feat: semantic (embedding-based) response cache

- cache.rs: cosine-similarity store (threshold, TTL, ring buffer), partitioned by
  routing signature; tracks hit rate and model cost saved
- pipeline: embed routing text, look up before the model call (route_source=cache on
  hit), insert successful responses; stats record cache hits
- config [cache] + admin settings card; dashboard shows hit-rate and savings
- embedding model resolved from the pool (or first kind="embedding")

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

web/js/i18n/de.js

@@ -254,4 +254,15 @@ export default {
   "toast.deleted": "Gelöscht",
   "toast.probing": "Prüfe…",
   "toast.imported": "Konfiguration importiert",
+  "dash.cache": "Semantischer Cache",
+  "dash.cache.hitRate": "Trefferquote",
+  "dash.cache.hits": "Treffer",
+  "dash.cache.saved": "Gespart",
+  "dash.cache.disabled": "Semantischer Cache ist deaktiviert — in den Einstellungen aktivieren.",
+  "settings.cache": "Semantischer Cache",
+  "settings.cache.enabled": "Semantischen Cache aktivieren",
+  "settings.cache.threshold": "Ähnlichkeitsschwelle",
+  "settings.cache.ttl": "Eintrags-TTL",
+  "settings.cache.embed": "Embedding-Modell",
+  "settings.cache.note": "Cache-Einstellungen werden nach einem Neustart wirksam.",
 };

web/js/i18n/en.js

@@ -255,4 +255,15 @@ export default {
   "toast.deleted": "Deleted",
   "toast.probing": "Probing…",
   "toast.imported": "Config imported",
+  "dash.cache": "Semantic cache",
+  "dash.cache.hitRate": "Hit rate",
+  "dash.cache.hits": "Hits",
+  "dash.cache.saved": "Saved",
+  "dash.cache.disabled": "Semantic cache is disabled — enable it in Settings.",
+  "settings.cache": "Semantic cache",
+  "settings.cache.enabled": "Enable semantic cache",
+  "settings.cache.threshold": "Similarity threshold",
+  "settings.cache.ttl": "Entry TTL",
+  "settings.cache.embed": "Embedding model",
+  "settings.cache.note": "Cache settings take effect after a restart.",
 };

web/js/i18n/es.js

@@ -254,4 +254,15 @@ export default {
   "toast.deleted": "Eliminado",
   "toast.probing": "Sondeando…",
   "toast.imported": "Configuración importada",
+  "dash.cache": "Caché semántico",
+  "dash.cache.hitRate": "Aciertos",
+  "dash.cache.hits": "Aciertos",
+  "dash.cache.saved": "Ahorrado",
+  "dash.cache.disabled": "El caché semántico está desactivado — actívalo en Ajustes.",
+  "settings.cache": "Caché semántico",
+  "settings.cache.enabled": "Activar caché semántico",
+  "settings.cache.threshold": "Umbral de similitud",
+  "settings.cache.ttl": "TTL de entrada",
+  "settings.cache.embed": "Modelo de embeddings",
+  "settings.cache.note": "Los ajustes del caché se aplican tras reiniciar.",
 };

web/js/i18n/fr.js

@@ -254,4 +254,15 @@ export default {
   "toast.deleted": "Supprimé",
   "toast.probing": "Sondage…",
   "toast.imported": "Config importée",
+  "dash.cache": "Cache sémantique",
+  "dash.cache.hitRate": "Taux de succès",
+  "dash.cache.hits": "Succès",
+  "dash.cache.saved": "Économisé",
+  "dash.cache.disabled": "Le cache sémantique est désactivé — activez-le dans les Paramètres.",
+  "settings.cache": "Cache sémantique",
+  "settings.cache.enabled": "Activer le cache sémantique",
+  "settings.cache.threshold": "Seuil de similarité",
+  "settings.cache.ttl": "TTL d'entrée",
+  "settings.cache.embed": "Modèle d'embeddings",
+  "settings.cache.note": "Les paramètres du cache prennent effet après un redémarrage.",
 };

web/js/i18n/ru.js

@@ -254,4 +254,15 @@ export default {
   "toast.deleted": "Удалено",
   "toast.probing": "Проверка…",
   "toast.imported": "Конфигурация импортирована",
+  "dash.cache": "Семантический кэш",
+  "dash.cache.hitRate": "Попаданий",
+  "dash.cache.hits": "Попадания",
+  "dash.cache.saved": "Сэкономлено",
+  "dash.cache.disabled": "Семантический кэш выключен — включите в Настройках.",
+  "settings.cache": "Семантический кэш",
+  "settings.cache.enabled": "Включить семантический кэш",
+  "settings.cache.threshold": "Порог сходства",
+  "settings.cache.ttl": "TTL записи",
+  "settings.cache.embed": "Модель эмбеддингов",
+  "settings.cache.note": "Настройки кэша применяются после перезапуска.",
 };

