feat: per-key spend accounting and per-task complexity pinning

API keys page: the table now answers "which department spends what" — per-key
requests, tokens in/out and cost for a selectable window (24h/7d/30d) plus a
cumulative all-time cost column, joined from stats by the key's account.

The stats log stays bounded while the accounting survives: once stats.jsonl
exceeds max_file_mb (default 16, 0 disables), records older than the
retention window fold into cumulative per-account totals in a small sidecar
file (tmp+rename on both) and leave the log. alltime = folded + in-file, a
record is never counted twice, verified end-to-end on synthetic data
(1.2 MB → 301 KB, totals identical before/after compaction and restarts).

Routing: a task rule can now PIN the complexity tier —
`[routing.tasks.legal] models=[...] tier="high"` (old plain-array rules parse
unchanged). The pinned tier replaces the router's verdict before the
escalation check and reports itself as route_source "router+task-rule@high".
The Routing page grows a per-task «Complexity» selector (Auto/low/medium/
high); verified live: a code prompt with a pinned high went
router+task-rule@high → the expensive model.

13 new strings in all 7 languages; docs/ROUTING(.ru) updated.

web/css/styles.css

@@ -592,6 +592,9 @@ body.modal-open { overflow: hidden; }
 
 .ok { color: var(--good); }
 
+.task-tier-wrap { display: flex; align-items: center; gap: 6px; margin-left: 10px; white-space: nowrap; }
+.task-tier { max-width: 130px; padding: 4px 8px; font-size: 12px; }
+
 /* 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/i18n/de.js

@@ -621,4 +621,10 @@ export default {
   "bm.cutByCap": "Budget ging fürs Denken drauf — keine Antwort mehr",
   "shell.uiStale": "Das Gateway wurde aktualisiert — diese Seite zeigt eine ältere Oberfläche.",
   "shell.reload": "Neu laden",
+  "keys.col.requests": "Anfragen",
+  "keys.col.tokens": "Tokens ein/aus",
+  "keys.col.costAll": "$ gesamt",
+  "routing.tasks.tier": "Komplexität",
+  "routing.tasks.tierAuto": "Auto (Router)",
+  "routing.tasks.tierHint": "Komplexität für diese Aufgabe festlegen: das Router-Urteil wird ersetzt, high eskaliert weiterhin über die Modellliste.",
 };

web/js/i18n/en.js

@@ -614,4 +614,10 @@ export default {
   "bm.cutByCap": "budget spent on reasoning — answer never came",
   "shell.uiStale": "The gateway was updated — this page is running an older interface.",
   "shell.reload": "Reload",
+  "keys.col.requests": "Requests",
+  "keys.col.tokens": "Tokens in/out",
+  "keys.col.costAll": "$ all-time",
+  "routing.tasks.tier": "Complexity",
+  "routing.tasks.tierAuto": "Auto (router)",
+  "routing.tasks.tierHint": "Pin the complexity tier for this task: the router's verdict is replaced, high still escalates over the model list.",
 };

web/js/i18n/es.js

@@ -621,4 +621,10 @@ export default {
   "bm.cutByCap": "presupuesto gastado en razonar — sin respuesta final",
   "shell.uiStale": "La pasarela se actualizó — esta página usa una interfaz antigua.",
   "shell.reload": "Recargar",
+  "keys.col.requests": "Peticiones",
+  "keys.col.tokens": "Tokens ent/sal",
+  "keys.col.costAll": "$ total",
+  "routing.tasks.tier": "Complejidad",
+  "routing.tasks.tierAuto": "Auto (router)",
+  "routing.tasks.tierHint": "Fijar la complejidad de esta tarea: el veredicto del router se sustituye, high sigue escalando por encima de la lista de modelos.",
 };

web/js/i18n/fr.js

@@ -621,4 +621,10 @@ export default {
   "bm.cutByCap": "budget épuisé en raisonnement — pas de réponse",
   "shell.uiStale": "La passerelle a été mise à jour — cette page utilise une ancienne interface.",
   "shell.reload": "Recharger",
+  "keys.col.requests": "Requêtes",
+  "keys.col.tokens": "Tokens in/out",
+  "keys.col.costAll": "$ au total",
+  "routing.tasks.tier": "Complexité",
+  "routing.tasks.tierAuto": "Auto (routeur)",
+  "routing.tasks.tierHint": "Fixer la complexité de cette tâche : le verdict du routeur est remplacé, high continue d'escalader au-dessus de la liste de modèles.",
 };

