fix: honest costs in streams, oracle-sized timeouts, history & log cleanup

Cost showed $0 for every streamed request: the X-Cortiq-Cost-USD header is
written before generation, when the cost cannot be known. The gateway now
ships the final number in a closing SSE event (`cortiq_cost_usd`, alongside
the token estimate when the provider sent no usage), and the console prefers
it over the header. Money renders with 4 decimals, the last two in a smaller
font — $0.0006 stays readable instead of collapsing to $0.

Timeouts, both ends: the router default was 800 ms, silently degrading every
prompt the hosted router escalates to its oracle (~10 s) — now 15 s. Provider
clients had NO timeout at all (a dead OpenRouter host hung requests forever) —
now a 10 s connect timeout, with no overall cap so long generations and
streams are never cut.

Benchmark history: per-run × and a Clear-all button. Logs view: a clear
button backed by DELETE /admin/api/logs.

src/admin/mod.rs

@@ -185,7 +185,7 @@ pub fn api_routes(admin_token: String) -> Router<SharedState> {
         .route("/admin/api/requests", get(get_requests))
         .route("/admin/api/test", post(run_test))
         .route("/admin/api/test/stream", post(run_test_stream))
-        .route("/admin/api/logs", get(get_logs))
+        .route("/admin/api/logs", get(get_logs).delete(clear_logs))
         .route("/admin/api/system", get(get_system))
         .route("/admin/api/restart", post(restart_gateway))
         .route("/admin/api/bench", get(bench_list).post(bench_start))
@@ -2113,6 +2113,11 @@ async fn get_logs(Query(q): Query<RecentQuery>) -> ApiResult {
     ok(json!({ "lines": crate::logbuf::snapshot(limit) }))
 }
 
+async fn clear_logs() -> ApiResult {
+    crate::logbuf::clear();
+    ok(json!({ "ok": true }))
+}
+
 /// Host metrics snapshot: CPU, RAM, free disk at the models dir, gateway RSS.
 async fn get_system(State(state): State<SharedState>) -> ApiResult {
     let snap = state.sysmon.snapshot();

src/config.rs

@@ -305,7 +305,9 @@ fn default_router_enabled() -> bool {
     true
 }
 fn default_router_timeout() -> u64 {
-    800
+    // the hosted router escalates hard prompts to an oracle (~10 s);
+    // an 800 ms budget silently degraded every one of those to the fallback
+    15_000
 }
 fn default_verify_tls() -> bool {
     true
@@ -736,7 +738,7 @@ impl Default for Config {
             router: RouterCfg {
                 enabled: true,
                 url: "https://138.226.222.209".to_string(),
-                timeout_ms: 12_000, // hard prompts escalate to an oracle (~10 s)
+                timeout_ms: 15_000, // hard prompts escalate to an oracle (~10 s)
                 verify_tls: false,  // the hosted endpoint is IP-bound
                 api_key_env: Some("CORTIQ_ROUTER_KEY".to_string()),
                 taxonomy_id: Some("data-assistant".to_string()),

src/logbuf.rs

@@ -23,6 +23,11 @@ pub fn snapshot(limit: usize) -> Vec<String> {
         .collect()
 }
 
+/// Drop everything in the ring (the admin console's "clear" button).
+pub fn clear() {
+    ring().lock().unwrap().clear();
+}
+
 pub fn push_line(line: &str) {
     let line = line.trim_end();
     if line.is_empty() {

