feat: separate contents, abstract and body evidence

backend/tests/test_llm_and_rag.py

@@ -4,7 +4,7 @@ from sqlalchemy import select
 
 from wisegrade.llm import DeepSeekClient, FactResult, ModelError, ScoreResult, validate_score
 from wisegrade.models import AppSetting, KnowledgeChunk, KnowledgePage, Project, Student
-from wisegrade.rag import ingest, local_encoder, retrieve, split_pages
+from wisegrade.rag import INDEX_VERSION, ingest, local_encoder, retrieve, split_pages
 from wisegrade.settings_store import model_config, save_model_config
 
 
@@ -21,7 +21,7 @@ def make_project(db, number):
 
 def test_json_validation_and_evidence():
     criterion = {"criterion_id": "stage1.problem", "max_score": 25}
-    chunks = [{"chunk_id": 7, "page": 2, "text": "工程需求是实时目标识别"}]
+    chunks = [{"chunk_id": 7, "page": 2, "text": "工程需求是实时目标识别", "page_type": "body"}]
     result = ScoreResult(criterion_id="stage1.problem", score=19, max_score=25, reason="满足需求",
                          evidence=[{"chunk_id": 7, "page": 2, "quote": "实时目标识别"}], confidence=.8)
     assert validate_score(result, criterion, chunks).score == 19
@@ -33,8 +33,8 @@ def test_json_validation_and_evidence():
 
 def test_evidence_quote_resolves_pdf_line_breaks_and_page():
     criterion = {"criterion_id": "stage1.problem", "max_score": 25}
-    chunks = [{"chunk_id": 7, "page": 2, "text": "机器人\n控制精度：2 cm。"},
-              {"chunk_id": 8, "page": 3, "text": "其他实验结果"}]
+    chunks = [{"chunk_id": 7, "page": 2, "text": "机器人\n控制精度：2 cm。", "page_type": "body"},
+              {"chunk_id": 8, "page": 3, "text": "其他实验结果", "page_type": "body"}]
     result = ScoreResult(criterion_id="stage1.problem", score=19, max_score=25, reason="有指标",
                          evidence=[{"chunk_id": 8, "page": 3, "quote": "机器人控制精度:2 cm"}], confidence=.8)
     checked = validate_score(result, criterion, chunks)
@@ -42,6 +42,59 @@ def test_evidence_quote_resolves_pdf_line_breaks_and_page():
     assert checked.evidence[0].quote in chunks[0]["text"]
 
 
+def test_content_evidence_rejects_navigation_and_heading_only_sources():
+    """A contents page, an abstract or a bare heading can never prove content."""
+    criterion = {"criterion_id": "stage3.data", "max_score": 20,
+                 "description": "实验数据和初步分析", "required_evidence": ["实验数据", "分析"]}
+    body = {"chunk_id": 1, "page": 11, "page_type": "body",
+            "text": "在自主巡线测试中，底盘在标准黑色轨迹线场地内运行，记录了直线段与弯道的时间数据。"}
+    good = ScoreResult(criterion_id="stage3.data", score=16, max_score=20, reason="有实测数据",
+                       evidence=[{"chunk_id": 1, "page": 11, "quote": "在自主巡线测试中", "target_id": "t0"}],
+                       confidence=.8)
+    assert validate_score(good, criterion, [body]).score == 16
+
+    toc = {"chunk_id": 2, "page": 2, "page_type": "toc",
+           "text": "第3 章系统测试与验证 ......... 8"}
+    bad = ScoreResult(criterion_id="stage3.data", score=16, max_score=20, reason="看目录",
+                      evidence=[{"chunk_id": 2, "page": 2, "quote": "系统测试与验证", "target_id": "t0"}],
+                      confidence=.8)
+    # The rejection is what matters; either guard may fire depending on the target's
+    # allowed page types.
+    with pytest.raises(ModelError, match="内容证据|不允许的页面类型"):
+        validate_score(bad, criterion, [toc])
+
+    abstract = {"chunk_id": 3, "page": 2, "page_type": "abstract",
+                "text": "摘要 本文实现了自瞄移动机器人系统，采用多处理器分布式架构。"}
+    bad.evidence[0].chunk_id, bad.evidence[0].page, bad.evidence[0].quote = 3, 2, "本文实现了自瞄移动机器人系统"
+    with pytest.raises(ModelError, match="内容证据|不允许的页面类型"):
+        validate_score(bad, criterion, [abstract])
+
+    heading_only = {"chunk_id": 4, "page": 11, "page_type": "body", "text": "第3 章 系统测试与验证"}
+    bad.evidence[0].chunk_id, bad.evidence[0].page, bad.evidence[0].quote = 4, 11, "第3 章 系统测试与验证"
+    with pytest.raises(ModelError, match="章节标题"):
+        validate_score(bad, criterion, [heading_only])
+
+
+def test_structural_targets_may_use_the_contents_page():
+    """A structure target legitimately reads the contents list; a content one may not."""
+    criterion = {"criterion_id": "stage1.format", "max_score": 5, "description": "报告完整性和规范性",
+                 "required_evidence": ["标题", "章节", "参考文献"]}
+    toc = {"chunk_id": 5, "page": 2, "page_type": "toc",
+           "text": "第1 章项目背景与需求分析 .......... 1\n第2 章文献调研与技术现状 .......... 3"}
+    result = ScoreResult(criterion_id="stage1.format", score=4, max_score=5, reason="章节完整",
+                         evidence=[{"chunk_id": 5, "page": 2, "quote": "第1 章项目背景与需求分析", "target_id": "t1"}],
+                         confidence=.8)
+    checked = validate_score(result, criterion, [toc])
+    assert checked.evidence[0].page == 2
+
+
+def test_model_may_return_a_null_score_when_content_evidence_is_missing():
+    result = ScoreResult(criterion_id="stage3.data", score=None, max_score=20,
+                         reason="仅检索到目录页，无法判断测试内容", evidence=[],
+                         missing_evidence=["实验数据"], confidence=.2)
+    assert result.score is None
+
+
 @pytest.mark.integration
 def test_deepseek_adapter_live_with_image(tmp_path):
     image = tmp_path / "page.png"
@@ -87,7 +140,7 @@ def test_stale_knowledge_index_reuses_document_id(db):
     db.commit()
     reindexed = ingest(db, course_version_id=1, project_id=project_id, submission_file_id=None,
                        title="报告", category="stage3", source_hash="same-source", pages=pages)
-    assert reindexed.id == document.id and reindexed.index_version == 2
+    assert reindexed.id == document.id and reindexed.index_version == INDEX_VERSION
     assert db.scalar(select(KnowledgeChunk.text).where(KnowledgeChunk.document_id == document.id)) == pages[0]["text"]
     assert db.get(KnowledgePage, (document.id, 1)).text == pages[0]["text"]