perf: aggregate batch status statistics in a single query

backend/tests/test_optimization.py

@@ -249,6 +249,38 @@ def test_last_review_updates_batch_and_keeps_zero(sqlite_db):
         assert sheet["D2"].value == 0
 
 
+@pytest.mark.parametrize("batch_count", [0, 20])
+def test_batch_list_status_statistics_use_constant_query_count(sqlite_db, batch_count):
+    from wisegrade.api import list_batches
+    db = sqlite_db
+    item = project(db)
+    expected = {}
+    states = ["scored", "reviewed", "needs_review", "failed", "unscorable"]
+    for index in range(batch_count):
+        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]["criterion_id"]
+        state = states[index % len(states)]
+        db.add(CriterionScore(batch_id=batch.id, project_id=item.id, criterion_id=criterion, status=state))
+        expected[batch.id] = {state: 1}
+    db.commit()
+    queries = []
+    def trace(_conn, _cursor, statement, _parameters, _context, _many):
+        if statement.lstrip().upper().startswith("SELECT"):
+            queries.append(statement)
+    event.listen(db.get_bind(), "before_cursor_execute", trace)
+    try:
+        listed = list_batches(db)
+    finally:
+        event.remove(db.get_bind(), "before_cursor_execute", trace)
+    assert len(queries) <= (2 if batch_count else 1), len(queries)
+    assert [row["id"] for row in listed] == sorted(expected, reverse=True)
+    for row in listed:
+        assert row["status_counts"] == expected[row["id"]]
+        for state in ("needs_review", "failed", "unscorable"):
+            assert row[state] == expected[row["id"]].get(state, 0)
+
+
 def test_pdf_html_preserves_zero_and_none():
     batch = SimpleNamespace(id=1, course_version_id=1, rubric_version_id=1, model_config_snapshot={},
                             embedding_model_name="test", embedding_model_version="test")

backend/wisegrade/api.py

@@ -468,12 +468,15 @@ def create_batch(data: BatchInput, db: Session = Depends(get_db)):
     return services.create_batch(data, db)
 
 
+def status_count_dict(counts: dict) -> dict:
+    return {"status_counts": counts, "needs_review": counts.get("needs_review", 0),
+            "unscorable": counts.get("unscorable", 0), "failed": counts.get("failed", 0)}
+
+
 def batch_status_counts(db, batch_id: int) -> dict:
     rows = db.execute(select(CriterionScore.status, func.count(CriterionScore.id))
                       .where(CriterionScore.batch_id == batch_id).group_by(CriterionScore.status)).all()
-    counts = {status: count for status, count in rows}
+    return status_count_dict({status: count for status, count in rows})
-    return {"status_counts": counts, "needs_review": counts.get("needs_review", 0),
-            "unscorable": counts.get("unscorable", 0), "failed": counts.get("failed", 0)}
 
 def batch_version_metadata(batch: ScoringBatch) -> dict:
     """Display the immutable rule/course versions, not their database IDs."""
@@ -485,12 +488,20 @@ def batch_version_metadata(batch: ScoringBatch) -> dict:
 
 @router.get("/scoring-batches")
 def list_batches(db: Session = Depends(get_db)):
+    batches = db.scalars(select(ScoringBatch).order_by(ScoringBatch.id.desc())).all()
+    counts_by_batch = {}
+    if batches:
+        rows = db.execute(select(CriterionScore.batch_id, CriterionScore.status, func.count(CriterionScore.id))
+                          .where(CriterionScore.batch_id.in_([batch.id for batch in batches]))
+                          .group_by(CriterionScore.batch_id, CriterionScore.status)).all()
+        for batch_id, status, count in rows:
+            counts_by_batch.setdefault(batch_id, {})[status] = count
     return [{**{key: getattr(batch, key) for key in ("id", "course_version_id", "rubric_version_id", "status", "progress_done", "progress_total", "error", "created_at", "finished_at")},
              "status_label": BATCH_STATUS_LABELS.get(batch.status, batch.status),
              "project_ids": batch.project_ids, "legacy_membership": batch.project_ids is None,
              **batch_version_metadata(batch),
-             **batch_status_counts(db, batch.id)}
+             **status_count_dict(counts_by_batch.get(batch.id, {}))}
-            for batch in db.scalars(select(ScoringBatch).order_by(ScoringBatch.id.desc()))]
+            for batch in batches]
 
 
 @router.get("/scoring-batches/{batch_id}/progress")