web/js/i18n/ru.js

@@ -613,4 +613,10 @@ export default {
   "bm.cutByCap": "бюджет ушёл на размышления — ответ не успел",
   "shell.uiStale": "Шлюз обновился — на этой странице старый интерфейс.",
   "shell.reload": "Перезагрузить",
+  "keys.col.requests": "Запросы",
+  "keys.col.tokens": "Токены вх/исх",
+  "keys.col.costAll": "$ за всё время",
+  "routing.tasks.tier": "Сложность",
+  "routing.tasks.tierAuto": "Авто (по роутеру)",
+  "routing.tasks.tierHint": "Закрепить уровень сложности для задачи: вердикт роутера заменяется, high по-прежнему эскалирует поверх списка моделей.",
 };

web/js/i18n/tr.js

@@ -621,4 +621,10 @@ export default {
   "bm.cutByCap": "bütçe düşünmeye gitti — yanıt gelemedi",
   "shell.uiStale": "Ağ geçidi güncellendi — bu sayfa eski arayüzü çalıştırıyor.",
   "shell.reload": "Yeniden yükle",
+  "keys.col.requests": "İstekler",
+  "keys.col.tokens": "Token giriş/çıkış",
+  "keys.col.costAll": "$ toplam",
+  "routing.tasks.tier": "Karmaşıklık",
+  "routing.tasks.tierAuto": "Otomatik (yönlendirici)",
+  "routing.tasks.tierHint": "Bu görev için karmaşıklık katmanını sabitle: yönlendiricinin kararı değiştirilir, high yine model listesinin üzerine tırmanır.",
 };

web/js/i18n/zh.js

@@ -621,4 +621,10 @@ export default {
   "bm.cutByCap": "预算全用于思考——未能给出答案",
   "shell.uiStale": "网关已更新 — 此页面运行的是旧界面。",
   "shell.reload": "重新加载",
+  "keys.col.requests": "请求数",
+  "keys.col.tokens": "Token 入/出",
+  "keys.col.costAll": "$ 累计",
+  "routing.tasks.tier": "复杂度",
+  "routing.tasks.tierAuto": "自动（路由器）",
+  "routing.tasks.tierHint": "为该任务固定复杂度层级：替换路由器的判断，high 仍会越过模型列表进行升级。",
 };

web/js/views/keys.js

@@ -1,10 +1,11 @@
 // API keys — list, create (with copy-once), revoke.
-import { h, mount, modal, toast, confirmDialog } from "../ui.js";
+import { h, mount, modal, toast, confirmDialog, moneyEl, num } from "../ui.js";
 import { t } from "../i18n.js";
 import { api } from "../api.js";
 
 export async function renderKeys() {
   const root = h("div");
+  let usageRange = "7d";
 
   function openCreate(reload) {
     const accountIn = h("input", { placeholder: "team-a" });
@@ -208,6 +209,15 @@ console.log(resp.choices[0].message.content);`,
   async function reload() {
     const data = await api.listKeys();
     const keys = data.keys || [];
+    // per-account usage: window breakdown + cumulative-forever totals — the
+    // "who spends what" view for departments/developers sharing one gateway
+    let usage = {};
+    let alltime = {};
+    try {
+      const st = await api.stats(usageRange, "account");
+      for (const b of st.breakdown || []) usage[b.key] = b;
+      alltime = st.alltime_by_account || {};
+    } catch { /* stats disabled — columns show dashes */ }
     mount(
       root,
       h(
@@ -217,6 +227,9 @@ console.log(resp.choices[0].message.content);`,
           "div",
           { class: "flex" },
           h("div", { class: "grow" }, h("h2", {}, t("keys.title")), h("p", {}, t("keys.subtitle"))),
+          h("div", { class: "seg", style: "margin-right:10px" },
+            ...["24h", "7d", "30d"].map((r) =>
+              h("button", { class: r === usageRange ? "active" : "", onClick: () => { usageRange = r; reload(); } }, r))),
           h("button", { class: "btn primary", onClick: () => openCreate(reload) }, "+ " + t("keys.add"))
         )
       ),
@@ -235,7 +248,16 @@ console.log(resp.choices[0].message.content);`,
                 h(
                   "thead",
                   {},
-                  h("tr", {}, h("th", {}, t("keys.col.key")), h("th", {}, t("keys.col.account")), h("th", {}, t("keys.col.rate")), h("th", {}, t("keys.col.models")), h("th", { class: "right-align" }, t("common.actions")))
+                  h("tr", {},
+                    h("th", {}, t("keys.col.key")),
+                    h("th", {}, t("keys.col.account")),
+                    h("th", {}, t("keys.col.rate")),
+                    h("th", {}, t("keys.col.models")),
+                    h("th", { class: "right-align" }, t("keys.col.requests") + " (" + usageRange + ")"),
+                    h("th", { class: "right-align" }, t("keys.col.tokens") + " (" + usageRange + ")"),
+                    h("th", { class: "right-align" }, "$ (" + usageRange + ")"),
+                    h("th", { class: "right-align" }, t("keys.col.costAll")),
+                    h("th", { class: "right-align" }, t("common.actions")))
                 ),
                 h(
                   "tbody",
@@ -248,6 +270,10 @@ console.log(resp.choices[0].message.content);`,
                       h("td", {}, k.account),
                       h("td", { class: "mono" }, k.rate_per_min || "—"),
                       h("td", {}, (k.allow_models && k.allow_models.length) ? k.allow_models.join(", ") : h("span", { class: "muted" }, t("keys.allowAll"))),
+                      h("td", { class: "right-align mono" }, String((usage[k.account] || {}).requests ?? "—")),
+                      h("td", { class: "right-align mono small" }, usage[k.account] ? num(usage[k.account].prompt_tokens) + " / " + num(usage[k.account].completion_tokens) : "—"),
+                      h("td", { class: "right-align" }, usage[k.account] ? moneyEl(usage[k.account].cost_usd) : "—"),
+                      h("td", { class: "right-align" }, alltime[k.account] ? moneyEl(alltime[k.account].cost_usd) : "—"),
                       h(
                         "td",
                         { class: "right-align" },

