feat(dashboard): add Cache Management page with stats, hit rate, and targeted invalidation (#701)

Adds a new /dashboard/cache page that surfaces the existing but UI-less semantic cache infrastructure. Changes: - New page: src/app/(dashboard)/dashboard/cache/page.tsx - Live stats: memory entries, DB entries, cache hits, tokens saved - Hit rate progress bar with color coding (green/yellow/red) - Hits/Misses/Total breakdown - Idempotency layer stats (active dedup keys + window) - Cache behavior info panel - Clear All button - Auto-refresh every 10s - Enhanced API: src/app/api/cache/route.ts - DELETE ?model=<name> — invalidate by model - DELETE ?signature=<hex> — invalidate single entry - DELETE ?staleMs=<ms> — invalidate entries older than N ms - DELETE (no params) — clear all (existing behavior) - Sidebar: added Cache nav item (icon: cached) - i18n: added cache + sidebar.cache keys for all 31 supported locales No new dependencies. All functionality builds on existing semanticCache.ts, cacheLayer.ts, and idempotencyLayer.ts modules. Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
2026-07-26 09:52:11 +03:00 · 2026-03-29 06:39:20 +07:00
parent dd9de2efa9
commit e6f0a780b7
37 changed files with 1534 additions and 44 deletions
--- a/package-lock.json
+++ b/package-lock.json
@@ -10697,6 +10697,7 @@
      "version": "2.3.2",
      "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
      "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
+      "dev": true,
      "hasInstallScript": true,
      "license": "MIT",
      "optional": true,
@@ -15527,9 +15528,9 @@
      }
    },
    "node_modules/path-to-regexp": {
-      "version": "8.3.0",
-      "resolved": "https://registry.npmjs.org/path-to-regexp/-/path-to-regexp-8.3.0.tgz",
-      "integrity": "sha512-7jdwVIRtsP8MYpdXSwOS0YdD0Du+qOoF/AEPIt88PcCFrZCzx41oxku1jD88hZBwbNUIEfpqvuhjFaMAqMTWnA==",
+      "version": "8.4.0",
+      "resolved": "https://registry.npmjs.org/path-to-regexp/-/path-to-regexp-8.4.0.tgz",
+      "integrity": "sha512-PuseHIvAnz3bjrM2rGJtSgo1zjgxapTLZ7x2pjhzWwlp4SJQgK3f3iZIQwkpEnBaKz6seKBADpM4B4ySkuYypg==",
      "license": "MIT",
      "funding": {
        "type": "opencollective",
--- a/package.json
+++ b/package.json
@@ -161,6 +161,7 @@
    ]
  },
  "overrides": {
-    "dompurify": "^3.3.2"
+    "dompurify": "^3.3.2",
+    "path-to-regexp": "^8.4.0"
  }
 }
--- a/src/app/(dashboard)/dashboard/cache/page.tsx
+++ b/src/app/(dashboard)/dashboard/cache/page.tsx
@@ -0,0 +1,340 @@
+"use client";
+
+import { useState, useEffect, useCallback } from "react";
+import { Card, Button, EmptyState } from "@/shared/components";
+import { useNotificationStore } from "@/store/notificationStore";
+import { useTranslations } from "next-intl";
+
+// ─── Types ───────────────────────────────────────────────────────────────────
+
+interface SemanticCacheStats {
+  memoryEntries: number;
+  dbEntries: number;
+  hits: number;
+  misses: number;
+  hitRate: string;
+  tokensSaved: number;
+}
+
+interface IdempotencyStats {
+  activeKeys: number;
+  windowMs: number;
+}
+
+interface CacheStats {
+  semanticCache: SemanticCacheStats;
+  idempotency: IdempotencyStats;
+}
+
+// ─── Sub-components ──────────────────────────────────────────────────────────
+
+function StatCard({
+  icon,
+  label,
+  value,
+  sub,
+  valueClass = "text-text",
+}: {
+  icon: string;
+  label: string;
+  value: string | number;
+  sub?: string;
+  valueClass?: string;
+}) {
+  return (
+    <div className="flex flex-col gap-1 p-4 rounded-xl bg-surface-raised border border-border/40">
+      <div className="flex items-center gap-1.5 text-text-muted text-xs">
+        <span className="material-symbols-outlined text-base leading-none" aria-hidden="true">
+          {icon}
+        </span>
