perf(api): batch supplementary queries — one per table, not five per school

get_supplementary_data ran ~5 sequential DB round-trips per URN, so
/api/compare scaled at ~37ms/school (measured on staging: 1 school 155ms,
3 schools 220ms, 6 schools 340ms). get_supplementary_data_batch fetches
each table once with WHERE urn IN (...) and groups in Python, collapsing
5*N round-trips to a constant 5. get_supplementary_data is now a thin
wrapper so the detail endpoint is unchanged; the compare endpoint makes
one batched call. Each table degrades independently on failure.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0146VHeLAWjDVE2B5uU67jCB

backend/tests/test_compare_enrichment.py

@@ -67,7 +67,9 @@ def client(monkeypatch):
 
     monkeypatch.setattr(app_module, "load_school_data", _two_primary_schools_df)
     monkeypatch.setattr(
-        app_module, "get_supplementary_data", lambda db, urn: dict(CANNED_SUPPLEMENTARY)
+        app_module,
+        "get_supplementary_data_batch",
+        lambda db, urns: {int(u): dict(CANNED_SUPPLEMENTARY) for u in urns},
     )
     monkeypatch.setattr(database_module, "SessionLocal", _StubSession)
     return TestClient(app_module.app, raise_server_exceptions=False)
@@ -102,10 +104,10 @@ def test_top_level_national_averages_and_benchmarks(client):
 def test_supplementary_failure_degrades_not_500(client, monkeypatch):
     from backend import app as app_module
 
-    def _boom(db, urn):
+    def _boom(db, urns):
         raise RuntimeError("marts unavailable")
 
-    monkeypatch.setattr(app_module, "get_supplementary_data", _boom)
+    monkeypatch.setattr(app_module, "get_supplementary_data_batch", _boom)
     resp = client.get("/api/compare?urns=100140")
     assert resp.status_code == 200
     school = resp.json()["comparison"]["100140"]

backend/tests/test_supplementary_batch.py

@@ -0,0 +1,111 @@
+"""get_supplementary_data_batch fetches one query per table for all URNs
+(not ~5 per school) and returns the same per-URN block shape as the
+single-URN function, picking the latest row per URN where relevant."""
+
+import types
+
+from backend import data_loader
+from backend.data_loader import get_supplementary_data_batch
+
+
+class _FakeQuery:
+    """Records that a query ran and serves canned rows filtered by an in-list."""
+
+    def __init__(self, recorder, model_name, rows):
+        self._rec = recorder
+        self._model = model_name
+        self._rows = rows
+
+    def filter(self, *args, **kwargs):
+        return self
+
+    def order_by(self, *args, **kwargs):
+        return self
+
+    def all(self):
+        self._rec.append(self._model)
+        return self._rows
+
+    def first(self):
+        self._rec.append(self._model)
+        return self._rows[0] if self._rows else None
+
+
+class _FakeSession:
+    def __init__(self, rows_by_model):
+        self.rows_by_model = rows_by_model
+        self.queries: list[str] = []
+
+    def query(self, model):
+        name = model.__name__
+        return _FakeQuery(self.queries, name, self.rows_by_model.get(name, []))
+
+    def rollback(self):
+        pass
+
+
+def _ofsted_row(urn, date, oe):
+    base = {f: None for f in (
+        "framework", "inspection_type", "quality_of_education", "behaviour_attitudes",
+        "personal_development", "leadership_management", "early_years_provision",
+        "sixth_form_provision", "ungraded_outcome", "ungraded_grade",
+        "rc_safeguarding_met", "rc_inclusion", "rc_curriculum_teaching", "rc_achievement",
+        "rc_attendance_behaviour", "rc_personal_development", "rc_leadership_governance",
+        "rc_early_years", "rc_sixth_form", "report_url",
+    )}
+    base.update(urn=urn, inspection_date=types.SimpleNamespace(isoformat=lambda: date),
+                overall_effectiveness=oe, grade_source=None)
+    return types.SimpleNamespace(**base)
+
+
+def _adm_row(urn, year):
+    return types.SimpleNamespace(
+        urn=urn, year=year, school_phase="Primary", places_offered=100,
+        total_applications=200, first_preference_applications=150,
+        first_preference_offers=140, first_preference_offer_pct=93.3,
+        oversubscription_ratio=1.5, oversubscribed=True,
+        total_offers=100, second_preference_offers=5, third_preference_offers=2,
+        cross_la_applications=10, cross_la_offers=3,
+    )
+
+
+def test_one_query_per_table_and_latest_row_per_urn():
+    rows = {
+        # URN 1 has two Ofsted rows; the batch must keep the most recent (2023).
+        "FactOfstedInspection": [
+            _ofsted_row(1, "2023-01-01", 2),
+            _ofsted_row(1, "2019-01-01", 3),
+            _ofsted_row(2, "2021-06-01", 1),
+        ],
+        "FactAdmissions": [_adm_row(1, 202526), _adm_row(1, 202627), _adm_row(2, 202627)],
+        "FactPupilCharacteristics": [],
+        "FactDeprivation": [],
+        "FactFinance": [],
+    }
+    session = _FakeSession(rows)
+    out = get_supplementary_data_batch(session, [1, 2])
+
+    # Exactly one query per table — five total, regardless of two URNs.
+    assert sorted(session.queries) == [
+        "FactAdmissions", "FactDeprivation", "FactFinance",
+        "FactOfstedInspection", "FactPupilCharacteristics",
+    ]
+
+    # Latest Ofsted kept per URN
+    assert out[1]["ofsted"]["overall_effectiveness"] == 2
+    assert out[2]["ofsted"]["overall_effectiveness"] == 1
+
+    # Admissions history grouped per URN, latest exposed as `admissions`
+    assert [r["year"] for r in out[1]["admissions_history"]] == [202526, 202627]
+    assert out[1]["admissions"]["year"] == 202627
+    assert out[2]["admissions_history"] == [{**out[2]["admissions_history"][0]}]
+
+    # Empty tables degrade to the null block, not a crash
+    assert out[1]["census"] is None and out[1]["deprivation"] is None
+
+
+def test_single_wrapper_matches_batch(monkeypatch):
+    session = _FakeSession({"FactOfstedInspection": [_ofsted_row(5, "2022-01-01", 2)]})
+    single = data_loader.get_supplementary_data(session, 5)
+    assert single["ofsted"]["overall_effectiveness"] == 2
+    assert single["admissions_history"] == []