feat: unify scoring and chat evidence pages

backend/tests/test_chat_agent.py

@@ -14,12 +14,13 @@ from wisegrade.actions import confirm, prepare
 from wisegrade.agent_tools import execute
 from wisegrade.db import get_db
 from wisegrade.indexing import run_index_task
-from wisegrade.llm import DeepSeekClient, ModelError
+from wisegrade.llm import DeepSeekClient, ModelError, ScoreResult
 from wisegrade.main import app
 from wisegrade.models import (AgentRun, ChatMessage, Conversation, CourseVersion, CriterionScore, IndexTask, PendingAction,
-                              Project, RubricVersion, ScoringBatch, Student, TeacherRevision, now)
+                              Project, RubricVersion, ScoreEvidence, ScoringBatch, Student, SubmissionFile,
+                              TeacherRevision, now)
 from wisegrade.rag import ingest
-from wisegrade.scoring import run_batch
+from wisegrade.scoring import _score_criterion, run_batch
 from wisegrade.storage import scan
 
 
@@ -93,9 +94,9 @@ def test_get_scores_pages_projects_and_criteria(db, monkeypatch):
     assert first_page["results"][0]["project_id"] == first.id
     assert len(first_page["results"][0]["rows"]) == 6
     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"][0]["url"] is None
+    assert first_page["citations"][0]["image_url"] is None
+    assert first_page["citations"][0]["score_url"] == f"/?page=scores&batch_id={created['id']}&project_id={first.id}"
     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
@@ -106,6 +107,44 @@ def test_get_scores_pages_projects_and_criteria(db, monkeypatch):
     assert later["next_project_offset"] is None and later["next_criterion_offset"] is None
 
 
+def test_scoring_uses_the_same_page_image_as_its_saved_evidence(db, environment):
+    project = add_project(db, "123450090")
+    created = services.create_batch(SimpleNamespace(course_version_id=1, rubric_version_id=1), db)
+    batch = db.get(ScoringBatch, created["id"])
+    criterion = batch.rubric_snapshot["criteria"][0]
+    file = SubmissionFile(project_id=project.id, category=criterion["category"],
+                          relative_path="test/score/source.pdf", mime_type="application/pdf", size=1,
+                          mtime=1, sha256="b" * 64, recognition_status="recognized", parse_status="ready")
+    db.add(file)
+    db.flush()
+    image = environment / "processed" / f"file-{file.id}" / "page-2.png"
+    image.parent.mkdir(parents=True)
+    image.write_bytes(b"\x89PNG\r\n\x1a\n")
+    source = {"page_number": 2, "text": "评分所用原文证据", "rendered_image_path": str(image)}
+    file.parsed = {"pages": [source]}
+    document = ingest(db, course_version_id=1, project_id=project.id, submission_file_id=file.id,
+                      title="报告.pdf", category=criterion["category"], source_hash=file.sha256,
+                      pages=[source], embedder=lambda texts: [[0.1] * 1024 for _ in texts])
+    from wisegrade.models import KnowledgeChunk
+    chunk = db.scalar(select(KnowledgeChunk).where(KnowledgeChunk.document_id == document.id))
+    evidence = {"chunk_id": chunk.id, "document_id": document.id, "project_id": project.id,
+                "page": 2, "text": chunk.text}
+    sent_images = []
+
+    class FakeClient:
+        def json_call(self, _prompt, _payload, _schema, *, images=None):
+            sent_images.extend(images or [])
+            return ScoreResult(criterion_id=criterion["criterion_id"], score=1,
+                               max_score=criterion["max_score"], reason="测试评分",
+                               evidence=[{"chunk_id": chunk.id, "page": 2, "quote": "原文证据"}], confidence=.9)
+
+    scored = _score_criterion(db, batch, project, criterion, FakeClient(),
+                              retriever=lambda *_, **kwargs: [] if kwargs.get("public_only") else [evidence])
+    saved = db.scalar(select(ScoreEvidence).where(ScoreEvidence.score_id == scored.id))
+    assert sent_images == [str(image)]
+    assert saved.document_id == document.id and saved.page == 2 and saved.image_path == str(image)
+
+
 def test_import_confirmation_hash_change_index_and_idempotency(environment, db, monkeypatch, session_factory):
     folder = environment / "inbox" / "batch" / "123450003_张三_机器人"
     folder.mkdir(parents=True)