feat(ui): the continuous complexity score shows next to the tier

Benchmark (routing mode) and the dashboard's recent-requests list now print
the router's raw 0..1 score under/next to the tier badge — people can see
what different prompts actually weigh and tune the boundary sliders from
real data. Tooltip explains the link to the Routing sliders (7 languages).

Caught before commit: naming the field row.score collided with the answer-
correctness fraction from evaluate() and dragged the benchmark's quality KPI
down to the average complexity — renamed to cscore, KPI verified back at
100%. Dashboard tier badges also render translated names now, and the
Russian locale calls the dashboard «Рабочий стол».

web/js/views/benchmark.js

@@ -238,6 +238,7 @@ export async function renderBenchmark() {
                   info.cost_usd = (info.cost_usd || 0) + (again.cost_usd || 0);
                   if (again.tier === "high") {
                     info.tier = again.tier;
+                    info.score = again.score;
                     info.selected_model = again.selected_model;
                     info.task_label = again.task_label;
                     info.route_source = again.route_source;
@@ -269,6 +270,8 @@ export async function renderBenchmark() {
               || String(info.route_source || "").includes("degraded");
             row.task = info.task_label || "—";
             row.tier = info.tier || "—";
+            row.cscore = info.score || 0; // непрерывный коэффициент сложности
+            // (row.score занят долей правильности ответа из evaluate())
             row.chosen = info.selected_model || "—";
             row.source = info.route_source || "—";
             row.expected = test.label; // null = classification not judged
@@ -402,7 +405,9 @@ export async function renderBenchmark() {
                 : h("span", { class: r.taskOk ? "" : "err" },
                     (r.taskOk ? "✓ " : "✗ ") + r.task,
                     r.taskOk ? "" : h("div", { class: "muted small" }, t("bm.expectedLbl") + " " + (r.expected || []).join("/")))),
-          h("td", {}, r.tier ? h("span", { class: "badge tier-" + r.tier }, trTier(r.tier)) : "—"),
+          h("td", {},
+            r.tier ? h("span", { class: "badge tier-" + r.tier }, trTier(r.tier)) : "—",
+            r.cscore > 0 ? h("div", { class: "muted small mono", title: t("bm.scoreHint") }, r.cscore.toFixed(2)) : null),
           h("td", {},
             h("span", { class: "mono small" }, r.chosen || "—"),
             r.cost > 0 ? h("div", { class: "muted small" }, moneyEl(r.cost)) : null,

web/js/views/dashboard.js

@@ -1,6 +1,6 @@
 // Dashboard — KPIs, time-series charts, breakdown, recent requests, health.
 import { h, mount, money, moneyEl, num, ms, pct, timeAgo, toast, confirmDialog } from "../ui.js";
-import { t } from "../i18n.js";
+import { t, trTier } from "../i18n.js";
 import { api } from "../api.js";
 import { lineChart, barList } from "../charts.js";
 import { SITE_URL } from "../app.js";
@@ -271,7 +271,9 @@ function recentTable(rows) {
             {},
             h("td", { class: "mono" }, timeAgo(r.ts)),
             h("td", {}, r.model_id || "—", r.failover ? h("span", { class: "badge warn", style: "margin-left:6px" }, "fo") : null),
-            h("td", {}, r.tier ? h("span", { class: "badge tier-" + r.tier }, r.tier) : "—"),
+            h("td", {},
+              r.tier ? h("span", { class: "badge tier-" + r.tier }, trTier(r.tier)) : "—",
+              r.score > 0 ? h("span", { class: "muted small mono", style: "margin-left:6px" }, r.score.toFixed(2)) : null),
             h("td", {}, r.task_label || "—"),
             h("td", { class: "mono" }, `${r.prompt_tokens}/${r.completion_tokens}`),
             h("td", { class: "mono" }, money(r.cost_usd)),