feat: separate contents, abstract and body evidence

backend/tests/test_chat_sessions.py

@@ -224,7 +224,9 @@ def test_score_citations_link_the_canonical_text_and_image_page(session_factory,
         assert generated["citations"][0]["url"] == expected
         assert generated["citations"][0]["image_url"] == expected + "/image"
         assert generated["citations"][0]["score_url"].startswith("/?page=scores")
-        assert chat_api._answer_citations(generated["citations"])[0]["url"] == expected
+        # An answer keeps only the citations it actually used: naming the page retains it.
+        assert chat_api._answer_citations(generated["citations"], "评分证据见第 2 页。")[0]["url"] == expected
+        assert chat_api._answer_citations(generated["citations"], "没有引用任何页面。") == []
         conversation_id = conversation.id
     client = client_for(session_factory)
     try:
@@ -268,8 +270,11 @@ def test_late_citations_and_search_snippets_survive_restoration(session_factory,
         assert response.status_code == 200
         detail = client.get(f"/api/conversations/{created['id']}").json()
         answer = detail['messages'][-1]
-        assert len(answer['citations']) == 30
-        assert [item['page'] for item in answer['citations'][-6:]] == [48] * 6
+        # The answer names page 48 only, so only that page's passages are attached; the
+        # other tool hits were retrieved but not used in the answer.
+        assert len(answer['citations']) == 6
+        assert [item['page'] for item in answer['citations']] == [48] * 6
+        # Every tool hit stays available in the tool record for auditing.
         assert answer['tool_calls'][-1]['result']['citations'][0]['quote'] == '第48页原文片段0'
         assert detail['runs'][0]['tool_calls'][-1]['result']['citations'][0]['page'] == 48
     finally:
@@ -383,7 +388,7 @@ def test_upgrade_from_legacy_0003_migrates_pages_and_citations(session_factory,
     config.set_main_option('script_location', str(root / 'migrations'))
     command.upgrade(config, 'head')
     with session_factory() as db:
-        assert db.scalar(text('SELECT version_num FROM alembic_version')) == '0005'
+        assert db.scalar(text('SELECT version_num FROM alembic_version')) == '0006'
         assert db.get(Conversation, conversation_id).title == '旧记录'
         assert db.scalar(select(ChatMessage.content).where(ChatMessage.conversation_id == conversation_id)) == '旧问题'
         run = db.scalar(select(AgentRun).where(AgentRun.conversation_id == conversation_id))