feat(routing): per-task rules on top of complexity tiers; hosted router is the default

The router has always returned two signals — task label and complexity tier — but only the tier picked models. [routing.tasks] adds `label → ordered models`: a matching rule's models lead the candidate chain and the tier chain follows as fallback, so pinning translations to a local model never weakens failover. Requests whose chain was headed by a task rule report route_source "router+task-rule". The Routing page grows a per-task editor built from the account's LIVE taxonomy (GET /v1/taxonomies via the new /admin/api/routing/labels proxy; built-in label set when the router is unreachable), with localized task names, each task's share of 7-day traffic, "by complexity (no rule)" as the explicit empty state, and custom labels for other taxonomies. Deleting a model scrubs it from task rules like it always did from tiers. Also fixes the default config pointing at a placeholder localhost:8080 router with a nonexistent taxonomy — a fresh install now targets the hosted allaigate router (IP endpoint, verify_tls off, data-assistant, 12 s oracle timeout) and degrades gracefully until a key is set. Verified end-to-end against the live router: translation → task-rule model, math → tier path. 16 new strings in all 7 languages.
2026-08-07 17:39:38 +03:00
parent 15de36be3b
commit 2ede0ee452
18 changed files with 507 additions and 58 deletions
@@ -68,6 +68,7 @@ export const api = {

  // routing
  getRouting: () => j("GET", "/routing"),
+  routingLabels: () => j("GET", "/routing/labels"),
  putRouting: (b) => j("PUT", "/routing", b),