src/pipeline.rs

@@ -798,28 +798,35 @@ fn tap_stream(
             // inject one final OpenAI-shaped usage event with the gateway's
             // estimate (~4 chars/token), flagged `cortiq_estimated` so nobody
             // mistakes it for the tokenizer's truth.
-            if done_marker && !got_usage {
+            if done_marker {
-                let est_completion = if delta_chunks > 0 {
+                // The initial X-Cortiq-Cost-USD header is always 0 — cost is
-                    delta_chunks
+                // only known after generation. Ship the final number (and the
-                } else {
+                // token estimate when the provider sent none) ahead of [DONE].
-                    (delta_chars / 4) as u32
+                if !got_usage {
-                };
+                    prompt_tokens = (prompt_chars / 4) as u32;
-                let est_prompt = (prompt_chars / 4) as u32;
+                    completion_tokens = if delta_chunks > 0 {
-                let evt = serde_json::json!({
+                        delta_chunks
+                    } else {
+                        (delta_chars / 4) as u32
+                    };
+                }
+                let cost = provider.price(prompt_tokens, completion_tokens);
+                let mut evt = serde_json::json!({
                     "object": "chat.completion.chunk",
                     "model": info.selected_model,
                     "choices": [],
-                    "usage": {
+                    "cortiq_cost_usd": cost,
-                        "prompt_tokens": est_prompt,
-                        "completion_tokens": est_completion,
-                        "total_tokens": est_prompt + est_completion,
-                    },
-                    "cortiq_estimated": true,
                 });
+                if !got_usage {
+                    evt["usage"] = serde_json::json!({
+                        "prompt_tokens": prompt_tokens,
+                        "completion_tokens": completion_tokens,
+                        "total_tokens": prompt_tokens + completion_tokens,
+                    });
+                    evt["cortiq_estimated"] = serde_json::json!(true);
+                    got_usage = true;
+                }
                 yield Ok(bytes::Bytes::from(format!("data: {evt}\n\n")));
-                prompt_tokens = est_prompt;
-                completion_tokens = est_completion;
-                got_usage = true;
             }
             yield item;
         }

src/providers/anthropic.rs

@@ -32,7 +32,13 @@ impl AnthropicProvider {
             caps: Caps::from_list(&cfg.caps),
             price_in: cfg.price_in,
             price_out: cfg.price_out,
-            http: reqwest::Client::new(),
+            // connect timeout: a dead host fails over in seconds instead of
+            // hanging the request; NO overall timeout — that would cut long
+            // generations and streams (OpenRouter can be slow legitimately)
+            http: reqwest::Client::builder()
+                .connect_timeout(std::time::Duration::from_secs(10))
+                .build()
+                .unwrap_or_else(|_| reqwest::Client::new()),
         })
     }
 

src/providers/openai.rs

@@ -28,7 +28,13 @@ impl OpenAiProvider {
             caps: Caps::from_list(&cfg.caps),
             price_in: cfg.price_in,
             price_out: cfg.price_out,
-            http: reqwest::Client::new(),
+            // connect timeout: a dead host fails over in seconds instead of
+            // hanging the request; NO overall timeout — that would cut long
+            // generations and streams (OpenRouter can be slow legitimately)
+            http: reqwest::Client::builder()
+                .connect_timeout(std::time::Duration::from_secs(10))
+                .build()
+                .unwrap_or_else(|_| reqwest::Client::new()),
         })
     }
 

web/css/styles.css

@@ -585,6 +585,9 @@ body.modal-open { overflow: hidden; }
 /* Featured gallery: the list grows as new models are published, so give it more
    room than the search grid before it starts scrolling. */
 .featured-section .hf-grid { max-height: min(62vh, 760px); }
+/* Money: 4 decimals, last two de-emphasized */
+.money-tail { font-size: .72em; opacity: .75; margin-left: 1px; }
+
 /* Benchmark view */
 @keyframes bm-in { from { opacity: 0; transform: translateY(-3px); } to { opacity: 1; transform: none; } }
 tbody tr:last-child { animation: bm-in .25s ease; }

web/js/api.js

@@ -130,6 +130,7 @@ export const api = {
   // system / logs / lifecycle
   system: () => j("GET", "/system"),
   logs: (limit = 300) => j("GET", "/logs?limit=" + limit),
+  clearLogs: () => j("DELETE", "/logs"),
   restart: () => j("POST", "/restart"),
   benchStart: (model) => j("POST", "/bench", { model }),
   benchList: () => j("GET", "/bench"),
@@ -190,6 +191,7 @@ export async function testStream(body, onDelta) {
   let ttftMs = null; // time to first content token
   let usage = null; // OpenAI-style final-chunk usage, when the provider sends it
   let usageEstimated = false; // gateway-injected estimate rather than tokenizer truth
+  let costUsd = null; // final cost from the gateway's closing event (headers carry 0)
   for (;;) {
     const { done, value } = await reader.read();
     if (done) break;
@@ -207,6 +209,7 @@ export async function testStream(body, onDelta) {
           usage = chunk.usage;
           usageEstimated = !!chunk.cortiq_estimated;
         }
+        if (chunk.cortiq_cost_usd != null) costUsd = chunk.cortiq_cost_usd;
         const d = chunk.choices?.[0]?.delta?.content;
         if (d) {
           if (ttftMs == null) ttftMs = Math.round(performance.now() - t0);
@@ -224,7 +227,7 @@ export async function testStream(body, onDelta) {
     score: parseFloat(h.get("x-cortiq-complexity-score") || "0"),
     selected_model: h.get("x-cortiq-selected-model") || "",
     route_source: h.get("x-cortiq-route-source") || "",
-    cost_usd: parseFloat(h.get("x-cortiq-cost-usd") || "0"),
+    cost_usd: costUsd != null ? costUsd : parseFloat(h.get("x-cortiq-cost-usd") || "0"),
     usage,
     usage_estimated: usageEstimated,
     ttft_ms: ttftMs,

