feat: add document file download API and related features

1. add `/api/v1/documents/{doc_id}/file` endpoint for downloading original document files
2. add file field to document detail API response based on metadata
3. add comprehensive tests for file download API and metadata integration
4. update API documentation in CLAUDE.md

tests/test_admin_integration.py

@@ -204,11 +204,13 @@ class TestAdminClosedLoop:
             assert item_b["category"] == DOC_B_CATEGORY
             assert item_b["tags"] == []
 
-            # 2. 详情：l1/l2_nodes/l3_nodes/chunks_count 与写入一致
+            # 2. 详情：l1/l2_nodes/l3_nodes/chunks_count/file 与写入一致
             resp = client.get(f"/api/v1/documents/{DOC_A}")
             assert resp.status_code == 200
             data = resp.json()["data"]
-            assert set(data.keys()) == {"l1", "l2_nodes", "l3_nodes", "chunks_count"}
+            assert set(data.keys()) == {"l1", "l2_nodes", "l3_nodes", "chunks_count", "file"}
+            # 文本入库无 metadata → file=None
+            assert data["file"] is None
             l1 = data["l1"]
             assert l1["doc_id"] == DOC_A
             assert l1["title"] == DOC_A_TITLE