v3.8 改成每个模型独立app，测试通过容器down， ray serve自动迁移模型

src/mvp/py/tests/test_app_serving_api.py

@@ -75,9 +75,10 @@ def test_serving_api_crud_flow(tmp_path: Path, monkeypatch):
         r4 = c.get("/api/v2/serve/models?limit=10&offset=0", headers=headers)
         assert r4.status_code == 200
         obj = r4.json()
-        assert obj["openai_base_url"] == "http://testserver:8000/v1"
+        assert obj["openai_base_url"] is None
         assert len(obj["items"]) == 1
         assert obj["items"][0]["model_key"] == "mk-alice"
+        assert obj["items"][0]["endpoint"]["openai_base_url"] == "http://testserver:8000/serve/mk-alice/v1"
 
         r5 = c.get("/api/v2/serve/models/mk-alice", headers=headers)
         assert r5.status_code == 200
@@ -99,6 +100,7 @@ def test_serving_api_crud_flow(tmp_path: Path, monkeypatch):
         r8 = c.get("/api/v2/serve/status", headers=admin_headers)
         assert r8.status_code == 200
         assert r8.json()["http_port"] == 8000
+        assert r8.json()["openai_base_url"] is None
 
 
 def test_serving_api_rejects_path_outside_user_and_hf(tmp_path: Path, monkeypatch):
@@ -245,8 +247,17 @@ def test_serving_api_list_include_deleted_and_forwarded_base_url(tmp_path: Path,
             headers={**headers, "x-forwarded-host": "example.com:8080", "x-forwarded-proto": "https"},
         )
         assert r1.status_code == 200
-        assert r1.json()["openai_base_url"] == "https://example.com:8000/v1"
+        assert r1.json()["openai_base_url"] is None
         assert {m["model_key"] for m in r1.json()["items"]} == {"mk-alice-1"}
+        assert r1.json()["items"][0]["endpoint"]["openai_base_url"] == "https://example.com:8000/serve/mk-alice-1/v1"
+
+        # IPv6 bracketed host should be preserved.
+        r1b = c.get(
+            "/api/v2/serve/models?limit=10&offset=0&include_deleted=0",
+            headers={**headers, "x-forwarded-host": "[::1]:8080", "x-forwarded-proto": "https"},
+        )
+        assert r1b.status_code == 200
+        assert r1b.json()["items"][0]["endpoint"]["openai_base_url"] == "https://[::1]:8000/serve/mk-alice-1/v1"
 
         r2 = c.get("/api/v2/serve/models?include_deleted=1", headers=headers)
         assert r2.status_code == 200