fix(api): inspectorate and Ofsted listing in payloads; Ofsted links that resolve (H4)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

backend/app.py

@@ -1048,6 +1048,11 @@ async def get_school_details(request: Request, urn: int):
             "age_range": latest.get("age_range", ""),
             "has_sixth_form": latest.get("has_sixth_form"),
             "nursery_provision": latest.get("nursery_provision"),
+            # What the Ofsted badge may say when there is no inspection record
+            # (audit H4): the inspectorate GIAS names, and whether Ofsted's own
+            # data lists the school at all.
+            "inspectorate": latest.get("inspectorate"),
+            "ofsted_listed": latest.get("ofsted_listed"),
             # The header's Selective flag reads it (lib/schoolFacts).
             "admissions_policy": latest.get("admissions_policy"),
             "status": latest.get("status"),
@@ -1210,6 +1215,9 @@ async def compare_schools(
                     # schools get entrance-test framing, never the distance template.
                     "admissions_policy": convert_to_native(latest.get("admissions_policy")),
                     "has_sixth_form": convert_to_native(latest.get("has_sixth_form")),
+                    # Audit H4: what compare may say when there is no inspection record.
+                    "inspectorate": convert_to_native(latest.get("inspectorate")),
+                    "ofsted_listed": convert_to_native(latest.get("ofsted_listed")),
                     "capacity": convert_to_native(latest.get("capacity")),
                     "gias_total_pupils": convert_to_native(latest.get("gias_total_pupils")),
                     "trust_name": convert_to_native(latest.get("trust_name")),

backend/data_loader.py

@@ -251,6 +251,8 @@ _MAIN_QUERY = text("""
         s.website,
         s.telephone,
         s.nursery_provision,
+        s.inspectorate,
+        s.ofsted_listed,
         foi.current_grade         AS ofsted_grade,
         foi.current_grade_date    AS ofsted_grade_date,
         foi.latest_visit_date     AS ofsted_date,
@@ -376,7 +378,8 @@ for _old, _new in _LEGACY_NAME_REPLACEMENTS:
 _MAIN_QUERY_LEGACY_NAMES = text(_MAIN_QUERY_LEGACY_NAMES)
 
 # Fallback used when marts predate the optional GIAS/location detail columns
-# (telephone, nursery provision, county, parliamentary constituency) — i.e. the
+# (telephone, nursery provision, county, parliamentary constituency, and the
+# inspectorate / Ofsted-listing columns added for audit H4) — i.e. the
 # nightly dbt pipeline hasn't rebuilt the mart yet on this DB. Keeps each column
 # present as NULL so the whole data load degrades gracefully instead of failing.
 _EXTRA_OPTIONAL_COLUMNS = (
@@ -384,6 +387,8 @@ _EXTRA_OPTIONAL_COLUMNS = (
     "nursery_provision",
     "county",
     "parliamentary_constituency",
+    "inspectorate",
+    "ofsted_listed",
 )
 _MAIN_QUERY_NO_EXTRA_COLS = str(_MAIN_QUERY)
 for _col, _tbl in (
@@ -391,6 +396,8 @@ for _col, _tbl in (
     ("nursery_provision", "s"),
     ("county", "l"),
     ("parliamentary_constituency", "l"),
+    ("inspectorate", "s"),
+    ("ofsted_listed", "s"),
 ):
     _src = f"{_tbl}.{_col},"
     assert _src in _MAIN_QUERY_NO_EXTRA_COLS, (

backend/ofsted_codes.py

@@ -39,6 +39,9 @@ def report_card_labels(ofsted: dict) -> dict:
 
 
 def ofsted_page_url(urn: int) -> str:
-    """The school's page on ofsted.gov.uk (all its reports live there —
+    """The school's page on ofsted.gov.uk (all its reports live there — we
-    we never deep-link an individual report)."""
+    never deep-link an individual report). Ofsted's provider pages sit under a
-    return f"https://reports.ofsted.gov.uk/provider/21/{urn}"
+    category (21 primary, 23 secondary, 25 special, 40 FE colleges, …); this
+    address redirects to the right one, where provider/21 404s for every
+    non-primary school."""
+    return f"https://reports.ofsted.gov.uk/inspection-reports/find-inspection-report/provider/ELS/{urn}"

