fix(cache): honest settings card — clean threshold, live stats, no-embedder warning

Full audit of the semantic cache against a live instance (mock embedder,
identical requests): the mechanism works — miss at 3.1s, then hits at 2ms
with entries/hits/saved-$ counting. Two honest gaps fixed:

- the threshold round-tripped through f32 and rendered as
  0.9200000166893005 in both the TOML and the settings input — the config
  field is f64 now (writes exactly what you typed) and the input rounds
  legacy values to 2 decimals;
- the card now shows proof of life (entries / hits / hit-rate / saved $)
  and, when the cache is enabled with NO embedding model available, a
  warning that it is silently doing nothing and how to fix it — previously
  that state looked identical to a working cache.

Also audited in the same pass, no changes needed: Prometheus /metrics
(toggle on/off applies live, 404 when off), and all 7 protocol switches
(each gates its endpoint instantly both ways). 4 strings ×7 languages.

src/cache.rs

@@ -55,7 +55,7 @@ impl SemanticCache {
     pub fn new(cfg: &CacheCfg) -> Arc<Self> {
         Arc::new(Self {
             enabled: cfg.enabled,
-            threshold: cfg.threshold,
+            threshold: cfg.threshold as f32,
             ttl_secs: parse_duration_secs(&cfg.ttl).unwrap_or(3600),
             max_entries: cfg.max_entries.max(1),
             embed_model: cfg.embed_model.clone(),

src/config.rs

@@ -829,9 +829,10 @@ fn default_shadow_soak() -> usize {
 pub struct CacheCfg {
     #[serde(default)]
     pub enabled: bool,
-    /// Cosine-similarity threshold for a hit (0..1).
+    /// Cosine-similarity threshold for a hit (0..1). f64 so the TOML holds
+    /// the number you typed (an f32 round-trips as 0.9200000166893005).
     #[serde(default = "default_semcache_threshold")]
-    pub threshold: f32,
+    pub threshold: f64,
     /// Entry time-to-live, e.g. `1h`.
     #[serde(default = "default_semcache_ttl")]
     pub ttl: String,
@@ -853,7 +854,7 @@ impl Default for CacheCfg {
         }
     }
 }
-fn default_semcache_threshold() -> f32 {
+fn default_semcache_threshold() -> f64 {
     0.92
 }
 fn default_semcache_ttl() -> String {

web/js/i18n/de.js

@@ -635,4 +635,8 @@ export default {
   "tier.medium": "mittel",
   "tier.high": "schwer",
   "bm.scoreHint": "Der kontinuierliche Komplexitätsscore des Routers (0..1) — die Grenzregler auf der Routing-Seite teilen ihn in Stufen.",
+  "settings.cache.noEmbed": "Der Cache ist aktiviert, hat aber KEIN Embedding-Modell — er tut nichts. Fügen Sie dem Pool ein Modell mit kind = \"embedding\" hinzu (z. B. OpenAI text-embedding) oder wählen Sie unten eines.",
+  "settings.cache.entries": "Einträge",
+  "settings.cache.hits": "Treffer",
+  "settings.cache.saved": "gespart",
 };

web/js/i18n/en.js

@@ -628,4 +628,8 @@ export default {
   "tier.medium": "medium",
   "tier.high": "high",
   "bm.scoreHint": "The router's continuous complexity score (0..1) — the boundary sliders on the Routing page cut it into tiers.",
+  "settings.cache.noEmbed": "The cache is enabled but has NO embedding model to work with — it is doing nothing. Add a model with kind = \"embedding\" to the pool (e.g. an OpenAI text-embedding model) or pick one below.",
+  "settings.cache.entries": "entries",
+  "settings.cache.hits": "hits",
+  "settings.cache.saved": "saved",
 };

web/js/i18n/es.js

@@ -635,4 +635,8 @@ export default {
   "tier.medium": "medio",
   "tier.high": "difícil",
   "bm.scoreHint": "La puntuación continua de complejidad del router (0..1) — los deslizadores de límites de la página Enrutado la dividen en niveles.",
+  "settings.cache.noEmbed": "La caché está activada pero NO tiene modelo de embeddings — no hace nada. Añade al pool un modelo con kind = \"embedding\" (p. ej. OpenAI text-embedding) o elige uno abajo.",
+  "settings.cache.entries": "entradas",
+  "settings.cache.hits": "aciertos",
+  "settings.cache.saved": "ahorrado",
 };

web/js/i18n/fr.js

@@ -635,4 +635,8 @@ export default {
   "tier.medium": "moyen",
   "tier.high": "difficile",
   "bm.scoreHint": "Le score de complexité continu du routeur (0..1) — les curseurs de limites de la page Routage le découpent en niveaux.",
+  "settings.cache.noEmbed": "Le cache est activé mais n'a AUCUN modèle d'embedding — il ne fait rien. Ajoutez au pool un modèle avec kind = \"embedding\" (p. ex. OpenAI text-embedding) ou choisissez-en un ci-dessous.",
+  "settings.cache.entries": "entrées",
+  "settings.cache.hits": "hits",
+  "settings.cache.saved": "économisé",
 };

