feat: 多专业小模型+路由模型系统 MVP（mock 全链路 + FastAPI 网关 + 论文调研）

tests/test_cache.py

@@ -0,0 +1,42 @@
+from router_system.cache import RouterCache
+
+
+def test_exact_hit():
+    c = RouterCache()
+    result = {"response": "hello", "domain": "general"}
+    assert c.get("query") is None
+    c.put("query", result)
+    level, got = c.get("query")
+    assert level == "exact"
+    assert got["response"] == "hello"
+
+
+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????????")
+    assert hit is not None
+    assert hit[0] == "semantic"
+
+
+def test_promote_to_exact():
+    c = RouterCache(promote_frequency=3)
+    result = {"response": "x", "domain": "general"}
+    c.put("query", result)
+    # ?????? 3 ? ? ???????
+    for _ in range(3):
+        hit = c.get("query")
+        assert hit is not None
+    assert c.stats()["exact_size"] == 1
+
+
+def test_stats():
+    c = RouterCache()
+    c.put("q", {"response": "r"})
+    c.get("q")
+    c.get("q")
+    c.get("miss")
+    s = c.stats()
+    assert s["exact_hits"] == 2
+    assert s["misses"] == 1