backend/schemas.py

@@ -578,6 +578,8 @@ SCHOOL_COLUMNS = [
     "ofsted_date",
     "ofsted_framework",
     "ofsted_rc_date",
+    "inspectorate",
+    "ofsted_listed",
     "latitude",
     "longitude",
 ]

backend/tests/test_inspection_status_payload.py

@@ -0,0 +1,63 @@
+"""Audit H4: every payload that feeds an Ofsted badge carries the inspectorate
+GIAS names and whether Ofsted's own data lists the school, so the site never
+says "Not yet inspected" on the strength of missing data."""
+
+import pandas as pd
+import pytest
+from fastapi.testclient import TestClient
+
+
+def _df():
+    base = dict(year=202425, local_authority='Cambridgeshire', local_authority_code=873,
+                postcode='CB1 1AA', latitude=52.2, longitude=0.12, address='1 High St',
+                status='Open', town='Cambridge')
+    return pd.DataFrame([
+        dict(base, urn=136083, school_name='Abbey College Cambridge', phase='Secondary',
+             school_type='Other independent school', inspectorate='ISI', ofsted_listed=False),
+        dict(base, urn=150031, school_name='Abbas and Templecombe Church School', phase='Primary',
+             school_type='Academy converter', inspectorate='Not applicable', ofsted_listed=True),
+    ])
+
+
+@pytest.fixture()
+def client(monkeypatch):
+    from backend import app as app_module
+    from backend import database as database_module
+
+    def _no_db():
+        raise RuntimeError('no database in this test')
+
+    monkeypatch.setattr(app_module, 'load_latest_school_data', _df)
+    monkeypatch.setattr(app_module, 'load_school_data', _df)
+    monkeypatch.setattr(app_module, 'get_supplementary_data', lambda db, urn: {})
+    monkeypatch.setattr(app_module, '_place_registry', None)
+    monkeypatch.setattr(database_module, 'SessionLocal', _no_db)
+    return TestClient(app_module.app, raise_server_exceptions=False)
+
+
+def test_the_list_carries_inspectorate_and_listing(client):
+    resp = client.get('/api/schools?page_size=50')
+    assert resp.status_code == 200, resp.text
+    by_urn = {s['urn']: s for s in resp.json()['schools']}
+    assert by_urn[136083]['inspectorate'] == 'ISI'
+    assert by_urn[150031]['ofsted_listed'] is True
+
+
+def test_the_school_page_carries_them(client):
+    info = client.get('/api/schools/136083').json()['school_info']
+    assert info['inspectorate'] == 'ISI'
+    assert info['ofsted_listed'] is False
+
+
+def test_compare_carries_them(client):
+    body = client.get('/api/compare?urns=136083,150031').json()
+    assert body['comparison']['150031']['school_info']['ofsted_listed'] is True
+    assert body['comparison']['136083']['school_info']['inspectorate'] == 'ISI'
+
+
+def test_a_mart_built_before_the_columns_still_loads():
+    # Missing columns make the main query retry with NULLs (data_loader).
+    from backend import data_loader
+    assert {'inspectorate', 'ofsted_listed'} <= set(data_loader._EXTRA_OPTIONAL_COLUMNS)
+    fallback = str(data_loader._MAIN_QUERY_NO_EXTRA_COLS)
+    assert 'NULL AS inspectorate,' in fallback and 'NULL AS ofsted_listed,' in fallback

backend/tests/test_ofsted_codes.py

@@ -42,4 +42,4 @@ def test_unknown_code_is_skipped_not_crashed():
 
 
 def test_provider_url():
-    assert ofsted_page_url(138690) == "https://reports.ofsted.gov.uk/provider/21/138690"
+    assert ofsted_page_url(138690) == "https://reports.ofsted.gov.uk/inspection-reports/find-inspection-report/provider/ELS/138690"

backend/tests/test_supplementary_enrichment.py

@@ -33,7 +33,7 @@ def test_report_card_block_and_provider_url():
     assert block["report_card"]["rc_achievement"]["label"] == "Strong standard"
     assert "rc_safeguarding_met" not in block["report_card"]
     assert block["rc_safeguarding_met"] is True
-    assert block["ofsted_page_url"] == "https://reports.ofsted.gov.uk/provider/21/100140"
+    assert block["ofsted_page_url"] == "https://reports.ofsted.gov.uk/inspection-reports/find-inspection-report/provider/ELS/100140"
 
 
 def test_no_grade_is_carried_past_a_newer_inspection():