            .by_account
-            .entry(if rec.account.is_empty() {
-                "anonymous".to_string()
-            } else {
-                rec.account.clone()
-            })
-            .or_default()
-            .apply(rec);
-        inner
-            .by_tier
-            .entry(rec.tier.clone())
-            .or_default()
-            .apply(rec);
-        inner
-            .by_label
-            .entry(rec.task_label.clone())
-            .or_default()
-            .apply(rec);
 
         let minute = rec.ts - (rec.ts % 60);
         match inner.buckets.back_mut() {
@@ -250,13 +257,31 @@ impl Stats {
             .filter(|b| b.minute >= cutoff)
             .collect();
 
-        let breakdown_src = match groupby {
-            "account" => &inner.by_account,
-            "tier" => &inner.by_tier,
-            "label" => &inner.by_label,
-            _ => &inner.by_model,
-        };
-        let mut breakdown: Vec<serde_json::Value> = breakdown_src
+        // Windowed totals + breakdown = sum of the in-window buckets, so the KPIs
+        // and the breakdown recompute whenever the range changes.
+        let mut win = Totals::default();
+        let mut group: HashMap<String, Totals> = HashMap::new();
+        for b in &series {
+            win.requests += b.requests;
+            win.errors += b.errors;
+            win.ok += b.requests.saturating_sub(b.errors);
+            win.failovers += b.failovers;
+            win.prompt_tokens += b.prompt_tokens;
+            win.completion_tokens += b.completion_tokens;
+            win.cost_usd += b.cost_usd;
+            win.latency_ms_sum += b.latency_ms_sum;
+            let src = match groupby {
+                "account" => &b.by_account,
+                "tier" => &b.by_tier,
+                "label" => &b.by_label,
+                _ => &b.by_model,
+            };
+            for (k, t) in src {
+                group.entry(k.clone()).or_default().merge(t);
+            }
+        }
+
+        let mut breakdown: Vec<serde_json::Value> = group
             .iter()
             .map(|(k, t)| {
                 serde_json::json!({
@@ -280,17 +305,17 @@ impl Stats {
 
         serde_json::json!({
             "totals": {
-                "requests": inner.total.requests,
-                "ok": inner.total.ok,
-                "errors": inner.total.errors,
-                "failovers": inner.total.failovers,
-                "prompt_tokens": inner.total.prompt_tokens,
-                "completion_tokens": inner.total.completion_tokens,
-                "total_tokens": inner.total.prompt_tokens + inner.total.completion_tokens,
-                "cost_usd": inner.total.cost_usd,
-                "avg_latency_ms": avg(inner.total.latency_ms_sum, inner.total.requests),
-                "success_rate": if inner.total.requests > 0 {
-                    inner.total.ok as f64 / inner.total.requests as f64
+                "requests": win.requests,
+                "ok": win.ok,
+                "errors": win.errors,
+                "failovers": win.failovers,
+                "prompt_tokens": win.prompt_tokens,
+                "completion_tokens": win.completion_tokens,
+                "total_tokens": win.prompt_tokens + win.completion_tokens,
+                "cost_usd": win.cost_usd,
+                "avg_latency_ms": avg(win.latency_ms_sum, win.requests),
+                "success_rate": if win.requests > 0 {
+                    win.ok as f64 / win.requests as f64
                 } else { 0.0 },
             },
             "groupby": groupby,
@@ -299,6 +324,18 @@ impl Stats {
         })
     }
 
+    /// Reset all in-memory stats and truncate the JSONL log — the "clear logs"
+    /// admin action.
+    pub fn clear(&self) {
+        {
+            let mut inner = self.inner.lock().unwrap();
+            *inner = Inner::default();
+        }
+        if let Some(path) = &self.file {
+            let _ = std::fs::write(path, "");
+        }
+    }
+
     /// Recent requests (newest first), with pagination.
     pub fn recent(&self, limit: usize, offset: usize) -> Vec<RequestRecord> {
         let inner = self.inner.lock().unwrap();
@@ -358,10 +395,25 @@ fn fill_bucket(b: &mut Bucket, r: &RequestRecord) {
     if r.outcome != "ok" {
         b.errors += 1;
     }
+    if r.failover {
+        b.failovers += 1;
+    }
     b.prompt_tokens += r.prompt_tokens as u64;
     b.completion_tokens += r.completion_tokens as u64;
     b.cost_usd += r.cost_usd;
     b.latency_ms_sum += r.latency_ms;
+    // per-group breakdown, so the snapshot can be windowed by summing buckets
+    b.by_model.entry(r.model_id.clone()).or_default().apply(r);
+    b.by_account
+        .entry(if r.account.is_empty() {
+            "anonymous".to_string()
+        } else {
+            r.account.clone()
+        })
+        .or_default()
+        .apply(r);
+    b.by_tier.entry(r.tier.clone()).or_default().apply(r);
+    b.by_label.entry(r.task_label.clone()).or_default().apply(r);
 }
 
 fn avg(sum: u64, n: u64) -> u64 {

web/js/api.js

@@ -87,6 +87,7 @@ export const api = {
 
   // stats
   stats: (range, groupby) => j("GET", `/stats?range=${range}&groupby=${groupby}`),
+  clearStats: () => j("DELETE", "/stats"),
   requests: (limit = 50, offset = 0) => j("GET", `/requests?limit=${limit}&offset=${offset}`),
 