+        {label}
+      </div>
+      <div className={`text-2xl font-semibold tabular-nums ${valueClass}`}>{value}</div>
+      {sub && <div className="text-xs text-text-muted">{sub}</div>}
+    </div>
+  );
+}
+
+function HitRateBar({ hitRate, label }: { hitRate: number; label: string }) {
+  const colorClass = hitRate >= 70 ? "bg-green-500" : hitRate >= 40 ? "bg-amber-400" : "bg-red-500";
+  const textClass =
+    hitRate >= 70 ? "text-green-500" : hitRate >= 40 ? "text-amber-400" : "text-red-500";
+
+  return (
+    <div
+      className="w-full"
+      role="progressbar"
+      aria-label={label}
+      aria-valuenow={hitRate}
+      aria-valuemin={0}
+      aria-valuemax={100}
+    >
+      <div className="flex justify-between text-xs mb-1.5">
+        <span className="text-text-muted">{label}</span>
+        <span className={`font-semibold tabular-nums ${textClass}`}>{hitRate.toFixed(1)}%</span>
+      </div>
+      <div className="w-full h-2 rounded-full bg-surface/50 overflow-hidden">
+        <div
+          className={`h-full rounded-full transition-all duration-500 ${colorClass}`}
+          style={{ width: `${Math.min(hitRate, 100)}%` }}
+        />
+      </div>
+    </div>
+  );
+}
+
+function InfoRow({ icon, children }: { icon: string; children: React.ReactNode }) {
+  return (
+    <div className="flex gap-2 text-sm text-text-muted">
+      <span
+        className="material-symbols-outlined text-base leading-5 text-blue-400 shrink-0"
+        aria-hidden="true"
+      >
+        {icon}
+      </span>
+      <span>{children}</span>
+    </div>
+  );
+}
+
+// ─── Page ────────────────────────────────────────────────────────────────────
+
+const REFRESH_INTERVAL_MS = 10_000;
+const REFRESH_INTERVAL_SECONDS = REFRESH_INTERVAL_MS / 1000;
+
+export default function CachePage() {
+  const t = useTranslations("cache");
+  const [stats, setStats] = useState<CacheStats | null>(null);
+  const [loading, setLoading] = useState(true);
+  const [clearing, setClearing] = useState(false);
+  const notify = useNotificationStore();
+
+  const fetchStats = useCallback(async () => {
+    try {
+      const res = await fetch("/api/cache");
+      if (res.ok) {
+        const data: CacheStats = await res.json();
+        setStats(data);
+      }
+    } catch (error) {
+      // Network error — keep stale stats rather than clearing the UI
+      console.error("[CachePage] Failed to fetch cache stats:", error);
+    } finally {
+      setLoading(false);
+    }
+  }, []);
+
+  useEffect(() => {
+    void fetchStats();
+    const id = setInterval(() => void fetchStats(), REFRESH_INTERVAL_MS);
+    return () => clearInterval(id);
+  }, [fetchStats]);
+
+  const handleClearAll = async () => {
+    setClearing(true);
+    try {
+      const res = await fetch("/api/cache", { method: "DELETE" });
+      if (res.ok) {
+        const data = await res.json();
+        notify.add({
+          type: "success",
+          message: t("clearSuccess", { count: data.expiredRemoved ?? 0 }),
+        });
+        await fetchStats();
+      } else {
+        notify.add({ type: "error", message: t("clearError") });
+      }
+    } catch (error) {
+      console.error("[CachePage] Failed to clear cache:", error);
+      notify.add({ type: "error", message: t("clearError") });
+    } finally {
+      setClearing(false);
+    }
+  };
+
+  const sc = stats?.semanticCache;
+  const idp = stats?.idempotency;
+  const hitRate = sc ? parseFloat(sc.hitRate) : 0;
+  const totalRequests = sc ? sc.hits + sc.misses : 0;
+
+  return (
+    <div className="flex flex-col gap-6">
+      {/* Header */}
+      <div className="flex items-start justify-between gap-4">
+        <div>
+          <h1 className="text-xl font-semibold">{t("title")}</h1>