  // protocols
@@ -545,4 +545,22 @@ export default {
  "bench.running": "misst…",
  "bench.failed": "fehlgeschlagen",
  "bench.none": "Noch keine lokalen .cmf-Chat-Modelle.",
+
+  // task-based routing
+  "task.chitchat": "Smalltalk",
+  "task.code": "Code",
+  "task.creative-writing": "Kreatives Schreiben",
+  "task.extraction": "Datenextraktion",
+  "task.math": "Mathematik",
+  "task.qa": "Fragen & Antworten",
+  "task.summarization": "Zusammenfassung",
+  "task.translation": "Übersetzung",
+  "routing.tasks.title": "Aufgabenbasiertes Routing",
+  "routing.tasks.hint": "Die Modelle einer Regel kommen für ihre Aufgabe zuerst; die Komplexitätskette bleibt als Fallback. Leer = nur nach Komplexität.",
+  "routing.tasks.inherit": "nach Komplexität (keine Regel)",
+  "routing.tasks.share": "{p}% der Anfragen (7 T)",
+  "routing.tasks.fromRouter": "Labels live vom Router",
+  "routing.tasks.builtin": "Router nicht erreichbar — eingebauter Labelsatz",
+  "routing.tasks.addCustom": "Aufgabe hinzufügen",
+  "routing.tasks.addPlaceholder": "eigenes Label…",
 };
@@ -538,4 +538,22 @@ export default {
  "bench.running": "measuring…",
  "bench.failed": "failed",
  "bench.none": "No local .cmf chat models yet.",
+
+  // task-based routing
+  "task.chitchat": "Small talk",
+  "task.code": "Code",
+  "task.creative-writing": "Creative writing",
+  "task.extraction": "Data extraction",
+  "task.math": "Math",
+  "task.qa": "Q&A",
+  "task.summarization": "Summarization",
+  "task.translation": "Translation",
+  "routing.tasks.title": "Task-based routing",
+  "routing.tasks.hint": "A rule's models go first for that task; the complexity chain below still applies as fallback. Empty = route by complexity only.",
+  "routing.tasks.inherit": "by complexity (no rule)",
+  "routing.tasks.share": "{p}% of requests (7d)",
+  "routing.tasks.fromRouter": "labels live from the router",
+  "routing.tasks.builtin": "router unreachable — built-in label set",
+  "routing.tasks.addCustom": "Add task",
+  "routing.tasks.addPlaceholder": "custom label…",
 };
@@ -545,4 +545,22 @@ export default {
  "bench.running": "midiendo…",
  "bench.failed": "falló",
  "bench.none": "Aún no hay modelos de chat .cmf locales.",
+
+  // task-based routing
+  "task.chitchat": "Charla",
+  "task.code": "Código",
+  "task.creative-writing": "Escritura creativa",
+  "task.extraction": "Extracción de datos",
+  "task.math": "Matemáticas",
+  "task.qa": "Preguntas y respuestas",
+  "task.summarization": "Resumen",
+  "task.translation": "Traducción",
+  "routing.tasks.title": "Enrutado por tarea",
+  "routing.tasks.hint": "Los modelos de una regla van primero para su tarea; la cadena por complejidad sigue como respaldo. Vacío = solo por complejidad.",
+  "routing.tasks.inherit": "por complejidad (sin regla)",
+  "routing.tasks.share": "{p}% de las peticiones (7 d)",
+  "routing.tasks.fromRouter": "etiquetas en vivo del router",
+  "routing.tasks.builtin": "router inaccesible — conjunto integrado",
+  "routing.tasks.addCustom": "Añadir tarea",
+  "routing.tasks.addPlaceholder": "etiqueta propia…",
 };
@@ -545,4 +545,22 @@ export default {
  "bench.running": "mesure…",
  "bench.failed": "échec",
  "bench.none": "Pas encore de modèles de chat .cmf locaux.",
+
+  // task-based routing
+  "task.chitchat": "Bavardage",
+  "task.code": "Code",
+  "task.creative-writing": "Écriture créative",
+  "task.extraction": "Extraction de données",
+  "task.math": "Mathématiques",
+  "task.qa": "Questions-réponses",
+  "task.summarization": "Résumé",
+  "task.translation": "Traduction",
+  "routing.tasks.title": "Routage par tâche",
+  "routing.tasks.hint": "Les modèles d'une règle passent en premier pour leur tâche ; la chaîne par complexité reste en secours. Vide = complexité seule.",
+  "routing.tasks.inherit": "par complexité (aucune règle)",
+  "routing.tasks.share": "{p}% des requêtes (7 j)",
+  "routing.tasks.fromRouter": "étiquettes reçues du routeur",
+  "routing.tasks.builtin": "routeur injoignable — jeu d'étiquettes intégré",
+  "routing.tasks.addCustom": "Ajouter une tâche",
+  "routing.tasks.addPlaceholder": "étiquette personnalisée…",
 };
@@ -537,4 +537,22 @@ export default {
  "bench.running": "замер…",
  "bench.failed": "ошибка",
  "bench.none": "Локальных чат-моделей .cmf пока нет.",
+
+  // task-based routing
+  "task.chitchat": "Светская беседа",
+  "task.code": "Код",
+  "task.creative-writing": "Творческие тексты",
+  "task.extraction": "Извлечение данных",
+  "task.math": "Математика",
+  "task.qa": "Вопросы и ответы",
+  "task.summarization": "Суммаризация",
+  "task.translation": "Перевод",
+  "routing.tasks.title": "Распределение по задачам",
+  "routing.tasks.hint": "Модели правила идут первыми для своей задачи; цепочка по сложности остаётся резервом. Пусто = только по сложности.",
+  "routing.tasks.inherit": "по сложности (без правила)",
+  "routing.tasks.share": "{p}% запросов (7д)",
+  "routing.tasks.fromRouter": "метки получены с роутера",
+  "routing.tasks.builtin": "роутер недоступен — встроенный набор меток",
+  "routing.tasks.addCustom": "Добавить задачу",
+  "routing.tasks.addPlaceholder": "своя метка…",
 };
@@ -545,4 +545,22 @@ export default {
  "bench.running": "ölçülüyor…",
  "bench.failed": "başarısız",
  "bench.none": "Henüz yerel .cmf sohbet modeli yok.",
+
+  // task-based routing
+  "task.chitchat": "Sohbet",
+  "task.code": "Kod",
+  "task.creative-writing": "Yaratıcı yazarlık",
+  "task.extraction": "Veri çıkarma",
+  "task.math": "Matematik",
+  "task.qa": "Soru-cevap",
+  "task.summarization": "Özetleme",
+  "task.translation": "Çeviri",
+  "routing.tasks.title": "Göreve göre yönlendirme",
+  "routing.tasks.hint": "Kuralın modelleri kendi görevi için önce gelir; karmaşıklık zinciri yedek olarak kalır. Boş = yalnızca karmaşıklığa göre.",
+  "routing.tasks.inherit": "karmaşıklığa göre (kural yok)",
+  "routing.tasks.share": "isteklerin %{p}'i (7 g)",
+  "routing.tasks.fromRouter": "etiketler yönlendiriciden canlı",
+  "routing.tasks.builtin": "yönlendiriciye ulaşılamıyor — yerleşik etiket seti",
+  "routing.tasks.addCustom": "Görev ekle",
+  "routing.tasks.addPlaceholder": "özel etiket…",
 };
@@ -545,4 +545,22 @@ export default {
  "bench.running": "测速中……",
  "bench.failed": "失败",
  "bench.none": "还没有本地 .cmf 聊天模型。",
+
+  // task-based routing
+  "task.chitchat": "闲聊",
+  "task.code": "代码",
+  "task.creative-writing": "创意写作",
+  "task.extraction": "数据提取",
+  "task.math": "数学",
+  "task.qa": "问答",
+  "task.summarization": "摘要",
+  "task.translation": "翻译",
+  "routing.tasks.title": "按任务路由",
+  "routing.tasks.hint": "规则中的模型对该任务优先；下方的复杂度链仍作为回退。留空 = 仅按复杂度。",
+  "routing.tasks.inherit": "按复杂度（无规则）",
+  "routing.tasks.share": "{p}% 的请求（7 天）",
+  "routing.tasks.fromRouter": "标签实时来自路由器",
+  "routing.tasks.builtin": "路由器不可达 — 使用内置标签集",
+  "routing.tasks.addCustom": "添加任务",
+  "routing.tasks.addPlaceholder": "自定义标签……",
 };
@@ -4,71 +4,155 @@ import { t } from "../i18n.js";
 import { api } from "../api.js";
 import { appState } from "../app.js";

