fix: link score citations to their source text pages

backend/tests/test_chat_agent.py

@@ -83,7 +83,7 @@ def test_get_scores_pages_projects_and_criteria(db, monkeypatch):
                 "rows": [{"criterion": {"criterion_id": f"C{index}", "name": f"评分项{index}", "max_score": 10},
                           "score_id": index, "model_score": 8, "teacher_score": None, "final_score": 8,
                           "status": "scored", "error": "", "evidence": [{"page": index + 1,
-                              "quote": "证据" * 200, "document": "报告.pdf",
+                              "quote": "证据" * 200, "document": "报告.pdf", "document_id": index + 100,
                               "image_url": f"/api/assets/{item.id}/1" if index == 0 else None}]}
                          for index in range(14)]}
 
@@ -95,6 +95,7 @@ def test_get_scores_pages_projects_and_criteria(db, monkeypatch):
     assert first_page["next_criterion_offset"] == 6 and first_page["next_project_offset"] == 1
     assert first_page["citations"][0]["url"] == f"/?page=scores&batch_id={created['id']}&project_id={first.id}"
     assert first_page["citations"][0]["image_url"] == f"/api/assets/{first.id}/1"
+    assert first_page["citations"][0]["text_url"] == "/api/knowledge/documents/100/pages/1"
     assert first_page["citations"][1]["url"] == first_page["citations"][0]["url"]
     assert first_page["citations"][1]["image_url"] is None
     assert len(json.dumps(first_page, ensure_ascii=False)) < 12000

backend/tests/test_chat_sessions.py

@@ -2,15 +2,18 @@
 import time
 from concurrent.futures import ThreadPoolExecutor
 from threading import Event
+from types import SimpleNamespace
 from uuid import uuid4
 
 from fastapi.testclient import TestClient
 from sqlalchemy import func, select
 
-from wisegrade import chat_api
+from wisegrade import agent_tools, chat_api, services
 from wisegrade.db import get_db
 from wisegrade.main import app
-from wisegrade.models import AgentRun, AuditLog, ChatMessage, Conversation, CourseVersion, PendingAction, Project, ScoringBatch, Student, now
+from wisegrade.models import (AgentRun, AuditLog, ChatMessage, Conversation, CourseVersion, CriterionScore,
+                              KnowledgeChunk, KnowledgeDocument, PendingAction, Project, ScoreEvidence,
+                              ScoringBatch, Student, SubmissionFile, now)
 
 
 def client_for(session_factory):
@@ -176,6 +179,64 @@ def test_tool_record_keeps_bounded_query_but_redacts_review_text_and_secrets():
     assert 'secret' not in str(search)
 
 
+def test_score_citations_link_text_and_restore_legacy_image_only(session_factory):
+    with session_factory() as db:
+        student = Student(student_no="987654320", name="测试学生")
+        db.add(student)
+        db.flush()
+        project = Project(course_version_id=1, student_id=student.id, topic="测试项目", source_dir="test/citation")
+        db.add(project)
+        db.flush()
+        file = SubmissionFile(project_id=project.id, category="final_report", relative_path="test/citation/report.pdf",
+                              mime_type="application/pdf", size=1, mtime=1, sha256="a" * 64,
+                              recognition_status="recognized", parse_status="ready")
+        db.add(file)
+        db.flush()
+        document = KnowledgeDocument(course_version_id=1, project_id=project.id, submission_file_id=file.id,
+                                     title="报告.pdf", document_type="final_report", source_hash="a" * 64,
+                                     index_version=2, status="ready")
+        db.add(document)
+        db.flush()
+        db.add(KnowledgeChunk(document_id=document.id, course_version_id=1, project_id=project.id,
+                              document_type="final_report", page=2, section="测试", text="这里有原文证据和分析"))
+        created = services.create_batch(SimpleNamespace(course_version_id=1, rubric_version_id=1), db)
+        batch = db.get(ScoringBatch, created["id"])
+        score = CriterionScore(batch_id=batch.id, project_id=project.id,
+                               criterion_id=batch.rubric_snapshot["criteria"][0]["criterion_id"],
+                               model_score=8, status="scored")
+        db.add(score)
+        db.flush()
+        db.add(ScoreEvidence(score_id=score.id, document_id=document.id, submission_file_id=file.id,
+                             page=2, quote="原文证据", image_path="page-2.png"))
+        conversation = Conversation(title="旧评分引用", course_version_id=1, batch_id=batch.id, project_id=project.id)
+        db.add(conversation)
+        db.flush()
+        image_url = f"/api/assets/{file.id}/2"
+        db.add(ChatMessage(conversation_id=conversation.id, role="assistant", content="历史回答", citations=[
+            {"title": "报告.pdf", "page": 2, "quote": "原文证据", "url": image_url},
+            {"title": "报告.pdf", "page": 2, "quote": "不匹配的引文", "url": image_url}]))
+        db.commit()
+        expected = f"/api/knowledge/documents/{document.id}/pages/2"
+        generated = agent_tools.execute(db, conversation, "get_scores",
+                                        {"batch_id": batch.id, "project_id": project.id}, "")
+        assert generated["citations"][0]["text_url"] == expected
+        assert chat_api._answer_citations(generated["citations"])[0]["text_url"] == expected
+        assert generated["citations"][0]["image_url"] == image_url
+        conversation_id = conversation.id
+    client = client_for(session_factory)
+    try:
+        detail = client.get(f"/api/conversations/{conversation_id}").json()
+        citations = detail["messages"][0]["citations"]
+        assert citations[0]["text_url"] == expected
+        assert "text_url" not in citations[1]
+        assert "原文证据" in client.get(expected).json()["text"]
+        with session_factory() as db:
+            stored = db.scalar(select(ChatMessage).where(ChatMessage.conversation_id == conversation_id))
+            assert "text_url" not in stored.citations[0]
+    finally:
+        app.dependency_overrides.clear()
+
+
 def test_late_citations_and_search_snippets_survive_restoration(session_factory, monkeypatch):
     class FakeClient:
         def tool_call(self, messages, _tools):