web/js/i18n/ru.js

@@ -627,4 +627,8 @@ export default {
   "tier.medium": "средний",
   "tier.high": "сложный",
   "bm.scoreHint": "Непрерывный коэффициент сложности роутера (0..1) — ползунки границ на вкладке Роутинг нарезают его на уровни.",
+  "settings.cache.noEmbed": "Кэш включён, но embedding-модели нет — он ничего не делает. Добавьте в пул модель с kind = \"embedding\" (например, OpenAI text-embedding) или выберите её ниже.",
+  "settings.cache.entries": "записей",
+  "settings.cache.hits": "попаданий",
+  "settings.cache.saved": "сэкономлено",
 };

web/js/i18n/tr.js

@@ -635,4 +635,8 @@ export default {
   "tier.medium": "orta",
   "tier.high": "zor",
   "bm.scoreHint": "Yönlendiricinin sürekli karmaşıklık puanı (0..1) — Yönlendirme sayfasındaki sınır kaydırıcıları onu katmanlara böler.",
+  "settings.cache.noEmbed": "Önbellek açık ama çalışacağı bir embedding modeli YOK — hiçbir şey yapmıyor. Havuza kind = \"embedding\" olan bir model ekleyin (örn. OpenAI text-embedding) veya aşağıdan seçin.",
+  "settings.cache.entries": "kayıt",
+  "settings.cache.hits": "isabet",
+  "settings.cache.saved": "tasarruf",
 };

web/js/i18n/zh.js

@@ -635,4 +635,8 @@ export default {
   "tier.medium": "中等",
   "tier.high": "困难",
   "bm.scoreHint": "路由器的连续复杂度得分（0..1）— 路由页面上的边界滑块将其划分为层级。",
+  "settings.cache.noEmbed": "缓存已启用，但没有可用的 embedding 模型 — 它没有任何作用。请向模型池添加 kind = \"embedding\" 的模型（如 OpenAI text-embedding），或在下方选择。",
+  "settings.cache.entries": "条目",
+  "settings.cache.hits": "命中",
+  "settings.cache.saved": "已节省",
 };

web/js/views/settings.js

@@ -194,8 +194,30 @@ export async function renderSettings() {
   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, t("settings.cache.enabledHelp"));
-  const cacheThresh = h("input", { type: "number", step: "0.01", value: s.cache?.threshold ?? 0.92 });
+  const cacheThresh = h("input", { type: "number", step: "0.01", min: "0.5", max: "0.999", value: Math.round(((s.cache?.threshold ?? 0.92) + Number.EPSILON) * 100) / 100 });
   const cacheTtlIn = h("input", { value: s.cache?.ttl || "1h" });
+  // Live proof-of-life for the cache card: entries/hits/saved — and an
+  // honest warning when the cache is on but has no embedding model to work
+  // with (it silently does nothing in that state).
+  let cacheStats = null;
+  try {
+    cacheStats = (await api.stats("24h", "model")).cache || null;
+  } catch { /* stats off */ }
+  function cacheStatus() {
+    const wrap = h("div", { style: "margin-bottom:10px" });
+    if (s.cache?.enabled && embedModels.length === 0 && !s.cache?.embed_model) {
+      mount(wrap, h("div", { class: "callout warn" }, "⚠ " + t("settings.cache.noEmbed")));
+      return wrap;
+    }
+    if (cacheStats && s.cache?.enabled) {
+      mount(wrap, h("div", { class: "flex wrap", style: "gap:8px" },
+        h("span", { class: "badge" }, t("settings.cache.entries") + ": " + cacheStats.entries),
+        h("span", { class: "badge ok" }, t("settings.cache.hits") + ": " + cacheStats.hits),
+        h("span", { class: "badge" }, "hit-rate " + Math.round((cacheStats.hit_rate || 0) * 100) + "%"),
+        h("span", { class: "badge" }, t("settings.cache.saved") + " $" + (cacheStats.saved_usd || 0).toFixed(4))));
+    }
+    return wrap;
+  }
   const cacheEmbedSel = h(
     "select",
     {},
@@ -610,6 +632,7 @@ export async function renderSettings() {
         "div",
         { class: "card" },
         h("div", { class: "card-head" }, h("h3", {}, t("settings.cache"))),
+        cacheStatus(),
         cacheEnabled.node,
         h("div", { class: "row" }, field(t("settings.cache.threshold"), cacheThresh), field(t("settings.cache.ttl"), cacheTtlIn)),
         field(t("settings.cache.embed"), cacheEmbedSel),