fix: separate news from publications and add employee refresh

tests/test_api_mcp.py

@@ -1,7 +1,8 @@
 from datetime import datetime, timezone
+from types import SimpleNamespace
 
 from fastapi.testclient import TestClient
-from sqlalchemy import create_engine
+from sqlalchemy import create_engine, select
 from sqlalchemy.orm import sessionmaker
 from sqlalchemy.pool import StaticPool
 
@@ -18,7 +19,7 @@ def test_health_returns_versions():
     response = client.get("/api/health")
 
     assert response.status_code == 200
-    assert response.json()["backend_version"] == "0.4.6"
+    assert response.json()["backend_version"] == "0.4.7"
 
 
 def test_mcp_lists_tools_without_auth_and_ignores_auth_header():
@@ -248,3 +249,56 @@ def test_api_employees_and_stats_require_admin_session():
     assert run_details.json()["changes"]["new"][0]["full_name"] == "Alpha Person"
 
     app.dependency_overrides.clear()
+
+
+def test_admin_refresh_employee_route_updates_only_requested_employee(monkeypatch):
+    engine = create_engine(
+        "sqlite:///:memory:",
+        connect_args={"check_same_thread": False},
+        poolclass=StaticPool,
+    )
+    Base.metadata.create_all(engine)
+    Session = sessionmaker(bind=engine)
+    db = Session()
+    db.add(
+        Employee(
+            profile_key="org_person:133709486",
+            profile_type="org_person",
+            profile_id="133709486",
+            canonical_url="https://www.hse.ru/org/persons/133709486",
+            full_name="Будков Юрий Алексеевич",
+            status="active",
+        )
+    )
+    db.commit()
+    employee_id = db.scalar(select(Employee.id))
+    db.close()
+
+    settings = Settings(admin_username="admin", admin_password="password", session_secret="session-secret")
+
+    def override_db():
+        session = Session()
+        try:
+            yield session
+        finally:
+            session.close()
+
+    calls = []
+
+    def fake_refresh_employee(db, refreshed_employee, route_settings):
+        calls.append((refreshed_employee.id, route_settings))
+        return SimpleNamespace(status="completed")
+
+    app.dependency_overrides[get_db] = override_db
+    app.dependency_overrides[get_settings] = lambda: settings
+    monkeypatch.setattr("app.admin.refresh_employee", fake_refresh_employee)
+    client = TestClient(app)
+    client.cookies.set(SESSION_COOKIE, sign_session("admin", settings))
+
+    response = client.post(f"/admin/employees/{employee_id}/refresh", follow_redirects=False)
+
+    assert response.status_code == 303
+    assert response.headers["location"] == f"/admin/employees/{employee_id}?refresh_status=success"
+    assert calls == [(employee_id, settings)]
+
+    app.dependency_overrides.clear()

tests/test_employee_detail_template.py

@@ -27,4 +27,6 @@ def test_employee_detail_template_is_human_readable():
     assert "Дата увольнения" in template
     assert "Тип профиля" in template
     assert "ID профиля" in template
+    assert "Обновить данные" in template
+    assert 'action="/admin/employees/{{ employee.id }}/refresh"' in template
     assert "Снапшоты" in template

tests/test_parser.py

@@ -1,6 +1,6 @@
 from bs4 import BeautifulSoup
 
-from app.parser.profile import enrich_sections_from_hse_widgets, extract_person_tabs
+from app.parser.profile import enrich_sections_from_hse_widgets, extract_person_tabs, extract_sections
 from app.parser.profile_url import normalize_profile_url, parse_profile_identity
 
 
@@ -184,3 +184,34 @@ def test_enrich_sections_from_hse_widgets_loads_grouped_publications():
     assert [item["id"] for item in publications["publications"]] == ["146366790", "146367323"]
     assert publications["publications"][0]["url"] == "https://publications.hse.ru/view/146366790"
     assert publications["publications"][1]["url"] == "https://publications.hse.ru/view/146367323"
+
+
+def test_news_heading_with_publications_word_does_not_absorb_widget_publications():
+    soup = BeautifulSoup(
+        """
+        <h2>Статья профессора МИЭМ вошла в число самых популярных публикаций на портале SpringerLink</h2>
+        <div class="post__text">
+          <p>Первоначально статья профессора вышла в российском журнале.</p>
+        </div>
+        <script src="/n/stat/publications/dist-w/publs.js" data-author="133709486" data-widget-name="AuthorSearch"></script>
+        """,
+        "html.parser",
+    )
+    session = FakeSession()
+
+    sections = extract_sections(soup, "https://www.hse.ru/org/persons/133709486")
+    sections = enrich_sections_from_hse_widgets(
+        session,
+        soup,
+        "https://www.hse.ru/org/persons/133709486",
+        {"User-Agent": "test"},
+        10,
+        sections,
+    )
+
+    assert sections[0]["type"] == "paragraphs"
+    assert sections[0]["title"].startswith("Статья профессора")
+    publications = [section for section in sections if section["type"] == "publications"]
+    assert len(publications) == 1
+    assert publications[0]["title"] == "Публикации и исследования"
+    assert publications[0]["publications_count"] == 1