+// Known labels of the hosted taxonomy — used for localized names/descriptions
+// and as the offline fallback; the live list comes from /routing/labels.
+const TASK_META = {
+  chitchat: { icon: "💬" },
+  code: { icon: "⌨" },
+  "creative-writing": { icon: "✍" },
+  extraction: { icon: "📑" },
+  math: { icon: "∑" },
+  qa: { icon: "❓" },
+  summarization: { icon: "📋" },
+  translation: { icon: "🌍" },
+};
+
 export async function renderRouting() {
  const meta = appState.meta || (await api.meta());
  const [routing, modelsData] = await Promise.all([api.getRouting(), api.listModels()]);
  const ids = (modelsData.models || []).map((m) => m.id);

+  // Task labels: live from the router when reachable, built-in set otherwise;
+  // labels that already have a rule are always shown (custom taxonomies).
+  let taskLabels = Object.keys(TASK_META);
+  let labelsSource = "builtin";
+  try {
+    const r = await api.routingLabels();
+    if (r.labels && r.labels.length) {
+      taskLabels = r.labels;
+      labelsSource = "router";
+    }
+  } catch {
+    /* offline — builtin list */
+  }
+  for (const k of Object.keys(routing.tasks || {})) {
+    if (!taskLabels.includes(k)) taskLabels.push(k);
+  }
+
+  // Share of recent traffic per task — shows which rules actually matter.
+  let taskShare = {};
+  try {
+    const stat = await api.stats("7d", "label");
+    const total = (stat.breakdown || []).reduce((a, b) => a + (b.requests || 0), 0);
+    if (total > 0) {
+      for (const b of stat.breakdown || []) taskShare[b.key] = (b.requests || 0) / total;
+    }
+  } catch {
+    /* no stats yet */
+  }
+
  // 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 st = {
    tiers,
+    tasks,
    default: routing.default || ids[0] || "",
    policy: routing.policy || { mode: "fixed_table", min_class: {} },
  };

  const root = h("div");