+          <p className="text-sm text-text-muted mt-0.5">{t("description")}</p>
+        </div>
+        <div className="flex gap-2 shrink-0">
+          <Button
+            variant="secondary"
+            icon="refresh"
+            size="sm"
+            onClick={() => void fetchStats()}
+            disabled={loading}
+            aria-label={t("refresh")}
+          >
+            {t("refresh")}
+          </Button>
+          <Button
+            variant="danger"
+            icon="delete_sweep"
+            size="sm"
+            onClick={() => void handleClearAll()}
+            disabled={clearing || loading}
+            loading={clearing}
+            aria-label={t("clearAll")}
+          >
+            {t("clearAll")}
+          </Button>
+        </div>
+      </div>
+
+      {/* Loading skeleton */}
+      {loading && (
+        <div
+          className="grid grid-cols-2 md:grid-cols-4 gap-4"
+          aria-busy="true"
+          aria-label="Loading cache statistics"
+        >
+          {Array.from({ length: 4 }).map((_, i) => (
+            <div key={i} className="h-24 rounded-xl bg-surface-raised animate-pulse" />
+          ))}
+        </div>
+      )}
+
+      {/* Error / empty state */}
+      {!loading && !stats && (
+        <EmptyState
+          icon="cached"
+          title={t("unavailable")}
+          description={t("unavailableDesc")}
+          actionLabel={t("refresh")}
+          onAction={() => void fetchStats()}
+        />
+      )}
+
+      {/* Main content */}
+      {!loading && stats && (
+        <>
+          {/* Stats grid */}
+          <div className="grid grid-cols-2 md:grid-cols-4 gap-4">
+            <StatCard
+              icon="memory"
+              label={t("memoryEntries")}
+              value={sc?.memoryEntries ?? 0}
+              sub={t("memoryEntriesSub")}
+            />
+            <StatCard
+              icon="storage"
+              label={t("dbEntries")}
+              value={sc?.dbEntries ?? 0}
+              sub={t("dbEntriesSub")}
+            />
+            <StatCard
+              icon="trending_up"
+              label={t("cacheHits")}
+              value={sc?.hits ?? 0}
+              sub={t("cacheHitsSub", { total: totalRequests })}
+              valueClass="text-green-500"
+            />
+            <StatCard
+              icon="token"
+              label={t("tokensSaved")}
+              value={(sc?.tokensSaved ?? 0).toLocaleString()}
+              sub={t("tokensSavedSub")}
+              valueClass="text-blue-400"
+            />
+          </div>
+
+          {/* Hit rate + breakdown */}
+          <Card>
+            <div className="p-5 flex flex-col gap-4">
+              <div className="flex items-center justify-between">
+                <h2 className="font-medium text-sm">{t("performance")}</h2>
+                <span className="text-xs text-text-muted">
+                  {t("autoRefresh", { seconds: REFRESH_INTERVAL_SECONDS })}
+                </span>
+              </div>
+              <HitRateBar hitRate={hitRate} label={t("hitRate")} />
+              <div className="grid grid-cols-3 gap-4 pt-3 border-t border-border/30 text-center">
+                <div>
+                  <div className="text-lg font-semibold tabular-nums text-green-500">
+                    {sc?.hits ?? 0}
+                  </div>
+                  <div className="text-xs text-text-muted mt-0.5">{t("hits")}</div>
+                </div>
+                <div>
+                  <div className="text-lg font-semibold tabular-nums text-red-400">
+                    {sc?.misses ?? 0}
+                  </div>
+                  <div className="text-xs text-text-muted mt-0.5">{t("misses")}</div>
+                </div>
+                <div>