   // playground

web/js/i18n/en.js

@@ -59,6 +59,9 @@ export default {
   // dashboard
   "dash.title": "Dashboard",
   "dash.subtitle": "Live traffic, cost and routing analytics for your model pool.",
+  "dash.clear": "Clear logs",
+  "dash.clearConfirm": "Clear all recorded stats and logs? This cannot be undone.",
+  "dash.cleared": "Logs cleared",
   "dash.range": "Range",
   "dash.range.1h": "1h",
   "dash.range.24h": "24h",
@@ -397,4 +400,15 @@ export default {
   "import.adv.shard": "Shard max (GB)",
   "import.adv.noShard": "no sharding",
   "import.adv.skipMtp": "skip MTP head",
+  "import.adv.o1": "O(1) attention",
+  "import.adv.o1Hint": "Constant-memory streaming attention: the KV cache is released after prefill, so long contexts don't grow memory. Weights stay byte-identical — only a load-time hint is recorded; you can switch back anytime (serve with --o1 off). Validated on Qwen3-0.6B: all layers ≈ ×1.18 perplexity.",
+  "import.adv.o1Off": "off — exact attention (default)",
+  "import.adv.o1All": "all — convert every softmax layer",
+  "import.adv.o1Deep": "deep N — only the N deepest layers",
+  "import.adv.o1Custom": "custom — explicit layer list",
+  "import.adv.o1DeepN": "N deep layers",
+  "import.adv.o1Layers": "Layers (comma-separated)",
+  "import.adv.o1mHint": "landmark budget (default 32)",
+  "import.adv.o1windowHint": "exact-window width (default 128)",
+  "import.adv.o1sinkHint": "permanent exact sink keys (default 4)",
 };

web/js/i18n/ru.js

@@ -58,6 +58,9 @@ export default {
   // dashboard
   "dash.title": "Дашборд",
   "dash.subtitle": "Трафик в реальном времени, расходы и аналитика роутинга по пулу моделей.",
+  "dash.clear": "Очистить логи",
+  "dash.clearConfirm": "Очистить всю статистику и логи? Отменить нельзя.",
+  "dash.cleared": "Логи очищены",
   "dash.range": "Период",
   "dash.range.1h": "1ч",
   "dash.range.24h": "24ч",
@@ -396,4 +399,15 @@ export default {
   "import.adv.shard": "Шард макс (ГБ)",
   "import.adv.noShard": "без шардинга",
   "import.adv.skipMtp": "пропустить MTP-голову",
+  "import.adv.o1": "O(1)-внимание",
+  "import.adv.o1Hint": "Потоковое внимание с постоянной памятью: KV-кэш освобождается после prefill, длинный контекст не раздувает память. Веса не меняются — записывается лишь подсказка на загрузку; вернуться можно всегда (запуск с --o1 off). Проверено на Qwen3-0.6B: все слои ≈ ×1.18 перплексии.",
+  "import.adv.o1Off": "выкл — точное внимание (по умолчанию)",
+  "import.adv.o1All": "all — конвертировать все softmax-слои",
+  "import.adv.o1Deep": "deep N — только N самых глубоких слоёв",
+  "import.adv.o1Custom": "вручную — явный список слоёв",
+  "import.adv.o1DeepN": "N глубоких слоёв",
+  "import.adv.o1Layers": "Слои (через запятую)",
+  "import.adv.o1mHint": "число опорных точек (по умолчанию 32)",
+  "import.adv.o1windowHint": "ширина точного окна (по умолчанию 128)",
+  "import.adv.o1sinkHint": "постоянные точные sink-ключи (по умолчанию 4)",
 };