web/js/i18n/tr.js

@@ -254,4 +254,15 @@ export default {
   "toast.deleted": "Silindi",
   "toast.probing": "Sınanıyor…",
   "toast.imported": "Yapılandırma içe aktarıldı",
+  "dash.cache": "Anlamsal önbellek",
+  "dash.cache.hitRate": "İsabet oranı",
+  "dash.cache.hits": "İsabet",
+  "dash.cache.saved": "Tasarruf",
+  "dash.cache.disabled": "Anlamsal önbellek kapalı — Ayarlar'dan etkinleştirin.",
+  "settings.cache": "Anlamsal önbellek",
+  "settings.cache.enabled": "Anlamsal önbelleği etkinleştir",
+  "settings.cache.threshold": "Benzerlik eşiği",
+  "settings.cache.ttl": "Giriş TTL",
+  "settings.cache.embed": "Gömme modeli",
+  "settings.cache.note": "Anlamsal önbellek ayarları yeniden başlatmadan sonra geçerli olur.",
 };

web/js/i18n/zh.js

@@ -254,4 +254,15 @@ export default {
   "toast.deleted": "已删除",
   "toast.probing": "探测中…",
   "toast.imported": "配置已导入",
+  "dash.cache": "语义缓存",
+  "dash.cache.hitRate": "命中率",
+  "dash.cache.hits": "命中",
+  "dash.cache.saved": "已节省",
+  "dash.cache.disabled": "语义缓存已禁用 — 在设置中启用。",
+  "settings.cache": "语义缓存",
+  "settings.cache.enabled": "启用语义缓存",
+  "settings.cache.threshold": "相似度阈值",
+  "settings.cache.ttl": "条目 TTL",
+  "settings.cache.embed": "嵌入模型",
+  "settings.cache.note": "缓存设置将在重启后生效。",
 };

web/js/views/dashboard.js

@@ -108,6 +108,22 @@ export async function renderDashboard() {
         barList(breakdown, num)
       ),
 
+      // semantic cache
+      stats.cache && stats.cache.enabled
+        ? h(
+            "div",
+            { class: "card" },
+            h("div", { class: "card-head" }, h("h3", {}, t("dash.cache"))),
+            h(
+              "div",
+              { class: "kpis" },
+              kpi(pct(stats.cache.hit_rate), t("dash.cache.hitRate")),
+              kpi(num(stats.cache.hits), t("dash.cache.hits")),
+              kpi(money(stats.cache.saved_usd), t("dash.cache.saved"))
+            )
+          )
+        : null,
+
       // recent
       h(
         "div",

web/js/views/settings.js

@@ -42,6 +42,18 @@ export async function renderSettings() {
   const statsEnabled = check(t("settings.stats.enabled"), s.stats?.enabled);
   const statsFile = h("input", { value: s.stats?.file || "" });
   const statsRet = h("input", { value: s.stats?.retention || "7d" });
+  // cache
+  const modelsData = await api.listModels();
+  const embedModels = (modelsData.models || []).filter((m) => m.kind === "embedding").map((m) => m.id);
+  const cacheEnabled = check(t("settings.cache.enabled"), s.cache?.enabled);
+  const cacheThresh = h("input", { type: "number", step: "0.01", value: s.cache?.threshold ?? 0.92 });
+  const cacheTtlIn = h("input", { value: s.cache?.ttl || "1h" });
+  const cacheEmbedSel = h(
+    "select",
+    {},
+    h("option", { value: "" }, "auto"),
+    ...embedModels.map((id) => h("option", { value: id, selected: id === s.cache?.embed_model }, id))
+  );
 
   const saveBtn = h("button", { class: "btn primary" }, t("common.save"));
   saveBtn.addEventListener("click", async () => {
@@ -71,11 +83,19 @@ export async function renderSettings() {
         retention: statsRet.value.trim() || "7d",
         ring_size: s.stats?.ring_size ?? 500,
       },
+      cache: {
+        enabled: cacheEnabled.cb.checked,
+        threshold: parseFloat(cacheThresh.value) || 0.92,
+        ttl: cacheTtlIn.value.trim() || "1h",
+        max_entries: s.cache?.max_entries ?? 1000,
+        embed_model: cacheEmbedSel.value || null,
+      },
     };
     // serde: drop null optionals
     if (!patch.router.api_key_env) delete patch.router.api_key_env;
     if (!patch.router.taxonomy_id) delete patch.router.taxonomy_id;
     if (!patch.telemetry.otlp_endpoint_env) delete patch.telemetry.otlp_endpoint_env;
+    if (!patch.cache.embed_model) delete patch.cache.embed_model;
     try {
       const r = await api.putSettings(patch);
       toast(r.needs_restart ? t("settings.needsRestart") : t("toast.saved"), r.needs_restart ? "warn" : "good");
@@ -170,6 +190,15 @@ export async function renderSettings() {
         statsEnabled.node,
         field(t("settings.stats.file"), statsFile),
         field(t("settings.stats.retention"), statsRet)
+      ),
+      h(
+        "div",
+        { class: "card" },
+        h("div", { class: "card-head" }, h("h3", {}, t("settings.cache"))),
+        cacheEnabled.node,
+        h("div", { class: "row" }, field(t("settings.cache.threshold"), cacheThresh), field(t("settings.cache.ttl"), cacheTtlIn)),
+        field(t("settings.cache.embed"), cacheEmbedSel),
+        h("div", { class: "hint" }, t("settings.cache.note"))
       )
     ),
     h(