Initial commit: QMDSearch 分层信息检索服务

- FastAPI + Qdrant + Redis + Ollama 技术栈
- L1→L2→L3→chunk 四层分层检索（dense + sparse RRF 融合）
- 文档三级总结与 2.5 级回退
- query 解析路由与分类
- /admin 管理页面

tests/test_admin_page.py

@@ -0,0 +1,125 @@
+"""管理页面挂载测试（GET /admin）
+
+覆盖：
+1. 路由存在性：200 + content-type 为 text/html
+2. 五区块可识别标记（文案与 section id）
+3. 零外部依赖：无 http(s) 外链资源、无 CDN 引用
+4. fetch 调用路径与后端 API 契约一致
+5. 删除操作的 confirm() 二次确认逻辑
+"""
+
+import re
+from collections.abc import Iterator
+
+import pytest
+from fastapi.testclient import TestClient
+
+from app.main import app
+from app.services.qdrant import QdrantService
+
+
+@pytest.fixture
+def client(monkeypatch: pytest.MonkeyPatch) -> Iterator[TestClient]:
+    """TestClient，lifespan 中的 Qdrant 集合初始化替换为空操作"""
+
+    async def _noop_ensure_collections(self: QdrantService) -> None:
+        return None
+
+    monkeypatch.setattr(QdrantService, "ensure_collections", _noop_ensure_collections)
+    with TestClient(app) as test_client:
+        yield test_client
+
+
+@pytest.fixture
+def admin_html(client: TestClient) -> str:
+    """请求 /admin 并返回 HTML 文本（前置断言 200）"""
+    resp = client.get("/admin")
+    assert resp.status_code == 200
+    return resp.text
+
+
+def test_admin_page_ok(client: TestClient) -> None:
+    """GET /admin → 200，content-type 含 text/html"""
+    resp = client.get("/admin")
+
+    assert resp.status_code == 200
+    assert "text/html" in resp.headers["content-type"]
+
+
+def test_admin_page_has_five_sections(admin_html: str) -> None:
+    """HTML 含五个区块的文案与对应 section id"""
+    for section_id in (
+        "section-overview",
+        "section-docs",
+        "section-ingest",
+        "section-search",
+        "section-categories",
+    ):
+        assert section_id in admin_html
+    for label in ("概览", "文档管理", "文档入库", "检索测试台", "类目列表"):
+        assert label in admin_html
+
+
+def test_admin_page_no_external_resources(admin_html: str) -> None:
+    """零外部依赖：无 src/href http(s) 外链，无 CDN 引用"""
+    assert re.search(r'src=["\']https?://', admin_html) is None
+    assert re.search(r'href=["\']https?://', admin_html) is None
+    assert re.search(r"//cdn", admin_html) is None
+
+
+def test_admin_page_fetch_paths(admin_html: str) -> None:
+    """fetch 调用路径与后端 API 契约一致"""
+    for path in (
+        "/api/v1/search",
+        "/api/v1/documents",
+        "/api/v1/knowledge/stats",
+        "/api/v1/knowledge/categories",
+    ):
+        assert path in admin_html
+
+
+def _collect_route_paths(routes: list) -> set[str]:
+    """递归收集路由路径（FastAPI 0.140+ include_router 包装为 _IncludedRouter）"""
+    paths: set[str] = set()
+    for route in routes:
+        path = getattr(route, "path", None)
+        if path:
+            paths.add(path)
+        sub_router = getattr(route, "original_router", None)
+        if sub_router is not None:
+            paths |= _collect_route_paths(sub_router.routes)
+    return paths
+
+
+def test_admin_page_fetch_paths_in_real_routes(admin_html: str) -> None:
+    """页面 api() 调用路径均在真实后端路由集合内（含新增的 tasks 路径）"""
+    route_paths = _collect_route_paths(app.routes)
+    assert "/api/v1/documents/tasks/{task_id}" in route_paths
+
+    prefixes = set(re.findall(r'api\("([^"?]+)', admin_html))
+    assert prefixes, "页面应包含 api() 调用"
+    for prefix in prefixes:
+        assert any(path == prefix or path.startswith(prefix) for path in route_paths), (
+            f"页面 fetch 路径 {prefix} 不在后端路由集合内"
+        )
+
+
+def test_admin_page_ingest_polling(admin_html: str) -> None:
+    """入库区块：异步任务轮询逻辑标记"""
+    # 轮询任务状态端点
+    assert "/api/v1/documents/tasks/" in admin_html
+    # 状态中文映射
+    for text in ("排队中", "总结中", "分类中", "向量化中", "写入中", "完成", "失败"):
+        assert text in admin_html
+    # 提交确认与超时提示
+    assert "任务已提交" in admin_html
+    assert "任务仍在进行，可稍后凭 task_id 查询" in admin_html
+    # 5 分钟超时：150 次 × 2s
+    assert "150" in admin_html
+    # 防重复提交：轮询中禁用提交按钮
+    assert "disabled" in admin_html
+
+
+def test_admin_page_has_confirm(admin_html: str) -> None:
+    """删除操作包含 confirm() 二次确认逻辑"""
+    assert "confirm(" in admin_html