fix: retain chat compatibility with lightweight score results

backend/tests/test_chat_agent.py

@@ -93,6 +93,7 @@ def test_get_scores_pages_projects_and_criteria(db, monkeypatch):
     assert first_page["count"] == 2 and len(first_page["results"]) == 1
     assert first_page["results"][0]["project_id"] == first.id
     assert len(first_page["results"][0]["rows"]) == 6
+    assert first_page["results"][0]["rows"][0]["status_label"] == "模型已评分"
     assert first_page["next_criterion_offset"] == 6 and first_page["next_project_offset"] == 1
     assert first_page["citations"][0]["url"] is None
     assert first_page["citations"][0]["image_url"] is None

backend/wisegrade/agent_tools.py

@@ -9,7 +9,7 @@ from sqlalchemy import select
 
 from .actions import prepare, require_scope
 from .evidence import CONTENT_ALLOWED, STRUCTURE_ALLOWED
-from .exports import batch_projects, page_type_label, project_result
+from .exports import batch_projects, criterion_status_label, page_type_label, project_result
 from .knowledge_pages import page_links
 from .models import (Conversation, Course, CourseVersion, IndexTask, KnowledgeChunk, KnowledgeDocument, KnowledgePage,
                      Project, RubricVersion, ScoringBatch, Student, SubmissionFile)
@@ -384,7 +384,7 @@ def scores(db, convo, args, _user):
                                  "max_score": row["criterion"]["max_score"], "score_id": row["score_id"],
                                  "model_score": row["model_score"], "teacher_score": row["teacher_score"],
                                  "final_score": row["final_score"], "status": row["status"],
-                                 "status_label": row["status_label"],
+                                 "status_label": row.get("status_label") or criterion_status_label(row["status"], row.get("error") or ""),
                                  "error": str(row["error"] or "")[:300],
                                  # Which body targets still lack evidence, so the answer can
                                  # explain a review item instead of reporting a score.