+                  <div className="text-lg font-semibold tabular-nums">{totalRequests}</div>
+                  <div className="text-xs text-text-muted mt-0.5">{t("total")}</div>
+                </div>
+              </div>
+            </div>
+          </Card>
+
+          {/* Cache behavior */}
+          <Card>
+            <div className="p-5 flex flex-col gap-3">
+              <h2 className="font-medium text-sm">{t("behavior")}</h2>
+              <div className="grid grid-cols-1 md:grid-cols-2 gap-3">
+                <InfoRow icon="info">{t("behaviorDeterministic")}</InfoRow>
+                <InfoRow icon="info">
+                  {t.rich("behaviorBypass", {
+                    header: () => (
+                      <code className="bg-surface px-1 py-0.5 rounded text-xs font-mono">
+                        X-OmniRoute-No-Cache: true
+                      </code>
+                    ),
+                  })}
+                </InfoRow>
+                <InfoRow icon="info">{t("behaviorTwoTier")}</InfoRow>
+                <InfoRow icon="info">
+                  {t.rich("behaviorTtl", {
+                    envVar: () => (
+                      <code className="bg-surface px-1 py-0.5 rounded text-xs font-mono">
+                        SEMANTIC_CACHE_TTL_MS
+                      </code>
+                    ),
+                  })}
+                </InfoRow>
+              </div>
+            </div>
+          </Card>
+
+          {/* Idempotency */}
+          <Card>
+            <div className="p-5 flex flex-col gap-3">
+              <div className="flex items-center gap-2">
+                <span
+                  className="material-symbols-outlined text-base text-text-muted"
+                  aria-hidden="true"
+                >
+                  fingerprint
+                </span>
+                <h2 className="font-medium text-sm">{t("idempotency")}</h2>
+              </div>
+              <div className="grid grid-cols-2 gap-4">
+                <div className="p-3 rounded-lg bg-surface/50">
+                  <div className="text-lg font-semibold tabular-nums">{idp?.activeKeys ?? 0}</div>
+                  <div className="text-xs text-text-muted mt-0.5">{t("activeDedupKeys")}</div>
+                </div>
+                <div className="p-3 rounded-lg bg-surface/50">
+                  <div className="text-lg font-semibold tabular-nums">
+                    {idp ? `${(idp.windowMs / 1000).toFixed(0)}s` : "—"}
+                  </div>
+                  <div className="text-xs text-text-muted mt-0.5">{t("dedupWindow")}</div>
+                </div>
+              </div>
+            </div>
+          </Card>
+        </>
+      )}
+    </div>
+  );
+}
--- a/src/app/api/cache/route.ts
+++ b/src/app/api/cache/route.ts
@@ -1,7 +1,18 @@
-import { NextResponse } from "next/server";
-import { getCacheStats, clearCache, cleanExpiredEntries } from "@/lib/semanticCache";
+import { NextRequest, NextResponse } from "next/server";
+import {
+  getCacheStats,
+  clearCache,
+  cleanExpiredEntries,
+  invalidateByModel,
+  invalidateBySignature,
+  invalidateStale,
+} from "@/lib/semanticCache";
 import { getIdempotencyStats } from "@/lib/idempotencyLayer";

+function errorMessage(error: unknown): string {
+  return error instanceof Error ? error.message : String(error);
+}
+
 /**
 * GET /api/cache — Cache statistics
 */
@@ -15,19 +26,67 @@ export async function GET() {
      idempotency: idempotencyStats,
    });
  } catch (error) {
-    return NextResponse.json({ error: error.message }, { status: 500 });
+    return NextResponse.json({ error: errorMessage(error) }, { status: 500 });
  }
 }

 /**
- * DELETE /api/cache — Clear all caches
+ * DELETE /api/cache — Clear all caches or targeted invalidation.