-  function moveChip(tier, i, dir) {
-    const arr = st.tiers[tier];
+  function moveChip(map, key, i, dir) {
+    const arr = map[key];
    const ni = i + dir;
    if (ni < 0 || ni >= arr.length) return;
    [arr[i], arr[ni]] = [arr[ni], arr[i]];
    render();
  }
-  function removeChip(tier, i) {
-    st.tiers[tier].splice(i, 1);
+  function removeChip(map, key, i) {
+    map[key].splice(i, 1);
    render();
  }
-  function addChip(tier, id) {
-    if (id && !st.tiers[tier].includes(id)) st.tiers[tier].push(id);
+  function addChip(map, key, id) {
+    if (id && !map[key].includes(id)) map[key].push(id);
    render();
  }
-
-  function tierRow(tier) {
-    const arr = st.tiers[tier];
+  function chipEditor(map, key, emptyLabel) {
+    const arr = map[key];
    const avail = ids.filter((id) => !arr.includes(id));
    const addSel = h(
      "select",
-      {
-        style: "width:auto",
-        onChange: (e) => {
-          addChip(tier, e.target.value);
-        },
-      },
+      { style: "width:auto", onChange: (e) => addChip(map, key, e.target.value) },
      h("option", { value: "" }, t("routing.addModel")),
      ...avail.map((id) => h("option", { value: id }, id))
    );
+    return h(
+      "div",
+      { class: "chips" },
+      arr.length === 0 && emptyLabel ? h("span", { class: "muted small chips-empty" }, emptyLabel) : null,
+      ...arr.map((id, i) =>
+        h(
+          "div",
+          { class: "chip" },
+          h("span", { class: "ord" }, i + 1),
+          id,
+          h("span", { class: "arrow", title: "←", onClick: () => moveChip(map, key, i, -1) }, "◄"),
+          h("span", { class: "arrow", title: "→", onClick: () => moveChip(map, key, i, 1) }, "►"),
+          h("span", { class: "x", onClick: () => removeChip(map, key, i) }, "×")
+        )
+      ),
+      avail.length ? addSel : null
+    );
+  }
+
+  function tierRow(tier) {
    return h(
      "div",
      { class: "tierrow" },
      h("div", { class: "tname" }, h("span", { class: "badge tier-" + tier }, tier)),
+      chipEditor(st.tiers, tier)
+    );
+  }
+
+  function taskRow(label) {
+    const known = TASK_META[label];
+    const name = known ? t("task." + label) : label;
+    const share = taskShare[label];
+    return h(
+      "div",
+      { class: "tierrow taskrow" },
      h(
        "div",
-        { class: "chips" },
-        ...arr.map((id, i) =>
-          h(
-            "div",
-            { class: "chip" },
-            h("span", { class: "ord" }, i + 1),
-            id,
-            h("span", { class: "arrow", title: "←", onClick: () => moveChip(tier, i, -1) }, "◄"),
-            h("span", { class: "arrow", title: "→", onClick: () => moveChip(tier, i, 1) }, "►"),
-            h("span", { class: "x", onClick: () => removeChip(tier, i) }, "×")
-          )
-        ),
-        avail.length ? addSel : null
-      )
+        { class: "tname taskname" },
+        h("div", {}, (known ? known.icon + " " : "") + name),
+        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"))
+    );
+  }
+
+  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"));
+    addBtn.addEventListener("click", () => {
+      const v = addIn.value.trim().toLowerCase();
+      if (!v || st.tasks[v]) return;
+      st.tasks[v] = [];
+      render();
+    });
+    return h(
+      "div",
+      { class: "card" },
+      h("div", { class: "card-head" },
+        h("h3", {}, "🎯 " + t("routing.tasks.title")),
+        h("span", { class: "card-head sub" },
+          labelsSource === "router" ? t("routing.tasks.fromRouter") : t("routing.tasks.builtin"))),
+      h("div", { class: "muted small", style: "margin-bottom:10px" }, t("routing.tasks.hint")),
+      ...Object.keys(st.tasks).map(taskRow),
+      h("div", { class: "flex", style: "gap:8px; margin-top:10px" }, addIn, addBtn)
    );
  }

@@ -116,7 +200,9 @@ export async function renderRouting() {
    saveBtn.addEventListener("click", async () => {
      saveBtn.disabled = true;
      try {
-        await api.putRouting({ tiers: st.tiers, default: st.default, policy: st.policy });
+        const tasks = {};
+        for (const [k, v] of Object.entries(st.tasks)) 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) {
        toast(String(e.message || e), "bad");
@@ -143,6 +229,7 @@ export async function renderRouting() {
        h("div", { class: "card-head" }, h("h3", {}, t("routing.tiers")), h("span", { class: "card-head sub" }, t("routing.tierHint"))),
        ...Object.keys(st.tiers).map(tierRow)
      ),
+      tasksCard(),
      h(
        "div",
        { class: "card" },