web/js/views/dashboard.js

@@ -1,5 +1,5 @@
 // Dashboard — KPIs, time-series charts, breakdown, recent requests, health.
-import { h, mount, money, num, ms, pct, timeAgo } from "../ui.js";
+import { h, mount, money, num, ms, pct, timeAgo, toast, confirmDialog } from "../ui.js";
 import { t } from "../i18n.js";
 import { api } from "../api.js";
 import { lineChart, barList } from "../charts.js";
@@ -53,10 +53,24 @@ export async function renderDashboard() {
           "div",
           { class: "flex" },
           h("div", { class: "grow" }, h("h2", {}, t("dash.title")), h("p", {}, t("dash.subtitle"))),
-          seg(RANGES, range, (r) => {
-            range = r;
-            load();
-          }, (r) => t("dash.range." + r))
+          h("div", { class: "flex", style: "gap:8px;align-items:center" },
+            seg(RANGES, range, (r) => {
+              range = r;
+              load();
+            }, (r) => t("dash.range." + r)),
+            h("button", {
+              class: "btn sm danger",
+              onClick: async () => {
+                if (!(await confirmDialog(t("dash.clearConfirm")))) return;
+                try {
+                  await api.clearStats();
+                  toast(t("dash.cleared"), "good");
+                  await load();
+                } catch (e) {
+                  toast(String(e.message || e), "bad");
+                }
+              },
+            }, t("dash.clear")))
         )
       ),
 

web/js/views/import.js

@@ -125,6 +125,32 @@ export function renderImport() {
     const meanBitsIn = h("input", { type: "number", step: "0.1", placeholder: "5.0" });
     const shardIn = h("input", { type: "number", step: "0.5", placeholder: t("import.adv.noShard") });
     const skipMtp = h("input", { type: "checkbox" });
+    // O(1) attention (cortiq ≥ 0.2.0): constant-memory streaming attention hint,
+    // weights byte-identical — the runtime applies it at load.
+    const o1Sel = h("select", {},
+      opt("", t("import.adv.o1Off")),
+      opt("all", t("import.adv.o1All")),
+      opt("deep", t("import.adv.o1Deep")),
+      opt("custom", t("import.adv.o1Custom")));
+    const o1DeepIn = h("input", { type: "number", min: "1", placeholder: "12" });
+    const o1CustomIn = h("input", { placeholder: "0,4,8" });
+    const o1M = h("input", { type: "number", min: "1", placeholder: "32" });
+    const o1Window = h("input", { type: "number", min: "0", placeholder: "128" });
+    const o1Sink = h("input", { type: "number", min: "0", placeholder: "4" });
+    const o1SpecRow = h("div", { class: "row", style: "display:none" },
+      field(t("import.adv.o1DeepN"), o1DeepIn),
+      field(t("import.adv.o1Layers"), o1CustomIn));
+    const o1Knobs = h("div", { class: "row", style: "display:none" },
+      field("--o1-m", o1M, t("import.adv.o1mHint")),
+      field("--o1-window", o1Window, t("import.adv.o1windowHint")),
+      field("--o1-sink", o1Sink, t("import.adv.o1sinkHint")));
+    o1Sel.addEventListener("change", () => {
+      const on = !!o1Sel.value;
+      o1Knobs.style.display = on ? "" : "none";
+      o1SpecRow.style.display = o1Sel.value === "deep" || o1Sel.value === "custom" ? "" : "none";
+      o1DeepIn.parentElement.style.display = o1Sel.value === "deep" ? "" : "none";
+      o1CustomIn.parentElement.style.display = o1Sel.value === "custom" ? "" : "none";
+    });
     const advBody = h(
       "div",
       { class: "adv-body", style: "display:none" },
@@ -137,6 +163,9 @@ export function renderImport() {
       h("div", { class: "row" },
         field(t("import.adv.shard"), shardIn),
         field("MTP", h("label", { class: "check" }, skipMtp, t("import.adv.skipMtp")))),
+      field(t("import.adv.o1"), o1Sel, t("import.adv.o1Hint")),
+      o1SpecRow,
+      o1Knobs,
     );
     const advToggle = h("button", { class: "btn ghost sm" }, "⚙ " + t("import.adv.title"));
     advToggle.addEventListener("click", () => {
@@ -156,6 +185,19 @@ export function renderImport() {
       if (vbitSel.value) params.vbit_shape = vbitSel.value;
       if (meanBitsIn.value) params.mean_bits = parseFloat(meanBitsIn.value);
       if (shardIn.value) params.shard_max_gb = parseFloat(shardIn.value);
+      if (o1Sel.value) {
+        // spec: all | deepN | explicit layer list
+        params.o1 =
+          o1Sel.value === "deep" ? "deep" + (parseInt(o1DeepIn.value) || 12)
+          : o1Sel.value === "custom" ? o1CustomIn.value.trim()
+          : "all";
+        if (!params.o1) delete params.o1;
+        else {
+          if (o1M.value) params.o1_m = parseInt(o1M.value);
+          if (o1Window.value) params.o1_window = parseInt(o1Window.value);
+          if (o1Sink.value) params.o1_sink = parseInt(o1Sink.value);
+        }
+      }
       goBtn.disabled = true;
       try {
         await api.startImport(params);