+ *
+ * Exactly one optional query parameter may be provided:
+ *   ?model=<name>      — invalidate all entries for a specific model
+ *   ?signature=<hex>   — invalidate a single entry by its SHA-256 signature
+ *   ?staleMs=<number>  — invalidate entries older than N milliseconds
+ *   (no params)        — clear all cache entries
+ *
+ * Providing more than one parameter returns 400 Bad Request.
 */
-export async function DELETE() {
+export async function DELETE(req: NextRequest) {
  try {
+    const { searchParams } = new URL(req.url);
+    const model = searchParams.get("model");
+    const signature = searchParams.get("signature");
+    const staleMsParam = searchParams.get("staleMs");
+
+    // Enforce mutual exclusivity — only one invalidation mode per request
+    const paramCount = [model, signature, staleMsParam].filter(Boolean).length;
+    if (paramCount > 1) {
+      return NextResponse.json(
+        {
+          error:
+            "Only one invalidation parameter (model, signature, or staleMs) may be provided per request.",
+        },
+        { status: 400 }
+      );
+    }
+
+    if (model) {
+      const removed = invalidateByModel(model);
+      return NextResponse.json({ ok: true, invalidated: removed, scope: "model", model });
+    }
+
+    if (signature) {
+      const removed = invalidateBySignature(signature);
+      return NextResponse.json({ ok: true, invalidated: removed ? 1 : 0, scope: "signature" });
+    }
+
+    if (staleMsParam) {
+      const maxAgeMs = parseInt(staleMsParam, 10);
+      if (Number.isNaN(maxAgeMs) || maxAgeMs <= 0) {
+        return NextResponse.json(
+          { error: "staleMs must be a positive integer (milliseconds)." },
+          { status: 400 }
+        );
+      }
+      const removed = invalidateStale(maxAgeMs);
+      return NextResponse.json({ ok: true, invalidated: removed, scope: "stale", maxAgeMs });
+    }
+
+    // Full clear
    clearCache();
-    const cleaned = cleanExpiredEntries();
-    return NextResponse.json({ ok: true, expiredRemoved: cleaned });
+    const expiredRemoved = cleanExpiredEntries();
+    return NextResponse.json({ ok: true, expiredRemoved, scope: "all" });
  } catch (error) {
-    return NextResponse.json({ error: error.message }, { status: 500 });
+    return NextResponse.json({ error: errorMessage(error) }, { status: 500 });
  }
 }
--- a/src/i18n/messages/ar.json
+++ b/src/i18n/messages/ar.json
@@ -185,7 +185,9 @@
    "agents": "وكلاء",
    "cliToolsShort": "أدوات",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "المواضيع",
@@ -2847,5 +2849,37 @@
      "userInitial": "انا بحاجة الى مساعدة مع",
      "userFollowUp": "هل يمكنك توضيح ذلك؟"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/bg.json
+++ b/src/i18n/messages/bg.json
@@ -185,7 +185,9 @@
    "agents": "Агенти",
    "cliToolsShort": "Инструменти",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Теми",
@@ -2847,5 +2849,37 @@
      "userInitial": "Имам нужда от помощ за",
      "userFollowUp": "Можете ли да разкажете по-подробно за това?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/cs.json
+++ b/src/i18n/messages/cs.json
@@ -185,7 +185,9 @@
    "themeViolet": "Fialová",
    "themeOrange": "Oranžová",
    "themeCyan": "Azurová",
-    "cliToolsShort": "Nástroje"
+    "cliToolsShort": "Nástroje",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Motivy",
@@ -2847,5 +2849,37 @@
      "userInitial": "Potřebuji pomoct",
      "userFollowUp": "Můžete to upřesnit?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/da.json
+++ b/src/i18n/messages/da.json
@@ -185,7 +185,9 @@
    "agents": "Agenter",
    "cliToolsShort": "Værktøjer",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Temaer",
@@ -2847,5 +2849,37 @@
      "userInitial": "Jeg har brug for hjælp til",
      "userFollowUp": "Kan du uddybe det?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/de.json
+++ b/src/i18n/messages/de.json
@@ -185,7 +185,9 @@
    "agents": "Agenten",
    "cliToolsShort": "Werkzeuge",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themen",
@@ -2847,5 +2849,37 @@
      "userInitial": "Ich brauche Hilfe dabei",
      "userFollowUp": "Können Sie das näher erläutern?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/en.json
+++ b/src/i18n/messages/en.json
@@ -185,7 +185,9 @@
    "themeViolet": "Violet",
    "themeOrange": "Orange",
    "themeCyan": "Cyan",
-    "cliToolsShort": "Tools"
+    "cliToolsShort": "Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2849,5 +2851,37 @@
      "userInitial": "I need help with",
      "userFollowUp": "Can you elaborate on that?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntries": "DB Entries",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHits": "Cache Hits",
+    "cacheHitsSub": "of {total} total",
+    "tokensSaved": "Tokens Saved",
+    "tokensSavedSub": "Estimated from hits",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behavior": "Cache Behavior",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "idempotency": "Idempotency Layer",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running."