web/js/i18n/de.js

@@ -601,4 +601,5 @@ export default {
   "bm.liveRunning": "läuft…",
   "bm.spent": "ausgegeben",
   "bm.verdict": "🏁 Fertig: Antworten {p}, ausgegeben {s}",
+  "bm.clearHistory": "Alle löschen",
 };

web/js/i18n/en.js

@@ -594,4 +594,5 @@ export default {
   "bm.liveRunning": "running…",
   "bm.spent": "spent",
   "bm.verdict": "🏁 Done: answers {p}, spent {s}",
+  "bm.clearHistory": "Clear all",
 };

web/js/i18n/es.js

@@ -601,4 +601,5 @@ export default {
   "bm.liveRunning": "en curso…",
   "bm.spent": "gastado",
   "bm.verdict": "🏁 Listo: respuestas {p}, gastado {s}",
+  "bm.clearHistory": "Borrar todo",
 };

web/js/i18n/fr.js

@@ -601,4 +601,5 @@ export default {
   "bm.liveRunning": "en cours…",
   "bm.spent": "dépensé",
   "bm.verdict": "🏁 Terminé : réponses {p}, dépensé {s}",
+  "bm.clearHistory": "Tout effacer",
 };

web/js/i18n/ru.js

@@ -593,4 +593,5 @@ export default {
   "bm.liveRunning": "идёт…",
   "bm.spent": "потрачено",
   "bm.verdict": "🏁 Готово: ответы {p}, потрачено {s}",
+  "bm.clearHistory": "Очистить всё",
 };

web/js/i18n/tr.js

@@ -601,4 +601,5 @@ export default {
   "bm.liveRunning": "sürüyor…",
   "bm.spent": "harcanan",
   "bm.verdict": "🏁 Bitti: yanıtlar {p}, harcanan {s}",
+  "bm.clearHistory": "Tümünü temizle",
 };

web/js/i18n/zh.js

@@ -601,4 +601,5 @@ export default {
   "bm.liveRunning": "进行中……",
   "bm.spent": "花费",
   "bm.verdict": "🏁 完成：回答 {p}，花费 {s}",
+  "bm.clearHistory": "全部清除",
 };

web/js/ui.js

@@ -95,11 +95,22 @@ export function confirmDialog(message) {
 }
 
 // number formatting
+// Money as a DOM node: 4 decimals, the last two rendered smaller — tiny
+// per-request prices stay readable without shouting six zeros.
+export function moneyEl(n) {
+  if (n == null) return document.createTextNode("—");
+  if (n === 0) return document.createTextNode("$0");
+  const s = n.toFixed(4);
+  return h("span", { class: "money" }, "$" + s.slice(0, -2), h("small", { class: "money-tail" }, s.slice(-2)));
+}
+
 export function money(n) {
   if (n == null) return "—";
   if (n === 0) return "$0";
-  if (Math.abs(n) < 0.01) return "$" + n.toFixed(6);
+  // up to 4 decimals, trailing zeros trimmed (but keep money-like 2 minimum)
-  return "$" + n.toFixed(4);
+  let s = n.toFixed(4).replace(/0+$/, "").replace(/\.$/, "");
+  if (/\.\d$/.test(s)) s += "0";
+  return "$" + s;
 }
 export function ms(n) {
   return n == null ? "—" : `${Math.round(Number(n))} ms`;

web/js/views/benchmark.js

@@ -7,7 +7,7 @@
 // A redesign of the old standalone benchmark.html: same scoring ideas
 // (keyword checks with | synonyms, think-tag stripping, anti-loop detection,
 // pass/partial/fail), now embedded, localized and CDN-free.
-import { h, mount, toast, ms, money } from "../ui.js";
+import { h, mount, toast, ms, money, moneyEl } from "../ui.js";
 import { t } from "../i18n.js";
 import { api, testStream } from "../api.js";
 
