feat(v3): Web 应用化基线（异步任务/SSE/llama-server 管理/Vue SPA 四页 + 设置页整页滚动修复）

tests/test_cache.py

@@ -13,9 +13,9 @@ def test_exact_hit():
 
 def test_semantic_hit():
     c = RouterCache(semantic_enabled=True, similarity_threshold=0.5)
-    c.put("?python?????", {"response": "code", "domain": "code"})
-    # ?????????? L2
-    hit = c.get("?python????????")
+    c.put("用python写一个快速排序", {"response": "code", "domain": "code"})
+    # 相似改写查询命中 L2 语义缓存
+    hit = c.get("用python写一个快速排序算法")
     assert hit is not None
     assert hit[0] == "semantic"
 
@@ -24,7 +24,7 @@ def test_promote_to_exact():
     c = RouterCache(promote_frequency=3)
     result = {"response": "x", "domain": "general"}
     c.put("query", result)
-    # ?????? 3 ? ? ???????
+    # 语义命中 3 次后提升为精确缓存
     for _ in range(3):
         hit = c.get("query")
         assert hit is not None