  }
 }
--- a/src/i18n/messages/es.json
+++ b/src/i18n/messages/es.json
@@ -185,7 +185,9 @@
    "agents": "Agentes",
    "cliToolsShort": "Herramientas",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Temas",
@@ -2847,5 +2849,37 @@
      "userInitial": "necesito ayuda con",
      "userFollowUp": "¿Puedes dar más detalles sobre eso?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/fi.json
+++ b/src/i18n/messages/fi.json
@@ -185,7 +185,9 @@
    "agents": "Agentit",
    "cliToolsShort": "Työkalut",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Teemat",
@@ -2847,5 +2849,37 @@
      "userInitial": "Tarvitsen apua",
      "userFollowUp": "Voitko tarkentaa sitä?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/fr.json
+++ b/src/i18n/messages/fr.json
@@ -185,7 +185,9 @@
    "agents": "Agents",
    "cliToolsShort": "Outils",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Thèmes",
@@ -2847,5 +2849,37 @@
      "userInitial": "J'ai besoin d'aide pour",
      "userFollowUp": "Pouvez-vous développer cela ?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/he.json
+++ b/src/i18n/messages/he.json
@@ -185,7 +185,9 @@
    "agents": "סוכנים",
    "cliToolsShort": "כלים",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "אני צריך עזרה עם",
      "userFollowUp": "אתה יכול לפרט על זה?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/hi.json
+++ b/src/i18n/messages/hi.json
@@ -107,7 +107,9 @@
    "agents": "एजेंट",
    "cliToolsShort": "उपकरण",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2689,5 +2691,37 @@
    "domainPlaceholder": "example.com",
    "requestTimedOut": "Request timed out ({seconds}s)",
    "networkError": "Network error"
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/hu.json
+++ b/src/i18n/messages/hu.json
@@ -185,7 +185,9 @@
    "agents": "Ügynökök",
    "cliToolsShort": "Eszközök",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Témák",
@@ -2847,5 +2849,37 @@
      "userInitial": "Segítségre van szükségem",
      "userFollowUp": "Kifejtenéd ezt bővebben?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/id.json
+++ b/src/i18n/messages/id.json
@@ -185,7 +185,9 @@
    "agents": "Agen",
    "cliToolsShort": "Alat",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Saya butuh bantuan",
      "userFollowUp": "Bisakah Anda menjelaskannya lebih lanjut?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/in.json
+++ b/src/i18n/messages/in.json
@@ -185,7 +185,9 @@
    "themeViolet": "बैंगनी",
    "themeOrange": "नारंगी",
    "themeCyan": "सियान",
-    "cliToolsShort": "उपकरण"
+    "cliToolsShort": "उपकरण",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "थीम्स",
@@ -2843,5 +2845,37 @@
      "userInitial": "मुझे मदद चाहिए",
      "userFollowUp": "क्या आप इसके बारे में विस्तार से बता सकते हैं?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/it.json
+++ b/src/i18n/messages/it.json
@@ -185,7 +185,9 @@
    "agents": "Agenti",
    "cliToolsShort": "Strumenti",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Ho bisogno di aiuto con",
      "userFollowUp": "Puoi approfondire questo argomento?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/ja.json
+++ b/src/i18n/messages/ja.json
@@ -185,7 +185,9 @@
    "agents": "エージェント",
    "cliToolsShort": "ツール",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "助けが必要です",
      "userFollowUp": "それについて詳しく教えてもらえますか？"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/ko.json
+++ b/src/i18n/messages/ko.json
@@ -185,7 +185,9 @@
    "agents": "에이전트",