@@ -60,6 +60,9 @@ function pushHistory(run) {
   l.unshift(run);
   localStorage.setItem(LS_HISTORY, JSON.stringify(l.slice(0, 12)));
 }
+function saveHistory(l) {
+  localStorage.setItem(LS_HISTORY, JSON.stringify(l));
+}
 
 // ── evaluation (ported from the old benchmark, trimmed) ─────────────────────
 function stripThink(text) {
@@ -261,11 +264,11 @@ export async function renderBenchmark() {
           h("div", { class: "kpi" }, h("div", { class: "big" }, judged.length ? `${okCount}/${judged.length}` : "—"), h("div", { class: "lbl" }, t("bm.classAcc"))),
           h("div", { class: "kpi" }, h("div", { class: "big" }, st.ttft != null ? ms(Math.round(st.ttft)) : "—"), h("div", { class: "lbl" }, t("pg.ttft"))),
           h("div", { class: "kpi" }, h("div", { class: "big" }, st.tokS != null ? st.tokS.toFixed(1) : "—"), h("div", { class: "lbl" }, "tok/s")),
-          h("div", { class: "kpi" }, h("div", { class: "big" }, money(st.cost)), h("div", { class: "lbl" }, t("bm.spent")))),
+          h("div", { class: "kpi" }, h("div", { class: "big" }, moneyEl(st.cost)), h("div", { class: "lbl" }, t("bm.spent")))),
         h("div", { class: "flex wrap", style: "gap:6px; margin-top:4px" },
           h("span", { class: "muted small" }, t("bm.modelDist") + ":"),
           ...Object.entries(dist).map(([m, d]) =>
-            h("span", { class: "badge" }, `${m} × ${d.n}` + (d.cost > 0 ? ` · ${money(d.cost)}` : "")))));
+            h("span", { class: "badge" }, `${m} × ${d.n}`, d.cost > 0 ? " · " : "", d.cost > 0 ? moneyEl(d.cost) : ""))));
     } else {
       const sorted = models.slice().sort((a, b) => stats(run.models[b]).score - stats(run.models[a]).score);
       summary = h("div", {},
@@ -278,7 +281,7 @@ export async function renderBenchmark() {
               h("span", { class: "badge " + (pct >= 80 ? "ok" : pct >= 50 ? "" : "bad") }, pct + "%"),
               st.tokS != null ? h("span", { class: "muted small", style: "margin-left:8px" }, st.tokS.toFixed(1) + " tok/s") : null,
               st.ttft != null ? h("span", { class: "muted small", style: "margin-left:8px" }, "TTFT " + ms(Math.round(st.ttft))) : null,
-              st.cost > 0 ? h("span", { class: "muted small", style: "margin-left:8px" }, t("bm.spent") + " " + money(st.cost)) : null),
+              st.cost > 0 ? h("span", { class: "muted small", style: "margin-left:8px" }, t("bm.spent") + " ", moneyEl(st.cost)) : null),
             h("div", { class: "sysbar" }, h("i", { class: pct < 50 ? "bad" : "", style: `width:${pct}%` })));
         }));
     }
@@ -316,7 +319,7 @@ export async function renderBenchmark() {
           h("td", {}, r.tier ? h("span", { class: "badge tier-" + r.tier }, r.tier) : "—"),
           h("td", {},
             h("span", { class: "mono small" }, r.chosen || "—"),
-            r.cost > 0 ? h("div", { class: "muted small" }, money(r.cost)) : null,
+            r.cost > 0 ? h("div", { class: "muted small" }, moneyEl(r.cost)) : null,
             r.source && r.source.includes("task-rule") ? h("div", { class: "badge", style: "margin-top:2px" }, "task-rule") : null),
           answerCell(r, r.chosen || "cortiq-auto")));
     } else {
@@ -350,9 +353,16 @@ export async function renderBenchmark() {
       mount(historyHost);
       return;
     }
+    const clearAll = h("button", { class: "btn ghost sm danger" }, "🗑 " + t("bm.clearHistory"));
+    clearAll.addEventListener("click", () => {
+      saveHistory([]);
+      renderHistory();
+    });
     mount(historyHost, h("div", { class: "card" },
-      h("div", { class: "card-title" }, t("bm.history")),
+      h("div", { class: "card-head" },
-      ...l.map((run) => {
+        h("h3", {}, t("bm.history")),
+        h("div", { class: "right" }, clearAll)),
+      ...l.map((run, idx) => {
         const models = Object.keys(run.models);
         const scoreOf = (m) => {
           const rs = run.models[m].results || [];
@@ -364,7 +374,13 @@ export async function renderBenchmark() {
           h("span", { class: "muted small" }, new Date(run.ts).toLocaleString()),
           h("span", { class: "grow mono small" }, run.mode === "routing" ? t("bm.mode.routing") : models.join(", ")),
           run.quick ? h("span", { class: "badge" }, t("bm.quick")) : null,
-          best ? h("b", {}, Math.round(scoreOf(best) * 100) + "%") : null);
+          best ? h("b", {}, Math.round(scoreOf(best) * 100) + "%") : null,
+          h("button", { class: "btn sm ghost danger", title: t("common.delete"), onClick: (e) => {
+            e.stopPropagation();
+            l.splice(idx, 1);
+            saveHistory(l);
+            renderHistory();
+          } }, "×"));
         row.addEventListener("click", () => renderResults(run));
         return row;
       })));