web/js/views/routing.js

@@ -54,10 +54,17 @@ export async function renderRouting() {
   // local editable state — ensure standard tiers exist for a friendly editor
   const tiers = Object.assign({ low: [], medium: [], high: [] }, routing.tiers || {});
   const tasks = {};
-  for (const l of taskLabels) tasks[l] = (routing.tasks || {})[l] || [];
+  const taskTiers = {};
+  for (const l of taskLabels) {
+    const v = (routing.tasks || {})[l];
+    // GET returns the full form {models, tier}; older configs may be arrays
+    tasks[l] = Array.isArray(v) ? v : (v && v.models) || [];
+    taskTiers[l] = (v && !Array.isArray(v) && v.tier) || "";
+  }
   const st = {
     tiers,
     tasks,
+    taskTiers,
     default: routing.default || ids[0] || "",
     policy: routing.policy || { mode: "fixed_table", min_class: {} },
   };
@@ -130,10 +137,29 @@ export async function renderRouting() {
         h("div", { class: "muted small mono" }, label),
         share != null ? h("div", { class: "muted small" }, t("routing.tasks.share", { p: Math.round(share * 100) })) : null
       ),
-      chipEditor(st.tasks, label, t("routing.tasks.inherit"))
+      chipEditor(st.tasks, label, t("routing.tasks.inherit")),
+      tierSelect(label)
     );
   }
 
+  // Per-task complexity pin: "авто" follows the router's verdict; a fixed
+  // tier forces it for this task (legal is always high, chitchat always low)
+  function tierSelect(label) {
+    const sel = h(
+      "select",
+      { class: "task-tier", title: t("routing.tasks.tierHint") },
+      h("option", { value: "" }, t("routing.tasks.tierAuto")),
+      ...Object.keys(st.tiers).map((tr) =>
+        h("option", { value: tr, selected: st.taskTiers[label] === tr ? "" : null }, tr))
+    );
+    sel.value = st.taskTiers[label] || "";
+    sel.addEventListener("change", () => {
+      st.taskTiers[label] = sel.value;
+    });
+    return h("div", { class: "task-tier-wrap" },
+      h("div", { class: "muted small" }, t("routing.tasks.tier")), sel);
+  }
+
   function tasksCard() {
     const addIn = h("input", { placeholder: t("routing.tasks.addPlaceholder"), style: "max-width:220px" });
     const addBtn = h("button", { class: "btn ghost sm" }, "+ " + t("routing.tasks.addCustom"));
@@ -201,7 +227,11 @@ export async function renderRouting() {
       saveBtn.disabled = true;
       try {
         const tasks = {};
-        for (const [k, v] of Object.entries(st.tasks)) if (v.length) tasks[k] = v;
+        for (const [k, v] of Object.entries(st.tasks)) {
+          const tier = (st.taskTiers || {})[k] || "";
+          if (tier) tasks[k] = { models: v, tier };
+          else if (v.length) tasks[k] = v;
+        }
         await api.putRouting({ tiers: st.tiers, tasks, default: st.default, policy: st.policy });
         toast(t("toast.saved"), "good");
       } catch (e) {