    "cliToolsShort": "도구",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "도움이 필요해요",
      "userFollowUp": "그것에 대해 자세히 설명해주실 수 있나요?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/ms.json
+++ b/src/i18n/messages/ms.json
@@ -185,7 +185,9 @@
    "agents": "Ejen",
    "cliToolsShort": "Alat",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Saya perlukan bantuan",
      "userFollowUp": "Bolehkah anda menghuraikan perkara itu?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/nl.json
+++ b/src/i18n/messages/nl.json
@@ -185,7 +185,9 @@
    "agents": "Agenten",
    "cliToolsShort": "Gereedschap",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Ik heb hulp nodig bij",
      "userFollowUp": "Kunt u dat nader toelichten?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/no.json
+++ b/src/i18n/messages/no.json
@@ -185,7 +185,9 @@
    "agents": "Agenter",
    "cliToolsShort": "Verktøy",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Jeg trenger hjelp med",
      "userFollowUp": "Kan du utdype det?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/phi.json
+++ b/src/i18n/messages/phi.json
@@ -185,7 +185,9 @@
    "agents": "Mga Agent",
    "cliToolsShort": "Mga Tool",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Kailangan ko ng tulong sa",
      "userFollowUp": "Maaari mo bang ipaliwanag iyon?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/pl.json
+++ b/src/i18n/messages/pl.json
@@ -185,7 +185,9 @@
    "agents": "Agenci",
    "cliToolsShort": "Narzędzia",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Potrzebuję pomocy",
      "userFollowUp": "Możesz to rozwinąć?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/pt-BR.json
+++ b/src/i18n/messages/pt-BR.json
@@ -185,7 +185,9 @@
    "playground": "Playground",
    "agents": "Agentes",
    "cliToolsShort": "Ferramentas",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2865,5 +2867,37 @@
      "userInitial": "preciso de ajuda com",
      "userFollowUp": "Você pode explicar isso?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/pt.json
+++ b/src/i18n/messages/pt.json
@@ -185,7 +185,9 @@
    "agents": "Agentes",
    "cliToolsShort": "Ferramentas",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "preciso de ajuda com",
      "userFollowUp": "Você pode explicar isso?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/ro.json
+++ b/src/i18n/messages/ro.json
@@ -185,7 +185,9 @@
    "agents": "Agenți",
    "cliToolsShort": "Instrumente",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Am nevoie de ajutor cu",
      "userFollowUp": "Puteți detalia asta?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/ru.json
+++ b/src/i18n/messages/ru.json
@@ -185,7 +185,9 @@
    "agents": "Агенты",
    "cliToolsShort": "Инструменты",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Темы",
@@ -2847,5 +2849,37 @@
      "userInitial": "мне нужна помощь с",
      "userFollowUp": "Можете ли вы рассказать об этом подробнее?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/sk.json
+++ b/src/i18n/messages/sk.json
@@ -185,7 +185,9 @@
    "agents": "Agenti",
    "cliToolsShort": "Nástroje",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Potrebujem pomoc s",
      "userFollowUp": "Môžete to upresniť?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/sv.json
+++ b/src/i18n/messages/sv.json
@@ -185,7 +185,9 @@
    "agents": "Agenter",
    "cliToolsShort": "Verktyg",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Jag behöver hjälp med",