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, toast, confirmDialog } from "../ui.js";
+import { h, mount, money, moneyEl, 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";
@@ -161,7 +161,7 @@ export async function renderDashboard() {
         { class: "kpis" },
         kpi(num(tot.requests), t("dash.kpi.requests")),
         kpi(num(tot.total_tokens), t("dash.kpi.tokens")),
-        kpi(money(tot.cost_usd), t("dash.kpi.cost")),
+        kpi(moneyEl(tot.cost_usd), t("dash.kpi.cost")),
         kpi(ms(tot.avg_latency_ms), t("dash.kpi.latency")),
         kpi(pct(tot.success_rate), t("dash.kpi.success")),
         kpi(num(tot.failovers), t("dash.kpi.failovers"))

web/js/views/logs.js

@@ -21,6 +21,17 @@ export function renderLogs() {
   );
   const pauseBtn = h("button", { class: "btn ghost sm" }, "⏸ " + t("logs.pause"));
   const copyBtn = h("button", { class: "btn ghost sm" }, "⧉ " + t("common.copy"));
+  const clearBtn = h("button", { class: "btn ghost sm danger" }, "🗑 " + t("dash.clear"));
+  clearBtn.addEventListener("click", async () => {
+    try {
+      await api.clearLogs();
+      lines = [];
+      paint();
+      toast(t("dash.cleared"), "ok");
+    } catch (e) {
+      toast(String(e.message || e), "err");
+    }
+  });
 
   let lines = [];
   function paint() {
@@ -76,7 +87,7 @@ export function renderLogs() {
     h(
       "div",
       { class: "card" },
-      h("div", { class: "flex", style: "gap:8px; flex-wrap:wrap; margin-bottom:10px" }, filterIn, levelSel, pauseBtn, copyBtn),
+      h("div", { class: "flex", style: "gap:8px; flex-wrap:wrap; margin-bottom:10px" }, filterIn, levelSel, pauseBtn, copyBtn, clearBtn),
       pre
     )
   );

web/js/views/playground.js

@@ -4,7 +4,7 @@
 //   video → `cortiq animate` over a local text-to-video .cmf (MiniMax-H3)
 // Media results are decoded in the browser (PPM → canvas, MJPEG AVI → canvas
 // player synced to the wav) — the same no-ffmpeg stance as the engine itself.
-import { h, mount, toast, money, ms } from "../ui.js";
+import { h, mount, toast, money, moneyEl, ms } from "../ui.js";
 import { t } from "../i18n.js";
 import { api, testStream, mediaFileUrl, mediaFileBytes } from "../api.js";
 import { appState } from "../app.js";
@@ -218,7 +218,7 @@ export async function renderPlayground() {
       kv(t("pg.tokens"), haveUsage ? `${r.usage_estimated ? "≈ " : ""}${u.prompt_tokens ?? 0} / ${u.completion_tokens ?? 0}` : "—"),
       kv(t("pg.tokSpeed"), tokS != null ? tokS + " tok/s" : "—"),
       kv(t("pg.ttft"), r.ttft_ms != null ? ms(r.ttft_ms) : "—"),
-      kv(t("pg.cost"), money(c.cost_usd)),
+      kv(t("pg.cost"), moneyEl(c.cost_usd)),
       kv(t("pg.latency"), ms(r.latency_ms)),
       kv(t("pg.failover"), c.failover ? "yes" : "no")
     );