      "userFollowUp": "Kan du utveckla det?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/th.json
+++ b/src/i18n/messages/th.json
@@ -185,7 +185,9 @@
    "agents": "เอเจนต์",
    "cliToolsShort": "เครื่องมือ",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "ธีมส์",
@@ -2847,5 +2849,37 @@
      "userInitial": "ฉันต้องการความช่วยเหลือเกี่ยวกับ",
      "userFollowUp": "คุณช่วยอธิบายรายละเอียดเกี่ยวกับเรื่องนั้นได้ไหม?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/uk-UA.json
+++ b/src/i18n/messages/uk-UA.json
@@ -185,7 +185,9 @@
    "agents": "Агенти",
    "cliToolsShort": "Інструменти",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Мені потрібна допомога з",
      "userFollowUp": "Чи можете ви розповісти про це?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/vi.json
+++ b/src/i18n/messages/vi.json
@@ -185,7 +185,9 @@
    "agents": "Tác nhân",
    "cliToolsShort": "Công cụ",
    "autoCombo": "Auto Combo",
-    "searchTools": "Search Tools"
+    "searchTools": "Search Tools",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "Themes",
@@ -2847,5 +2849,37 @@
      "userInitial": "Tôi cần giúp đỡ với",
      "userFollowUp": "Bạn có thể giải thích về điều đó?"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/i18n/messages/zh-CN.json
+++ b/src/i18n/messages/zh-CN.json
@@ -185,7 +185,9 @@
    "themeViolet": "紫罗兰",
    "themeOrange": "橙色",
    "themeCyan": "青色",
-    "cliToolsShort": "工具"
+    "cliToolsShort": "工具",
+    "cache": "Cache",
+    "cacheShort": "Cache"
  },
  "themesPage": {
    "title": "主题",
@@ -2843,5 +2845,37 @@
      "userInitial": "我需要帮助来处理",
      "userFollowUp": "你可以再详细说明一下吗？"
    }
+  },
+  "cache": {
+    "title": "Cache Management",
+    "description": "Monitor and manage semantic response cache, hit rates, and token savings.",
+    "refresh": "Refresh",
+    "clearAll": "Clear All",
+    "memoryEntries": "Memory Entries",
+    "dbEntries": "DB Entries",
+    "cacheHits": "Cache Hits",
+    "tokensSaved": "Tokens Saved",
+    "hitRate": "Hit Rate",
+    "performance": "Cache Performance",
+    "behavior": "Cache Behavior",
+    "idempotency": "Idempotency Layer",
+    "clearSuccess": "Cache cleared. {count} expired entries removed.",
+    "clearError": "Failed to clear cache.",
+    "unavailable": "Cache unavailable",
+    "unavailableDesc": "Could not fetch cache statistics. Make sure the server is running.",
+    "memoryEntriesSub": "In-memory LRU",
+    "dbEntriesSub": "Persisted (SQLite)",
+    "cacheHitsSub": "of {total} total",
+    "tokensSavedSub": "Estimated from hits",
+    "autoRefresh": "Auto-refreshes every {seconds}s",
+    "hits": "Hits",
+    "misses": "Misses",
+    "total": "Total",
+    "behaviorDeterministic": "Only non-streaming requests with temperature=0 are cached.",
+    "behaviorBypass": "Bypass with header {header}.",
+    "behaviorTwoTier": "Two-tier storage: in-memory LRU (fast) + SQLite (persistent across restarts).",
+    "behaviorTtl": "Default TTL: 30 minutes. Configure via {envVar}.",
+    "activeDedupKeys": "Active Dedup Keys",
+    "dedupWindow": "Dedup Window"
  }
 }
--- a/src/shared/components/Sidebar.tsx
+++ b/src/shared/components/Sidebar.tsx
@@ -21,6 +21,7 @@ const navItemDefs = [
  { href: "/dashboard/costs", i18nKey: "costs", icon: "account_balance_wallet" },
  { href: "/dashboard/analytics", i18nKey: "analytics", icon: "analytics" },
  { href: "/dashboard/limits", i18nKey: "limits", icon: "tune" },
+  { href: "/dashboard/cache", i18nKey: "cache", icon: "cached" },
 ];

 const cliItemDefs = [